A. A. Dokukin, A. V. Kuznetsova, N. V. Okulov, O. V. Senko, V. Ya. Chuchupal
{"title":"Interpretability of Learning in a Signal Processing System","authors":"A. A. Dokukin, A. V. Kuznetsova, N. V. Okulov, O. V. Senko, V. Ya. Chuchupal","doi":"10.1134/s1064230724700096","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>This paper presents a software package that allows us to generate algorithms for the automatic classification of signals. The software package includes an algorithm that converts records of continuous signals into vector form and a set of machine learning methods, as well as data mining tools aimed at achieving transparency and interpretability of learning. This approach is based on the presentation of differences between the compared classes as a set of relatively simple, statistically significant and interpretable effects, which are graphically represented on two-dimensional diagrams. The performance of the method is illustrated on the problem of assessing the state of a hive by sound signals. The software package can be used in solving applied problems of automatic diagnostics and data analysis.</p>","PeriodicalId":50223,"journal":{"name":"Journal of Computer and Systems Sciences International","volume":"53 1","pages":""},"PeriodicalIF":0.5000,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computer and Systems Sciences International","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s1064230724700096","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
This paper presents a software package that allows us to generate algorithms for the automatic classification of signals. The software package includes an algorithm that converts records of continuous signals into vector form and a set of machine learning methods, as well as data mining tools aimed at achieving transparency and interpretability of learning. This approach is based on the presentation of differences between the compared classes as a set of relatively simple, statistically significant and interpretable effects, which are graphically represented on two-dimensional diagrams. The performance of the method is illustrated on the problem of assessing the state of a hive by sound signals. The software package can be used in solving applied problems of automatic diagnostics and data analysis.
期刊介绍：
Journal of Computer and System Sciences International is a journal published in collaboration with the Russian Academy of Sciences. It covers all areas of control theory and systems. The journal features papers on the theory and methods of control, as well as papers devoted to the study, design, modeling, development, and application of new control systems. The journal publishes papers that reflect contemporary research and development in the field of control. Particular attention is given to applications of computer methods and technologies to control theory and control engineering. The journal publishes proceedings of international scientific conferences in the form of collections of regular journal articles and reviews by top experts on topical problems of modern studies in control theory.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
