شبکه های کانولوشنی

In this research, field experiments were carried out in two types of soil (sandy clay loam and clay) to model the traction performance of the tractor considering drawbar power, rolling resistance, and traction efficiency, using deep learning and convolutional neural network while having some parameters such as soil type and conditions, tool parameters, and operation parameters. The tests were conducted within each soil texture in the form of factorial tests based on the randomized complete block design (RCBD) in triplicates. The tests were done in various moisture levels (8-17% for dry soils and 18-40% for moist soils), tractor forward speed (1.2, 1.6, 1.8, and 2.2 km h-1), working depth (30 and 50 cm), the number of pass (2 and 6 times), and tire inflation pressure (20 and 25 psi). The cone index, dynamic load, draft force, and moisture content were measured in each tests. The networks designed to model the drawbar power, rolling resistance, and traction efficiency were of convolutional neural network type. Various algorithms such as Sgdm, Adam, and Rmsprop were utilized to train the network. The results showed that the neural network developed by Sgdm algorithm outperformed the others. Therefore, this algorithm was utilized for the modeling process. Statistical criteria such as R2 and MSE were also employed to evaluate the performance of the network. For the drawbar power, the 8-499-499-1 architecture showed the best performance with R2=0.9953 and MSE=0.0016. Concerning the rolling resistance, the best performance was observed in 8-301-305-1 architecture with R2=0.9903 and MSE=0.0039. The best performance for the traction efficiency was obtained by 8-371-371-1 architecture with R2=0.9888 and MSE=0.003. The results showed that these networks can be used to model parameters by removing convolution layers and reducing dimensions.

Red meat, having all kinds of essential amino acids needed by humans and as one of the main sources of protein for human societies, has long been of great importance in the human diet, this special place has made the need to provide healthy and high-quality materials more urgent than ever. One of the most important and practical techniques for evaluating meat quality is studying its appearance and physical characteristics. This research designed and implemented a model based on convolutional neural networks based on three structures: Mobile Net, InceptionV3, and VGG16. In this research, the shear resistance value of each meat sample was measured by the Warner-Bratzler method, and input data for training and evaluation of the convolutional neural networks were digital images taken by the LG model smartphone (LG G4 H815) in uncontrolled conditions and independent of the environment and light. In the end, the designed models were able to classify the prototypes based on the extracted features with acceptable accuracy. The performance of the designed models was evaluated with statistical indicators of accuracy, precision, sensitivity, and specificity, and the best classification model was the model designed based on the structure of the Mobile Net, which was able to classify image data with an accuracy of 92.61%.

One of the methods of assessing the performance of seed drills may be to compare the performance with the crop population growth. Pixels of crop emergence zone appear to have similar characteristics concerning image parameter variations between soil and crop. The use of deep learning methods based on convolution neural networks to map regions of interest in the image seems appropriate. In this regard, a total of 2720 images of early-growth cereals were obtained from a field. 212 images with different backgrounds were selected and annotated to feed and train a neural network model. Raw images were defined as inputs and maps of manually marked growth points as network outputs. In order to calculate the network cost, the predicted output of the network was compared with the pre-marked pixel map. Prediction errors were then back-propagated and the network parameters updated. Examination of the initial network output showed that the trained network had responded incorrectly to plant tips, weeds and plant remains as plant growth points. To overcome these errors and improve network performance, a penalty function was defined for the mistaken predicted points. The network was trained with three penalty rates and evaluated with nine Soft Max thresholds. According to the network output, images were arranged in terms of plant density. In order to evaluate the model in different ranges, images from each particular range were selected at random. These images were fed to the model and their outputs compared with the truth. For the ranges where approximately 94% of the total field images existed, the average harmonic accuracy of the precision index and the recall index was estimated to be over 80%, indicating good model performance. The results showed that the model can provide acceptable feedback on sowing performance and improve farm management and efficiency in the next steps.