Instruments and Systems: Monitoring, Control, and Diagnostics Annotation << Back Problems of Aggregation and Complexation of Heterogeneous Information in Multisensory Expert Systems R.A. BAGUTDINOV The article is devoted to the analysis of problems and challenges associated with the aggregation and integration of heterogeneous information in multisensory expert systems (MES). In the context of increasing volumes and heterogeneity of data coming from various sensors, the development of adaptive methods for processing and synthesizing information becomes a priority task. The article discusses methods for aggregating and combining heterogeneous information in multisensory expert systems designed to operate under conditions of high uncertainty. The proposed approaches are aimed at improving the efficiency and speed of MES operation, as well as ensuring the reliability and completeness of information necessary for making management decisions. The methodology is based on system analysis, methods of automatic control theory, pattern recognition, artificial intelligence and object-oriented modeling. The levels of information structuring in MES are presented. The criteria for assessing the effectiveness of: efficiency, reliability and completeness of data are formulated. It is shown that existing methods require adaptation to the specifics of working with streaming and weakly structured data. The necessity of using adaptive and intelligent algorithms is substantiated. The materials of the article can be useful in developing monitoring, control and diagnostic systems in high-tech industries. The obtained results contribute to the development of intelligent sensor systems and the expansion of their application in robotics, monitoring and control systems of complex objects, demonstrate the potential for increasing the reliability, efficiency and completeness in intelligent decision-making systems. Keywords: multisensory systems, data aggregation, information integration, expert systems, system analysis, processing of heterogeneous data, artificial intelligence, neural networks, modeling. DOI: 10.25791/pribor.8.2025.1607 Pp. 46-49.