ali khorramifar

Potato is an important vegetable that grows all over the world and is considered as an important product in developing and developed countries for human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and its origin is from Peru, and after wheat, rice and corn, it is the fourth product in the food basket of human societies. According to the statistics of the Food and Agriculture Organization of the United Nations, the area under cultivation of this crop in Iran in 2017 was 161 thousand hectares and the crop harvested from this area is about 5.1 million tons. Traditional methods of determining potato varieties were based more on morphological features, but with the production of new products, there was a need for methods that were faster and more recognizable. Meanwhile, the high-performance artificial neural network can be used to classify cultivars. An artificial neural network can classify and detect cultivars, is flexible and is used in most agricultural products. Azizi conducted a study on 120 potatoes in 10 different cultivars using a visual and image processing machine with a MATLAB R2012 software toolbox to detect texture, shape parameters and potato cultivars. First, potato cultivars were classified usithe ng LDA method, which obtained 66.7% accuracy. This method also erred in distinguishing the two cultivars Agria and Savalan and also classified the two cultivars Fontane and Satina in other classes. They also used artificial neural networks to classify potato cultivars, in which the network was 82.41% accurate with one hidden layer and 100% accurate with two hidden layers. In this study, it was found that different types of potatoes can be identified and identified with a very high level of accuracy using the three color characteristics, textural and morphological features extracted by the visual machine and the use of a non-linear classifier artificial neural network. Categorized.In another study that was conducted using neural networks and image processing on 5 sweet potato cultivars, the researchers showed that this method was successful and could classify sweet potato cultivars with 100% accuracy.By determining and examining the existing relations between the force and the deformation of agricultural products up to the point of surrender, the range of forces harmful to fruit can be determined so that harvesting and transportation machines are designed in such a way that the forces from them do not exceed this range. On the other hand, one of the ways to determine the degree of ripeness of the fruit is to touch and press it with the thumb, which is an experimental way and depends on the skill of the person touching it. The mechanical penetration test of the fruit can be an indicator to check the ripeness of the fruit by quantifying this diagnosis and using this diagnosis to determine the optimal harvest time.Several types of research have been conducted on the physical and mechanical properties of agricultural products in Iran and other countries. In a research conducted by Ali Mohammadi and Rasakh to determine some mechanical properties of lime fruit under quasi-static loading, the results showed that the effect of loading speed, loading direction and size of a lime on the breaking force of lime is significant. As the size of the lemon decreases, the breaking force and deformation decrease, and also with increasing loading speed, the braking force increases. In another research conducted by Mohd Nejad and Khosdada, the effect of size, speed and direction of loading on the mechanical properties of lime was investigated and the results showed that the interaction of loading speed and size on fracture energy and toughness and the main effects of size, loading speed and The loading direction is significant on the modulus of elasticity, but none of the effects on the rupture force is significant.

First, 5 different varieties of potatoes (Agria, Spirit, Sante, Marfona and Jelly) were prepared from Ardabil Agricultural Research Center immediately after harvest. After preparing the varieties, 21 samples of each potato variety were prepared using a cutting cylinder and then data collection was done with santam machine.To measure the rupture energy of potato samples, santam device (available in the Biosystem Engineering Department of Mohaghegh Ardabili University) was used. For this purpose, each potato variety was subjected to a compressive force at three loading speed levels (10, 40 and 70 mm/min) with 7 repetitions. Then, using the amount of rupture force and deformation (surface area under the force-deformation curve), the amount of rupture energy was calculated. The data obtained from the experiment were analyzed statistically with Minitab 18 software.

Conclusion:

 The amount of rupture energy in 5 different varieties of potato was obtained using santam device and equation 1. The values obtained for 5 potato cultivars were analyzed using Minitab18 software and the results are given in Table (1).The results of the analysis of variance for the firmness of 5 different potato cultivars were significant at the 1% level and the coefficient of variation was 9.6. In Figure 2, you can see the average results.According to Figure 2, it is clear that the lowest amount of rupture energy is related to the Agria variety and the highest is related to the Jali variety. Also, it can be found that with a loading speed of 10 mm/min, the highest amount of rupture energy is obtained in all figures.In this research, the firmness level for 5 different potato cultivars was calculated using the santam machine available at Mohaghegh Ardabili University and the area under the force-deformation curve. The amount of calculated rupture energy has the ability to be used as a method for the proper selection of different potato cultivars. The use of this method in potato cultivars will be very useful for factories such as chips factories and processing units, and it is also expected that similar methods related to mechanical properties such as crispness and hardness and with the help of different statistical methods to optimize production and The processing of agricultural products can be used in the food industry, which leads to more customer-friendliness and can also reduce agricultural waste.

Introduction:

 Potato with scientific name Solanum tuberosum. L is a plant that is cultivated as an important crop in all countries and is known as a source of carbohydrates, proteins, and vitamins in the human diet. This is a native product of South America and its origin is from Peru. After wheat, rice and corn, potato is the fourth product in people's food basket, which in Iran sometimes takes the place of rice and takes second place, which shows its importance in meeting people's food needs. According to the reports of the Food and Agriculture Organization of the United Nations, the area under potato cultivation in Iran in 2019 was more than 164 thousand hectares and the harvested product from this area was about 32.5 million tons. In the food industry, this product is transformed into various products such as baked potatoes, fried potatoes, potato chips, potato starch, dry fried potatoes, etc.Agria, Sante, Arinda, Marfona, Jelli, Born, Satina, Milva, Banba, Fontane, Ramos and Esprit varieties are among the most common potato varieties in Iran. Due to the increasing expectations for food products with high quality and safety standards, it is necessary to accurately, quickly and purposefully determine the characteristics of food products. In the apple-potato product, quality assessment after the harvest stage is necessary to provide a reliable and uniform product to the market, because potatoes, like many other products, have uneven quality and handling during the harvest stage. - Be At the same time, the safety and desirability of food play an important role in the food industry and are directly related to people's health. In addition, a huge part of the potatoes used in the processing industry is stored, so considering the importance of this food item and the demand of the people throughout the year, it is possible to meet the needs of the applicants only through long-term storage with optimal conditions was responsible. Potatoes for the processing industry must have some requirements such as low sugar content, high dry matter and specific weight, high antioxidants, light skin color and no sprouting. Storage conditions after harvesting can cause changes in the chemical composition and quality of the product.The nutritional and chemical composition of potatoes differs from each other depending on the variety, storage period, growing season, soil type and pre-harvest nutrition. In general, potatoes contain 70-80% water and 16-24% starch and contain small amounts (less than 4%) of protein, fat, anthocyanins, minerals, etc.Storage conditions after harvesting can cause many changes in the chemical composition of potato tubers and as a result, change the quality characteristics of the final product. Sugar and starch are the main components that are affected by metabolism after harvesting in the potato tuber and may ultimately affect their texture, sensory and cooking properties.The quality of potatoes and, consequently, the quality of processed products, significantly depends on the variety and environmental conditions, both during the growing season and during the storage period.Although the quality of raw potatoes is determined primarily by the size, shape, color and attractiveness of the tuber, its quality is mainly determined by examining the quality of the final product. The quality of processed potato products is evaluated in terms of color, flavor and texture, and most of their quality depends on the quality of raw potatoes.By analyzing the relationship between the color of chips, dry solids, sucrose, reducing sugar, ascorbic acid, protein and storage temperature data, Meza showed that dry solids, reducing sugar and sucrose in determining the color of fresh potato chips and reducing sugar, tuber temperature and sucrose content are very important in determining the color of stored tuber chips, and the relative importance of each of these parameters changes with the variety and age of potato tubers.

different varieties of potato were prepared from Arallo Agricultural Research Center (Ardebil Province) immediately after harvest. Then, data collection was done from different samples and cultivars (measurement of carbohydrate content) as explained below.The carbohydrate content of the samples was extracted using the equipment available in the central laboratory of Mohaghegh Ardabili University. This process was carried out by the Schlegel method, in which carbohydrates were extracted using 95% ethanol based on the sulfuric acid method in each sample. The amount of light absorption of each sample was obtained from a nano-spectrophotometer device (Nanodrop) with a volume of 1000 microliters (Figure 1) using a cuvette (made by Termo scientific company from the USA) and the amount of extracted carbohydrates were obtained based on micrograms per millilitre from the standard curve.Glucose was used to prepare the standard curve. Serial dilution of glucose was prepared and color development at 490 nm was controlled for different concentrations of glucose and one millilitre of distilled water was used as a blank. This standard curve was used to calculate the concentration of total carbohydrates in the samples. The standard curve had a coefficient of determination of 0.9955.For each sample, data collection was done in three repetitions and the amount of absorption wavelength and then the amount of carbohydrate was calculated.

In order to obtain the number of carbohydrates, the number of the absorption wavelength was placed in the relationship obtained from the standard curve, and the number of carbohydrates was obtained in micrograms per millilitre. The results of the analysis of the variance of the effect of cultivar on potato carbohydrate content can be seen in Table 1. According to the analysis of the variance table, the effect of variety on potato carbohydrate content was significant at the 1% probability level.As you can see, Sante and Esprit cultivars have more carbohydrates than other cultivars. Also, the carbohydrate content of the Marfona variety was the lowest.According to the data and results of the research, it was observed that the amount of carbohydrates in different potato cultivars is different, and Sante and Esprit cultivars had more carbohydrates at the time of harvest. Also, according to the resulting graphs, it was observed that the amount of carbohydrates of the Marfona cultivar is lower than other cultivars. It is recommended to choose a more suitable variety according to the type of consumption and the importance of quality characteristics for consumption and processing, according to the storage conditions and time.

The use of plant-derived compounds is common in medicine and preventive health care, while the scope of use of some substances is steadily increasing. The mint family, with more than 200 genera and 3000 species, is very important economically and medicinally. The mint genus contains 25 to 30 species that grow in different temperate regions of Asia, Europe, Australia and South Africa. There is a great diversity in terms of chemical composition among the species of the mint genus. Peppermint essential oil (Mentha spicata L.) is rich in carvone, which produces the special aroma of mint. The yield of essential oil of Sentha spicata is lower than that of Mentha piperita. Carvone is the main component of Mentha spicata and Mentha longlifolia, while Carvone is absent in Mentha piperita, Mentha aquatic, Mentha arvensis and Mentha pulegium. Peppermint essential oil and extract are used in the pharmaceutical, cosmetic and food industries all over the world. Mentha spicata essential oil and leaves have therapeutic uses and its general properties are analgesic, tonic, stomach tonic, antitussive, anticonvulsant, astringent, analgesic and sedative. Peppermint oil has been used since ancient times for medicinal purposes, mostly to treat headaches, colds and neuralgia. It can also relieve skin irritations and digestive problems and has antispasmodic effects. Although, there is mixed information about the chemical composition of Mentha spicata essential oil, many studies have confirmed carone and limonene as its main components. Carvone is responsible for the smell of peppermint essential oil. The high price of carvone in the market has pushed breeders to improve mint varieties with high carvone. Different chemotypes are characterized by specific odors and biological activities, which indicate different applications in the aromatic and pharmaceutical industries. For example, Europeans enjoy the scent of Carvone. The use of medicinal plants in the food and pharmaceutical industries depends on the amount of biologically active substances and their chemical composition. Changes in the concentration of volatile compounds of mint during drying also depend on several factors, including drying conditions (temperature, air speed), humidity, variety and age of the plant, climate, soil and harvesting method. The drying process and storage conditions of the dried plant can have an adverse effect on the medicinal properties of the essential oil. Drying is one of the efficient methods to preserve agricultural products and maintain food quality. Drying, as an important food preservation technique, is used in the food industry. Drying is required to reduce the water activity of the product to suppress the growth of microorganisms and inhibit chemical reactions to increase the shelf life of the product at room temperature. In addition, drying lightens shipping weight and reduces storage space. Conventional drying methods include hot air drying (HAD), vacuum drying (VD), vacuum freeze drying (VFD), and microwave-hot air alternating drying (MW-HAD). HAD is the most common method that dries food in an oven with a constant flow of hot air. As an optimal approach for drying raw vegetable food, this method has easy operation and low cost, but it requires a long drying time and has low energy consumption.

