جستجوی مقالات مرتبط با کلیدواژه "electronic nose" در نشریات گروه "مهندسی شیمی، نفت و پلیمر"

Today, human’s specific attention to food quality has led to the development of fast, easy and non-destructive methods to assess the quality of foodstuffs. Meat is one of the most important foods and its freshness is considered as the most important qualitative feature. Therefore, checking its quality for consumption has great value worthwhile. The main objective of the present study is to investigate the possibility of using electronic nose and artificial neural network methods for detecting the freshness of chicken meat during storage in a refrigerator at 4 ºC. In the used neural network system, the input layer consists of 10 neurons based on the number of sensors and the output layer includes 3 neurons related to classes of different freshness classes of chicken meat. Different classifier networks were designed and after investigation of different network structures; the best structure of the network was obtained with a hidden layer and 6 neurons in that layer. Finally, the optimal network with a general structure of 10-6-3 was created to detect the freshness of chicken meat during different days of storage. The used statistical indices to assess the classifier to evaluate the freshness of chicken meat including accuracy, precision, sensitivity, specificity and area under the curve factors. The values of these indices for classification using selected characteristics are 95.77, 94.7, 92.18, 95.95, and 94.1 respectively. Therefore, given that the main objective of the present study was to develop and implementation of an intelligent diagnosis system of chicken meat freshness using an electronic nose system. The acceptable obtained results of the present study indicate that the proposed applied system based on the electronic nose system and artificial neural networks methods as a smart and reliable method can online classification of chicken meat as fast, easy, economical, non-destructive and with appropriate accuracy.

Tea is one of the strategic products in north of Iran. The tea produced in tea factories have different qualities as it is affected by various factors such as weather conditions during growth, soil, harvest time, as well as processing and preparation methods. In addition to its appearance, other essential properties of tea are its chemical compounds and aromatic characteristics. Investigating new and accurate methods for tea quality assessment has a significant effect on the development of tea processing industries. In this research, an electronic nose system was used to extract the characteristics of tea aroma and applying of these features for qualitative classification of black tea. Extracted Features from a sensor array, including ten different metal oxide gas sensors (MOS) were used for classification of five qualitative categories of black tea by means of chemometric methods. Results showed that the best classification performance was obtained by Artificial Neural Network (ANN) with a total classification accuracy of 88.00%. Also, Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) resulted in accuracies of 78.00% and 86.67% respectively. Based on the results of Principle Components Analysis (PCA), it was found that MQ7 and MQ2 sensors had the highest effect on the separation of different classes of tea. Generally, the performance of electronic nose system was suitable for qualitative classification of Iranian black tea.

Spices in addition to effect on the taste and quality of food, it also increases the shelf-life of foods because of its antimicrobial or antioxidant properties. Different types of spices have various quality and economic value based on their geographical origin. Therefore, classification and separation based on geographic origin are of great interest to consumers and sellers and is particular importance. In this research, the ability of an electronic nose based on metal oxide semiconductor sensors as a non-destructive tool for detecting the geographical origin (India, China and Pakistan) of three spices of black pepper, cinnamon and turmeric was studied. Temperature modulation was performed as a sinusoidal voltage pattern and transient responses of sensors were analyzed for data analysis. Principal component analysis (PCA), linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural network (ANN) were the methods used to achieve this goal. The results showed that the data visualization using the PCA method, created a completely distinct cluster on the PC's deformed space. By using the LDA, SVM and ANN methods, the classification accuracy was 100% based on the geographical origin for all three spices. Also, verification of these models was carried out and accuracy of 100% was achieved. Therefore, we can conclude that the electronic nose based on metal oxide semiconductor sensors under temperature modulation and in combination with the chemometrics methods as an effective and efficient tool can be used for fast and non-destructive classification of black pepper, cinnamon and turmeric samples based on geographical origin.