The article proposes a method for analyzing and assessing the quality of wheat seeds by classifying their images using artificial intelligence, namely a convolutional neural network. The architecture of a deep convolutional neural network was proposed, an image base was created for training and testing the proposed neural network, training and testing of the neural network was carried out in Tensorflow. Conclusions about the efficiency of image classification are made and areas of use of the proposed method for analyzing and assessing the quality of wheat seeds are proposed.

Keywords: convolutional neural networks, artificial intelligence, image classification

The paper proposes a method for preparing a dataset for training and testing neural networks in the MATLAB environment using the Image Processing Toolbox package of functions. An example of the implementation of this technique for preparing a dataset for training convolutional neural networks to classify wheat seeds into high-quality and low-quality classes according to its images is given. This technique was used to obtain a dataset of 900 images, which were successfully used to train and test the convolutional neural network.

Keywords: dataset, convolutional neural networks, artificial intelligence, image classification

The article describes the design of the integral micromechanical sensor of linear accelerations of the capacitive type; A construction method is briefly described using the self-assembly operation based on controlled self-organization of mechanically stressed semiconductor GaAs / InAs layers. The design of the capacitive accelerometer was modeled in the CAD system ANSYS, where static and modal analysis were performed. The results of mathematical modeling meet the requirements of modern micromechanical accelerometers, and allow them to be used for the further development of structures of this type. The obtained data can be used in particular for calculating the recommended parameters in the development of methods for designing capacitive sensors of angular velocities and linear accelerations and for developing more accurate models of MEMS structures.

Keywords: MEMS, microelectromechanical system, accelerometer, modeling, design, sensor, sensor, mathematical model

The article describes the implementation methodology, structure and functional diagram of a surface defect detection system based on the method of electrical impedance tomography in materials of engineering structures that are subjected to significant loads during operation. A control device for the system for collecting measurements and supplying voltage to the boundary electrodes of the sensing element is considered and an algorithm for its operation is described. The implementation method is proposed and the simulation results of this system are presented.

Keywords: defect monitoring, non-destructive testing, electrical impedance tomography, modeling, sensitive element, functional diagram

In this article, the evaluation of the effect of the trace elements on the reliability of the design of the combinational circuit in the field-programmable gate array (FPGA) basis is researched. An evaluation of the reliability of combinational circuits in the basis of three-input FPGA cells, as well as three-input FPGA cells, taking into account the trace elements, is given. Proposed methods for evaluate the reliability of the project at various stages of the development of fault-tolerance projects in the FPGA basis. The use of these methods allows the design of combinational circuits of increased reliability in the basis of reconfigurable integrated circuits without built-in reliability features.

Keywords: reliability, evaluation fault tolerance, combinational circuit, FPGA, fault injection