检索结果-南通市图书馆

NLoS Mitigation in ToA Localization Based on Spatial Correlation Filter and Iterative Minimum Residual

在线全文

学校读者我要写书评

暂无评论

China Communications 2012年第4期9卷 13-19页

作者： luo haiyong Liu Shujing Liu Xiaoming Institute of Computing Technology Chinese Academy of Sciences Beijing 100191 P. R. China

To mitigate the Non-Line-of-Sight (NLoS) error which seriously affects the localization accuracy and robustness in complex indoor environment,a novel Iterative Minimum Residual (IMR) based on the consistency hypothesis of the residual and the error is proposed in this *** chooses the best subset of measurements to calculate the coordinates of the unknown node by comparing the residuals obtained with different subsets of *** reduce the time complexity of the IMR algorithm,Spatial Correlation Filter (SCF) is also proposed,which can remove the most serious NLoS distance with low calculation *** with the proposed SCF and IMR algorithm,nodes can be localized with high accuracy and low time *** results with real dataset demonstrate that the proposed algorithm can identify the NLoS range effectively with about 50% time cost of employing SCF only.

关键词： localization NLoS mitigation ToA iterativeminimum residual spatial correlation filter

An RSSl Gradient-based AP Localization Algorithm

在线全文

学校读者我要写书评

暂无评论

China Communications 2014年第2期11卷 100-108页

作者： ZHAO Fang luo haiyong GENG Hao SUN Qijin School of Software Engineering B eijing University of Posts and Telecommunications B eijing 100876 China Institute of Computing Technology CAS Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing 100190 China

Recent rapid rise of indoor location based services for smartphones has further increased the importance of precise localization of Wi-Fi Access Point(AP).However,most existing AP localization algorithms either exhibit high errors or need specialized hardware in practical *** this paper,we propose a novel RSSI gradient-based AP localization *** consists of the following three major steps:firstly,it uses the local received signal strength variations to estimate the direction(minus gradient) of AP,then employs a direction clustering method to identify and filter measurement outliers,and finally adopts triangulation method to localize AP with the selected gradient *** results demonstrate that the average localization error of our proposed algorithm is less than 2meters,far outperforming that of the weighted centroid approach.

关键词： AP localization RSSI gradient clustering triangulation

A Robust Turn Detection Algorithm based on Periodic Signal Identification

在线全文

学校读者我要写书评

暂无评论

A Robust Turn Detection Algorithm based on Periodic Signal I...

A Bluetooth Localization Algorithm Based on Map Path Calibration and Time Series Filtering

第九届中国卫星导航学术年会

作者： Yu Chen haiyong luo Fang Zhao Wenhua Shao Qu Wang School of Software Engineering Beijing University of Posts and Telecommunications Research Centre of Pervasive Computing Institute of Computing Technology Chinese Academy of Sciences School of Information and Communication Engineering Beijing University of Posts and Telecommunications

Turn detection can be widely used in location navigation, user behavior identification, and scene awareness. Accurate real-time identification of pedestrian turns contributes to improving the accuracy of positioning navigation accuracy and scene awareness. Considering the problem of the insufficient accuracy and robustness of the existing turn detection algorithm, this paper proposes a turn detection algorithm based on periodic signal recognition, which effectively solves the misjudgment caused by the periodic swing of user walking. The algorithm collects the acceleration sensor and the gyro sensor data in real time and calculates the angular velocity of the rotation in the vertical direction by multiplying the vertical gravitational acceleration unit vector by the gyro sensor data. In this paper, fast Fourier transform(FFT) is used to identify and eliminate periodic interfering signals generated by user walking, only keeping the non-periodic signal generated by user walking(such as turning). By integrating the vertical angular velocity data in the sliding window to obtain the angle change value of the user walking within a certain period of time, and the threshold value is compared to realize the accurate identification of the turning behavior. In order to adapt to the user’s turn size and the turn speed, the algorithm also proposes a corner detection method based on multi-sliding window. The experiment results show that the proposed algorithm has higher accuracy and lower power consumption than other algorithms which based on GPS and electronic compass. The algorithm can realize the accurate identification of the turning behavior of the mobile phone in various positions of the user, and has good robustness. The accuracy of turning recognition can reach 93% and the average power consumption is about 60 mW.

关键词： turn detection scene awareness signal recognition multi-sliding window high accuracy low power consumption

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Bluetooth Localization Algorithm Based on Map Path Calibra...

