基于MWKNN-PF的两阶段室内蓝牙定位方法

doi:10.13229/j.cnki.jdxbgxb.20240931

摘要/Abstract

摘要：

针对蓝牙行人定位中加权K近邻（WKNN）算法存在指纹匹配计算负荷大、定位精度受固定K值影响等问题，提出了一种改进的WKNN（Modified WKNN，MWKNN）算法，用于目标的初始定位。为进一步提高定位精度，又引入粒子滤波算法，将MWKNN算法的初始定位结果作为观测值对粒子进行更新，最终实现目标位置的精确估计。实验结果表明，所提出的MWKNN-PF算法与WKNN算法相比，定位精度提高了41.8%，计算时间减少59.6%，所提算法可为相关应用场景提供更精确、实时的室内行人定位服务。

关键词: 室内定位, 蓝牙指纹, K均值聚类, 加权K近邻, 粒子滤波

Abstract:

To address the issues of the high computational load for fingerprint matching and the dependence of positioning accuracy on the fixed K valuein the weighted K-nearest neighbor （WKNN） algorithm for bluetooth pedestrian localization， a modified WKNN （MWKNN） algorithm is proposed for the initial localization of the target. To further enhance positioning accuracy， a particle filtering algorithm is introduced， using the initial localization resultsfrom the MWKNN algorithm as measurement values to update the particles，and ultimately achieves precise target localization. Experimental results indicate that the proposed MWKNN-PF algorithm improves positioning accuracy by 41.8% and reduces computation time by 59.6%. This algorithm provides more accurate and real-time indoor pedestrian localization for related applications.

Key words: indoor localization, bluetooth fingerprint, K-means clustering, weighted K-nearest neighbor, particle filtering

中图分类号:

TP393

周宁,雷少刚,赵东升,吴敦. 基于MWKNN-PF的两阶段室内蓝牙定位方法[J]. 吉林大学学报(工学版), 2026, 56(3): 860-868.

Ning ZHOU,Shao-gang LEI,Dong-sheng ZHAO,Dun WU. Two⁃stage indoor bluetooth localization method based on MWKNN⁃PF[J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(3): 860-868.

图/表 6

图1

图2

图3

表1

图4

图5

参考文献 13

[1]	沈天盛, 陈文莹, 朱彬斌, 等. 基于改进WKNN的蓝牙室内定位方法[J]. 现代电子技术, 2023, 46(10): 11-16.
	Shen Tian-sheng, Chen Wen-ying, Zhu Bin-bin, et al. Method of bluetooth indoor positioning based on improved WKNN[J]. Modern Electronics Technique, 2023, 46(10): 11-16.
[2]	孙大洋, 王雪莹, 韩双雪, 等. 虚拟锚点高维坐标的非视距识别及定位优化[J]. 吉林大学学报:工学版, 2021, 51(6): 2207-2215.
	Sun Da-yang, Wang Xue-ying, Han Shuang-xue, et al. Non⁃line⁃of⁃sight identification and optimization based on virtual coordinates of anchors[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2207-2215.
[3]	杨海峰, 张勇波, 黄裕梁, 等. 基于空间特征分区和前点约束的WKNN室内定位方法[J]. 软件学报, 2019, 30(11): 3427-3439.
	Yang Hai-feng, Zhang Yong-bo, Huang Yu-liang, et al. WKNN indoor positioning algorithm based on spatial characteristics partition and former location restriction[J]. Journal of Software, 2019, 30(11): 3427-3439.
[4]	Li X, Dai Z, He L. A K-nearest neighbor indoor fingerprint location method based on coarse positioning circular domain and the highest similarity threshold[J]. Measurement Science and Technology, 2022, 34(1): 015108.
[5]	Chen B, Ma J, Zhang L, et al. An improved weighted KNN fingerprint positioning algorithm[J]. Wireless Networks, 2024, 30: 6011-6022.
[6]	王轩, 陈国良, 曹晓祥, 等. 自适应K值及指纹库扩充的WLAN室内定位方法[J]. 测绘科学, 2020, 45(7): 26-32.
	Wang Xuan, Chen Guo-liang, Cao Xiao-xiang, et al. Research on WLAN indoor positioning method based on adaptive K value fingerprint database expansion[J]. Science of Surveying and Mapping, 2020, 45(7): 26-32.
[7]	梁哲豪, 石磊, 唐杰, 等. 室内可见光指纹定位系统中改进的加权K最近邻算法[J]. 激光与光电子学进展, 2022, 59(17):123-127.
	Liang Zhe-hao, Shi Lei, Tang Jie, et al. Improved weighted K nearest neighbor algorithm for indoor visible light fingerprint positioning system[J]. Laser & Optoelectronics Progress, 2022, 59(17): 123-127.
[8]	顾亚雄, 钟文. 混合滤波与改进贝叶斯相融合的室内可见光指纹定位方法[J]. 测绘通报, 2023(6): 104-109, 128.
	Gu Ya-xiong, Zhong Wen. Indoor visible light fingerprint location method based on GF-KF and improved-Bayes[J]. Bulletin of Surveying and Mapping, 2023(6): 104-109, 128.
[9]	Yang X, Wu Z, Zhang Q. Bluetooth indoor localization with Gaussian-Bernoulli restricted boltzmann machine plus liquid state machine[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1000208.
[10]	Philips D, Salami E, Ramiah H, et al. Location accuracy optimization in bluetooth low energy (BLE) 5.1-based indoor positioning system (IPS)—a machine learning approach[J]. IEEE Access, 2023, 11: 140186-140201.
[11]	Liu Y, Wu C, Kong X, et al. A tightly-coupled method for indoor vehicle navigation based on smartphone IMU and BLE[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 8509612.
[12]	Xia H, Zuo J, Liu S, et al. Indoor localization on smartphones using built-in sensors and map constraints[J].IEEE Transactions on Instrumentation and Measurement, 2019, 68(4): 1189-1198.
[13]	Zhang J, Yu B, Ge Y, et al. An effective GNSS/PDR fusion positioning algorithm on smartphones for challenging scenarios[J]. Sensors, 2024, 24:1452.

