基于WLAN(wireless local area network)的定位在智能家居、室内导航、个性化服务等应用中扮演着重要的角色。研究了基于序列到序列seq2seq模型的室内WLAN定位方法。该方法基于在自然语言处理中广泛应用的seq2seq神经网络模型,通过样本...基于WLAN(wireless local area network)的定位在智能家居、室内导航、个性化服务等应用中扮演着重要的角色。研究了基于序列到序列seq2seq模型的室内WLAN定位方法。该方法基于在自然语言处理中广泛应用的seq2seq神经网络模型,通过样本数据学习信号指纹空间中的时间序列和坐标空间中的时间序列的关系。经过滤波等预处理后,再进行样本增强,并设计合理的输入输出及代价函数,本方法能够实现更高精度定位。实测的数据表明,提出的方法相比于其他几种基于神经网络的定位方法,度量学习RFSM方法、去噪自编码器DAE方法、f-RNN方法,平均定位精度分别提高了23%、11%和20%。展开更多
室内定位技术在多领域有着重要的应用,而传统的无线局域网(Wireless Local Area Network,WLAN)指纹定位方法通常很少考虑WLAN接收信号强度(Received Signal Strength,RSS)特征的多样性以及来自不同接入点(Access Point,AP)的RSS特征位...室内定位技术在多领域有着重要的应用,而传统的无线局域网(Wireless Local Area Network,WLAN)指纹定位方法通常很少考虑WLAN接收信号强度(Received Signal Strength,RSS)特征的多样性以及来自不同接入点(Access Point,AP)的RSS特征位置分辨力的差异性问题,从而导致WLAN定位精度不高且定位效率较低.对此,本文提出一种基于多维模糊映射AP优化的WLAN室内定位方法.在离线阶段通过多次采集RSS数据提取多维RSS特征,计算AP信息增益比及相应的离线模糊隶属度,并利用模糊关系方程求解多维RSS特征模糊权重;而在在线阶段,则通过多维模糊映射构造模糊判定矩阵并计算AP在线模糊隶属度,同时结合K近邻(K-Nearest Neighbor,KNN)算法完成对目标的位置坐标计算.实验结果表明,相较于传统的AP优化定位方法,所提方法在线阶段的定位计算开销最高减少了4.12 s,定位误差4 m内的置信概率为91.91%.展开更多
Although k-nearest neighbors （KNN） is a popular fingerprint match algorithm for its simplicity and accuracy, because it is sensitive to the circumstances, a fuzzy c-means （FCM） clustering algorithm is applied to i...Although k-nearest neighbors （KNN） is a popular fingerprint match algorithm for its simplicity and accuracy, because it is sensitive to the circumstances, a fuzzy c-means （FCM） clustering algorithm is applied to improve it. Thus, a KNN-based two-step FCM weighted （KTFW） algorithm for indoor positioning in wireless local area networks （WLAN） is presented in this paper. In KTFW algorithm, k reference points （RPs） chosen by KNN are clustered through FCM based on received signal strength （RSS） and location coordinates. The right clusters are chosen according to rules, so three sets of RPs are formed including the set of k RPs chosen by KNN and are given different weights. RPs supposed to have better contribution to positioning accuracy are given larger weights to improve the positioning accuracy. Simulation results indicate that KTFW generally outperforms KNN and its complexity is greatly reduced through providing initial clustering centers for FCM.展开更多
Currently,the WLAN indoor positioning system attracts a lot of interests,not only because of the cheap implementation but also because of the high positioning accuracy comparing with other indoor positioning systems.T...Currently,the WLAN indoor positioning system attracts a lot of interests,not only because of the cheap implementation but also because of the high positioning accuracy comparing with other indoor positioning systems.The WLAN indoor positioning system contains two phases,which are offline phase and online phase.In the online phase,the WLAN equipment user(UE) has to access to the WLAN for the latest radio map and positioning software.Due to during the network allocation vector(NAV) duration,the WLAN channel is only reserved for one WLAN UE,others UEs' carrier accessing will be blocked.In addition,the blocked UE will make a retrial accessing,which will definitely introduce more traffic blocking to the WLAN.So In this paper,based on the analysis of the WLAN indoor positioning system architecture,a proper queuing model by using of the Extended Erlang B formula is proposed,which takes the retrial calling percentage into consideration in the proposed model.The simulation results show that the proposed method is more accurate and performs well to predict the blocking probability.展开更多
