基于GAWK-means的地铁车站指纹定位方法

doi:10.16180/j.cnki.issn1007-7820.2022.02.006

电子科技 ›› 2022, Vol. 35 ›› Issue (2): 34-39.doi: 10.16180/j.cnki.issn1007-7820.2022.02.006

基于GAWK-means的地铁车站指纹定位方法

金霄,吴飞,鄢松,陆雯霞,张忠艺

上海工程技术大学电子电气工程学院,上海 201620

收稿日期:2020-10-30 出版日期:2022-02-15 发布日期:2022-02-24
作者简介:金霄(1995-),男,硕士研究生。研究方向:室内定位。|吴飞(1967-),男,博士,教授。研究方向:计算机网络。
基金资助:
国家自然科学基金青年项目(61902237);上海市科技学术委员会重点项目(18511101600);上海市自然科学基金(17ZR1411900);上海市科委青年科技英才"杨帆计划"项目(19YF1418200);上海工程技术大学研究生科研创新项目(19KY0207)

Fingerprint Location Method of Metro Station Based on GAWK-means

JIN Xiao,WU Fei,YAN Song,LU Wenxia,ZHANG Zhongyi

School of Electronic and Electrical Engineering,Shanghai University of Engineering Science, Shanghai 201620,China

Received:2020-10-30 Online:2022-02-15 Published:2022-02-24
Supported by:
National Natural Science Foundation of China(61902237);Key Projects of Shanghai Science and Technology Academic Committee(18511101600);Shanghai Natural Science Foundation(17ZR1411900);Shanghai Science and Technology Commission Young Scientific and Technological Talents "Yang Fan Plan"(19YF1418200);Graduate Scientific Research and Innovation Program of Shanghai University of Engineering Science(19KY0207)

摘要/Abstract

摘要：

针对在城市轨道交通车站内,利用iBeacon技术进行指纹定位时存在匹配效率较低、定位精度不理想的问题,文中提出了一种基于GAWK-means的地铁车站指纹定位方法。离线阶段,根据指纹数据本身的离散程度进行K-means欧式距离权重优化以便更好地体现类内相似度,再将改进的K-means结合遗传算法,优化聚类结果以减少陷入局部最优。在线阶段,利用K近邻法将信号向量与最为接近的子指纹库匹配获得定位结果,通过平均定位误差对该方法整体性能进行评估。实验结果表明,在地铁车站离线阶段使用GAWK-means算法平均定位误差为1.52 m,相较于未聚类和传统K-means聚类,定位误差减少了0.41 m以上。

关键词: 地铁车站, iBeacon技术, 指纹定位, 遗传算法, K-means聚类, 欧式距离, K近邻法, GAWK-means

Abstract:

In order to solve the problem of low matching efficiency and poor positioning accuracy when using iBeacon technology for fingerprint location in urban rail transit stations, a metro station fingerprint location method based on GAWK-means is proposed in this study. In the offline stage, the K-means Euclidean distance weight is optimized according to the discreteness of the fingerprint data to better reflect the intra-class similarity. Then, the improved K-means is combined with the genetic algorithm to optimize the clustering results to reduce the clustering results from falling into the local optimum. In the online stage, the K-nearest neighbor method is used to match the signal vector with the nearest sub-fingerprint database to get the location result, and the overall performance of the method is evaluated by the average positioning error. The experimental results show that the average positioning error of the GAWK-means algorithm is 1.52 m in the offline phase of the subway station. Compared with the un-clustered and traditional K-means clustering, the positioning error of the proposed method is reduced by more than 0.41 m.

Key words: metro station, iBeacon technology, fingerprint location, genetic algorithm, K-means clustering, Euclidean distance, K-nearest neighbor method, GAWK-means

中图分类号:

TN92

金霄,吴飞,鄢松,陆雯霞,张忠艺. 基于GAWK-means的地铁车站指纹定位方法[J]. 电子科技, 2022, 35(2): 34-39.

JIN Xiao,WU Fei,YAN Song,LU Wenxia,ZHANG Zhongyi. Fingerprint Location Method of Metro Station Based on GAWK-means[J]. Electronic Science and Technology, 2022, 35(2): 34-39.