第九届中国卫星导航学术年会

作者： Shaomeng Chen haiyong luo Qu Wang Wenhua Shao Fang Zhao School of Software Engineering Beijing University of Posts and Telecommunications Research Centre of Pervasive Computing Institute of Computing Technology Chinese Academy of Sciences School of Information and Communication Engineering Beijing University of Posts and Telecommunications

With the gradual progress of the urbanization process of modern society and the continuous improvement of residents’ living standard, people’s demand for IPS(Indoor Positioning System) is more urgent than that of the past, higher requirements for positioning accuracy, positioning robustness and positioning energy consumption are put forward. Low-power Bluetooth technology has the characteristics of low-cost, easy deployment and low power consumption, supporting all mainstream smartphone operating systems, and attracting extensive attention from academic and industry field. In this paper, aiming at the situation that current Bluetooth low energy positioning accuracy has large fluctuation under the circumstance of multipath propagation, external disturbance and other factors, and has poor user experience, a Bluetooth localization algorithm based on map path calibration and time series filtering is proposed(MCTF). This algorithm comprehensively utilizes a post-processing method based on the average sliding window, time-series based spatial restraint post-processing method and path information based location calibration method, effectively eliminating the large fluctuation of positioning results caused by multipath propagation and other external wireless signal interference in complex indoor environment. By using map information, based on the fact that position cannot be transient, utilizing feedback filtering, positioning results can get path correction and directioncorrection respectively, solving the problem that the positioning coordinates jump between adjacent narrow aisles and jump back and forth on the same path during the positioning process. Extensive experiments performed in shopping mall, building office, exhibition center and other typical indoor environments demonstrate that the average positioning error of the proposed algorithm is within 1.5 m, which has good robustness and ensures the smoothness, accuracy and stability of the positioning result.

关键词： indoor positioning Bluetooth location map path information time series filtering BLE path correction direction correction

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

基于随机森林的跌倒检测算法

计算机应用 2015年第11期35卷 3157-3160,3165页

作者：罗丹罗海勇北京邮电大学国际学院北京100083 中国科学院计算技术研究所普适计算研究中心北京100190

针对现有跌倒检测算法由于缺乏真实老人跌倒样本以及使用年轻人仿真跌倒样本规模较小导致的过拟合和适应性不足等问题,提出了基于随机森林的跌倒检测算法。该算法采用滑动窗口机制,对窗口内的加速度数据进行时间域和变换域处理,提取时... 详细信息

针对现有跌倒检测算法由于缺乏真实老人跌倒样本以及使用年轻人仿真跌倒样本规模较小导致的过拟合和适应性不足等问题,提出了基于随机森林的跌倒检测算法。该算法采用滑动窗口机制,对窗口内的加速度数据进行时间域和变换域处理,提取时间域和变换域特征参数后,在所有样本集中进行有放回的Bootstrap随机抽样和属性随机选择,构建多个基于最佳属性分割的支持向量机(SVM)基本分类器。在线跌倒检测阶段,对多个SVM基本分类器的分类结果采用少数服从多数的原则,给出最终判定结果。实验表明,随机森林跌倒检测算法可获得95.2%的准确率、90.6%的敏感度和93.5%的特异性,明显优于基于SVM和反向传播(BP)神经网络跌倒检测算法,反映出随机森林跌倒检测算法能更准确地检测跌倒行为,具有较强的泛化能力和鲁棒性。

关键词：跌倒检测随机森林支持向量机反向传播神经网络属性

在线全文

学校读者我要写书评

暂无评论

基于公共信标集的高精度射频指纹定位算法

计算机研究与发展 2012年第2期49卷 243-252页

作者：赵方罗海勇马严徐俊俊北京邮电大学软件学院北京100876 中国科学院计算技术研究所移动计算与新型终端北京市重点实验室北京100190

目前基于WiFi射频指纹定位技术有望成为大规模城区室内外全空间定位的首选.针对RSS信号时变特性严重影响WiFi定位精度和鲁棒性的问题,提出了一种基于公共信标集的高精度射频指纹定位算法.该算法把目标定位看成贝叶斯估计问题,通过采用... 详细信息

目前基于WiFi射频指纹定位技术有望成为大规模城区室内外全空间定位的首选.针对RSS信号时变特性严重影响WiFi定位精度和鲁棒性的问题,提出了一种基于公共信标集的高精度射频指纹定位算法.该算法把目标定位看成贝叶斯估计问题,通过采用高斯混合模型更加准确地表征复杂训练指纹的信号特征,以及使用基于Markov链的状态转移模型和基于后验概率的自适应网格集选择机制,充分利用目标的历史状态信息和环境布局信息,不仅减少了定位搜索网格空间,而且还抑制了移动过程中不可能发生的位置跳变,提高了定位精度和鲁棒性.实验结果表明,所提定位算法以90%的概率可获得3m以内的定位误差,其定位性能明显优于传统单一高斯模型.

