Search

Context. The problem of a neural network model synthesis for industrial processes with the definition of an optimal topology characterized by a high level of logical transparency and acceptable accuracy is considered. The object of research is the process of neural network modeling of industrial processes using an indicator system to simplify and select the topology of neuromodels.. Objective of the work is consists in synthesis a neural network model of industrial processes with a high level of logical transparency and acceptable accuracy based on the use of the system. Method. A method is proposed to use artificial neural networks of feedforward propagation for modeling industrial processes. After evaluating the overall level of complexity of the modeling problem based on the indicator system, it was decided to build a neuromodel based on historical data. Using the characteristics of the input data of the problem, the most optimal structure of the neural network was calculated for further modeling of the system. A high level of logical transparency of neuromodels significantly expands their practical use and reduces the resource intensity of industrial processes. Results. Neuromodels of industrial processes are obtained based on historical data. The use of an indicator system made it possible to significantly increase the level of logical transparency of models, while maintaining a high level of accuracy. Constructed neuromodels reduce the resource intensity of industrial processes by increasing the level of preliminary modeling. Conclusions. The conducted experiments confirmed the operability of the proposed mathematical software and allow us to recommend it for use in practice in modeling industrial processes. Prospects for further research may lie in the neuroevolutionary synthesis of more complex topologies of artificial neural networks for performing multi-criteria optimization.

Context. The problem of skin disease diagnosis was investigated in the paper. Its actuality is caused by the necessity of automation of at least advisory medical decision making. Such decisions are made in telemedicine, for instance, when skin disease diagnostics is performed under specific conditions. These conditions are specified by situations when data for analysis are collected but a qualified doctor has no possibility to process the data and to make a diagnosis decision based on it. The object of the study is a process of skin disease diagnosis. Objective. The objective of the study is to develop a skin disease diagnosis method to automate making of advisory medical diagnosis decisions and to increase efficiency of such decisions. Method. The skin disease diagnosis method was proposed in the work. This method applies the modified ResNet50 model. It was proposed to add layers to the ResNet50 model and to train it using transfer learning and fine-tuning techniques. The method also defines image processing in particular through the change of its resolution and uses oversampling technique to prepare a dataset for model training. Results. Experimental investigation of the proposed method was performed using the HAM10000 dataset which contains images of skin diseases. The images were collected using dermatoscopy method. The dataset contains observations for 7 different skin diseases. The proposed method is characterized by the accuracy of 96.31% on this dataset. It is improved accuracy in comparison with the existing neural network models. Software component model was created to give a possibility to integrate the proposed method into a medical diagnosis system. Conclusions. The obtained results of the investigation suggest application of the proposed skin disease method in medical diagnostic system to make advisory decisions by the system and to support making final decisions by a doctor.

Context. The problem of synthesizing pulsed neural networks based on an evolutionary approach to the synthesis of artificial neural networks using a neuropathic mechanism for constructing diagnostic models with a high level of accuracy is considered. The object of research is the process of synthesis of pulsed neural networks using an evolutionary approach and a neuropathic mechanism. Objective of the work is to develop a method for synthesizing pulsed neural networks based on an evolutionary approach using a neuropathic mechanism to build diagnostic models with a high level of accuracy of work. Method. A method for synthesizing pulsed neural networks based on an evolutionary approach is proposed. At the beginning, a population of pulsed neural networks is generated, and a neuropathic mechanism is used for their encoding and further development, which consists in separate encoding of neurons with different activation functions that are determined beforehand. So each pattern with multiple entry points can define the relationship between a pair of points. In the future, this simplifies the evolutionary development of networks. To decipher a pulsed neural network from a pattern, the coordinates for a pair of neurons are passed to the network that creates the pattern. The network output determines the weight and delay of the connection between two neurons in a pulsed neural network. After that, you can evaluate each neuromodel after evolutionary changes and check the criteria for stopping synthesis. This method allows you to reduce the resource intensity during network synthesis by abstracting the evolutionary changes of the network pattern from itself. Results. The developed method is implemented and investigated on the example of the synthesis of a pulsed neural network for use as a model for technical diagnostics. Using the developed method to increase the accuracy of the neuromodel with a test sample by 20%, depending on the computing resources used. Conclusions. The conducted experiments confirmed the operability of the proposed mathematical software and allow us to recommend it for use in practice in the synthesis of pulsed neural networks as the basis of diagnostic models for further automation of tasks of diagnostics, forecasting, evaluation and pattern recognition using big data. Prospects for further research may lie in the use of a neuropathic mechanism for indirect encoding of pulsed neural networks, which will provide even more compact data storage and speed up the synthesis process.

Context. The problem of synthesis of an optimal neural network model for diagnostics of aircraft parts after operational processes is considered. The object of the study is the process of synthesis of neural network diagnostic models for aircraft parts based on the results of operational processes Objective is to synthesize neural network diagnostic models of aircraft parts after operational processes with a high level of accuracy. Method. It is proposed to research the use of two approaches to the synthesis of neural network diagnostic models. So, using a system of indicators, the topology of the neural network is calculated, which will be trained using the method of Backpropagation method in the future. The second approach is based on the use of a neuroevolutionary approach, which allows for a complete synthesis of the neural network, dynamically modifying the topology of the solution in addition to the parameters. the final decisions are compared in the accuracy of work on the training and test data set. This approach will allow to determine the possibility and correctness of using neuroevolutionary methods for the synthesis of diagnostic models. Results. Neuromodels for diagnostics of aircraft parts based on the results of operational processes have been obtained. The obtained results of comparing the methods used for synthesis made it possible to form recommendations for the implementation of neuroevolutionary methods in the synthesis of diagnostic neuromodels. Conclusions. The results obtained during the experiments confirmed the operability of the mathematical software used and allowed us to form recommendations for further use of the considered methods in practice in order to synthesize diagnostic neuromodels. The prospects for further research may consist in expanding the input data sets in order to synthesize and study more complex topologies of neural network models.

Context. The problem of synthesis a neural network model of operational processes with the determination of the optimal topology, which is characterized by a high level of logical transparency and acceptable accuracy, is considered. The object of the study is the process of neural network modeling of operational processes using an indicator system to simplify the selection of the topology of neuromodels. Objective of the work is to synthesis a neural network model of operational processes with a high level of logical transparency and acceptable accuracy based on the use of an indicator system. Method. It is proposed to use a system of indicators to determine the topological features of ANN, which is the basis for modeling operational processes. The assessment of the level of complexity of the task obtained on the basis of information about the input data and the values of the criteria for assessing the specificity of the task allows to categorize the task to one of the types of complexity in order to determine the approach to the synthesis of a neuromodel. Complexity category OS allows, based on analytical data about the selection of input data, to obtain the exact number of neurons in the hidden layer for the synthesis of a neuromodel with a high level of logical transparency, which significantly expands their practical use and reduces the cost of subsequent operational processes. Results. The obtained neuromodels of operational processes based on historical data. The use of the indicator system made it possible to significantly increase the level of logical transparency of the models, while maintaining high accuracy. Synthesized neuromodels reduce the resource intensity of operational processes by increasing the level of previous modeling. Conclusions. The conducted experiments confirmed the operability of the proposed mathematical software and allow to recommend it for use in practice when modeling operational processes. The prospects for further research may consist in the use of more complex methods of feature selection to fix the group relationships of information features for the construction of more complex models