图/表 8

图1

图2

表1

图3

图4

图5

图6

表2

参考文献 18

[1]	万慧颖, 万旺根, 罗天杭. 基于蓝牙定位的地下空间逃生疏散系统设计与实现[J]. 电子测量技术, 2019, 42(24):43-48.
	Wan Huiying, Wan Wanggen, Luo Tianhang. Design of escape system for underground space based on bluetooth location[J]. Electronic Measurement Technology, 2019, 42(24):43-48.
[2]	刘成. LBS定位技术研究与发展现状[J]. 导航定位学报, 2013, 1(1):78-83.
	Liu Cheng. Research and development status of LBS positioning technology[J]. Journal of Navigation and Positioning, 2013, 1(1):78-83.
[3]	程金晶, 魏东岩, 唐阳阳. WLAN指纹定位中AP选择策略研究[J]. 计算机技术与发展, 2015, 25(3):1-5.
	Cheng Jinjing, Wei Dongyan, Tang Yangyang. Research on AP selection strategy based on WLAN fingerprint positioning[J]. Computer Technology and Development, 2015, 25(3):1-5.
[4]	王琦. 基于RSSI测距的室内定位技术[J]. 电子科技, 2012, 25(6):64-66.
	Wang Qi. Research on an indoor positioning technology based on RSSI ranging[J]. Electronic Science and Technology, 2012, 25(6):64-66.
[5]	Kawaguchi N, Yano M, Ishida S, et al. Underground positioning: subway information system using WiFi location technology[C]. Taipei:Proceedings of the Tenth International Conference on Mobile Data Management: Systems, Services and Middleware, 2009.
[6]	张立东, 孙煜, 万明俊. 基于蓝牙技术的城市轨道交通室内定位导航及应用[J]. 城市轨道交通研究, 2019, 22(5):166-170.
	Zhang Lidong, Sun Yu, Wan Mingjun. Indoor location and navigation of bluetooth and the application in urban rail transit[J]. Urban Mass Transit, 2019, 22(5):166-170.
[7]	Wu C M, Qi S N, Zhao C. Fingerprint location algorithm based on K-means for spatial farthest access point in Wi-Fi environment[J]. The Journal of Engineering, 2020(4):115-119.
[8]	毛万葵, 吴飞, 张玉金, 等. 基于改进BKM聚类算法的WiFi室内定位方法[J]. 测控技术, 2019, 38(5):44-47.
	Mao Wankui, Wu Fei, Zhang Yujin, et al. WiFi indoor location technique using improved bisecting K-means clustering algorithm[J]. Measurement and Control Technology, 2019, 38(5):44-47.
[9]	郭靖. 对K-means聚类算法欧氏距离加权系数的研究[J]. 网络安全技术与应用, 2016, 19(10):74-75.
	Guo Jing. Research on Euclidean distance weighting coefficient of K-means clustering algorithm[J]. Network Security Technology and Application, 2016, 19(10):74-75.
[10]	张伟, 花向红, 邱卫宁, 等. WiFi指纹定位的一种新组合算法[J]. 测绘工程, 2017, 26(3):14-18.
	Zhang Wei, Hua Xianghong, Qiu Weining, et al. A new optimization algorithm for WiFi positioning[J]. Engineering of Surveying and Mapping, 2017, 26(3):14-18.
[11]	何洋, 吴飞, 张玉金, 等. 后验加权贝叶斯算法的WiFi室内定位[J]. 导航定位学报, 2019, 7(3):51-56.
	He Yang, Wu Fei, Zhang Yujin, et al. WiFi indoor positioning based on a posterior weighted Bayesian algorithm[J]. Journal of Navigation and Positioning, 2019, 7(3):51-56.
[12]	朱轶峰. 基于WiFi-BP的室内定位算法[J]. 电子科技, 2020, 33(8):74-79.
	Zhu Yifeng. Indoor positioning algorithm based on WiFi-BP[J]. Electronic Science and Technology, 2020, 33(8):74-79.
[13]	Youssef M A, Agrawala A, Shankar A U. WLAN location determination via clustering and probability distributions[C]. Fort Worth:Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003.
[14]	曹雪朋, 施伟斌. 基于RSSI的WSN室内定位系统研究[J]. 电子科技, 2017, 30(1):94-96.
	Cao Xuepeng, Shi Weibin. Study of WSN indoor postioning system based on RSSI[J]. Electronic Science and Technology, 2017, 30(1):94-96.
[15]	Shen G B, Chen Z, Zhang P C, et al. Walkie-Markie: indoor pathway mapping made easy[C]. Lombard:Proceedings of the Tenth Symposium on Networked Systems Design and Implementation, 2013.
[16]	吴广建, 章剑林, 袁丁. 基于K-means的手肘法自动获取K值方法研究[J]. 软件, 2019, 40(5),167-170.
	Wu Guangjian, Zhang Jianlin, Yuan Ding. Automatically obtaining K value based on K-means elbow method[J]. Software, 2019, 40(5):167-170.
[17]	Meng H, Yuan F, Yan T H, et al. Indoor positioning of RBF neural network based on improved fast clustering algorithm combined with LM algorithm[J]. IEEE Access, 2019(7):5932-5945.
[18]	王小平, 曹立明. 遗传算法:理论、应用及软件实现[M]. 西安: 西安交通大学出版社, 2002.
	Wang Xiaoping, Cao Liming. Genetic algorithm: theory, application and software implementation[M]. Xi'an: Xi'an Jiaotong University Press, 2002.

