基于LS-SVM方向判别模型的WLAN室内定位方法
|
摘要
为解决WLAN室内定位中信号在传播过程受人体遮挡产生阴影衰落而影响定位精度的问题,提出了一种最小二乘法支持向量机(LS-SVM)方向判别模型的WLAN室内定位方法。该方法主要分为两个部分:首先,充分利用人体在不同遮挡方向上产生阴影衰落的接收信号强度变化(RSS)特征信息,判定人体遮挡方向;然后,通过LS-SVM回归算法建立指纹点特征数据与位置之间的映射关系获取定位点位置结果。实验结果表明,与传统利用SVM的定位方法相比,提出的方向判别模型可解决人体遮挡产生的阴影衰落影响定位精度的问题,提高了定位的实用性和鲁棒性。
In order to solve the problem of positioning accuracy error caused by body blocking in the process of WLAN indoor positioning, a WLAN indoor positioning method called Direction Discrimination Model(DDM) is proposed based on Least Squares Support Vector Machine(LS-SVM) algorithm.The method is mainly divided into two parts: First, the body's obstruction direction is determined with the information of the Received Signal Strength(RSS) changes in the shaded fading caused by the human body in different directions of obstruction;Then, the LS-SVMregression algorithm is used to establish the mapping relationship between the fingerprint point feature data and the location to obtain the positioning point location result.The experimental results show that the proposed direction discrimination model reduces the influence of shadow fading caused by human shadows on positioning accuracy and improves the practicability and robustness of positioning,compared with the traditional positioning method based on SVM.
In order to solve the problem of positioning accuracy error caused by body blocking in the process of WLAN indoor positioning, a WLAN indoor positioning method called Direction Discrimination Model(DDM) is proposed based on Least Squares Support Vector Machine(LS-SVM) algorithm.The method is mainly divided into two parts: First, the body's obstruction direction is determined with the information of the Received Signal Strength(RSS) changes in the shaded fading caused by the human body in different directions of obstruction;Then, the LS-SVMregression algorithm is used to establish the mapping relationship between the fingerprint point feature data and the location to obtain the positioning point location result.The experimental results show that the proposed direction discrimination model reduces the influence of shadow fading caused by human shadows on positioning accuracy and improves the practicability and robustness of positioning,compared with the traditional positioning method based on SVM.
引文
[1]吴泽泰,蔡仁钦,徐书燕,等.基于K近邻法的Wi-Fi定位研究与改进[J].计算机工程,2017,43:289-293.
[2]Zhou S,Pollard J K.Position measurement using Bluetooth[J].IEEE Transactions on consumer electronics,2006,52:555-558.
[3]Leh L.ZigBee-based intelligent indoor positioning system soft computing[J].Soft Computing,2014,18:443-456.
[4]李强,王玫,刘争红.基于RFID覆盖扫描的标签定位方法[J].计算机工程,2017,43:294-298.
[5]Xiao J H,Liu Z,Yang Y,et al.Comparison and analysis of indoor wireless position in techniques[C].International Conference on Computer Science and Service System(CSSS),2011:293-296.
[6]Deng Z L,Yu Y P,Yuan X,et al.Situation and development tendency of indoor positioning[J].China Communications,2013,10:42-55.
[7]Xia S X,Liu Y,Yuan G,et al.Indoor Fingerprint Positioning Based on Wi-Fi:An Overview[J].International Journal of Geo-Information,2017,6:135.
[8]李石荣,李飞腾.基于RSS概率统计分布的室内定位方法[J].计算机工程与应用,2016,52:119-124.
[9]朱雪梅,李石荣.基于RSS分布重叠的WKNN室内定位方法[J].徐州工程学院学报,2017,32.48-52.
[10]覃团发,姚海涛,覃远年,等.移动通信[M].重庆:重庆大学出版社,2004:56-74.
[11]Luo J Y,Zhan X Q.Characterization of smart phone received signal strength indication for WLAN indoor positioning accuracy improvement.Journal of Networks,2014,9:1061-1065.
[12]张明华,张申生,曹健.无线局域网中基于信号强度的室内定位[J].计算机科学,2014,41:68-71.
