一种动态校正的信号双尺度近邻定位方法

doi:10.19665/j.issn1001-2400.2022.03.011

西安电子科技大学学报 ›› 2022, Vol. 49 ›› Issue (3): 93-100.doi: 10.19665/j.issn1001-2400.2022.03.011

一种动态校正的信号双尺度近邻定位方法

孙顺远¹(),朱红洲¹(),秦宁宁^1,²()

1.江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122
2.南京航空航天大学电磁频谱空间认知动态系统工信部重点实验室,江苏南京 211106

收稿日期:2021-02-03 修回日期:2022-03-18 出版日期:2022-06-20 发布日期:2022-07-04
作者简介:孙顺远(1984—),男,副教授,博士,E-mail: hzrobin@jiangnan.edu.cn|朱红洲(1996—),男,硕士,E-mail: 6181913053@stu.jiangnan.edu.cn|秦宁宁(1980—),女,教授,博士, E-mail: ningning801108@163.com
基金资助:
国家自然科学基金(61702228);国家自然科学基金(61803183);江苏省自然科学基金(BK20170198);江苏省自然科学基金(BK20180591);电磁频谱空间认知动态系统工信部重点实验室开放研究基金(KF20202104)

Signal two-scale nearest neighbor positioning method under dynamic correction

SUN Shunyuan¹(),ZHU Hongzhou¹(),QIN Ningning^1,²()

1. Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education,Jiangnan University,Wuxi 214122,China
2. Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space,Ministry of Industry and Information Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China

Received:2021-02-03 Revised:2022-03-18 Online:2022-06-20 Published:2022-07-04

摘要/Abstract

摘要：

在大型室内定位场景中,利用接收信号强度的指纹定位算法存在信号传播不稳定、计算复杂度高以及定位精度低等问题。为解决该问题,提出一种动态校正的信号双尺度近邻定位算法。根据目标区域的物理连通性,采用一对多支持向量机构建分区模型,缩小信号变化范围,减小在线阶段的数据计算量。以高斯过程回归训练接入点信号距离模型预测分区路径损耗特性,校正信号波动值,使定位结果更加稳定。在线阶段,引入斯皮尔曼相似系数来衡量信号间的相似度,减小指纹库中异常值带来的影响,基于动态邻近算法计算信号间的差异值,然后使用Blending模型融合算法将这两种尺度进行线性融合,建立具备动态高斯校正能力的双尺度近邻定位算法,并设计环境参数自适应获取近邻k值,减小环境噪声的影响,克服了单一的信号尺度易导致定位结果波动较大的问题。测试结果表明,所提算法在房间和走廊区域定位精度均小于0.517 3 m,相较于传统算法,定位精度提升约25%以上。

关键词: 室内定位, 指纹定位, 分区, 高斯过程回归, 信号双尺度

Abstract:

Among indoor position scenarios,the positioning method based on the Received Signal Strength has several problems such as unstable signal propagation,high computational complexity and low positioning accuracy caused by large target areas.In order to solve these problems,this paper proposes a signal two-scale nearest neighbor with dynamic correction method,according to the connectivity structure of the target area,and the system uses the one-vs-rest support vector machine to construct a partition model of the target area in order to predict the subarea with signal changes.This paper trains the AP signal-distance model based on Gaussian process regression in partition.It is important to realize the correction of signal fluctuation value by predicting the path-loss characteristics in partition.In order to improve the positioning accuracy,by combining signal similarity with signal difference,a two-scale nearest neighbor algorithm is established.The k value of the nearest neighbor is adaptively calculated by combining the environmental parameter in order to reduce the influence of environmental noise.Through simulation experiments,the average localization error of the proposed algorithm is less than 0.5173 m,indicating that the algorithm causes a lower error than the traditional algorithm by more than 25 percent.

Key words: indoor positioning, fingerprint positioning, subarea, Gaussian process regression, signal two-scale

中图分类号:

TN96

孙顺远,朱红洲,秦宁宁. 一种动态校正的信号双尺度近邻定位方法[J]. 西安电子科技大学学报, 2022, 49(3): 93-100.

SUN Shunyuan,ZHU Hongzhou,QIN Ningning. Signal two-scale nearest neighbor positioning method under dynamic correction[J]. Journal of Xidian University, 2022, 49(3): 93-100.

