Search academic texts

Information × Registration Number 0124U000672, R & D request Title Application of artificial intelligence to predict radar scattering on complex large-scale objects to reduce visibility Head Legenkiy Maxim M., Кандидат фізико-математичних наук Registration Date 22-01-2024 Organization V.N. Karazin Kharkiv National University popup.description1 The goal of the project is to create new methods of processing data on the scattering characteristics of an object of complex shape to predict its visibility in the far zone. To achieve the goal of the project, it is necessary to solve three main tasks: 1) prepare models of the representation of objects of complex shape and their characteristics; 2) apply the created models for learning neural networks and applications of other artificial intelligence methods for predicting the radar visibility of complex objects; 3) test the obtained methods and algorithms, applying them to analyze the visibility of models of large-sized objects with and without means of reducing visibility. It is planned to create appropriate models for the application of artificial intelligence methods at the second stage. When using neural networks, input information is usually provided to the network in the form of a series of discrete input values and received also in the form of a series of output values. When applying such an approach to solving the problems of determining the radar visibility, one should correctly choose the input data to obtain correct and useful output data. You should also select data for full model training. It is planned to consider models based on commonly known methods in this field to build new models that can find applications in other scientific fields. Methods necessary for the application of other methods of artificial learning will be considered. The created models will be applied to the training of neural networks, the evaluation of the effectiveness of the application of various methods of artificial intelligence to predict the change in the radar visibility of complex objects. Further, it is planned to test the received methods and algorithms for assessing the visibility of specific samples of equipment using various means of reducing visibility. popup.nrat_date 2024-12-09 Close