The Procedure for Aggregating Initial Data on the Required Quality Level of Complex Data Processing Systems
( Pp. 61-70)
More about authors
Samokhina Natalia S.
Cand. Sci. (Eng.); associate professor, Department of Higher School of Advanced Manufacturing Technologies
Volga Region State University of Service
Tolyatti, Russian Federation Efremov Alexey S. postgraduate student; Volga Region State University of Service; Tolyatti, Russian Federation
Volga Region State University of Service
Tolyatti, Russian Federation Efremov Alexey S. postgraduate student; Volga Region State University of Service; Tolyatti, Russian Federation
Abstract:
The aim of the research is to develop a procedure for aggregating data on the required quality level of complex data processing systems through the integration of multicriteria analysis with machine learning methods. Existing approaches based on GOST R 59797–2021 and ISO/IEC 25010 demonstrate limited efficiency due to the absence of a unified aggregation procedure]. A three-stage hybrid procedure has been devised: collection and normalization of quality indicators using a modified z-transformation; calculation of adaptive weights via synthesis of the AHP method with a random forest algorithm; formation of an integrated criterion for the required quality level. Validation was carried out on two industrial systems with scales of 50–80 TB/day. Results include an increase in forecast accuracy from 82.1 to 92.4%, a 3.4-fold reduction in decision-making time, and a decrease in critical incidents by 34–45%. The algorithmic complexity is O(n2m + n log nk), with execution time under 30 seconds. The procedure is applicable to CDPS with data volumes exceeding 10 TB/day and requires at least 500 historical observations. The findings are valuable for architects and specialists in quality management of critically important information systems.
How to Cite:
Samokhina N.S., and Efremov A.S. The procedure for aggregating initial data on the required quality level of complex data processing systems. Computational Nanotechnology. 12, 4 (2025), 61–70. DOI: 10.33693/2313-223X-2025-12-4-61-70. EDN: FPYQLP
Reference list:
Eremenko V.T., Loginov I.V., Fisun A.P., Rytov M.Yu. Control of restructuring of information and computing platforms of evolving cyber-physical systems under uncertainty. Bulletin of Computer and Information Technologies. 2023. No. 2. Pp. 26–36. (In Rus.). DOI: 10.14489/vkit.2023.02.pp.026-036. EDN: HOSPS.
Chukanov S.N., Chukanov I.S. Formation of machine learning features based on topological data analysis. VSU Bulletin. Series: System Analysis and Information Technologies. 2022. No. 3. Pp. 115–126. (In Rus.). DOI: 10.17308/sait/1995-5499/2022/3/115-126. EDN: GEZXCX.
Rezova N.L., Kazakovtsev L.A., Shkaberina G.Sh., Tsepkova M.I. Preliminary data processing for analyzing the behavior of complex systems. Control Systems and Information Technologies: Scientific and Technical Journal. 2022. No. 2 (88). (In Rus.). DOI: 10.36622/VSTU.2022.88.2.008. EDN: BYGESB.
Melnikov A.V., Kobyakov N.S. Numerical method for modifying models developed on the basis of the analytic hierarchy process using an artificial neural network. VSU Bulletin. Series: System Analysis and Information Technology. 2025. No. 4. Pp. 5–21. (In Rus.). DOI: 10.17308/sait/1995-5499/2024/4/5-21. EDN: CENQIP.
Menshikh V.V., Morozova V.O. Numerical Method for Studying Dynamic Series with Aperiodic Anomalies. VSU Bulletin. Series: System Analysis and Information Technologies. 2023. No. 2. Pp. 22–30. (In Rus.). DOI: 10.17308/sait/1995-5499/2023/2/22-30. EDN: GVIANX.
Dushkin R.V. Principles for solving the problem of symbol binding in the development of general-level artificial cognitive agents. Journal of Information Technologies. 2022. No. 7. Pp. 15–29. (In Rus.). DOI: 10.17587/it.28.368-377. EDN: BZMVWL.
Popov A.P., Tikhomirov S.G., Khaustov I.A. et al. System analysis and synthesis of a predictive control system for the process of thermal-oxidative degradation of a polymer in a batch reactor. VSU Bulletin. Series: System Analysis and Information Technologies. 2020. No. 1. Pp. 36–50. (In Rus.). DOI: 10.17308/sait.2020.1/2582. EDN: LLVDQL.
Vasiliev N.N. Modeling of bumping routes in the RSK algorithm and analysis of their approach to limiting forms. Information Control Systems. 2022. No. 6. Pp. 2–8. (In Rus.). DOI: 10.31799/1684-8853-2022-6. EDN: WRCOSH.