部分采样点坐标/m	部分采样点处的部分RSS值/dB·m
(0.9,65.7)	-83	-85	-68	-66	-68	-64	-65	-67	-70
(0.9,67.5)	-74	-76	-66	-67	-67	-60	-56	-68	-72
(0.9,69.3)	-73	-72	-72	-64	-69	-58	-57	-68	-76
(0.9,71.1)	-73	-71	-68	-99	-68	-60	-62	-72	-73
(0.9,72.9)	-71	-67	-67	-68	-64	-60	-68	-68	-79
(0.9,74.7)	-72	-71	-62	-66	-58	-69	-71	-73	-76
(0.9,76.5)	-70	-66	-62	-67	-55	-65	-71	-71	-76

聚类方法	匹配定位时间/s	平均定位误差/m
未聚类	0.047 2	2.370 5
传统K-means	0.017 9	1.932 5
本文方法	0.014 3	1.520 8

基于GAWK-means的地铁车站指纹定位方法

Fingerprint Location Method of Metro Station Based on GAWK-means

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	邵志慧,杨俭,袁天辰,伍伟嘉. 基于排列熵和支持向量机的轨枕病害诊断[J]. 电子科技, 2022, 35(2): 52-58.
[2]	修晓波,李伯全,周峰. 基于遗传算法的温度传感器布置优化[J]. 电子科技, 2021, 34(9): 17-23.
[3]	王阳,王亚刚. 基于阶跃响应和遗传算法优化高阶加时滞模型的辨识方法[J]. 电子科技, 2021, 34(9): 41-46.
[4]	丁家会,张兆军. 基于个体排序的自适应遗传算法[J]. 电子科技, 2020, 33(3): 6-11.
[5]	杨振宇,傅迎华,付东翔,王雅静. 多算法融合的眼底图像渗出液分割[J]. 电子科技, 2020, 33(11): 24-30.
[6]	孙铭阳,谢子殿,韩龙,毕思达. 自适应阈值函数小波算法的电机振动信号去噪[J]. 电子科技, 2020, 33(1): 63-67.
[7]	陈昊,沈景凤,赵程. 无人机在抢险救灾中的优化应用[J]. 电子科技, 2019, 32(9): 20-25.
[8]	章裕润,吴飞,毛万葵. 基于WiFi-GM指纹的室内定位算法[J]. 电子科技, 2019, 32(5): 49-54.
[9]	陈强,刘瑾,杨海马,刘海珊,韦钰. 基于改进遗传算法的配电网无功优化研究[J]. 电子科技, 2019, 32(5): 11-16.
[10]	朱望纯,程浩,高海英. 自适应谱减声发射消噪及轴承故障诊断[J]. 电子科技, 2019, 32(4): 16-20.
[11]	李存进,孙红. 改进自适应遗传算法在关联规则中的研究[J]. 电子科技, 2019, 32(12): 58-63.
[12]	吴延凯,张伟,马盈满,李佳阳. 基于GA-PSO融合算法的二自由度PID参数优化[J]. 电子科技, 2019, 32(10): 54-59.
[13]	赵曙光，崔平，罗霄，李智伟. 基于NCV门库的可逆逻辑门进化设计与优化[J]. , 2017, 30(9): 1-.
[14]	胡晓锐，骆艳洁，麦云飞. 遗传算法在恒张力控制系统中的应用[J]. , 2017, 30(4): 72-.
[15]	金焱飞，张会林，张松，史超然，李荣伟. 基于GABPNN的MPPT控制方法与P&O的比较[J]. , 2016, 29(8): 145-.