Assessment of the connectedness of data representations in the design of multimodal analytical processes for big data processing
Abstract
The paper investigates the problem of designing multimodal analytical processes for big data processing with varying connectedness of data representations. Depending on the process structure, data of different types may be processed independently, transformed between representations, or jointly used in forming the result. To account for these features, a system of indicators of the connectedness of data representations and an assessment procedure based on a logical rule of preliminary selection and additive evaluation are proposed. The connectedness of data representations is assessed using examples of analytical processes described with the contract-graph approach: primary processing of industrial monitoring data, preliminary verification of a completed educational assignment, and formation of a medical report based on laboratory test results. The proposed assessment procedure is applied to determine the need for aligning data, operations, and intermediate results and can be used by data analysts, developers of analytical systems, and domain specialists in the design of multimodal analytical processes.
Full Text:
PDF (Russian)References
Rozony F.Z., Aktar M.N.A., Ashrafuzzaman M. et al, “A systematic review of big data integration challenges and solutions for heterogeneous data sources,” Academic Journal on Business Administration, Innovation & Sustainability, pp. 1–18, 2024.
Abdurrahman A., Zeigler B.P., “Multimodal semantic fusion of heterogeneous data silos,” Systems 2025, 13, no. 11, 2025.
Zhao F., Zhang C., Geng B., “Deep multimodal data fusion,” ACM Computing Surveys 56, pp. 1–36, 2024.
Peng Y., Heyn H., Horkoff J., “Data challenges in ai systems and their solutions: a requirements and ai engineering systematic literature review and comparison,” 2025 — 10.21203/rs.3.rs-8077403/v1.
Yoo S., Lee J., Yoon C. et al, “Data transformation strategies to remove heterogeneity,” 2025 — arXiv:2507.12677.
Oakes B.J., Famelis M., Sahraoui H. “Building domain-specific machine learning workflows: a conceptual framework for the state of the practice,” ACM Transactions on Software Engineering and Methodology, vol. 33, issue 4, no. 91, pp. 1–50, 2024.
Li S., Tang H. “Multimodal alignment and fusion: a survey," 2025 — arXiv:2411.17040.
Takemura K., Murakami H., Tamari Y. “A probabilistic modeling approach to decision strategies: predicting expected information search and decision time in multi-attribute choice tasks with varying numbers of attributes and alternatives,” Mathematics 2026, no. 1, 2026.
Steffen V., Oliveira M.S., Trojan, F., “A novel approach for systematic literature reviews using multi-criteria decision analysis,” Journal of Intelligent Management Decision, vol. 3, issue 2, pp. 116–138, 2024.
Trung D.D., Ozcalici M., Dua T.V., “Comparative analysis of the simple additive weighting method and the deviation-based pairwise assessment ratio technique for material selection,” Tribology and Materials ISSN 2812-9717, 2026.
Liborio M.P., Ekel P.I., Fusco E., et al, “Fuzzy inference system for measuring composite indicators' overall quality,” Social indicators research vol. 179, pp. 1587–1613, 2025.
Charugin V.V., Charugin V.V., Stavtsev A.V., Chesalin A.N. “Architecture of a constructor for multimodal data processing: graph models and their application in information security tasks,” 2026 — 10.33693/2313-223X-2026-13-1-55-67.
Charugin V.V., Charugin V.V., Chesalin A.N. “Constructor for multimodal data processing,” Innovative, information and communication technologies. proceedings of the xxi international scientific and practical conference, pp. 146–150, 2024.
Zheng Y., “Fusing cross-domain knowledge from multimodal data to solve problems in the physical world,” ACM Transactions on Intelligent Systems and Technology, vol. 17, issue 1, pp. 1–32, 2025.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИТ-КОНГРЕСС ВМК МГУ 2026 СНЭ
ISSN: 2307-8162