关键词：室内定位射频指纹贝叶斯估计高斯混合模型 Markov链

在线全文

学校读者我要写书评

暂无评论

人群行为分析研究综述

计算机辅助设计与图形学学报 2018年第12期30卷 2353-2365页

作者：王曲赵炜琪罗海勇门爱东赵方北京邮电大学信息与通信工程学院北京100876 中国科学院自动化研究所模式识别国家重点实验室北京100190 中国科学院计算技术研究所泛在计算系统研究中心北京100190 北京邮电大学软件学院北京100876

近年来,人群行为分析成为计算机视觉领域中备受关注的研究方向,主要运用于智能视频监控、人机交互、智能家居、视频检索等领域,以视频中运动人群的行为分析和理解为研究目的,对输入序列图像中的运动目标进行运动检测、匹配和建模.文中... 详细信息

近年来,人群行为分析成为计算机视觉领域中备受关注的研究方向,主要运用于智能视频监控、人机交互、智能家居、视频检索等领域,以视频中运动人群的行为分析和理解为研究目的,对输入序列图像中的运动目标进行运动检测、匹配和建模.文中对人群行为分析的研究现状以及典型算法进行全面综述.首先对当前人群行为数据库进行简要介绍并分类比较;之后根据人群行为分析算法核心侧重点的不同,将人群行为分析算法分为基于特征和基于模型两大类,并根据每一大类各自的特点进行细分和比较,详细介绍了每类中具有代表性的算法,分析各算法的优缺点和适用的人群场景;最后总结了人群行为分析中的困难和挑战,对该研究领域的发展进行展望.

关键词：人群行为识别异常检测运动轨迹目标跟踪

在线全文

学校读者我要写书评

暂无评论

基于局部网络拓扑特征的鲁棒节点定位算法

高技术通讯 2009年第5期19卷 453-460页

作者：赵方马严罗海勇林权宋茂强北京邮电大学软件学院北京100876 北京邮电大学网络技术研究院北京100876 中国科学院计算技术研究所北京100190 北京航空航天大学北京100083

针对无线传感器网络的较大测距误差严重影响定位算法精度和鲁棒性的问题,利用节点均匀部署网络的拓扑特征,提出了一种基于局部网络拓扑特征的鲁棒节点定位算法(LFLS算法)。该算法通过构建节点测距高估粗差阈值参数和测距低估粗差阈值参... 详细信息

针对无线传感器网络的较大测距误差严重影响定位算法精度和鲁棒性的问题,利用节点均匀部署网络的拓扑特征,提出了一种基于局部网络拓扑特征的鲁棒节点定位算法(LFLS算法)。该算法通过构建节点测距高估粗差阈值参数和测距低估粗差阈值参数,在对未知节点1跳测距数据集进行粗差识别及剔除等预处理滤波的基础上,使用高斯加权最小二乘定位算法实现节点定位。仿真结果表明,基于局部网络拓扑特征的鲁棒节点定位算法的定位精度明显优于未采用局部网络拓扑特征进行粗差预处理的加权最小二乘定位算法,其中粗差测距直接相关节点的定位精度改进尤为明显。

关键词：无线传感器网络节点定位加权最小二乘局部网络拓扑特征

基于动态Radio Map的粒子滤波室内无线定位算法

在线全文

学校读者我要写书评

暂无评论

计算机研究与发展 2011年第1期48卷 139-146页

作者：林以明罗海勇李锦涛赵方中国科学院计算技术研究所北京100190 中国科学院研究生院北京100190 北京邮电大学北京100876

针对目前大多数基于射频信号强度匹配定位算法在定位精度及鲁棒性方面不足,提出了一种基于动态Radio Map的粒子滤波室内无线定位算法.该算法利用参考节点构建基于空间关联性的动态Radio Map模型,以反映信号环境的实时变化,并将移动目标... 详细信息

针对目前大多数基于射频信号强度匹配定位算法在定位精度及鲁棒性方面不足,提出了一种基于动态Radio Map的粒子滤波室内无线定位算法.该算法利用参考节点构建基于空间关联性的动态Radio Map模型,以反映信号环境的实时变化,并将移动目标定位由分类问题转化为回归问题,打破了传统网格式Radio Map模型的限制,降低了算法的时空复杂度.实验结果表明,相对于静态Radio Map模型,动态Radio Map模型将定位精度平均提高了约20%,表现出良好的环境动态自适应能力.

关键词：无线定位动态Radio Map 粒子滤波空间关联性模型迁移学习