Veresnikov G.S., Golev A.V., Moskovtsev A.M., Martirosyan M.P. Methods and algorithms for solving the problem of early diagnostics of technical objects using data mining methods. Information Technologies. 2022. No. 9 (28). Pp. 475–484. (In Rus.). DOI: 10.17587/it.28.475-484. EDN: UJWIRT.
Desnitsky V.A., Novikova E.S. Fault detection in industrial products using small training datasets. VSU Bulletin. Series: System Analysis and Information Technology. 2024. No. 1. Pp. 49–61. (In Rus.). DOI: 10.17308/sait/1995-5499/2024/1/49-61. EDN: DHNYCM.
Arshinsky L.V., Lebedev V.S. Objectification of knowledge bases of intelligent systems based on inductive inference using non-strict probabilities. Information and Mathematical Technologies in Science and Management. 2022. No. 4 (28). Pp. 190–200. (In Rus.). DOI: 10.38028/ESI.2022.28.4.015. EDN: LGJXFH.
Chukanov S.N., Chukanov I.S. Formation of machine learning features based on topological data analysis. VSU Bulletin. Series: System Analysis and Information Technologies. 2022. No. 3. Pp. 115–126. (In Rus.). DOI: 10.17308/sait/1995-5499/2022/3/115-126. EDN: GEZXCX.
Rezova N.L., Kazakovtsev L.A., Shkaberina G.Sh., Tsepkova M.I. Preliminary data processing for analyzing the behavior of complex systems. Control Systems and Information Technologies: Scientific and Technical Journal. 2022. No. 2 (88). (In Rus.). DOI: 10.36622/VSTU.2022.88.2.008. EDN: BYGESB.
Melnikov A.V., Kobyakov N.S. Numerical method for modifying models developed on the basis of the analytic hierarchy process using an artificial neural network. VSU Bulletin. Series: System Analysis and Information Technology. 2025. No. 4. Pp. 5–21. (In Rus.). DOI: 10.17308/sait/1995-5499/2024/4/5-21. EDN: CENQIP.
Menshikh V.V., Morozova V.O. Numerical Method for Studying Dynamic Series with Aperiodic Anomalies. VSU Bulletin. Series: System Analysis and Information Technologies. 2023. No. 2. Pp. 22–30. (In Rus.). DOI: 10.17308/sait/1995-5499/2023/2/22-30. EDN: GVIANX.
Dushkin R.V. Principles for solving the problem of symbol binding in the development of general-level artificial cognitive agents. Journal of Information Technologies. 2022. No. 7. Pp. 15–29. (In Rus.). DOI: 10.17587/it.28.368-377. EDN: BZMVWL.
Popov A.P., Tikhomirov S.G., Khaustov I.A. et al. System analysis and synthesis of a predictive control system for the process of thermal-oxidative degradation of a polymer in a batch reactor. VSU Bulletin. Series: System Analysis and Information Technologies. 2020. No. 1. Pp. 36–50. (In Rus.). DOI: 10.17308/sait.2020.1/2582. EDN: LLVDQL.
Vasiliev N.N. Modeling of bumping routes in the RSK algorithm and analysis of their approach to limiting forms. Information Control Systems. 2022. No. 6. Pp. 2–8. (In Rus.). DOI: 10.31799/1684-8853-2022-6. EDN: WRCOSH.
Veresnikov G.S., Golev A.V., Moskovtsev A.M., Martirosyan M.P. Methods and algorithms for solving the problem of early diagnostics of technical objects using data mining methods. Information Technologies. 2022. No. 9 (28). Pp. 475–484. (In Rus.). DOI: 10.17587/it.28.475-484. EDN: UJWIRT.
Desnitsky V.A., Novikova E.S. Fault detection in industrial products using small training datasets. VSU Bulletin. Series: System Analysis and Information Technology. 2024. No. 1. Pp. 49–61. (In Rus.). DOI: 10.17308/sait/1995-5499/2024/1/49-61. EDN: DHNYCM.
Arshinsky L.V., Lebedev V.S. Objectification of knowledge bases of intelligent systems based on inductive inference using non-strict probabilities. Information and Mathematical Technologies in Science and Management. 2022. No. 4 (28). Pp. 190–200. (In Rus.). DOI: 10.38028/ESI.2022.28.4.015. EDN: LGJXFH.
Keywords:
computational modeling, dynamic adaptation, system lifecycle, neural network algorithms, system analysis, complex data processing systems, event-predictive quality management, emergent properties.
