APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS FOR TECHNICAL OBJECT RECOGNITION IN THE INTERESTS OF RADIO MONITORING

The article examines the possibility of using convolutional neural networks for technical objectrecognition in the context of radio monitoring. The focus is on the development and optimization of algorithmsfor processing radar signals using deep neural networks. Studies have shown that the use of CNNcan significantly improve the classification accuracy of radio signals compared to traditional processingmethods. The developed approach is based on the extraction of hierarchical features from spectral imagesof radio signals and their subsequent classification using a trained neural network. The paper presents theresults of experimental studies conducted on a dataset of more than 10,000 samples of radio signals ofvarious types. It is shown that the proposed technique ensures recognition accuracy of up to 94% whenworking with noisy signals and the probability of a false alarm is no more than 0.05. Special attention ispaid to the choice of neural network architecture for the specifics of the radio monitoring task. The optionsfor converting radio signals into a spectral image for real-time processing were also considered indetail. Data preprocessing methods have been developed, including amplitude normalization, frequencycorrection, and interference elimination. The results of the study can be used in radio broadcast controlsystems and to ensure electromagnetic compatibility of electronic devices. The results obtained demonstratethe prospects of using CNN in the tasks of technical recognition of radio monitoring objects andopen new opportunities for the development of intelligent radar information processing methods. Promisingareas of further research include the development of adaptive neural network training methods in achanging radio environment and the creation of hybrid systems combining traditional signal processingmethods with modern neural network algorithms