相关文章 15

[1]	邵小强,马博,韩泽辉,杨永德,原泽文,李鑫. 基于改进WKNN的CSI被动室内指纹定位方法[J]. 吉林大学学报(工学版), 2025, 55(7): 2444-2454.
[2]	樊学平,刘月飞. 基于改进高斯混合粒子滤波新算法的桥梁极值应力动态预测[J]. 吉林大学学报(工学版), 2024, 54(4): 1038-1044.
[3]	易晓宇,易绵竹. 基于兴趣信息深度融合的网络图书资源推荐[J]. 吉林大学学报(工学版), 2024, 54(12): 3614-3619.
[4]	王宁,刘繁明. 基于约束优化的自适应衰减记忆平方根混合阶容积粒子滤波在惯性/卫星组合导航中的应用[J]. 吉林大学学报(工学版), 2024, 54(12): 3660-3672.
[5]	孙大洋,王雪莹,韩双雪,钟辉,戴江南. 虚拟锚点高维坐标的非视距识别及定位优化[J]. 吉林大学学报(工学版), 2021, 51(6): 2207-2215.
[6]	金静,党建武,王阳萍,申东. 融合模糊统计纹理特征的多线索粒子滤波跟踪[J]. 吉林大学学报(工学版), 2021, 51(3): 1111-1120.
[7]	樊学平,屈广,刘月飞. 应用新数据同化算法的桥梁极值应力预测[J]. 吉林大学学报(工学版), 2020, 50(2): 572-580.
[8]	刘富, 权美静, 王柯, 刘云, 康冰, 韩志武, 侯涛. 仿蝎子振源定位机理的位置指纹室内定位方法[J]. 吉林大学学报(工学版), 2019, 49(6): 2076-2082.
[9]	杨超宇, 李策, 梁胤程, 杨峰. 基于改进粒子滤波的煤矿视频监控模糊目标检测[J]. 吉林大学学报(工学版), 2017, 47(6): 1976-1985.
[10]	李娟，刘晓龙，卢长刚，左英泽. 改进的粒子滤波重采样算法[J]. 吉林大学学报(工学版), 2015, 45(6): 2069-2074.
[11]	武勇, 王俊, 曹运合, 张培川. 基于二次预测的粒子滤波算法[J]. 吉林大学学报(工学版), 2015, 45(5): 1696-1701.
[12]	杨欣，刘加，周鹏宇，周大可. 基于多特征融合的粒子滤波自适应目标跟踪算法[J]. 吉林大学学报(工学版), 2015, 45(2): 533-539.
[13]	孔云波, 冯新喜, 鹿传国, 刘振涛. 基于Sigma点H_∞滤波的拟蒙特卡罗粒子滤波算法[J]. 吉林大学学报(工学版), 2014, 44(6): 1831-1837.
[14]	曹洁, 戴彬, 李晓旭. 基于高斯Sigma点选取的改进UPF算法[J]. 吉林大学学报(工学版), 2014, 44(5): 1435-1440.
[15]	卞亚涛, 赵旭, 宋健, 刘允才. 并行化退火粒子滤波[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 239-243.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

定位精度	WKNN	MWKNN	MWKNN-PF	文献［1］算法
均方根误差/m	1.665	1.291	0.969	1.109
最大误差/m	2.985	2.662	2.006	2.295
最小误差/m	0.272	0.113	0.097	0.034
时间/s	1.238	0.436	0.502	1.326