基于改进SVM算法的室内人员身份识别技术

Indoor Personnel Identification Technology Based on Improved SVM Algorithm

针对传统的身份识别系统设备昂贵、侵犯隐私等缺点,提出一种基于Wi-Fi的信道状态信息的身份识别系统。首先,从改进的无线信号接收设备中提取反映人体步态特征的数据信息,然后对数据进行预处理并且提取出关键特征数据,利用改进支持向量机算法实现分类。提出了面向Wi-Fi人员身份识别的遗传算法迭代优化SVM的参数组合方法,进行自适应调节训练分类器,达到最优身份识别率。实验结果表明,在10名受试者参与中,系统平均识别准确率有92.5%。

Aiming at the disadvantages of traditional identification system,such as expensive equipment and privacy invasion,this paper proposes an identification system based on Wi-Fi channel state information.Firstly,the data information reflecting human gait characteristics is extracted from the improved wireless signal receiving equipment,and then the data is preprocessed and the key feature data is extracted,and an improved support vector machine algorithm is used to realize the classification.In this paper,a genetic algorithm is proposed to iteratively optimize the SVM parameter combination for Wi-Fi personnel identity recognition,and the classifier is adaptively adjusted to achieve the optimal identification rate.The experimental results show that the average recognition accuracy rate of the system is 92.5%in the participation of 10 subjects.