After the drying process, the essential oil was extracted from the dried product, and for this purpose, a Clonger machine was used using the water distillation method. Distillation with water is a method of extracting essential oils. This method is cheap because it mostly uses water as a solvent. Qualitative GC-MS analysis of the extracted essential oils was performed using an HP 6890 gas chromatograph coupled to an HP 5973 mass-selective detector (Agilent Technologies, Foster City, CA, USA) operating at 70 eV mode. The electronic nose consists of three parts: (1) a sample transport system (2) a detection system consisting of a set of gas sensors with partial characteristics and (3) an odor data processing system. The e-nose instrument can detect the presence of VOCs in various molecular structures with high accuracy and reliability regardless of more or less odor. Samples were analyzed using a portable e-nose, which consists of a multiple gas sensor array, a signal acquisition unit, and pattern recognition software. Essential oil samples (1 mL) were placed in a 10 mL sealed glass vial and equilibrated at 40 °C for 30 min under stirring. Clean ambient air was used as the carrier gas to transport the volatiles in the headspace of the sealed glass vials to the temperature and humidity controlled sensing chamber. The conductivity change in the sensor array is expressed by the normalized response of the sensor. Each measurement cycle lasted 100 seconds, which allows the sensor to reach a steady state, and the data collection interval using a computer was 1 second. Between measurement cycles, the sensor was purged for 200 s with purge gas filtered through activated charcoal to return the sensor signal to baseline. 15 measurements were made for each sample of peppermint essential oil. Data obtained from GC-MS analysis were first processed by in-house MSD Chemstation and structural identification was performed through NIST 2014 library research along withretention index (RI) validation. The dataset consists of pre-processed signals from 9 MOS gas sensors obtained in the e-nose during 120 measurements corresponding to 8 independent samples evaluated with 15 repetitions. The performance of e-nose for evaluating peppermint essential oil samples was evaluated using three supervised statistical methods, namely QDA, MDA and ANN.

Drying is the most suitable method used to preserve the natural products of plants. Choosing a special drying method is one of the important costs in the production and commercialization of medicinal plants. This study determined the effect of different drying methods on the quantity and quality of peppermint essential oil. The results showed that the highest yield of essential oil was in the HAD1A drying method and the lowest yield was related to the sun drying method. Also, the obtained compounds of the essential oil were determined by the GC-MS method, and in the HAD drying method, 18 compounds were determined, and the content of some of them decreased significantly with the increase of the drying temperature. In the dried samples, the main components were Carvone (64.30-7.45%), Limonene (24.21- 6.59%) and Carveol (18.34-1.92%). Also, the aroma characteristics of mint essential oil were evaluated with the help of an E-nose. Three classification algorithms QDA, MDA and ANN were used, and the highest percentage of classification related to QDA and MDA methods was 100%, and the accuracy of the ANN method was also 0.967%. The findings of this study provide a theoretical basis for the development of hot air thin layer drying process for medicinal plants and improving their sensory quality and related products. The future perspective is to continuously improve the in situ drying technique for medicinal plants and develop a suitable monitor system to control the sensory quality of the final products based on the findings of the current study.

Nectarine is a plant that is cultivated as an important commercial product in some countries and is known as an important source of sugar and vitamins in the human diet. Due to the increase in expectations for food products with high quality and safety standards, accurate, fast and targeted determination of the characteristics of food products is necessary. In the nectarine product, quality evaluation after the harvesting stage is necessary to provide a reliable and uniform product to the market. The purpose of this study is to identify and classify nectarines by extracting characteristics from the response patterns of the spectrometer and using chemometrics methods. A near-infrared spectrometer can detect the spectrum of reflected light by estimating its concentration or determining some of its inherent properties. The quality assessment of agricultural products includes two main methods, quality grading systems based on the external characteristics of agricultural products and quality grading systems based on internal quality assessment, which has gained outstanding points in recent years. In the meantime, several methods have been invented for the qualitative grading of agricultural products based on the assessment of their internal properties in a non-destructive manner, and only some of them have been able to meet the above conditions and have been justified in terms of technical and industrial aspects. To be meanwhile, spectrometry can be highly efficient in determining the quality of cultivars. Spectroscopy is a type of system that has a different structure and approach from other methods (image processing, neural network, etc.) and can perform classification and determination of digit quality. With increasing expectations for food products with high quality and safety standards, the need for accurate, fast and targeted determination of the characteristics of food products is now essential. Because manual methods do not have automatic control, they are very tiring, difficult and expensive, and they are easily affected by environmental factors. Today, spectroscopic systems are non-destructive and cost-effective and are ideally used for routine inspections and quality assurance in the food industry and related products. This technology allows inspection works to be carried out using wavelength data analysis techniques and is a non-destructive method for measuring quality parameters. In this research, using spectrometry and chemometrics methods, the variety of nectarine fruit was identified.

For this study, 5 different nectarine cultivars were prepared from the gardens of Moghan city (Ardebil province) and were tested and data collected. A spectroradiometer model PS-100 (Apogee Instruments, INC., Logan, UT, USA) was used to acquire the spectrum of the samples. This spectroradiometer is very small, light, and portable, has a single-wavelength sputtering type with a resolution of 1 nm and a linear silicon CCD array detector with 2048 pixels that covers the spectral range of 250-1150 nm (Vis/NIR) well. Also, there is the ability to connect the optical fibre to the PS-100 spectroradiometer and transfer the data to the computer with the purpose of displaying and storing the acquired spectra in the Spectra Wiz software through the USB port. With the aim of creating optimal light in contrast mode measurements, an OPTC (Halogen Light Source) model halogen-tungsten light source, which can be connected to an optical fibre, was used. This light source has three output powers of 10, 20, and 30 watts, which were used in this research. Also, a two-branch optical fibre probe model (Apogee Instruments, INC., Logan, Utah, USA), which includes 7 parallel optical fibres with a diameter of 400 micrometres, was used in counter-mode measurements. After providing the necessary equipment, the optimal spectroscopic arrangement was designed and implemented in order to facilitate the experiments and minimize the effect of environmental factors during the spectroscopic process. The data obtained from spectral imaging may be affected by the scattering of light by the detector with sample change, sample size change, surface roughness in the sample, the noise created due to the increase in temperature of the device and many other factors, and unwanted information affect the accuracy of calibration models. Therefore, to achieve stable, accurate and reliable calibration models, data pre-processing is needed (Rossel, 2008). In this research, Savitzky-Golay smoothing, first and second derivatives, baseline, standard normal distribution, and incremental scatter correction were applied to the data. The use of non-destructive methods based on spectroscopy in the full range of wavelengths requires spending time and very high costs, which makes the practical application of this method almost impossible; therefore, one should look for a way to find the optimal wavelengths and limit the wavelengths to the minimum possible value. Chemometrics uses multivariate statistics to extract useful information from complex analytical data. The chemometrics used in this study started with principal component analysis (PCA) to explore the output response of the sensors and reduce the dimensionality of the data. In the next step, linear diagnostic analysis (LDA) was also used to classify 5 varieties of Shail. (PCA) is one of the most common statistical data reduction methods. This method is an unsupervised technique used to explore and reduce the dimensionality of a dataset. The analysis itself involves the determination of variable components, which are linear combinations of many investigated characteristics. In this research, in order to construct the LDA model, the data were randomly divided into two parts: 70% of the samples were used for training and cross-validation, and the rest of the data were used for independent validation.

Based on the results of the PCA analysis presented in Figure 2, the first principal component (PC-1) describes 72% and the second principal component (PC-2) 13% of the variance of the tested samples. As a result, the first two principal components together express 85% of the data. Considering that it is possible that the degree of correlation between the properties of different samples during the tests, due to various reasons such as technical problems of the equipment, data collection, incorrect sampling, etc., in some samples, inappropriate or socalled outliers The LDA method is a supervised method that is used to find the most distinct eigenvectors and maximizes the between-class and intra-class variance ratios and is capable of classifying two or more groups of samples. The LDA method was used to identify the nectarine cultivars based on the output response of the spectrometer. Unlike the PCA method, the LDA method can extract the resulting information to optimize the resolution between classes. Therefore, this method was used to detect 5 nectarine cultivars based on the output response of the spectrometer. The results of the identification of figures equal to 100% were obtained.

Potato is considered one of the most important food sources in the world (4th rank) and studying its various aspects is very important to ensure that the produced product has the necessary qualifications and can satisfy the customer. In the food industry, this product is transformed into various products such as baked potatoes, fried potatoes, potato chips, potato starch, dry fried potatoes, etc.The complexity of food odours makes it difficult to analyze them with conventional analytical techniques such as gas chromatography. However, expert sensory analysis is costly and requires trained people who can only work for a relatively short period. Problems such as the human subjectivity of the response to smell and the variation between people should also be considered. Hence, there is a need for a tool such as an electronic nose with high sensitivity and correlation with human sensory panel data for specific applications in food control. Due to its easy construction, cheapness and the need for little time for analysis, the electronic nose is becoming an automatic non-destructive method to describe the smell of food.An olfactory machine can recognize the fragrance composition by estimating its concentration or determining some of its intrinsic properties, which the human nose is hardly able to do. In general, the human olfactory system is a five-step process including smelling, receiving the scent, evaluating, detecting and erasing the effect of the scent. The olfactory phenomenon begins with inhaling the intended smell and ends with breathing fresh air to remove the effect of the scent. The human olfactory system, with all its unique capabilities, also has disadvantages that limit its use in quality control processes, including subjectivity, low reproducibility (for example, results depending on time, people's health, analysis before the presence of odour and fatigue is variable), time-consuming, high labour cost, adaptation of people (less sensitivity when exposed to odour for a long time). In addition, it cannot be used to evaluate dangerous odours.Meanwhile, the electronic nose can detect the volatile compounds of potatoes. The electronic nose has been used in extensive research to identify and classify food and agricultural products.
The purpose of this research was to evaluate the ability of the electronic nose using one of the chemometrics methods to detect 5 different potato cultivars.

First, 5 varieties of potato were prepared from the agricultural research centre of Ardabil city. These 5 varieties included Colombo, Milwa, Agria, Esprit and Sante.After preparing the cultivars, first, the samples were placed in a closed container (sample compartment) for 1 day to saturate the space of the container with the aroma and smell of potatoes, and then the sample compartments were used for data collection with the electronic nose.In this research, the electronic nose made in the Biosystems Engineering Department of Mohaghegh Ardabili University was used. In this device, 9 metal oxide semiconductor (MOS) sensors with low power consumption are used, which are listed in Table 1.The sample chamber was connected to the electronic nose device and data collection was done. This data collection was done in such a way that first, clean air was passed through the sensor chamber for 150 seconds to clean the sensors from the presence of odours and other gases. Then, the smell of the sample was sucked from the sample chamber by the pump for 150 seconds and directed to the sensors, and finally, clean air was injected into the sensor chamber for 150 seconds to prepare the device for repetition and subsequent tests. 15 repetitions were considered for each sample.Through the mentioned steps, the output voltage of the sensors was changed due to exposure to gases emitted from the sample (potato smell) and their olfactory responses were collected and recorded by data collection cards, the sensor signals were recorded and stored at 1-second intervals. . A fractional method was used to correct the baseline, in which noise or possible deviations were removed and the responses of the sensors were normalized and dimensionless.
By chemometrics method in this research, it started with principal component analysis (PCA) to discover the output response of the sensors and reduce the dimension of the data.Principal component analysis (PCA) is one of the simplest multivariatemethods and is known as an unsupervised technique for clustering data according to groups. It is usually used to reduce the dimensionality of the data and the best results are obtained when the data are positively or negatively correlated. Another advantage of PCA is that this technique reduces the volume of multidimensional data while removing redundant data without losing important information.

The scores chart (Figure 1) showed that the variance of the total data is equal to PC-1 (94%) and PC-2 (3%), respectively, and the first two principal components account for 97% of the variance of the total normalized data. When the total variance is higher than 90%, it means that the first two PCs are sufficient to explain the total variance of the data set. So it can be concluded that the electronic nose has a good response to the smell of potatoes and its cultivars can be distinguished, which shows the high accuracy of the electronic nose in identifying the smell of different products.With the correlation loadings plot, the relationships between all variables can be shown. The loading diagram (Figure 2) shows the relative role of sensors for each main component. The inner oval represents 50% and the outer oval represents 100% of the total variance of the data. The higher the loading coefficient of a sensor is, the greater the role of that sensor in identification and classification. Therefore, the sensors that are located on the outer circle have a greater role in data classification. According to the figure, it is clear that all the sensors have an important role in identifying the rice variety, including the role of sensors number 1 and 9, which are respectively the same sensors as MQ9 (to detect carbon dioxide and combustible gases) and MQ3 (to detect alcohol, methane, natural gases), it was less than the rest of the sensors, and by removing these two sensors, the cost of making an olfactory device (to distinguish genuine and fake rice) can be reduced and costs can be saved. In this research, an electronic nose with 9 metal oxide sensors was used to identify and distinguish potato cultivars. The Chemometrics PCA method was used for qualitative and quantitative analysis of complex data from the electronic sensor array. PCA was used to reduce the data and with two main components PC1 and PC2, it described 97% of the variance of the data set and provided an initial classification. The electronic nose has the ability to be used as a fast and non-destructive method to identify potato varieties. Using this method will be very useful for consumers, especially restaurants and processing units, in order to choose high-quality cultivars.

