摘要
提出了一种核主成分分析（KPCA）与最小二乘支持向量回归机（LSSVM）回归算法相结合的室内定位方法。由于RSSI（received signal strength indication,接收信号强度）在室内WLAN环境中受到噪声和多径效应的影响,使得位置指纹与物理位置之间的相关性降低。本文先用缺失值处理方法对采集到的指纹样本做预处理,去除异常值;然后用KPCA方法来进一步处理指纹库,提取定位所需的主要特征,最后利用最小二乘支持向量机进行回归建模,构建位置指纹与实际物理位置之间的非线性映射关系,并用遗传算法（GA）来优化模型参数。实验仿真结果表明,与传统定位方法相比,本文方法定位精度更高,定位速度更快。
An indoor location method is proposed,which combines the kernel principal component analysis（KPCA） with least square support vector regression（LSSVM） regression algorithm. Due to the acquisition of received signal strength indication（RSSI） is affected by the noise and multipath effect in the indoor WLAN environment,which makes the correlation between location fingerprint and actual location decrease. In this paper,the collected fingerprint library is preprocessed to remove the abnormal value,and then use the KPCA method to further deal with it,which can extract the main features required for positioning. Finally,the regression modeling of the least squares support vector machine is used to construct the nonlinear mapping relationship between the location fingerprint and the actual physical location. The genetic algorithm（GA） is used to optimize the model parameters. The experimental simulation results show that the proposed method has higher positioning accuracy and faster positioning speed compared with the traditional positioning method.
作者
王修平
覃锡忠
贾振红
牛红梅
王哲辉
WANG Xiuping;QIN Xizhong;JIA Zhenhong;NIU Hongmei;WANG Zhehui(School of Information Science and Engineering,Xinjiang University,Urumqi Xinjiang 830046,China;Department of Network Monitoring,China Mobile Group Xinjiang Company Limited,Urumqi Xinjiang 830063,China)
出处
《激光杂志》
北大核心
2018年第7期121-125,共5页
Laser Journal
基金
中国移动通信集团新疆有限公司研究发展基金项目(No.XTM2013-2788)
关键词
室内定位
核主成分分析
最小二乘支持向量机
遗传算法
indoor location
kernel principal component analysis
least squares support vector machine
genetic algorithm