[13]Basheer M R,Jagannathan S.Localization and Tracking of Objects Using Cross-Correlation of Shadow Fading Noise[J].IEEE Transactions on Mobile Computing.2014,13:2293-2305.
[14]陈斌涛,刘任任,陈益强,等.动态环境中的Wi-Fi指纹自适应室内定位方法[J].传感技术学报,2015,28:729-738.
[15]张勇,徐小龙,徐科宇.基于加权质心法的WLAN室内定位系统[J].电子测量与仪器学报,2015,29:1036-1041.
[16]韦燕华,周彦,王冬丽.基于LS-SVM的位置指纹室内定位[J].计算机工程与应用,2016,52:122-125.
[17]朱宇佳,邓中亮,刘文龙,等.基于支持向量机多分类的室内定位系统[J].计算机科学,2012,39:32-35.
[18]桑楠,袁兴中,周瑞.基于SVM分类和回归的WiFi室内定位方法[J].计算机应用研究,2014,31:1820-1823.
[19]Molisch A F.Wireless Communications[M].Wiley,2011:39-62.
[20]邓乃扬,田英杰.支持向量机:理论、算法与拓展[M].北京:科学出版社,2009:81-115.
[2]Zhou S,Pollard J K.Position measurement using Bluetooth[J].IEEE Transactions on consumer electronics,2006,52:555-558.
[3]Leh L.ZigBee-based intelligent indoor positioning system soft computing[J].Soft Computing,2014,18:443-456.
[4]李强,王玫,刘争红.基于RFID覆盖扫描的标签定位方法[J].计算机工程,2017,43:294-298.
[5]Xiao J H,Liu Z,Yang Y,et al.Comparison and analysis of indoor wireless position in techniques[C].International Conference on Computer Science and Service System(CSSS),2011:293-296.
[6]Deng Z L,Yu Y P,Yuan X,et al.Situation and development tendency of indoor positioning[J].China Communications,2013,10:42-55.
[7]Xia S X,Liu Y,Yuan G,et al.Indoor Fingerprint Positioning Based on Wi-Fi:An Overview[J].International Journal of Geo-Information,2017,6:135.
[8]李石荣,李飞腾.基于RSS概率统计分布的室内定位方法[J].计算机工程与应用,2016,52:119-124.
[9]朱雪梅,李石荣.基于RSS分布重叠的WKNN室内定位方法[J].徐州工程学院学报,2017,32.48-52.
[10]覃团发,姚海涛,覃远年,等.移动通信[M].重庆:重庆大学出版社,2004:56-74.
[11]Luo J Y,Zhan X Q.Characterization of smart phone received signal strength indication for WLAN indoor positioning accuracy improvement.Journal of Networks,2014,9:1061-1065.
[12]张明华,张申生,曹健.无线局域网中基于信号强度的室内定位[J].计算机科学,2014,41:68-71.
[13]Basheer M R,Jagannathan S.Localization and Tracking of Objects Using Cross-Correlation of Shadow Fading Noise[J].IEEE Transactions on Mobile Computing.2014,13:2293-2305.
[14]陈斌涛,刘任任,陈益强,等.动态环境中的Wi-Fi指纹自适应室内定位方法[J].传感技术学报,2015,28:729-738.
[15]张勇,徐小龙,徐科宇.基于加权质心法的WLAN室内定位系统[J].电子测量与仪器学报,2015,29:1036-1041.
[16]韦燕华,周彦,王冬丽.基于LS-SVM的位置指纹室内定位[J].计算机工程与应用,2016,52:122-125.
[17]朱宇佳,邓中亮,刘文龙,等.基于支持向量机多分类的室内定位系统[J].计算机科学,2012,39:32-35.
[18]桑楠,袁兴中,周瑞.基于SVM分类和回归的WiFi室内定位方法[J].计算机应用研究,2014,31:1820-1823.
[19]Molisch A F.Wireless Communications[M].Wiley,2011:39-62.
[20]邓乃扬,田英杰.支持向量机:理论、算法与拓展[M].北京:科学出版社,2009:81-115.