图/表 6

图1

图2

表1

表2

图3

图4

参考文献 15

[1]	DAI S, HE L, ZHANG X. Autonomous WiFi Fingerprinting for Indoor Localization[C]// 2020 ACM/IEEE 11th International Conference on Cyber-Physical Systems.Piscatawy:IEEE, 2020:141-150.
[2]	BAI L, CIRAVEGNA F, BOND R, et al. A Low Cost Indoor Positioning System Using Bluetooth Low Energy[J]. IEEE Access, 2020, 8:136858-136871. doi: 10.1109/ACCESS.2020.3012342
[3]	ZHU Q, XIONG Q, WANG K, et al. Accurate WiFi-based Indoor Localization By Using Fuzzy Classifier And Mlps Ensemble In Complex Environment[J]. Journal of the Franklin Institute, 2020, 357(3):1420-1436. doi: 10.1016/j.jfranklin.2019.10.028
[4]	闫千里, 万鹏武, 卢光跃, 等. 非视距环境下RSS和TDOA联合的信源被动定位[J]. 西安电子科技大学学报, 2019, 46(3):180-188.
	YAN Qianli, WAN Pengwu, LU Guangyue, et al. Passive Positioning of RSS and TDOA in Non-Line-of-Sight Environment[J]. Journal of Xidian University, 2019, 46(3):180-188.
[5]	KANG S Y, KIM T H, CHUNG W Z. Hybrid RSS/AOA Localization Using Approximated Weighted Least Square in Wireless Sensor Networks[J]. Sensors, 2020, 20(4):1159-1170. doi: 10.3390/s20041159
[6]	SVECKO J, MALAJNE M, GLEICH D. Distance Estimation Using RSSI and Particle Filter[J]. ISA transactions, 2015, 55:275-285. doi: 10.1016/j.isatra.2014.10.003
[7]	YANG H, ZHANG Y, HUANG Y, et al. WKNN Indoor Location Algorithm Based On Zone Partition By Spatial Features And Restriction Of Former Location[J]. Pervasive and Mobile Computing, 2019, 60:101085. doi: 10.1016/j.pmcj.2019.101085
[8]	HE S, LIN W, CHAN S. Indoor localization and automatic fingerprint update with altered AP signals[J]. IEEE Transactions on Mobile Computing, 2016, 16(7):1897-1910. doi: 10.1109/TMC.2016.2608946
[9]	江志炜, 黄洋, 吴启晖. 基于核函数强化学习的抗干扰频点分配[J]. 系统工程与电子技术, 2021, 43(6):1547-1556.
	JANG Zhiwei, HUANG Yang, WU Qihui. Anti-jamming Frequency Allocation With Kernel-Based Reinforcement Learning[J]. Systems Engineering and Electronics, 2021, 43(6):1547-1556.
[10]	王博远, 刘学林, 蔚保国, 等. WiFi指纹定位中改进的加权k近邻算法[J]. 西安电子科技大学学报, 2019, 46(5):41-47.
	WANG Boyuan, LIU Xuelin, WEI Baoguo, et al. Improved Weighted K-Nearest Neighbor Algorithm for Wifi Fingerprint Positioning[J]. Journal of Xidian University, 2019, 46(5):41-47.
[11]	胡久松, 刘宏立, 徐琨. 自适应动态K的WKNN室内定位方法[J]. 重庆邮电大学学报:自然科学版, 2018, 30(4):431-438.
	HU Jiusong, LIU Hongli, XU Kun. WKNN Indoor Positioning Method Based on Adaptive Dynamic K[J]. Journal of Chongqing University of Posts and Telecommunications:natural science, 2018, 30(4):431-438.
[12]	王威, 李祖广, 吴启晖. 基于区块链的动态频谱共享接入技术[J]. 物联网学报, 2020, 4(2):26-34.
	WANG Wei, LI Zuguang, WU Qihui. Dynamic Spectrum Sharing Access Technology Based on Blockchain[J]. Chinese Journal on Internet of Things, 2020, 4(2):26-34.
[13]	HE S, TAN J, CHAN S. Towards Area Classification For Large-Scale Fingerprint-Based System[C]// Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: ACM, 2016:232-243.
[14]	江小平, 王妙羽, 丁昊, 等. 基于信道状态信息幅值-相位的被动式室内指纹定位[J]. 电子与信息学报, 2020, 42(5):1165-1171.
	JIANG Xiaoping, WANG Miaoyu, DING Hao, et al. Passive Indoor Fingerprint Location Based on Channel State Information Amplitude-phase[J]. Journal of Electronics & Information Technology, 2020, 42(5):1165-1171.
[15]	HE Z, LI Y, PEI L, et al. Calibrating Multi-channel RSS Observations for Localization Using Gaussian Process[J]. IEEE Wireless Communications Letters, 2019, 8(4):1116-1119. doi: 10.1109/LWC.2019.2908397