Potato with the scientific name (Solanum tuberosum. L.) is a plant that is cultivated as an important product in all countries and is known as a source of carbohydrates, proteins, and vitamins in the human diet. This is a native product of South America and its origin is from Peru. After wheat, rice and corn, potato is the fourth product in people's food basket, which in Iran sometimes takes the place of rice and takes second place, which shows its importance in meeting people's food needs. According to the reports of the Food and Agriculture Organization of the United Nations, the area under potato cultivation in Iran in 2019 was more than 164 thousand hectares and the harvested product from this area was about 32.5 million tons. In the food industry, this product is transformed into various products such as baked potatoes, fried potatoes, potato chips, potato starch, dry fried potatoes, etc.Since the expectations for food products with appropriate quality and safety standards have increased, it seems necessary to determine the characteristics of food products. In the meantime, in the potato product, quality evaluation after the harvest stage is necessary to provide a reliable and uniform product to the market, because potatoes, like many other products, have uneven quality and handling in It is the harvesting stage. At the same time, the safety and desirability of food play an important role in the food industry and are directly related to people's health. Potatoes for the processing industry must have some requirements such as low sugar content, high dry matter and specific weight, high antioxidants, light skin color and no sprouting. Stored potatoes may suffer from sweetening, rotting, water loss and sprout growth during storage. Storage conditions after harvesting can cause changes in the chemical composition and quality of the product. Therefore, the management of potato tubers in all stages of production and storage is very important.The quality of this product and its processed products depends on the variety and environmental conditions (both during the growing season and during the storage period). By analyzing the relationship between chips color, dry solids, sucrose, reducing sugar, ascorbic acid, protein and storage temperature data, Meza showed that dry solids, reducing sugar and sucrose in determining the color of fresh potato chips and reducing sugar, tuber temperature and sucrose content are very important in determining the color of stored tuber chips and the relative importance of each of these parameters changes with the type of tuber variety and storage.The amount of potato sugar significantly depends on the variety and storage temperature and it happens quickly in cold weather. In potato tubers during the storage period, starch is gradually hydrolyzed and turned into sugar (glucose). In unripe tubers and potatoes that are stored for a long time at low temperatures, there are more amounts of glucose, this feature is considered an anti-quality feature for the potato product in the industry, why? The increase of regenerating sugars causes the produced chips to turn brown and bitter. Storing potatoes for more than 7 months can cause ageing or old sweetness, and storage at a temperature of fewer than 10 degrees Celsius can cause sweetness caused by cold. Although potato storage at low temperatures can have beneficial results such as reducing respiration rate, reducing physiological ageing, inhibiting germination, reducing evaporative water loss and reducing microbial pathogens. But sugars accumulate when the balance between starch degradation and breakdown is not established and there is carbohydrate respiration. Therefore, potatoes that are kept at a lower temperature have a lot of sugar. Researchers reported that when potatoes are stored at zero degrees Celsius, there will be a complete stop in th accumulation of sugar.

First, 5 different varieties of fresh potatoes (Spirit, Agria, Sante, Jelli and Marfona) were prepared from Ardabil Agricultural Research Center (Arallo District). It should be noted that these potatoes were prepared immediately after harvesting so that there are no changes in the amount of sugar due to the time interval after harvesting.The amount of sugar in each sample was measured in three replicates using a liquid refractometer model BPTR100 (Middle East Control System Company, brand name Prisma Tech, made in Iran) available at Mohaghegh Ardabili University (Figure 1). For this, first, some water was taken from the samples and after pouring it into a microtube, it was placed inside a refrigerated centrifuge (top speed) of the LISA France model, and after rotating at a speed of 1800 rpm for 2 minutes, the impurities at the bottom settled and separated the pure liquid (pure potato juice). After reaching the ambient temperature, the said liquid was placed on the refractometer and its sugar content was read in terms of Brix.

The results of the analysis of the variance of cultivar effect on potato sugar content are shown in Table 1. According to the analysis of the variance table, the effect of variety on potato sugar level was significant at 1% probability level. You can see the changes in the amount of sugar of different potato cultivars in Figure 2. The difference in the amount of sugar in different cultivars is due to the difference in their starch hydrolysis (the main compound of potato-potato tubers) which occurs as a result of the respiration of the product, and it is in this way that the higher the amount of starch in If one variety is less, that variety has less sugar, and it is important to note that the chemical composition depends on the potato variety, soil, climate, and agricultural factors. In general, it can be said that potatoes with more sugar are suitable for the chips industry, and potatoes with medium sugar are suitable for frying. According to Figure 2, the highest amount of sugar is related to the Esprit variety and the lowest amount is related to the Jelly variety. The reason for the difference in the amount of sugar between different cultivars is mainly related to the type of soil, fertilizer and poison used. According to the data and the results of the research, it was observed that the amount of sugar in different varieties of potato is different, in the meantime, the jelly variety generally has a lower amount of sugar at the time of harvesting, and the variety of Esprit has the highest amount of sugar at the time of harvesting. Was. It is recommended to choose a more suitable variety according to the conditions according to the type of consumption and the importance of quality characteristics for consumption and processing, of course, physical characteristics are also involved in this relationship, which should be taken into consideration.

Potato with the scientific name (Solanum tuberosum. L.) is a plant that is cultivated as an important crop in all countries and is known as a source of carbohydrates, proteins, and vitamins in the human diet. This is a native product of South America and its origin is from Peru. In the food industry, this product is transformed into various products such as baked potatoes, fried potatoes, potato chips, potato starch, dry fried potatoes, etc.Due to the increase in expectations for food products with high quality and safety standards, accurate, fast and targeted determination of the characteristics of food products is necessary. In the apple-potato product, quality assessment after the harvest stage is necessary to provide a reliable and uniform product to the market, because potatoes, like many other products, have uneven quality and processing during the harvest stage. - Be At the same time, the safety and desirability of food play an important role in the food industry and are directly related to people's health. In addition, a huge part of potatoes used in the processing industry is stored, so considering the importance of this food item and the demand of the people throughout the year, it is possible to meet the needs of the applicants only through long-term storage with optimal conditions was responsible. Potatoes for the processing industry must have some requirements such as low sugar content, high dry matter and specific weight, high antioxidants, light skin colour and no sprouting.The complexity of the reflectance spectrum of food makes it difficult to analyze them with conventional analytical techniques such as gas chromatography. However, sensory analysis by experts is a costly process and requires trained people who can only work for a relatively short period. A near-infrared spectrometer can detect the spectrum of reflected light by estimating its concentration or determining some of its inherent properties.The quality assessment of agricultural products includes two main methods, quality grading systems based on the external characteristics of agricultural products and quality grading systems based on internal quality assessment, which has gained outstanding points in recent years. In the meantime, several methods have been invented so far for the qualitative grading of agricultural products based on the assessment of their internal properties in a non-destructive way, and only some of them havebeen able to meet the above conditions and have been justified in terms of technical and industrial aspects.Meanwhile, spectrometry can be highly efficient in determining the quality of cultivars. Spectroscopy is a type of system that has a different structure and approach from other methods (image processing, neural network, etc.) and can perform classification and determination of digit quality.With increasing expectations for food products with high quality and safety standards, the need for accurate, fast and targeted determination of the characteristics of food products is now necessary. Because manual methods do not have automatic control, they are very tiring, difficult and expensive, and they are easily affected by environmental factors. Today, spectroscopic systems are non-destructive and cost-effective and are ideally used for routine inspections and quality assurance in the food industry and related products. This technology allows inspection works to be carried out using wavelength data analysis techniques and is a non-destructive method for measuring quality parameters. In this research, using spectrometry and chemometrics methods, changes in acidity and SSC of potato were investigated over time.

In each treatment period (in total 5 periods were considered and the intervals of periods were determined as one week), unripe walnut samples in addition to ripe samples (in the last period) were taken from one of the orchards around Ardabil (located in Shahrivar village) was prepared, tested and data collected.A spectroradiometer model PS-100 (Apogee Instruments, INC., Logan, UT, USA) was used to acquire the spectrum of the samples. This spectroradiometer is very small, light, portable, has a single-wavelength sputtering type with a resolution of 1 nm and a linear silicon CCD array detector with 2048 pixels that covers the spectral range of 250-1150 nm (Vis/NIR) well. Also, there is the ability to connect the optical fibre to the PS-100 spectroradiometer and transfer the data to the computer to display and store the acquired spectra in the Spectra Wiz software through the USB port. To create optimal light in contrast mode measurements, an OPTC (Halogen Light Source) model halogen-tungsten light source, which can be connected to an optical fibre, was used. This light source has three output powers of 10, 20, and 30 watts, which were used in this research. Also, a two-branch optical fibre probe model (Apogee Instruments, INC., Logan, Utah, USA), which includes 7 parallel optical fibres with a diameter of 400 micrometres, was used in counter-mode measurements. After providing the necessary equipment, the optimal spectroscopic arrangement was designed and implemented to facilitate the experiments and minimize the effect of environmental factors during the spectroscopic process.To measure SSC, liquid refractometer model BPTR100 (Middle East System Control Company, brand name Prisma Tech, made in Iran) available at Mohaghegh Ardabili University is used. For this, first, some water is taken from the samples and after pouring it into the microtube, we allow it to reach the ambient temperature, and then it is placed on the refractometer and the amount of sugar is read in terms of Brix.For this purpose, a laboratory pH meter, which is also called a pH meter, was used. The pH meter is actually a potentiometer consisting of an ion-selective glass electrode that selectively responds to the activity of hydrogen ions in the solution and measures the potential difference between the external solution (sample) and the internal solution (reference electrode solution). The pH-sensitive part is made of a special thin glass membrane that is at the bottom of the electrode.

In this research, in order to estimate the amount of acidity and SSC of potato-potato and the amount of wavelength absorption in 5 different periods of storage (two-week periods), reflectance spectroscopy was performed in the wavelength range of 400 to 1100 nm. After removing the noises by PCA analysis, to improve the spectrum, different pre-processings were applied and their effects were investigated. The appropriate model was determined using the partial least squares (PLS) method. Important wavelengths were selected based on the regression coefficient of the best model. Based on PLS analysis, the best results were obtained with Savitzky-Golay smoothing preprocessing. As a result, it seems that the non-destructive method of ultraspectral imaging was able to detect the amount of SSC in potatoes, but no acceptable result was obtained in the case of acidity.

Potato is an important vegetable that grows all over the world and is considered an important product in developing and developed countries for the human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and its origin is from Peru, after wheat, rice and corn, it is the fourth product in the food basket of human societies. According to the statistics of the Food and Agriculture Organization of the United Nations, the area under cultivation of this crop in Iran in 2017 was 161 thousand hectares and the crop harvested from this area is about 5.1 million tons. Traditional methods of determining potato varieties were based more on morphological features, but with the production of new products, there was a need for methods that were faster and more recognizable. In the meantime, the high-performance artificial neural network can be used to classify cultivars. Artificial neural networks can classify and detect cultivars, are flexible, and are used in most agricultural products. Therefore, the olfactory machine can have high efficiency in classifying and distinguishing cultivar, originality and storage time. The olfactory machine is a system that has a different structure and approach from other methods (image processing, neural network, etc.), is flexible and is used in most agricultural products due to the presence of odour in them.With the rapid and rapid advancement of computer technology and sensor technology, the application of the bionic electronic nose, including a semiconductor gas-sensitive sensor and a pattern recognition system as a means of detection, offers a new method for rapid classification and digit recognition. Give. The electronic nose has also introduced a new method for classifying and detecting rough rice in a non-destructive and fast way.Due to a large number of potato varieties and sometimes the lack of familiarity of processing units with its cultivars and also time-consuming and inaccurate in identifying different potato cultivars by experts and farmers, and the importance of identifying potato cultivars and other agricultural products in At every stage of the food industry process, it is necessary to find ways to do this accurately and quickly enough. The aim of this study was to evaluate the ability and accuracy of the electronic nose with the help of an artificial neural network to detect and differentiate several potato cultivars.

