|
个人信息Personal Information
教授
博士生导师
硕士生导师
主要任职：Professor, Head of Lab of Intelligent System
其他任职：大连市工业无线传感器网络工程实验室主任
性别：男
毕业院校：英国杜伦大学
学位：博士
所在单位：控制科学与工程学院
学科：控制理论与控制工程. 模式识别与智能系统. 检测技术与自动化装置
办公地点：海山楼A0624
课题组网址http://lis.dlut.edu.cn/
联系方式：0411-84709010 wangzl@dlut.edu.cn
电子邮箱：wangzl@dlut.edu.cn
Children Abnormal Gait Analysis Based on SVM
点击次数：
论文类型：会议论文
发表时间：2009-01-01
收录刊物：CPCI-S
页面范围：835-838
关键字：Children Abnormal Gait Analysis; SVM
摘要：Support Vector Machine (SVM) has become a hotspot of machine learning because of its rigorous theory background and remarkable generalization performance. Recent researches on SVM mainly concentrate on the property of SVM and variety of its applications. In this paper, an improved SVM algorithm is proposed for children abnormal gait analysis. The algorithm combines SVM with fuzzy clustering in order to improve the accuracy of SVM. Only samples that have weak relationships with all clusters are involved in SVM. Simulation experiment has been carried out to show that the algorithm based on the improved SVM may obtain better effectiveness than the normal SVM when it is applied for children abnormal gait analysis.