Research on Application of MEMS Accelerometer in Target Classification by Advanced Information Processing

This paper presents a novel application of MEMS accelerometer in target classification by means of advanced information processing. The detection system based on MEMS accelerometer is small in size, light in weight, has low power consumption and low cost, and can work under severe circumstances for many different applications. In order to extract features of seismic signals stimulated by different vehicle targets and to recognize targets, seismic properties of typical vehicle targets are researched in the paper. A technique of artificial neural networks combined with genetic algorithm (ANNCGA) is applied to classification of seismic signals that belong to different kinds of vehicle targets. The technique and its architecture have been presented. The algorithm had been used for classification of seismic signals of vehicle targets in the outdoor environment. Through experiments, it can be proven that seismic properties of target acquired are correct, ANNCGA method is effective to solve the problem of target classification, and MEMS accelerometer can be used in vehicle target classification