First, potatoes in 3 different cultivars (Colombo, Milvana and Sante) were prepared from Ardabil Agricultural Research Center and kept at a temperature of 10-4 ° C. One day after the data were collected, data collection began with an olfactory machine. 3-4 potatoes from each cultivar were placed in the sample container for 1 day to saturate the sample container with the smell. Then the sample chamber was connected to the electronic nasal device and data collection was performed. The data were collected by the olfactory machine in such a way that first clean air was passed through the sensor chamber for 100 seconds to clean the sensors from other odours. The odour (gases emitted from the sample) was then pumped out of the sample chamber by the pump for 100 seconds and directed to the sensors. Finally, clean air was injected into the sensor chamber for 100 seconds to prepare it for further data collection. According to these steps, the output voltage of the sensors was changed due to exposure to various gases (potato odour) and their olfactory response was collected by data collection cards, sensor signals were recorded and stored in the USB gate of the computer at 1-second intervals. A fractional method was used to correct the baseline in which noise or possible deviations were eliminated and the sensor responses were normalized and dimensionless. In the next step, linear diagnostic analysis (LDA) and artificial neural networks (ANN) were used to classify the 3 potato cultivars. LDA is a supervised method used to find the most distinctive special vectors, maximizing the ratio of the variance between class and within the class, and being able to classify two or more groups of samples. ANN and pattern recognition were used to find similarities and differences in the classification of potato cultivars. For this, 1 neuron was considered for the input layer, the hidden layer with the optimal number of neurons will be considered and five output neurons with Depending on the number of output classes the target will be considered. In-network training, logarithmic sigmoid transfer function and Lunberg-Marquardt learning method were used. Also, the amount of error was calculated using the mean square error. For learning (70%), testing (15%) and validation (15%) all data were randomly selected. Training data was provided to the network during the training and the network was adjusted according to their error. Validation was used to measure network generalization and completion of training. Data testing had no effect on training and therefore provided an independent measurement of network performance during and after training.

LDA and ANN methods were used to detect potato cultivars based on sensor output response. The LDA method can extract multi-sensor information to optimize resolution between classes. Therefore, this method was used to detect 3 potato cultivars based on the output response of the sensors. Detection results of cultivars equal to 100% were obtained (Figure 1). Also, in the ANN method, 8 sensors were considered in the input layer of 8 neurons according to the output data. Also, 3 layers of neurons were considered for the output layer according to the type of cultivars. Therefore, the 3-6-8 topology had the highest accuracy for detecting potato cultivars, so the RMSE value was 0.008 and the R2 value was 99.8. There was also a very high correlation between predicted and measured data (Figure 2). In this study, a portable olfactory machine system with 8 metal oxide sensors was used to investigate the detection of potato cultivars. Chemometrics methods including LDA and ANN were used for qualitative and quantitative analysis of complex data using an electronic sensor array. LDA and ANN were able to accurately identify and classify different potato cultivars with 100% accuracy. The electronic nose has the potential to be used as a fast and non-destructive method to detect different potato cultivars. Using this method in identifying potato cultivars will be very useful for researchers to select and produce pure cultivars and for farmers to produce a uniform and certified crop.

Walnut is an important economic and commercial product all over the world. The smell can be one of the key factors in determining the ripening time of the fruit and it depends on the content of the chemical compounds of the fruit and its skin. Crunchyness and easy peeling are the main features that affect the level of satisfaction of walnut consumers.The complexity of food odor makes it difficult to analyze them with conventional analytical techniques such as gas chromatography. However, sensory analysis by experts is a costly process and requires trained people who can only work for a relatively short period of time. Problems such as the human subjectivity of the response to smell and the variation between people should also be considered. Hence, there is a need for a tool such as an electronic nose with high sensitivity and correlation with human sensory panel data for specific applications in food control. Due to its easy construction, cheapness and the need for little time for analysis, the electronic nose is becoming an automatic non-destructive method to describe the smell of food.An olfactory machine can recognize the fragrance composition by estimating its concentration or determining some of its intrinsic properties, which the human nose is hardly able to do. In general, the human olfactory system is a five-step process including smelling, receiving the scent, evaluating, detecting and erasing the effect of the scent. The olfactory phenomenon begins with inhaling the intended smell and ends with breathing fresh air to remove the effect of the scent. The human olfactory system, with all its unique capabilities, also has disadvantages that limit its use in quality control processes, including subjectivity, low reproducibility (for example, results depending on time, people's health, analysis before the presence of odor and fatigue is variable), time-consuming, high labor cost, adaptation of people (less sensitivity when exposed to odor for a long time). In addition, it cannot be used to evaluate dangerous odors.The purpose of this research was to evaluate the ability of the electronic nose using chemometrics methods to detect the ripening time of walnuts with the help of its volatile compounds during the ripening period.

In each process of investigation (including 5 courses and intervals were determined as one week), premature walnut samples plus its ripe samples (in the last period) from one of the gardens around Ardebil (located in the village September) It was prepared and with an electronic data nose.In this study, the electronic nose was made in the Biosystem Engineering Department of Mohaghegh Ardebili University. The device uses 9 metal oxide semiconductor sensors (MOS) with low power consumption. The data is that the clean air was first passed through the sensor chamber for 150 seconds to clean the sensors from the smell and other gases. The sample smell was then sucked for 150 seconds by the pump from the sample chamber and directed to the sensors, and finally, clean air was injected into the sensor chamber for 150 seconds to prepare the device for recurring and subsequent tests. 20 repetitions are intended for each sample. During the above steps, the output voltage of the sensors was changed due to exposure to gases emitted from the sample (walnut aroma) and their smell response was collected and recorded by data collection cards.The Chemometrics method in this study will begin with the analysis of the main components (PCA) to discover the sensor output response and reduce the data dimension. The next step is to classify the time of walnut proceedings using artificial neural network analysis (ANN).

The scores chart (Figure 2) showed the total variance of the total data to PC-1 (98%) and PC-2 (1%), respectively, and the first two main components make up 99%of the total variance of normal data. When the total variance is above 90 %, it means that the first two PCSs are sufficient to explain the total variance. So it can be concluded that E-nose has a good response to peach smell and can be distinguished from peach figures, which indicates the high accuracy of the electronic nose in identifying the smell of different products. These results are highly compatible with the results obtained by XU et al., In a study conducted on class 6 rice digits, the PCA method was 99.5% accurate. The artificial neural network method was also used to identify and differentiate peaches based on the output of the sensors. The results of the diagnosis of walnut proceedings were obtained by 99% (Figure 3), which was the same as the PCA method.Aimin Li and colleagues, using an electronic nose with GC-MS tests, identified Chinese maca (MacA) at macroscopic and microscopic levels, concluding that there was a direct relationship between the Maca smell and chemical compounds (LI ET AL, 2019). Min Yee Lim and colleagues also achieved good results with the PCA method (Lim et al, 2020). They used the electronic nose to grade the quality of the Chinese commercial mum and were able to classify their quality with 94.3% accuracy, with the results of their PCA method in accordance with our research results. Arun Jana et al. (Jana et al, 2011) also used the olfactory machine with Ann, PCA and LDA to detect aromatic and non-aromatic rice, with the accuracy of the results used for the methods used, respectively: 93%, 96.5% and 80%. The results of our research were far more accurate than this study, which could be due to the presence of different volatile compounds in grape leaves.In this study, an olfactory machine with 9 metal oxide sensors was used to handle walnuts using their smell. Chemometrics, including PCA and ANN, were used for qualitative and quantitative data analysis of electronic sensor arrays. PCA was used to reduce data and, with two main components of PC1 and PC2, described 99% of the variance of the data set and provided an initial classification, as well as the artificial neural network capable of identifying and accurately classifying grape figures with grape cultivars the accuracy was 99%. The olfactory machine has the ability to use and operate as a rapid and non -destructive way to detect walnuts from their smell. Using this method will be very useful in identifying proper harvesting time for gardeners and manufacturers, especially processing units and food industries.

Potato is an important vegetable that grows all over the world and is considered as an important product in developing and developed countries for the human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and its origin is from Peru, and after wheat, rice and corn, it is the fourth product in the food basket of human societies. According to the statistics of the Food and Agriculture Organization of the United Nations, the area under cultivation of this crop in Iran in 2017 was 161 thousand hectares and the crop harvested from this area is about 5.1 million tons. Traditional methods of determining potato varieties were based more on morphological features, but with the production of new products, there was a need for methods that were faster and more recognizable. Meanwhile, the high-performance artificial neural network can be used to classify cultivars. An artificial neural network can classify and detect cultivars, is flexible and is used in most agricultural products. Azizi conducted a study on 120 potatoes in 10 different cultivars using a visual and image processing machine with a MATLAB R2012 software toolbox to detect texture, shape parameters and potato cultivars. First, potato cultivars were classified use the ng LDA method, which obtained 66.7% accuracy. This method also erred in distinguishing the two cultivars Agria and Savalan and also classified the two cultivars Fontane and Satina in other classes. They also used artificial neural networks to classify potato cultivars, in which the network was 82.41% accurate with one hidden layer and 100% accurate with two hidden layers. In this study, it was found that different types of potatoes can be identified and identified with a very high level of accuracy using the three color characteristics, textural and morphological features extracted by the visual machine and the use of a non-linear classifier artificial neural network. Categorized.In another study that was conducted using neural networks and image processing on 5 sweet potato cultivars, the researchers showed that this method was successful and could classify sweet potato cultivars with 100% accuracy.By determining and examining the existing relations between the force and the deformation of agricultural products up to the point of surrender, the range of forces harmful to fruit can be determined so that harvesting and transportation machines are designed in such a way that the forces from them do not exceed this range. On the other hand, one of the ways to determine the degree of ripeness of the fruit is to touch and press it with the thumb, which is an experimental way and depends on the skill of the person touching it. The mechanical penetration test of the fruit can be an indicator to check the ripeness of the fruit by quantifying this diagnosis and using this diagnosis to determine the optimal harvest time.Several types of research have been conducted on the physical and mechanical properties of agricultural products in Iran and other countries. In a research conducted by Ali Mohammadi and Rasakh to determine some mechanical properties of lime fruit under quasi-static loading, the results showed that the effect of loading speed, loading direction and size of a lime on the breaking force of lime is significant. As the size of the lemon decreases, the breaking force and deformation decrease, and also with increasing loading speed, the braking force increases. In another research conducted by Mohd Nejad and Khosdada, the effect of size, speed and direction of loading on the mechanical properties of lime was investigated and the results showed that the interaction of loading speed and size on fracture energy and toughness and the main effects of size, loading speed and The loading direction is significant on the modulus of elasticity, but none of the effects on the rupture force is significant.

First, potatoes in 5 different varieties (Agria, Esprit, Sante, Marfona and Jelli) were prepared at Ardabil Agricultural Research Center and stored at 4-10 degrees Celsius. One day after preparing the varieties, 21 samples of each potato variety were prepared using a cutting cylinder and then data collection was done. The data collection included mechanical properties.To determine the toughness of the samples, the santam machine available in the mechanical properties laboratory of the biosystem engineering department of Mohaghegh Ardabili University was used. Each potato variety was subjected to a compressive force at three loading speed levels of 10, 40 and 70 mm/min and with 7 repetitions. Then, using the amount of braking force, deformation and sample volume, the toughness was calculated according to equation (1).
These experiments were carried out in 5 storage periods (at 2-week intervals).

The toughness of different cultivars showed different behavior during the storage period so no changes were observed in the Marfona cultivar for toughness during the storage period, and in the Sante cultivar, the toughness level was almost the same at the beginning and end of the period and only in the middle of the storage period the value There was a slight increase. But in the case of Agria, Sprit and Jali cultivars, it should be said that the changes in toughness do not follow a specific trend and are unpredictable. Also, according to Figure 3, it is quite clear that in all figures, the lower the loading speed, the greater the toughness obtained, and the reason for this is that at a lower loading speed, the breaking force occurs in high values. Falls, and as a result, according to relation 1, the toughness value also increases.According to Figure 3, during the storage period, the two varieties of Jelli and Marfona (especially the Marfona variety) did not change much in terms of toughness and considering this issue, it is recommended to use these two varieties for some purposes, including frying.In this research, firmness was calculated for 5 different varieties of potatoes in 5 storage periods using the santam machine available at Mohaghegh Ardabili University and with the help of equation 1. The results showed that Jali and Marfona cultivars maintained their firmness during the storage period, and hence they are recommended for uses such as chips.

Peach, as an edible fruit with an acceptable economic advantage, is mainly produced in the Mediterranean region and Central Asia and consumed all over the world. Flavor is one of the key factors in fruit quality, and it largely depends on the content of soluble sugars and organic acids. Sweetness, which is determined by the level of soluble sugars, is one of the main characteristics that affect consumer satisfaction. In the mature peach fruit, sucrose constitutes more than 54% of the total soluble sugars, which are mainly stored in the vacuole and occupy up to 90% of the total cell. However, the underlying mechanisms of sugar accumulation in peach fruit remain largely unknown.The complexity of food odor makes it difficult to analyze them with conventional analytical techniques such as gas chromatography. However, sensory analysis by experts is a costly process and requires trained people who can only work for a relatively short period of time. Problems such as the human subjectivity of the response to smell and the variation between people should also be considered. Hence, there is a need for a tool such as an electronic nose with high sensitivity and correlation with human sensory panel data for specific applications in food control. Due to its easy construction, cheapness and the need for little time for analysis, the electronic nose is becoming an automatic non-destructive method to describe the smell of food.An olfactory machine can recognize the fragrance composition by estimating its concentration or determining some of its intrinsic properties, which the human nose is hardly able to do. In general, the human olfactory system is a five-step process including smelling, receiving the scent, evaluating, detecting and erasing the effect of the scent. The olfactory phenomenon begins with inhaling the intended smell and ends with breathing fresh air to remove the effect of the scent. The human olfactory system, with all its unique capabilities, also has disadvantages that limit its use in quality control processes, including subjectivity, low reproducibility (for example, results depending on time, people's health, analysis before the presence of odor and fatigue is variable), time-consuming, high labor cost, adaptation of people (less sensitivity when exposed to odor for a long time). In addition, it cannot be used to evaluate dangerous odors.The purpose of this research was to evaluate the ability and accuracy of the electronic nose using chemometrics methods to detect and differentiate peach cultivars using their volatile compounds.

