{"title":"计算机用户的行为模型","authors":"N. Axak, Andrii Tatarnykov","doi":"10.1109/CSIT56902.2022.10000499","DOIUrl":null,"url":null,"abstract":"A graphical model of the user’s behavior during electronic testing is proposed, which is a Markov decision process that allows finding an appropriate strategy of the supervisor in case of unacceptable user actions. A system for analyzing student behavior during e-testing has been developed. The system is implemented on the basis of the proposed three-level client-server architecture, which provides the ability to detect user violations in real time. It is shown that the proposed approach significantly reduces decision-making time by synchronizing the interval of receiving the address of active web resources on the user’s computerю. This leads to the possibility of detection under different lighting conditions of a large number of violations at the same time, which increases the quality of recognition of various violations. A comparative analysis was carried out with existing software solutions in terms of the number of detected violations and the accuracy of face recognition. The conducted experiments confirmed the efficiency of the proposed approaches.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"The Behavior Model of the Computer User\",\"authors\":\"N. Axak, Andrii Tatarnykov\",\"doi\":\"10.1109/CSIT56902.2022.10000499\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A graphical model of the user’s behavior during electronic testing is proposed, which is a Markov decision process that allows finding an appropriate strategy of the supervisor in case of unacceptable user actions. A system for analyzing student behavior during e-testing has been developed. The system is implemented on the basis of the proposed three-level client-server architecture, which provides the ability to detect user violations in real time. It is shown that the proposed approach significantly reduces decision-making time by synchronizing the interval of receiving the address of active web resources on the user’s computerю. This leads to the possibility of detection under different lighting conditions of a large number of violations at the same time, which increases the quality of recognition of various violations. A comparative analysis was carried out with existing software solutions in terms of the number of detected violations and the accuracy of face recognition. The conducted experiments confirmed the efficiency of the proposed approaches.\",\"PeriodicalId\":282561,\"journal\":{\"name\":\"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)\",\"volume\":\"24 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CSIT56902.2022.10000499\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSIT56902.2022.10000499","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A graphical model of the user’s behavior during electronic testing is proposed, which is a Markov decision process that allows finding an appropriate strategy of the supervisor in case of unacceptable user actions. A system for analyzing student behavior during e-testing has been developed. The system is implemented on the basis of the proposed three-level client-server architecture, which provides the ability to detect user violations in real time. It is shown that the proposed approach significantly reduces decision-making time by synchronizing the interval of receiving the address of active web resources on the user’s computerю. This leads to the possibility of detection under different lighting conditions of a large number of violations at the same time, which increases the quality of recognition of various violations. A comparative analysis was carried out with existing software solutions in terms of the number of detected violations and the accuracy of face recognition. The conducted experiments confirmed the efficiency of the proposed approaches.