关键词: 人工蜂群算法, 支持向量机, 参数优化, 小麦碰撞声, 分类

Abstract: In order to improve the classification precision of Support Vector Machines（SVM）, a parameter optimization method based on artificial bee colony algorithm is proposed to solve this problem. Then the proposed method is applied to the recognition of undamaged wheat kernel, moldy damaged wheat kernel and sprout-damaged wheat kernel. The wavelet transform is applied to wheat impact acoustic signals and the normalized energy values of every frequency band are extracted to compose feature vectors. And the inverse of classification error rate is used as fitness value, and the artificial bee colony algorithm is used to optimize the penalty factor and kernel parameter of SVM. Then the optimized SVM is used to classify the undamaged kernel, moldy damaged kernel and sprout-damaged kernel, and the recognition accuracy rate is above 86%. The experimental results show that the research has a more universal value in application and provide a novel method for the optimization of SVM performance as well.

Key words: artificial bee colony algorithm, Support Vector Machine（SVM）, parameter optimization, wheat impact acoustic signals, classification