First, 5 varieties of peaches were prepared. After preparing different varieties of peaches, first, the samples were placed in a closed container (sample compartment) for 1 day to saturate the space of the container with the aroma and smell of peach fruit, and then the sample compartments were used for data collection with an odor machine.In this research, the electronic nose made in the Biosystems Engineering Department of Mohaghegh Ardabili University was used. In this device, 9 metal oxide semiconductor (MOS) sensors with low power consumption are used, which are listed in Table1.The sample chamber was connected to the electronic nose device and data collection was done. This data collection was done in such a way that first, clean air was passed through the sensor chamber for 100 seconds to clean the sensors from thepresence of odors and other gases. Then the smell of the sample was sucked from the sample chamber by the pump for 100 seconds and directed to the sensors, and finally, clean air was injected into the sensor chamber for 100 seconds to prepare the device for repetition and subsequent tests. 30 repetitions were considered for each sample.The chemometrics method in this research, started with principal component analysis (PCA) to discover the output response of the sensors and reduce the dimension of the data. In the next step, linear discriminant analysis (LDA) was used to classify 5 peach cultivars.Principal component analysis (PCA) is one of the simplest multivariate methods and is known as an unsupervised technique for clustering data according to groups. It is usually used to reduce the dimensionality of the data and the best results are obtained when the data are highly correlated, positively or negatively.

The scores chart (Figure 2) showed that the total variance of the data is equal to PC-1 (89%) and PC-2 (7%), respectively, and the first two principal components account for 96% of the total variance of the normalized data. When the total variance is higher than 90%, it means that the first two PCs are sufficient to explain the total variance of the data set. So it can be concluded that the e-Nose has a good response to the smell of peaches and it is possible to distinguish peach cultivars, which shows the high accuracy of the electronic nose in identifying the smell of different products.The LDA method was also used to identify and distinguish peach cultivars based on the output response of the sensors. Unlike the PCA method, the LDA method can extract multi-sensor information to optimize the resolution between classes. Therefore, this method was used to detect 5 varieties of peach based on the output response of the sensors. The results of the identification of cultivars were equal to 90% (Figure 3).
In this research, an olfactory machine with 9 metal oxide sensors was used to identify and differentiate peach cultivars using their scent. Chemometrics methods including PCA and LDA were used for qualitative and quantitative analysis of complex data from the electronic sensor arrays. PCA was used for data reduction and with two principal components PC1 and PC2, it described 96% of the variance of the data set and provided an initial classification, while LDA was able to accurately identify and classify grape cultivars. It became 90%. The scent machine has the ability to be used and exploited as a quick and non-destructive method to identify peach cultivars based on their smell. The use of this method in identifying peach cultivars will be very useful for consumers, especially processing units and food industries, in order to choose suitable cultivars.

Structural heterogeneity of fruits and vegetables makes it difficult to understand the associated physicochemical changes that occur during drying. Due to its heterogeneous structure, food is one of the most complex types of metamorphic materials. The porosity and hygroscopic nature of fruits and vegetables increase their shrinkage during the drying process, which is a physical process commonly observed during drying. Shrinkage has a significant effect on the mechanical and textural properties of fruits and vegetables. Most importantly, shrinkage is an important factor that has a great impact on drought rate and drought kinetics. Because of these factors, food researchers emphasize that shrinkage should not be ignored when predicting volume and heat transfer during drying. The shrinkage model is better suited to the experimental data during drying than the non-shrinkage model. Food shrinkage depends on several factors such as material properties, mechanical properties, and process status.Knowledge of porosity during drying can also help to accurately predict the transfer phenomenon and quality characteristics. Some researchers have used mathematical equations to predict the porosity of food as a function of moisture content, which can be classified into two categories: (1) theoretical models based on understanding of fundamental physics and the mechanisms involved in pore formation have been established, and (2) experimental models have been developed using parameters in experimental data. Many previous studies on experimental or laboratory shrinkage have predicted porosity as linear, quadratic, and exponential equations. On the other hand, theoretical modeling can provide a better understanding of the shrinkage that occurs simultaneously with heat and volume transfer during drying. However, limited efforts have been made in the theoretical modeling of the contraction of fruits and vegetables, due to the complexity of creating physics-based models. The first porosity model was introduced in the 1950s. Kilpatrick and colleagues proposed a simple model considering the volumetric contraction of fruits and vegetables during drying. Many models in previous research have considered shrinkage to be ideal, during which the reduction of the geometric volume of the product is exactly equal to that of water lost. But in fact, this linear relationship between the decrease in physical volume and the volume of water lost during the drying period is not observed. Cell loss and shrinkage of food tissues occur during the drying process of food. There is a fine distinction between shrinkage and loss, in that shrinkage refers to a reduction in food sample size, but loss indicates irreversible breakdown of cellular and tissue structure. Structural changes at the cellular level occur due to the transfer phenomenon during the dry period. As mentioned earlier, porosity and shrinkage during drying affect the transfer process as well as other quality characteristics. Accurate prediction of porosity and shrinkage helps design an advanced drying system to ensure quality products.Careful examination of theoretical and experimental models of porosity indicates the need for a simple model that can compensate for some of the limitations of theoretical models and use them for drying products and processes. Therefore, the aim of this study is to create a real contraction model with minimal use of experimental coefficients. A simple model considering heat gradient and humidity, glass transfer temperature, and drying time can be a potential way to predict structural changes during drying. Therefore, in this study, a new approach to contraction velocity is introduced. Therefore, paying attention to these parameters in shrinkage rate, process parameters, and material properties are considered in predicting metamorphism during drying. The physical meaning of shrinkage velocity is as follows: The velocity of the outer surface of the specimen during drying.

Apples were selected as the study sample in this study. Apples have high initial porosity and change of porosity during the drying period is very important. Therefore, it is expected that the experimental measurement of porosity changes and confirmation of the proposed model for this sample will be better. Kohn rose apples were prepared from a local supermarket and stored in a refrigerator at 2 ° C. The apples were selected from a box to have the same degree of ripeness. The treatment step was calculated using a liquid refractometer (BPTR-100 V3.0). The average ripeness of apples was 14.20 ± 0.20. The initial moisture content of fresh apples was calculated to be 77 ± 0.50% wb. 10 samples were used to measure the moisture content. Apples were removed from the refrigerator and washed at room temperature for one and a half hours. The skin of the samples was taken and cut into round pieces 10 mm thick and 40 mm in diameter. A hot air dryer with a fan was used. The drying temperature varied from 50 to 65 ° C and airspeed was set at 1 m / s. Particle density was measured using a gas (helium) pycnometer. The density of the mass was measured from the volume of the sample and the weight of the sample so that the sample was first coated with organic solvents to cover the open pores because there were numerous open pores that were large enough to be glass beads. They could have entered them. The density of the same sample was calculated before and after coating. The density of the glass beads was calculated from the weight of the required glass beads. The simulation was performed using COMSOL Multiphysics 5.6.0.280 Win / Linux. This software facilitates all stages of the modeling process including geometric structure definition, lattice, physical dimensioning, solving, and displaying results. COMSOL Multiphysics can manage variable properties that are a function of independent variables. A two-dimensional symmetry mode is also provided to facilitate the simulation process. There will be a small amount of 3D effects that can be ignored, and 3D consideration can complicate matters.

The physical quality of dried food depends on the degree of metamorphosis during drying. Shrinkage also has a significant effect on mechanical and textural properties as well as drying speed and kinetics. Accurate prediction of shrinkage can lead to better food quality and optimal drying process design. Food shrinkage depends on several factors including material properties, microstructure, mechanical properties, and process conditions. Experimental models can be created quickly that have a high impact. However, they do not show physical changes in the process. Physics-based models, on the other hand, are used as predictive models not only in food drying but also in other food industries. However, the theoretical model for predicting porosity is a complex one, due to the need for a number of properties that change under drying conditions. In this study, in order to counter the limitations of experimental and theoretical models, a simple shrinkage model based on the shrinkage rate was developed, which considers the main factors affecting porosity. The results show that the proposed model accurately predicts shrinkage and porosity, and this shows that the simulated shrinkage of the apple is related to the experimental results. For example, the porosity of the apple sample simulation is 0.6, which is consistent with laboratory data. The influence of desiccant air temperature and air velocity was also investigated. Studies show that process parameters (including air velocity and temperature) have a significant effect on the final porosity of the dried food. The porosity model proposed in this study requires the least experimental parameters. Future research could use this model to examine other foods because the structure of different foods is different, and this affects the porosity detection mechanism. Different types of process conditions can be used in future research to develop a general model for pore formation.

Walnut is an important economic and commercial product all over the world. The reflected light spectrum can be one of the key factors in determining the ripening time of the fruit and it depends on the content of the chemical compounds of the fruit and its skin. Crunchyness and easy peeling are the main features that affect the level of satisfaction of walnut consumers. The complexity of the reflectance spectrum of food makes it difficult to analyze them with conventional analytical techniques such as gas chromatography. However, sensory analysis by experts is a costly process and requires trained people who can only work for a relatively short period of time. A near-infrared spectrometer can detect the spectrum of reflected light by estimating its concentration or determining some of its inherent properties.The quality assessment of agricultural products includes two main methods, quality grading systems based on the external characteristics of agricultural products and quality grading systems based on internal quality assessment, which has gained outstanding points in recent years. In the meantime, several methods have been invented so far for the qualitative grading of agricultural products based on the assessment of their internal properties in a non-destructive way, and only some of them have been able to meet the above conditions and have been justified in terms of technical and industrial aspects. To be meanwhile, spectrometry can be highly efficient in determining the quality of cultivars. Spectroscopy is a type of system that has a different structure and approach from other methods (image processing, neural network, etc.) and can perform classification and determination of digit quality.With increasing expectations for food products with high quality and safety standards, the need for accurate, fast and targeted determination of the characteristics of food products is now necessary. Because manual methods do not have automaticcontrol, they are very tiring, difficult and expensive, and they are easily affected by environmental factors. Today, spectroscopic systems are non-destructive and cost-effective and are ideally used for routine inspections and quality assurance in the food industry and related products. This technology allows inspection works to be carried out using wavelength data analysis techniques and is a non-destructive method for measuring quality parameters. In this research, the ripening time of walnuts was investigated using spectrometry and chemometrics methods.

In each treatment period (in total 5 periods were considered and the intervals of periods were determined as one week), unripe walnut samples in addition to ripe samples (in the last period) were taken from one of the orchards around Ardabil (located in Shahrivar village) was prepared, tested and data collected.A spectroradiometer model PS-100 (Apogee Instruments, INC., Logan, UT, USA) was used to acquire the spectrum of the samples. This spectroradiometer is very small, light, portable, has a single-wavelength sputtering type with a resolution of 1 nm and a linear silicon CCD array detector with 2048 pixels that covers the spectral range of 250-1150 nm (Vis/NIR) well. Also, there is the ability to connect the optical fibre to the PS-100 spectroradiometer and transfer the data to the computer with the purpose of displaying and storing the acquired spectra in the Spectra Wiz software through the USB port. With the aim of creating optimal light in contrast mode measurements, an OPTC (Halogen Light Source) model halogen-tungsten light source, which can be connected to an optical fibre, was used. This light source has three output powers of 10, 20, and 30 watts, which were used in this research. Also, a two-branch optical fibre probe model (Apogee Instruments, INC., Logan, Utah, USA), which includes 7 parallel optical fibres with a diameter of 400 micrometres, was used in counter-mode measurements. After providing the necessary equipment, the optimal spectroscopic arrangement was designed and implemented in order to facilitate the experiments and minimize the effect of environmental factors during the spectroscopic process, which is shown in Figure 1.

