关键词: 表具识别, 量子粒子群算法, 粗糙集, 属性约简, 支持向量机

Abstract: In order to restrain particles from trapping in local optimum, this paper presents a new algorithm, which is based on the combination of rough sets and Support Vector Machine（SVM） optimized by Improved Quantum-behaved Particle Swarm Optimization（IQPSO）, the artificial bee colony algorithm and immune algorithm are introduced to speed up the search space and improve the convergence speed. Firstly, the rough set optimized by IQPSO is used to reduce the attributes of the feature vector, and then the parameters of SVM are optimized by IQPSO. Finally, the simulation experiment shows that the improved algorithm can effectively reduce the number of decision attribute, improve rough set attribute reduction ability, obtain the better parameters of SVM, this algorithm has a fast convergence speed and high recognition accuracy.

Key words: gas meter recognition, quantum-behaved particle swarm optimization, rough set, attribute reduction, support vector machine