文摘基于WLAN(wireless local area network)的定位在智能家居、室内导航、个性化服务等应用中扮演着重要的角色。研究了基于序列到序列seq2seq模型的室内WLAN定位方法。该方法基于在自然语言处理中广泛应用的seq2seq神经网络模型,通过样本数据学习信号指纹空间中的时间序列和坐标空间中的时间序列的关系。经过滤波等预处理后,再进行样本增强,并设计合理的输入输出及代价函数,本方法能够实现更高精度定位。实测的数据表明,提出的方法相比于其他几种基于神经网络的定位方法,度量学习RFSM方法、去噪自编码器DAE方法、f-RNN方法,平均定位精度分别提高了23%、11%和20%。
文摘室内定位技术在多领域有着重要的应用,而传统的无线局域网(Wireless Local Area Network,WLAN)指纹定位方法通常很少考虑WLAN接收信号强度(Received Signal Strength,RSS)特征的多样性以及来自不同接入点(Access Point,AP)的RSS特征位置分辨力的差异性问题,从而导致WLAN定位精度不高且定位效率较低.对此,本文提出一种基于多维模糊映射AP优化的WLAN室内定位方法.在离线阶段通过多次采集RSS数据提取多维RSS特征,计算AP信息增益比及相应的离线模糊隶属度,并利用模糊关系方程求解多维RSS特征模糊权重;而在在线阶段,则通过多维模糊映射构造模糊判定矩阵并计算AP在线模糊隶属度,同时结合K近邻(K-Nearest Neighbor,KNN)算法完成对目标的位置坐标计算.实验结果表明,相较于传统的AP优化定位方法,所提方法在线阶段的定位计算开销最高减少了4.12 s,定位误差4 m内的置信概率为91.91%.
文摘Although k-nearest neighbors （KNN） is a popular fingerprint match algorithm for its simplicity and accuracy, because it is sensitive to the circumstances, a fuzzy c-means （FCM） clustering algorithm is applied to improve it. Thus, a KNN-based two-step FCM weighted （KTFW） algorithm for indoor positioning in wireless local area networks （WLAN） is presented in this paper. In KTFW algorithm, k reference points （RPs） chosen by KNN are clustered through FCM based on received signal strength （RSS） and location coordinates. The right clusters are chosen according to rules, so three sets of RPs are formed including the set of k RPs chosen by KNN and are given different weights. RPs supposed to have better contribution to positioning accuracy are given larger weights to improve the positioning accuracy. Simulation results indicate that KTFW generally outperforms KNN and its complexity is greatly reduced through providing initial clustering centers for FCM.
基金Sponsored by the National Natural Science Foundation and Civil Aviation Administration of China (Grant No. 61101122)the Fundamental Research Funds for the Central Universities (Grant No. HIT. NSRIF. 2010090)+1 种基金the China Postdoctoral Science Foundation (Grant No. 20100471079)the Heilongjiang Province Postdoctoral Science Foundation (Grant No. LBH-z10127)
文摘Currently,the WLAN indoor positioning system attracts a lot of interests,not only because of the cheap implementation but also because of the high positioning accuracy comparing with other indoor positioning systems.The WLAN indoor positioning system contains two phases,which are offline phase and online phase.In the online phase,the WLAN equipment user(UE) has to access to the WLAN for the latest radio map and positioning software.Due to during the network allocation vector(NAV) duration,the WLAN channel is only reserved for one WLAN UE,others UEs' carrier accessing will be blocked.In addition,the blocked UE will make a retrial accessing,which will definitely introduce more traffic blocking to the WLAN.So In this paper,based on the analysis of the WLAN indoor positioning system architecture,a proper queuing model by using of the Extended Erlang B formula is proposed,which takes the retrial calling percentage into consideration in the proposed model.The simulation results show that the proposed method is more accurate and performs well to predict the blocking probability.