The average absorption spectra of Vis/NIR absorption spectra for different treatments in the range of 680-970 nm are presented in Figure 1.Environmental factors (light and heat) as well as the spectrometer's expression quality cause disturbances in the initial and final wavelengths of the spectra, so some of these wavelengths are removed from the data set. And as it is clear in Figure 1, the samples had an almost similar trend; this may be affected by the colour of the samples. According to Figure 1, there are two distinct peaks for the spectra and it is that the peaks appeared around the wavelength of 680 and 970 nm. It can also be seen in Figure 1 that the amount of absorption of ripe walnuts is higher compared to other periods, which can be due to the difference in the content and texture of the product.Based on the PCA analysis results presented in Figure 2, the first principal component (PC-1) describes 94% and the second principal component (PC-2) describes 5% of the variance of the tested samples. As a result, the first two principal components together express 99% of the data. Considering that it is possible that the degree of correlation between the properties of different samples during the tests, due to various reasons such as technical problems of the equipment, data collection, incorrect sampling, etc., in some samples, inappropriate or so-called outliers.The values of R2 and RMSE for calibration and validation sets of different regression models (PLS) with raw and processed data are presented in Figure 3, which is equal to 0.98. The results show that the spectra are able to detect the ripening time of walnuts with high accuracy. Khodabakhshian et al investigated the potential of visible and infrared spectroscopy to classify the ripening stage and predict the quality traits of pomegranate varieties including SSC and TA. Among the methods of centring, Savitzky-Golay smoothing, median filter, standard normal variable, incremental spread correction (MSC) and differentiation with first derivative and second derivative, the use of incremental spread correction (MSC) has the highest accuracy in identifying pomegranate quality parameters. followed Zhang and colleagues (Zhang et al, 2018) in estimating the SSC of red Fuji apple using near-infrared spectroscopy to reduce noises using the functions of additive scatter correction (MSC) and standard normal distribution (SNV) and reported that the additive scatter correction method (MSC) compared to the standard normal distribution (SNV) will result in a more accurate estimate of the SSC value. Kim et al. estimated the SSC of oriental melon using near-infrared spectroscopy among different pre-processing methods including Savitzky-Golay smoothing, normalization with maximum and minimum, stable normalization, standardization, stable normal variable, distribution Standard normal (SNV) and incremental spread correction (MSC) reported that the best result was obtained with a standard normal distribution (SNV). Although considering the different nature of the samples, measurement methods and equipment, and other conditions affecting the spectral properties of the product, it is better not to compare the data obtained from different researches with each other.

Sweet potato grows as a strong plant all over the world and is a product compatible with drought, temperature, and low fertile soils. Potatoes are high in starch, vitamins, minerals, and non-mineral salts such as calcium, phosphorus, iron and low in calories. This product is widely consumed fresh, boiled, etc. due to its functions for various reasons, such as improving immunity and preventing cancer, and its consumption is due to the abundance of nutrients such as carbohydrates, dietary fiber, minerals and other health-promoting compounds such as beta-carotene, vitamin C, phenolic acids, etc. are on the rise.Conventional evaluation methods for the internal quality of potatoes are mostly destructive and inefficient. In the practical production of potatoes, the quality evaluation system must have good accuracy, high speed, and low cost. Such goals can be achieved using modern techniques such as spectroscopy and electronic nose, as they do not require sample preparation, are non-destructive, efficient, fast, accurate, pollution-free, and inexpensive.Organic acids (OAs) are organic acidic compounds containing carboxyl groups that are widely present in organisms. Organic acids in fruits mainly include citric acid, malic acid, tartaric acid, and succinic acid. The traditional method for detecting OA concentrations is ion chromatography in the laboratory. Ion chromatographic testing requires standard solutions as a reference, also requires the use of chemical reagents, and organic acids must be measured separately. This is a tedious operation that wastes a lot of time. Therefore, a rapid detection technology is needed and preferred as an alternative.Near-infrared spectroscopy is a type of rapid detection technology that extracts spectral information from a sample through the difference between radiated light and reflected light. NIR technology has the advantages of fast performance, no use of chemical reagents and is also able to detect multiple components simultaneously. Spectral signals can be further amplified by the combined use of the Fourier transform technique. Fourier transform near-infrared spectroscopy has been widely used in the fields of food science, agricultural informatics, environmental monitoring, biomedicine, and pharmacy.Based on the simplicity of PLS regression, nonlinear methods are investigated to improve the PLS algorithm by embedding nonlinear core functions. This method plots the data before PLS scoring in a high-dimensional feature space, and the data converted in the new space characterize the samples. In this study, a neural network as a core function is designed to optimize PLS in the quantitative NIR analysis of OA concentrations in potato samples. A three-layer lattice with an adjustable number of neural nodes is designed to extract spectral feature variables to optimize the PLS core model.

Potato samples were harvested and 248 of healthy size and almost the same size were selected. The samples were transferred to the laboratory 24 hours after picking and stored at room temperature for 2 days. In the next 5 days, about 50 glands per day were selected and their OA concentration and FT-NIR spectrum were identified. Each potato sample was divided into two parts, half of which were used to detect the OA concentration and the other half to measure the NIR spectrum. The FT-NIR spectrum was measured using a PS-100 spectroradiometer (Apogee Instruments, INC., Logan, UT, USA) made in the USA. Temperature and humidity were kept constant at 25 ° C and 47% during the spectrum study.PLS kernel is an improved PLS method to deal with the nonlinear problem of spectral data. Raw data is mapped by a special nonlinear core function in high-resolution image space, so the original PLS linear algorithm can be used to discover the relationship between feature data and sample analysis. In short, this method can be done in two consecutive steps of mapping and regression.In modern studies, a neural network is a good tool for operating dynamic data, as it is flexibly taught by automatically fitting its link weights to the data-based model. A three-layer neural network was constructed in this study as a new nucleus for PLS output in the quantitative NIR analysis of potato OA concentrations.All 248 potato samples were divided into three parts for calibration, validation, and testing. The calibration section is used to create models and teach the model structure as well as the main algorithmic parameters. The validation section is used to check the model and optimize the parameter values. And the test section to evaluate the model.All 248 potato samples were divided into three parts for calibration, validation, and testing. The calibration section is used to create models and teach the model structure as well as the main algorithmic parameters. The validation section is used to check the model and optimize the parameter values. And the test section to evaluate the model.

Core PLS regression was applied to create FT-NIR calibration models to quantify OA concentrations in potato samples. The proposed network architecture was used as a new kernel conversion function to select attribute variables. The network was created connected with an input layer, a hidden layer, and an output layer.All 3114 wave number variables were transferred to the input layer. The same number of input nodes were generated to accept the data, and then perceptron units were applied, converting the data into a hidden layer. In the case of using a data-driven learning mechanism, the number of hidden nodes varies from 10 to 200 with step 10. Each Nh value was tested to screen for the best latent structure. Perceptron calculations converted the hidden data into an output layer, and a total of 20 output neurons were generated in the output layer to reduce the dimensions. These output variables were mostly used for PLS regression.In general, neural perceptron units were adjusted with their link weights, which automatically matched the data. 20 output variables were delivered to the softmax MLR predictor. Predictive errors were used for 50 rounds of error-feedback repetition optimization on link weights. Figure 3 shows that the RMSEV gradually shrinks with more repetitions and gradually decreases for each Nh number. This phenomenon means that the initial feedback and error replication mechanism can optimize machine learning for the network kernel. Duplicate optimized network link weights were used to serve the network architecture as a core evaluation function to optimize PLS regression. . The most optimal network structure was constructed with 130 hidden nodes and 20 output nodes.Then, the optimal network structure constructed with 130 hidden nodes and 20 output nodes is used as the core function for PLS regression. Hidden PLS variables were selected by network search mode. We tested PLS regression models with f = 1, 2… 20 based on the optimal network core. The results of model training for validation samples are shown in Figure 4. The optimal number of latent variables was determined as f = 8. The results of the network core model prediction and common cores are listed in Table 2.According to the principle of sample division introduced, PLS core models were quantified for FT-NIR analysis of potato OA concentration based on calibration samples and optimized by validation samples. The PLS model of the selected optimal network core should then be evaluated by 64 experimental samples that were unique to the model training process. Spectral data of the experimental samples were entered into the core of the optimal network with 130 hidden nodes and 20 output nodes.Table 2 shows that for PLS kernel regression, the proposed network kernel performs better than conventional kernels, regardless of the model training process or in the model evaluation process. Therefore, using neural network architecture to optimize the PLS regression kernel is a practical idea. FT-NIR calibration models have clearly improved compatibility by the adjustable network core.

Potato is an important vegetable that grows all over the world and is considered an important product in developing and developed countries for the human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and its origin is from Peru, and after wheat, rice and corn, it is the fourth product in the food basket of human societies. According to the statistics of the Food and Agriculture Organization of the United Nations, the area under cultivation of this crop in Iran in 2017 was 161 thousand hectares and the crop harvested from this area is about 5.1 million tons. As expectations for food products with high quality and safety standards increase, it is necessary to determine their characteristics accurately, quickly, and purposefully. In the potato crop, quality evaluation, after harvest and isolation, is very important to provide a reliable and uniform product to the market, because the potato, like many other crops, has the non-uniform quality and care during the harvest stage. While the quality of raw potatoes is primarily determined by the size, shape, color, and attractiveness of the tuber, the quality of potatoes is generally determined by examining the quality of the final product. The quality of processed products is examined in terms of color, flavor, and texture. The quality of most processed products stems from the quality of raw potatoes. Uniformity in size, shape, and composition is essential for optimal quality. During storage, processing, or cooking, potatoes are exposed to a variety of phenomena that affect the final quality of the product. For consumers, the main quality characteristics of potatoes are color, size, and texture. However, quality assessment for industrial potato processing includes various parameters such as dry matter content, starch content and characteristics, shelf life after storage (storage), and after processing. The type of cultivar, physical and chemical composition, and post-harvest storage are important factors that can affect the cooking characteristics of potatoes and potato crops. Quality assessment of agricultural products includes two main methods, quality rating systems based on the apparent properties of agricultural products and quality rating systems based on internal quality assessment, which has gained prominence in recent years. In the meantime, several methods have been developed so far for non-destructive quality classification of agricultural products based on the evaluation of their internal properties, only some of which have been able to meet the above conditions and are technically and industrially justified. To be. In the meantime, spectroscopy can have high efficiency in determining the quality of figures. Spectroscopy is a system that has a different structure and approach from other methods (image processing, neural network, etc.) and can classify and determine the quality of the digit.

First, 3 different potato cultivars were prepared from Ardabil Agricultural Research Center. After preparing the data, data were collected to determine the amount of sugar (SSC) and at the same time, the samples were tested with a spectrometer to determine the wavelengths of the samples. The glucose level of each sample was measured in 18 replications using an SBR-62T ocular refractometer. To do this, the water of the samples was placed on a refractometer at ambient temperature and its sugar level was read in terms of Brix. A PS-100 spectroradiometer (Apogee Instruments, INC., Logan, UT, USA) made in the USA was used to obtain the spectrum of the samples. This ultra-small, lightweight, portable spectrophotometer has a 1nm sprayer-type single-diffuser and a linear silicon CCD array detector with 2048 pixels, which has a range of 250-150 nm (Vis / NIR) cover. There is also the ability to connect fiber optics to the PS-100 spectroradiometer and transfer data to a computer for the purpose of displaying and storing the acquired spectra in the Spectra Wiz software via the USB port. The data obtained from spectral imaging may be affected by the scattering of light by the detector by changing the sample, changing the sample size, surface roughness in the sample, noise caused by the temperature of the device and many other factors, and unwanted information Affect the accuracy of calibration models. Therefore, data processing is required to achieve stable, accurate, and reliable calibration models. The application of non-destructive methods based on spectroscopy in the full range of wavelengths requires a lot of time and money, which makes the practical application of this method almost impossible; therefore, one should look for a way to find the optimal wavelengths and limit the wavelengths to the minimum possible. The partial least squares (PLS) regression method seems ideal in this regard. In this study, in order to build the models, the data were randomly divided into two parts: 80% of the samples were used for cross-training and cross-validation and the rest of the data were used for independent validation.

Mean absorption spectra Vis / NIR absorption spectra for different treatments in the range of 1000-500 nm are shown in Figure 1. Environmental factors (light and heat) as well as the quality of spectrometer expression cause perturbations in the initial and final wavelengths of the spectra, so part of these wavelengths are removed from the data set and as shown in Figure 1, the samples had a roughly similar pattern; This may be due to the color of the samples. According to Figure 1, there are two well-defined peaks for the spectra, and it appears that for the Colombo and Sante cultivars the peaks appeared at around 480 and 1000 nm and for the Milwa cultivar at around 540 and 950 nm. Figure 1 also shows that the absorption rate of the Milwa cultivar is higher than the other two cultivars, which can be due to differences in the number of different substances such as sugar or SSC. Based on the analysis (PCA) results presented in Figure 2, the first principal component (PC-1) describes 67% and the second principal component (PC-3) describes 27% of the variance of the samples tested. As a result, the first two principal components together represent 94% of the data. Due to the fact that the relationship between the properties of different samples during the tests, for various reasons such as technical problems of equipment, data collection, incorrect sampling, etc. in some samples is inappropriate or to correct. To be out. The values of R2 and RMSE for the calibration and validation sets of different regression models (PLS) with raw and processed data are presented in Figure 3, which is equal to 1.

