Multisensor Cross-Media Data Mining Method Assisted by Expert System

Abstract

The information generated by the multifaceted and multilevel processing of the data of multiple sensors is more meaningful than the information obtained by a single sensor and provides accurate information and decision-making basis for various application systems. How to apply data mining theory to the multisensor cross-media field has become a research hotspot. Through the analysis of multisensor cross-media data, it is of great significance to dig out the important rules, information, or knowledge hidden in it and use it for cross-media retrieval engine. The rule acquisition is the “bottleneck” problem of the expert system. This paper adopts the data mining method based on the rough set to acquire the rules and improves the basic algorithm of attribute reduction. Using the attribute reduction algorithm and the heuristic value reduction algorithm, the calculation is simplified and the reduction efficiency is improved. In the presentation, according to the characteristics of cross-media and the application requirements of expert systems, this paper takes the case representation based on features as the basis and classifies cases according to feature attributes. In case retrieval, according to the hierarchical structure of case features, the entire case database is organized into a multilevel hierarchical index structure. In this paper, a cross-media retrieval engine is constructed from the perspective of classifier design, and the Euclidean distance is used as the similarity matching model of image content. The mutual retrieval of images and audios preliminarily forms the design process of retrieval from one media type to another and establishes a corresponding cross-media index. The experimental results show that the algorithm has better processing effect and higher accuracy than other algorithms. Different k-nearest neighbor values were selected in the experiment, and it reached about 96% in the test environment of libsvm toolbox, which is better than the processing results of LE and LLE algorithms.