分区	分区判别精度(Ω₁/Ω₂)	GPR校正(Ω₁校正前/后)
分区1	96.97%/95.25%	1.179 9 m/0.349 8 m
分区2	98.48%/96.42%	1.302 9 m/0.445 8 m
分区3	96.97%/96.42%	0.957 8 m/0.365 7 m
分区4	96.97%/96.42%	1.088 2 m/0.436 2 m

参数	WKNN(Ω₁/Ω₂)	CCM(Ω₁/Ω₂)	Bayesian(Ω₁/Ω₂)	DGC-TSNN(Ω₁/Ω₂)
均方根误差/m	0.873 5/1.143 6	0.639 8/0.857 3	0.799 7/0.931 2	0.460 8/0.766 5
平均绝对误差/m	0.774 3/1.018 5	0.529 1/0.684 7	0.567 9/0.813 4	0.405 3/0.517 3
最大误差/m	2.007 6/2.699 9	1.901 3/2.392 3	1.530 0/1.688 7	1.030 6/2.337 4

一种动态校正的信号双尺度近邻定位方法

Signal two-scale nearest neighbor positioning method under dynamic correction

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 15

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	孔繁锵, 余圣杰, 王坤, 方煦, 吕志杰. 卷积循环神经网络的高光谱图像解混方法[J]. 西安电子科技大学学报, 2025, 52(1): 142-151.
[2]	栗琳轲, 陈杰, 刘君. 神经网络差分区分器的改进方案与应用[J]. 西安电子科技大学学报, 2025, 52(1): 196-214.
[3]	杨小雪, 陈杰. 几类密码算法的神经网络差分区分器的改进[J]. 西安电子科技大学学报, 2024, 51(1): 210-222.
[4]	李雅宁,李宏生,蔚保国. 一种室内伪卫星混合指纹定位方法[J]. 西安电子科技大学学报, 2023, 50(5): 21-31.
[5]	郑安琪, 秦宁宁. 模糊空间下双标签指纹定位算法[J]. 西安电子科技大学学报, 2023, 50(2): 81-91.
[6]	秦宁宁,张臣臣. 模糊聚类下的接入点选择匹配定位算法[J]. 西安电子科技大学学报, 2022, 49(4): 71-81.
[7]	秦宁宁,吴忆松,孙顺远. 一种双信标机制下的指纹库构建方法[J]. 西安电子科技大学学报, 2022, 49(3): 111-119.
[8]	陈昌川,王海宁,黄炼,黄涛,李连杰,黄向康,代少升. 一种基于局部表征的面部表情识别算法[J]. 西安电子科技大学学报, 2021, 48(5): 100-109.
[9]	秦宁宁,吴忆松,杨乐. 动态模糊匹配下的多元相似度定位算法[J]. 西安电子科技大学学报, 2021, 48(4): 27-35.
[10]	秦宁宁,王超. 时序测量信息触发的递归贝叶斯定位算法[J]. 西安电子科技大学学报, 2020, 47(4): 10-17.
[11]	王博远,刘学林,蔚保国,贾瑞才,甘兴利,黄璐. WiFi指纹定位中改进的加权k近邻算法[J]. 西安电子科技大学学报, 2019, 46(5): 41-47.
[12]	李翠芸;王精毅;姬红兵. 高斯过程回归下的多机动扩展目标跟踪[J]. 西安电子科技大学学报, 2017, 44(6): 31-36.
[13]	贺磊南;卢虎;姬正洲. WiFi/PDR室内分层三维定位技术[J]. 西安电子科技大学学报, 2017, 44(4): 167-173+166.
[14]	鲁航;崔维嘉;巴斌;逯志宇. 多观测值约束的可见光定位算法[J]. 西安电子科技大学学报, 2017, 44(4): 156-161.
[15]	李翠芸;王精毅;姬红兵. 高斯过程回归的CPHD扩展目标跟踪[J]. 西安电子科技大学学报, 2017, 44(3): 8-12+30.