Annual herbaceous rice, standing, rooted, shallow, strong, and white, belongs to the Oryza family, belonging to the Oryzeae family. Rice is the staple food of about 2.5 billion people, which is about 20 percent of the energy needed, and provides protein for 15 percent of the world's population. In general, tropical and subtropical countries Burma, Thailand, Vietnam, Laos, Indonesia, Philippines, Pakistan, India, USA, Japan, Italy, Egypt, China, Brazil, Cuba, Mexico, and Australia are the main rice producers in the world. Among them, Sadri, Tarom, and Hashemi cultivars are among the best and most high-quality rice cultivars native to Iran, and the most productive cultivars of this country can be Caspian, Speedroad, Sahel, Kadous, Shafaq, Darfak, Gohar and Neda pointed out. Accurate determination and evaluation of odor in rice require identification of substances affecting odor in parallel with the development of methods for determining their amount. More than 3 decades have passed since the beginning of studies related to recognizing the creative and effective factors in rice aroma. Much research has been done in the field of using more efficient and faster methods in identifying rice volatiles and identifying the main causes. Of the more than 100 known compounds in rice, a few are effective in creating its aroma and aroma. In the meantime, the electronic nose can detect volatile compounds in rice. The electronic nose has been used in extensive research to identify and classify food and agricultural products. Pandan leaf aroma of rice is a special feature and is used to differentiate the quality of rice. Quality determines whether it has a certain percentage of cleanliness and purity or not. Aromatic rice is usually preferred by consumers due to its good quality, which includes delicacy, shape, colour, aroma, taste, and consumers use aromatic rice for celebrations and occasions due to high demand and use good quality. The quality of aromatic rice is influenced by various factors such as cultivation location, climatic conditions, genetic activities and post-harvest. Important issues in the rice industry include quality control, incorrect labelling, grading and fraud in different types of rice. For this reason, the rice industry uses standard grades based on market criteria to identify grain. Due to these factors, quality control and fraud are the main issues that are wrong labelling and grading are the main problems. The use of human expert panels is the most common technique used to evaluate the quality of aromatic rice. They distinguish rice based on its aroma. With the rapid and rapid advancement of computer technology and sensor technology, the application of the bionic electronic nose, including a semiconductor gas-sensitive sensor and a pattern recognition system as a means of detection, offers a new method for rapid classification and digit recognition. Give. The electronic nose has also introduced a new method for classifying and detecting rough rice in a non-destructive and fast way. The aim of this study was to evaluate the ability and accuracy of the electronic noses using one of the chemometrics methods to distinguish pure rice cultivars from 3 gross cultivars.

First, 4 rice cultivars were prepared from the Iranian Rice Research Center located in Rasht. These 4 cultivars included 1 high-quality rice cultivar named Hashemi and 3 substandard rice cultivars named Neda, Khazar, and Sahel. Therefore, in the experiments, one genuine rice cultivar (Hashemi) and three non-genuine or counterfeit cultivars (mixture of Caspian, Neda, and Sahel cultivars with Hashemi cultivars) were prepared, so that the counterfeit cultivars each contained 80% of Hashemi cultivars and 20% of substandard cultivars. After preparing and mixing the cultivars, first, the samples were placed in a closed container (sample container) for 1 day to saturate the container with the aroma of rice, then the sample containers were used for data collection with an electronic nose. Were located. In this research, an electronic nose made in the Department of Biosystem Engineering of Mohaghegh Ardabili University was used. In this device, 9 low-power metal oxide (MOS) semiconductor sensors are used, which are given in Table 1 of the sensor specifications. The sample chamber was connected to the electronic nasal device and data collection was performed. The data collection was done by first passing clean air through the sensor chamber for 150 seconds to clear the sensors of odours and other gases. The sample odor was then sucked out of the sample chamber by the pump for 150 seconds and directed to the sensors, and finally, fresh air was injected into the sensor chamber for 150 seconds to prepare the device for repetition and subsequent tests. 22 replicates were considered for each sample. The study started with the chemometrics method with principal component analysis (PCA) to detect the output response of the sensors and reduce the data dimension. Principal component analysis (PCA) is one of the simplest multivariate methods and is known as an unsupervised technique for clustering data by groups. It is usually used to reduce the size of the data and the best results are obtained when the data are positively or negatively correlated. Another advantage of PCA is that this technique reduces the size of multidimensional data while eliminating additional data without losing important information.

The scores diagram (Figure 1) showed the total variance of the data equal to PC-1 (99%) and PC-2 (0%), respectively, and the first two principal components constitute 99% of the total variance of the normalized data. When the total variance is greater than 90%, it means that the first two PCs are sufficient to explain the total variance of the data set. According to the shape of Hashemi's main cultivar (a) on the left side of the chart and 3 fake cultivars (b, c, and d) are visible, which are well separated by the PCA method. Therefore, it can be concluded that e-Nose has a good response to rice odor and it is possible to distinguish between original and counterfeit rice cultivars, which shows the high accuracy of electronic nose in detecting the smell of different products. The correlation loadings plot diagram can show the relationships between all variables. The loading diagram (Figure 2) shows the relative role of the sensors for each principal component. The inner ellipse represents 50% and the outer ellipse represents 100% of the total variance of the data. The higher the loading coefficient of a sensor, the greater the role of that sensor in identifying and classifying. Therefore, sensors mounted on the outer circle have a greater role in data classification. According to the figure, it is clear that all sensors have played an important role in identifying rice cultivars, including the role of sensors No. 1 and 9, which are the same sensors MQ9 (to detect carbon dioxide, combustible gases) and MQ3 (to detect). Alcohol, methane, natural gases) were slightly less than the other sensors, which can be reduced by removing these two sensors to reduce the cost of making the olfactory device (to detect genuine and counterfeit rice) and save costs. In this study, an electronic nose with 9 metal oxide sensors was used to identify and distinguish between original and counterfeit rice cultivars. PCA chemometrics method for qualitative and quantitative analysis of complex data, an electronic sensor array was used. PCA was used to reduce the data and with 99 main components PC1 and PC2, it described 99% of the variance of the data set and provided a preliminary classification. The electronic nose has the ability to be used and exploited as a fast and non-destructive method to detect genuine and counterfeit rice cultivars. Using this method in identifying rice cultivars will be very useful for consumers, especially in restaurants and halls, in order to select pure and high-quality cultivars.

Potato with the scientific name Solanum tuberosum. L is a plant that is cultivated as an important crop in all countries and is known in the human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and originally from Peru. Potato is the fourth crop in the food basket of the people after wheat, rice and corn, which sometimes replaces rice in Iran and is in the second place, which shows its importance in meeting the nutritional needs of the people. According to the reports of the Food and Agriculture Organization of the United Nations, the area under potato cultivation in Iran in 2019 was more than 164 thousand hectares and the harvest from this area was about 5.32 million tons. In the food industry, this product is converted into a variety of products such as baked potatoes, fried potatoes, potato chips, potato starch, dried fries and so on. Due to the increasing expectations for food products with high quality and safety standards, accurate, fast and purposeful determination of food characteristics is essential. In the potato crop, quality evaluation after the harvest stage seems necessary to provide a reliable and uniform product to the market, because the potato, like many other products, has a non-uniform quality and care during the harvest stage. - Be. In addition, food safety and desirability play an important role in the food industry and is directly related to people's health. In addition, a large part of the potatoes used in the processing industry, potatoes are stored, so given the importance of this food and the demand of the people throughout the year, only through optimal and long-term storage can meet the needs of applicants. Was responsive. Potatoes for the processing industry must have some requirements such as low sugar content, dry matter and high specific gravity, high antioxidants, light skin color and no germination. Stored potatoes may be sweetened, rotted, dehydrated, and sprouted during storage. Post-harvest storage conditions can cause changes in chemical composition and product quality. Therefore, the management of potato tubers is very important in all stages of production and storage. Potato changes in storage depend on the variety, storage conditions. Although potato storage is very necessary for domestic and industrial use, due to its chemical and physical changes in the warehouse, it should be said that the characteristics of high quality potatoes in commercial exchanges of this product include more than 70 to 80% of tubers. Light-colored, uniform, firm, no bruising, no scaling, no cracks, no insect damage, rot and greening. Post-harvest storage conditions can cause many changes in the chemical composition of the potato tuber, resulting in changes in the quality characteristics of the final product. Sugar and starch are the main components that are affected by postharvest metabolism in the potato tuber and may ultimately affect their texture, sensory and cooking properties. The quality of potatoes and, consequently, the quality of processed products, depends significantly on the cultivar and environmental conditions, both during the growing season and during storage.

First, potatoes were prepared in 5 different cultivars and stored at 4-10 ° C. Data collection included measuring sugar and carbohydrate levels during storage.The sugar content of each sample was measured in three replications using a liquid refractometer available at Mohaghegh Ardabili University. To do this, first some water was taken from the samples and after pouring into the microtube, it was placed in a refrigerated centrifuge, and after rotating at a speed of 1800 rpm for 2 minutes, the impurities were deposited and the pure liquid was separated. After reaching ambient temperature, the liquid was placed on a refractometer and its sugar level was read in terms of brix.The amount of carbohydrates in the samples was extracted using the equipment available in the central laboratory of Mohaghegh Ardabili University. This operation was performed by the Skigel method. Glucose was used to prepare the standard curve. Consecutive dilution of glucose Preparation and color development at 490 nm for different concentrations of glucose were controlled and one ml of distilled water was used as a blank. This standard curve was used to calculate the total concentration of carbohydrates in the samples.For each sample, sampling was performed in three replications and the amount of absorption wavelength was obtained, then the amount of carbohydrates was calculated by placing the wavelength in Equation (1).

According to the analysis of variance table, the interaction effect of cultivar and storage period on potato sugar content was significant at 1% probability level. You can see the changes in the sugar content of potato cultivars along the storage valley in Figure 4. According to Figure 4, the highest amount of sugar is related to Sprite cultivar and the lowest amount is related to Jali cultivar. Meanwhile, the sugar content of Agria and Jeli cultivars was the same at the time of harvest. Also, after 1 month from the time of potato harvest, the sugar content of Agria and Marfona cultivars were equal and this equality continued until the end of storage period. The reason for the difference in sugar content between different cultivars is mainly related to the type of soil, fertilizer and toxin used. According to the chart, the amount of sugar in all 5 potato cultivars during the storage period first decreases and then with increasing storage period, the amount of sugar also increases.According to the analysis of variance table, the interaction of cultivar and storage period on the amount of potato carbohydrates was also significant at the level of 1% probability. Carbohydrate variations of potato cultivars along the storage valley are shown in Figure 5. According to Figure 5, the highest amount of carbohydrates is related to Sante cultivar and the lowest is related to Marfona cultivar. Also, at the end of the storage period, Marfona and Agria cultivars had the same amount of carbohydrates. As you can see, the amount of potato carbohydrates has decreased over time and with increasing storage time. Among these cultivars, the carbohydrate content of Marfona and Agria cultivars was higher than other cultivars. Also, carbohydrate changes

The wheel is one of the simple and important components of the tractor because it must bear the weight of the car and also communicate the car with the ground. The tire pressure determines the tire stiffness, which has a significant effect on the tire contact surface and ground pressure distribution. Adjusting the air pressure inside the tire as a possibility to reduce soil compaction and improve the tensile efficiency of agricultural tractors. The shape of the contact surface of a wheel with the ground has a certain complexity due to the curvature of the wheel and the flexibility caused by the load on the wheel and the internal wind pressure of the wheel. Hence, several models have been proposed by researchers to estimate this parameter in accordance with wheel and surface conditions. Checking the contact surface of the wheel with the soil is important in two ways: Energy loss and Negative impact on product growth and production.

