Search academic texts

Information × Registration Number 0217U002134, 0116U007419 , R & D reports Title Methods and tools of computational intelligence and parallel computing for large data processing in diagnostic systems. popup.stage_title Head Subbotin Sergey Alexandrovich, Registration Date 23-01-2017 Organization Zaporizhzhia National Technical University popup.description2 The object of study is the process of intelligent data-driven diagnosis. The objective is the research and development of methods and software for high-performance intelligent processing of large data in technical and biomedical diagnosis systems. At the development of mathematical software for intelligent processing of large data in the problems of diagnosis and decision-making the analysis of deep learning methods for neural networks is conducted in the work, the parallel construct model based production rules extraction method is proposed, that generalize the specified data samples in the form of models based on decision trees, association rules, and negative selection. The proposed methods allow to significantly reduce the time required for the synthesis of models for solving the practical problems, which are characterized by large amounts of diagnostic data as well as tasks where there is a need to modify the existing diagnostic and recognition models in connection with the new information as a result of monitoring the status of the test objects or processes. This provides the possibility of synthesis of models with high approximating and generalizing properties. The results of research are recommended for use in solving the problems of diagnosis and pattern recognition, etc. Product Description popup.authors popup.nrat_date 2020-04-02 Close