جستجوی مقالات مرتبط با کلیدواژه « Identification » در نشریات گروه « مکانیزاسیون کشاورزی »

Various methods have been performed to control weeds in the world and the use of herbicides is one of them, but public concerns about human health have changed interest in alternative methods. Thermal methods based on flame-weeder, hot air, steam, and hot water have the potential to control weeds, but due to the high cost are not economical. Electromagnetic waves transfer energy into weeds and finally destroy them. The effect of radiation on plant mutation, high consumption of energy, and human health are problems for this approach. Unlike other methods, electrical energy is an ideal and non-chemical method for weeds. This method applies high voltage to weeds, their roots, and soil so that electric currents pass through them, and the vaporization of the liquid content of weeds kills the weeds. To increase the severity of damage to weeds, the development of a feedback mechanism is required. The ultrasonic sensor measuring physical parameters like plant height is a simple method. Some complex sensing systems include optical sensors such as infrared, and machine vision that require high-speed processors and expensive equipment. In this project, as a simple method, the monitoring of the electrical current passing through weeds was used for developing the feedback mechanism and increasing electric damage to weeds.

In this study, the system consisted of a high-voltage device that generated a 15 kV AC voltage to kill weeds, as well as a feedback mechanism that included a sensor to measure the electric current on the input of the weed killer and identify the presence of weeds and their annihilation. All parts were installed on a robotic platform, and an application on a laptop was connected to it via an access point for navigation and data reception. The system was tested in a greenhouse lab with various weeds. Initially, a test was performed to investigate the effect of high voltage on the weeds and establish relationships between the electric currents passing through weeds and their presence (before and after annihilation). During the test, the system was guided along a path and applied high voltage to kill the weeds. The feedback mechanism was then calibrated based on the extracted data on electric current relations. This allowed the system to detect weeds and their annihilation, enabling it to move to the next target once a weed had been eliminated. After calibration, a comparative test was conducted to evaluate the weed-killing efficiency of the two methods (with and without the feedback mechanism), and the results were analyzed using a t-test with p ≤ 0.01.

The observations indicated that the input electric current on the weed killer was dependent on the electric current passing through weeds. When the high-voltage electrode touched a weed, the electric current passed through it increased, and simultaneously, the high electrical energy destroyed the weed. After the removal of the weed, the electric current rapidly decreased. The average energy consumption per weed plant was estimated to be 250 joules, which can be compared with other methods. The final test comparing the use and non-use of the feedback mechanism revealed significant differences (P < 0.01) between the results obtained with and without the mechanism, demonstrating that the feedback mechanism increased the efficiency of weed annihilation. The sensing system used in the developed feedback mechanism is a simple method that is affected by the electrical resistivity of weeds. As such, it did not mistakenly detect other objects as weeds, unlike an ultrasonic mechanism. Based on these results, monitoring the electrical current passing through weeds proved to be a suitable method for developing a feedback mechanism for the weed killer to identify the presence of weeds and their annihilation.

The use of high voltage as a non-chemical and alternative method for weed control has shown promising results. The study revealed that measuring the electric current applied to the weed killer was an effective and straightforward approach to developing a feedback mechanism. This mechanism aids in identifying the presence of weeds and ensuring their elimination by intensifying the damage inflicted on them through the application of high electrical energy. To further enhance the efficiency and speed of weed control, future research should consider integrating an automatic guidance mechanism with the weed killer.

Pistachio or Green Gold is one of the most important agricultural crops and is especially important for Iranian exports. A group of pistachio's pests mainly feed on pistachio, among which Idiocerus stali is very important. Conventional methods for identifying insects using identification keys are time-consuming and costly. Due to the rapid development of the Pistachio industry, the use of artificial intelligence techniques such as image processing, for identification and population monitoring is highly recommended. On the other hand, little research was carried out on I. stali. Therefore, in this research, I. stali was selected as a target insect for the identification and counting on sticky yellow cards using image processing techniques and artificial neural networks. The purpose of this study was to determine the feasibility of I. stali identification algorithm by image processing, to determine the possibility of separation and counting of I. stali from other non-target insects by artificial neural network and to determine its accuracy in identification of I. Stali.

Idiocerus stali was selected as the target insect for identification. Sticky yellow cards were used for collecting samples. Taking the photos with the help of a SONY Handycam Camera, which had a 12-megapixel resolution and G lens, was carried out (SONY, HDR-XR500, CMOS, SONY Lens G, Made in Japan). Then insects were counted on each card manually and the data was recorded. The data, which were digital images of yellow sticky cards, were imported into the MatLab R2017b software environment. A total of 357 color properties and 20 shape's features for the identification of I. stali were extracted by an image processing algorithm. Color properties were divided into two categories of mean and standard deviation and characteristics related to vegetation indices. An ANN-PSO (Artificial Neural Network hybrid method-Particle Swarm Optimization) algorithm was used to select the effective features. The selected effective characteristics for insect classification were: Color index for extra collective vegetation related to HSL color space, normalized difference index for LCH color space, gray channel for color space YCbCr, second component index minus third component for color space YCbCr, area and mean of the first, second and third components of color space Luv.

Comparing the results with the results of Qiao et al. (2008), we found that in his study, which divided the data into three categories, for medium and high-density groups, the detection rate was 95.2% and 94.6%, respectively. On the other hand, in low densities (less than 10 trapped insects); its detection rate was 72.9%, while the detection rate of the classifier system designed in this study for different densities of trapped insects, was identical and equal to 99.59%. Also, comparing the results of this study with Espinoza et al. (2016), we found that their algorithm in whiteflies detection had a high accuracy of about 0.96 on a sticky yellow card, while the Thrips identification algorithm accuracy was 0.92 on a sticky blue card. As stated above, the correct detection rate of I. stali by the algorithm designed in this study was 99.72%.

The results showed the feasibility of the new method for identifying the pest insects without destroying them on the farm and in natural light conditions and in a short time and with very high accuracy. This suggests that this algorithm can be applied to the machine vision system and can be used in future in the construction of agricultural robots.

Pot cheese is a traditional cheese that is preferred for its characteristic aroma and flavor. This type of cheese is made without added starter cultures; the native lactic flora contribute to the ripening and development of the typical aroma and flavor of this cheese. It is essential to identify the type of lactic acid bacteria involved in the ripening process. In this study, pot cheese was made traditionally and then ripened in underground stroage for three months. Lactic acid bacteria were isolated and identified in the ripened cheese. Identification of isolates at the species level was performed using phenotypic and 16s rDNA methods. Overall, 51 strains were isolated; the dominant genera were Lactobacilli (37.3%) and Enterococci (25.5%). Other species belonged to Lactococci (19.6%), Leuconostoc (9.8%) and Pediococci (7.8%). At the end of the ripening period, Lactobacilli dominated and the changes were significant. Enterococci and Lactococci showed significant changes during ripening, but significant changes were not found for Pediococci and Leuconostoc. The dominant isolated species was Enterococcus faecium (8 isolates), Lactococcuslactis ssp. lactis (7 isolates), Lactobacilluscasei ssp. casei (4 isolates) and Pediococcusacidilactici (4 isolates). These species are recommended for use as starter cultures in the manufacture of pot cheese or a new type of cheese with similar flavor.