Wheel and soil tests are mainly performed under controlled conditions and are usually performed in the form of single-wheel testers in the soil storage environment. In these environments, it is possible to have more control over the wheel and soil variables. A typical agricultural tire (Barez Co., Iran, 8.25-16) with the following specifications was used in the experiments: HLFS flower tire specifications, rim width 175 mm, outer diameter 840 mm and cross section width 220 mm. Two soils were used in this study: sand which was clay loam clay with 13.8% sand, 79.31% sand and 6.89% of the tested soil, from a sieve score of 200 which is the size of Its holes, about 0.075 mm, had passed. The experiments were performed after preparing the soil storage and the single-wheel tester set. Prior to each experiment, the soil inside the canal was completely shaken by nail pruning to a depth of 20 cm. Then, with the help of a timber installed to the wheel carrier, the soil surface was leveled well. By placing the tester set on the track, a dynamic load was applied through a power screw. Dynamic loads on the wheel were considered 1814.85, 2207.25, 2599.65, 290.05 and 3384.45 kN at five levels. The amount of load is measured by the load cell and read on the screen and finally stored. The tire pressure was applied at three levels of 100, 200 and 300 kPa by a 600 liter compressor, 8 bar pressure and 5.5 hp. Wind pressure was measured and controlled by a Borden Gauge sphygmomanometer. After placing the tire on the ground (under a certain wind pressure and load), some gypsum powder was sprayed around it. The tire was then lifted off the ground and photographed from a fixed distance by the wheel on the ground with a digital camera. All images are processed using AutoCAD 2015 software (Autodesk, Inc., USA) to calculate the numerical value of the contact area (figures 2, 3). Equation 1 was used to determine the contact pressure between the tire and the soil. The experiments were performed factorially in a completely randomized design with three replications. Independent variables were: soil type (in two levels of clay and sand), vertical load (in five levels of 1814.85, 2207.25, 2599.65, 295.05, and 3384.45 kN) and tire pressure (in three levels of 100, 200 and 300 kPa). The dependent variables were: the contact surface between the wheel and soil and the contact pressure between them. Data were analyzed using SAS 9.1 software (SAS Institute, USA) and Duncan's multiple range test was used to compare the means.

In this study, the effects of tire pressure and vertical load on the wheel in two clay and sand substrates on the contact surface and contact pressure between soil and tire were investigated. Table 1 shows the analysis of variance of the test data obtained from the tests. The results showed that the simple effects of soil type, tire pressure and vertical load on the wheel on the tire contact surface with soil were significant at 1% level. Regarding the contact pressure between the tire and the soil, except for the simple effect of soil type which was significant at the 5% level, the other simple effects were significant at the 1% level. In addition, dual and triple interactions were also significant on the contact surface and contact pressure between the tire and the soil at the 1% level. Figures 4 and 5 show the trend of changes in the tire contact surface with the soil. As can be seen, the contact surface area increases with increasing vertical load on the wheel and decreases with increasing tire pressure. Figures 6 and 7 also show the trend of contact pressure changes between the tire and the ground. As it is known, the contact pressure between the tire and the ground has increased with increasing vertical load on the wheel as well as the tire pressure. Based on the findings of this study, it was found that with increasing tire pressure at different loads on the wheel, the contact pressure between the wheel and the soil increased. The changes in contact pressure were linear in terms of changes in tire pressure in sandy soil and at loads of 2207.257 and 2599.6599 kN in clay soil. However, in clay at loads above 2599.65 and below 2207.225, contact pressure changes did not show linear behavior. Also, similarly, the contact surface of the wheel with the soil changed under the influence of these factors, but in reverse. The contact surface in sandy soil had an inverse linear relationship between tire pressure and in clay, except for the mentioned loads, it had the same inverse linear relationship. In at all, it can be stated that with the change of tire pressure and vertical load on the wheel, changes in contact surface and contact pressure in sandy soil were almost linear and in clay soil were only linear in some conditions. It seems that because sandy soil had a more uniform texture composition, this linear relationship occurred, but since clay soil didn’t have a more uniform composition, a linear relationship did not occur.

Grape is a creeping plant that has ivy in front of some of its leaves. France, Italy and Germany are among the most important grape producing countries in Europe, and Iran is one of the most important centers for grape production and cultivation in the world due to its favorable geographical and climatic conditions. Grape fruit is divided into two types, seeded and seedless, each of which is found in different colors of red, yellow, black and almost green. In areas where the maximum temperature is not more than 40 degrees Celsius and the minimum temperature is not less than 15 degrees Celsius below zero, grape fruit grows better. Grapes are made from raisins, jellies, raisins, jams, vinegar and juice, and various products are made from grape seeds. This product is a good source of potassium, fiber and a variety of vitamins and other minerals. Is. According to available reports, there are about 800 to 1000 grape cultivars in Iran, and some of these cultivars are of great economic importance, especially for fresh consumption and preparation of raisins. In Iran, edible grapes are of the genus Winifra, and in addition, there are two types of Labrosca grapes, which are scattered in the north of the country, and wild grapes of the subspecies Westeris in the northern forests and wetlands of the Zagros Mountains. Grapes are widely distributed in terms of climate and have recently been cultivated in temperate and tropical regions in all parts of the world. By recognizing grape cultivars before fruit growth, it is an effective step in determining the purpose and use of the harvest product, in the meantime, the type of grape cultivar can be identified using new post-harvest technologies. One of these methods is to use an electronic nose to identify volatile compounds in grape leaves and to identify its cultivar. Electronic nose has been used in extensive research to identify and classify food and agricultural products.

First, 3 varieties of grape leaves were obtained from vineyards located in Bonab city of West Azerbaijan province. These 3 cultivars were: Jovini, Aq Shaliq and Qara Shaliq. 200 grams of each of these leaves were prepared. After preparing leaves from different grape cultivars, first the samples were placed in a closed container (sample container) for 1 day to saturate the container space with the aroma of grape leaves, then the sample containers were used for data collection with the case of the electronic nose.In this research, an electronic nose made in the Department of Biosystem Engineering of Mohaghegh Ardabili University was used. This device uses 9 low-power metal oxide (MOS) semiconductor sensors.The sample chamber was connected to the electronic nose and data collection was performed. The data collection was done by first passing clean air through the sensor chamber for 100 seconds to clear the sensors of odors and other gases. The sample odor was then sucked out of the sample chamber by the pump for 100 seconds and directed to the sensors, and finally fresh air was injected into the sensor chamber for 100 seconds to prepare the device for repetition and subsequent tests. 30 replicates were considered for each sample.The study began with the chemometrics method with principal component analysis (PCA) to detect the output response of the sensors and reduce the data dimension. In the next step, linear detection analysis (LDA) and support vector machine (SVM) were used to classify 3 grape cultivars. Principal component analysis (PCA) is one of the simplest multivariate methods and is known as an unsupervised technique for clustering data by groups. It is usually used to reduce the size of the data and the best results are obtained when the data are positively or negatively correlated with each other.Linear Detection Analysis (LDA) is the most common monitored technique for separating samples into predetermined categories. This technique selects independent data variables to differentiate the sample that is to follow the normal distribution. The LDA is based on linear classification functions in which intergroup variance is maximized and intragroup variance is minimized.

The scores diagram (Figure 2) shows the total variance of the data equal to PC-1 (82%) and PC-2 (11%), respectively, and the first two principal components constitute 93% of the total variance of the normalized data. When the total variance is above 90%, it means that the first two PCs are sufficient to explain the total variance of the data set. Grape cultivars are well differentiated by PCA method. Therefore, it can be concluded that e-Nose has a good response to the smell of grape leaves and grape cultivars can be distinguished from each other, which shows the high accuracy of the electronic nose in detecting the smell of different products. The correlation loadings plot diagram can show the relationships between all variables. The loading diagram (Figure 3) shows the relative role of the sensors for each principal component. The inner ellipse shows 50% and the outer ellipse shows 100% of the total variance of the data. The higher the loading coefficient of a sensor, the greater the role of that sensor in identifying and classifying. Therefore, the sensors located on the outer circle have a greater role in data classification and it is clear that the three sensors TGS2620, TGS822 and TGS813 have played an important role in identifying grape cultivars from their leaf aroma.LDA and SVM methods were used to identify and differentiate grape cultivars based on the output response of sensors. Unlike the PCA method, the LDA method can extract multi-sensor information to optimize resolution between classes. Therefore, this method was used to detect 3 grape cultivars based on the output response of sensors. The results of detection of cultivars were equal to 100% and also the accuracy of SVM method for detection of 3 grape cultivars was equal to 83.33% (Figures 4 and 5).In this study, an electronic nose with 9 metal oxide sensors was used to identify and differentiate grape cultivars using their leaf aroma. Chemometrics methods including PCA, LDA and SVM were used for qualitative and quantitative analysis of complex data using electronic sensor array. The electronic nose has the ability to be used and exploited as a fast and non-destructive method to distinguish grape cultivars from leaf odor. Using this method in identifying grape cultivars will be very useful for consumers, especially processing units and food industries in order to select appropriate cultivars.

Potato is an important vegetable that grows all over the world and is considered as an important product in developing and developed countries for human diet as a source of carbohydrates, proteins, and vitamins. This product is native to South America and its origin is from Peru, and after wheat, rice and corn, it is the fourth product in the food basket of human societies. According to the statistics of the Food and Agriculture Organization of the United Nations, the area under cultivation of this crop in Iran in 2017 was 161 thousand hectares and the crop harvested from this area is about 5.1 million tons. Traditional methods of determining potato varieties were based more on morphological features, but with the production of new products, there was a need for methods that were faster and more recognizable. Meanwhile, high-performance artificial neural network can be used to classify cultivars. Artificial neural network can classify and detect cultivars, is flexible and is used in most agricultural products. Azizi conducted a study on 120 potatoes in 10 different cultivars using a visual and image processing machine with a MATLAB R2012 software toolbox to detect texture, shape parameters and potato cultivars. First, potato cultivars were classified using LDA method, which obtained 66.7% accuracy. This method also erred in distinguishing the two cultivars Agria and Savalan and also classified the two cultivars Fontane and Satina in other classes. They also used artificial neural networks to classify potato cultivars, in which the network was 82.41% accurate with one hidden layer and 100% accurate with two hidden layers. In this study, it was found that different types of potatoes can be identified and identified with a very high level of accuracy using the three color characteristics, textural and morphological features extracted by the visual machine and the use of a non-linear classifier artificial neural network. Categorized.By determining and examining the existing relations between the force and the deformation of agricultural products up to the point of surrender, the range of forces harmful to fruit can be determined so that harvesting and transportation machines are designed in such a way that the forces from them do not exceed this range. On the other hand, one of the ways to determine the degree of ripeness of the fruit is to touch and press it with the thumb, which is an experimental way and depends on the skill of the person touching. The mechanical penetration test of the fruit can be an indicator to check the ripeness of the fruit by quantifying this diagnosis and using this diagnosis to determine the optimal harvest time.

First, 5 different potato cultivars were prepared from Ardabil Agricultural Research Center and kept at a temperature of 4-10 ° C. One day later, 21 samples of each potato cultivar were prepared using a cutting cylinder and then data were collected. To determine the toughness of the samples, the Centam device available in Mohaghegh Ardabili University was used. Each potato cultivar was subjected to compressive force at three levels of loading speed of 10, 40 and 70 mm / min with 7 repetitions. Then the amount of toughness was calculated according to Equation (1). Then linear diagnostic analysis (LDA) and artificial neural networks (ANN) were used to classify potato cultivars. LDA is a supervised method used to find the most distinctive special vectors, maximizing the ratio of variance between class and within the class, and being able to classify two or more groups of samples. ANN and pattern recognition were used to find similarities and differences in the classification of potato cultivars. For this, 1 neuron was considered for the input layer, the hidden layer with the optimal number of neurons will be considered and five output neurons with Depending on the number of output classes the target will be considered. In network training, the logarithmic sigmoid transfer function and Lunberg-Marquardt learning method were used (Figure 4), and the error value was calculated using the mean square error. For learning (70%), testing (15%) and validation (15%) all data were randomly selected. Training data was provided to the network during the training and the network was adjusted according to their error. Validation was used to measure network generalization and completion of training. Data testing had no effect on training and therefore provided an independent measurement of network performance during and after training. All of the calculations and matrix classification were performed using MATLAB R2018a and X 10.4 Unscrambler software.Toughness in 5 different potato cultivars was obtained using Centam machine and Equation 1. The values obtained for the toughness of 5 potato cultivars were analyzed using Mstatc software. The results of analysis of variance were significant for the toughness of 5 different potato cultivars at the level of 1% and its coefficient of variation was 2.28. LDA and ANN methods were used to detect potato cultivars based on the values calculated for toughness. Detection results of cultivars using LDA were equal to 70.48% (Figure 6). Also, the accuracy of ANN method according to the perturbation matrix was equal to 72.4% (Figure 7).

In this study, the amount of toughness for 5 different potato cultivars was calculated using Centam machine available in Mohaghegh Ardabili University with the help of Equation 1. Chemometrics methods including LDA and ANN were used for qualitative and quantitative analysis of data to identify and classify potato cultivars. Thus, LDA and ANN were able to identify and accurately classify different potato cultivars with an accuracy of over 70%. The obtained toughness has the ability to be used as a method to distinguish different potato cultivars. The use of this method in identifying potato cultivars will be very useful for factories such as chips factory and processing units, and it is also expected that similar methods related to mechanical properties such as crispness and stiffness with the help of chemometrics methods to optimize production and The processing of agricultural products should be used in the food industry, which has led to more customer friendliness and, in addition, can reduce agricultural waste.