基于遗传算法和SVM的肝豆状核变性震颤评估方法研究

Research on the Evaluation Method of Tremor in Hepatolenticular Degeneration Based on Genetic Algorithm and Support Vector Machine(SVM)

震颤是肝豆状核变性疾病常见的症状之一.设计了一个监督学习模式评价系统,采用九轴传感器来记录震颤的加速度信号,分别在时域、频域上提取特征,再采用遗传算法选取出峰值振幅、特征峰值频率和峰值功率为显著特征,针对这些显著特征采用监督式学习,再通过支持向量机将患者和健康人进行分类.实验采用遗传算法迭代80次之后得到三个显著特征,再分别采用高斯核函数的支持向量机进行分类.实验结果显示,采用峰值频率分类的准确率最高,达到93%以上.

Tremor is one of the common symptoms of hepatolenticular degeneration.In this paper,a supervised learning mode evaluation system is designed.Nine axis sensor is used to record the acceleration signal of tremor,and features are extracted in time domain and frequency domain respectively.Then genetic algorithm is used to select peak amplitude,characteristic peak frequency and peak power as significant features.For these significant features,supervised learning is used,and patients and healthy people are classified by SVM.Finally,after 80 iterations of genetic algorithm,three significant features are obtained,and then the SVM of Gauss kernel function is used for classification.The results show that the accuracy of peak frequency classification is the highest,reaching more than 93%.