JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering 2021 Vol.22 No.6 P.827-838

http://doi.org/10.1631/FITEE.2000093

Received signal strength based indoor positioning algorithm using advanced clustering and kernel ridge regression

Author(s): Yanfen Le, Hena Zhang, Weibin Shi, Heng Yao
Affiliation(s): School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
Corresponding email(s): leyanfen@usst.edu.cn, hyao@usst.edu.cn
Key Words: Indoor positioning, Received signal strength (RSS) fingerprint, Kernel ridge regression, Cluster matching, Advanced clustering

Share this article to： More <<< Previous Article \|Next Article >>>

Abstract: We propose a novel indoor positioning algorithm based on the received signal strength (RSS) fingerprint. The proposed algorithm can be divided into three steps, an offline phase at which an advanced clustering (AC) strategy is used, an online phase of approximate localization at which cluster matching is used, and an online phase of precise localization with kernel ridge regression. Specifically, after offline fingerprint collection and similarity measurement, we employ an AC strategy based on the K-medoids clustering algorithm using additional reference points that are geographically located at the outer cluster boundary to enrich the data of each cluster. During the approximate localization, RSS measurements are compared with the cluster radio maps to determine to which cluster the target most likely belongs. Both the Euclidean distance of the RSSs and the Hamming distance of the coverage vectors between the observations and training records are explored for cluster matching. Then, a kernel-based ridge regression method is used to obtain the ultimate positioning of the target. The performance of the proposed algorithm is evaluated in two typical indoor environments, and compared with those of state-of-the-art algorithms. The experimental results demonstrate the effectiveness and advantages of the proposed algorithm in terms of positioning accuracy and complexity.

基于改进型分簇和核岭回归的RSS室内定位算法

乐燕芬，张贺娜，施伟斌，姚恒
上海理工大学光电信息与计算机工程学院，中国上海市，200093
摘要：智能移动设备和无线传感器网络相关技术的融合发展，使得基于位置的服务受到广泛关注。如何利用无线信号在室内复杂环境下实时获得理想的定位精度，成为当前研究热点之一。提出一种基于接收信号强度（RSS, received signal strength）的位置指纹定位算法。该算法分为离线和在线阶段。离线阶段采用一种改进的分簇方法，采用K中心点分簇算法，把物理位置位于簇外边缘的参考点加入簇指纹库，使得参考位置点的RSS信号特性与物理位置结合。在线定位时，基于簇匹配的粗定位与簇内二次精确定位结合。簇内定位采用基于核岭回归的算法，通过核函数实现RSS信号特性与物理位置非线性关系挖掘，同时算法在簇内成员中进行，减小了时间复杂度。通过两个典型室内环境下的定位实验，探究了基于RSS信号强度和覆盖向量的两种分簇和簇匹配准则对算法性能的影响，以及不同环境下参数的选择，验证了所提算法的定位性能。

关键词：室内定位；接收信号强度（RSS）指纹；核岭回归；簇匹配；改进型分簇

Reference

[1]Al-Moukhles H, Jaber AK, Abdel-Qader I, 2016. Impact of APs selection scheme on compressive sensing-fingerprinting based IPS performance. Proc IEEE 7^th Annual Ubiquitous Computing, Electronics & Mobile Communication Conf, p.1-7.

[2]Al Nuaimi K, Kamel H, 2011. A survey of indoor positioning systems and algorithms. Proc Int Conf on Innovations in Information Technology, p.185-190.

[3]Bahl P, Padmanabhan VN, 2000. RADAR: an in-building RF-based user location and tracking system. Proc IEEE Conf on Computer Communications and 19^th Annual Joint Conf of the IEEE Computer and Communications Societies, p.775-784.

[4]Chen C, Wang YJ, Zhang Y, et al., 2018. Indoor positioning algorithm based on nonlinear PLS integrated with RVM. IEEE Sens J, 18(2):660-668.

[5]Chen YQ, Yang Q, Yin J, et al., 2006. Power-efficient access-point selection for indoor location estimation. IEEE Trans Knowl Data Eng, 18(7):877-888.

[6]Dai H, Ying WH, Xu J, 2016. Multi-layer neural network for received signal strength-based indoor localisation. IET Commun, 10(6):717-723.

[7]Fang SH, Lin T, 2012. Principal component localization in indoor WLAN environments. IEEE Trans Mob Comput, 11(1):100-110.

[8]Fang XM, Jiang ZH, Nan L, et al., 2018. Optimal weighted K-nearest neighbour algorithm for wireless sensor network fingerprint localisation in noisy environment. IET Commun, 12(10):1171-1177.

[9]Feng C, Au WSA, Valaee S, et al., 2012. Received-signal-strength-based indoor positioning using compressive sensing. IEEE Trans Mob Comput, 11(12):1983-1993.

[10]Harroud H, Ahmed M, Karmouch A, 2003. Policy-driven personalized multimedia services for mobile users. IEEE Trans Mob Comput, 2(1):16-24.

[11]Honeine P, Mourad F, Kallas M, et al., 2011. Wireless sensor networks in biomedical: body area networks. Proc Int Workshop on Systems, Signal Processing and Their Applications, p.388-391.

[12]Hu JS, Liu HL, Liu DW, et al., 2018. Reducing Wi-Fi fingerprint collection based on affinity propagation clustering and WKNN interpolation algorithm. Proc 2^nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conf, p.2463-2468.

[13]Huang CC, Manh HN, 2016. RSS-based indoor positioning based on multi-dimensional kernel modeling and weighted average tracking. IEEE Sens J, 16(9):3231-3245.

[14]Khalajmehrabadi A, Gatsis N, Pack DJ, et al., 2017a. A joint indoor WLAN localization and outlier detection scheme using LASSO and elastic-net optimization techniques. IEEE Trans Mob Comput, 16(8):2079-2092.

[15]Khalajmehrabadi A, Gatsis N, Akopian D, 2017b. Structured group sparsity: a novel indoor WLAN localization, outlier detection, and radio map interpolation scheme. IEEE Trans Veh Technol, 66(7):6498-6510.

[16]Kumar C, Rajawat K, 2019. Dictionary-based statistical fingerprinting for indoor localization. IEEE Trans Veh Technol, 68(9):8827-8841.

[17]Kushki A, Plataniotis KN, Venetsanopoulos AN, et al., 2007. Kernel-based positioning in wireless local area networks. IEEE Trans Mob Comput, 6(6):689-705.

[18]Li LQ, He Z, Nielsen J, et al., 2015. Using Wi-Fi/magnetometers for indoor location and personal navigation. Proc Int Conf on Indoor Positioning and Indoor Navigation, p.1-7.

[19]Lu XX, Zou H, Zhou HM, et al., 2016. Robust extreme learning machine with its application to indoor positioning. IEEE Trans Cybern, 46(1):194-205.

[20]Maalouf M, Homouz D, 2014. Kernel ridge regression using truncated Newton method. Knowl-Based Syst, 71:339-344.

[21]Mahfouz S, Mourad-Chehade F, Honeine P, et al., 2013. Kernel-based localization using fingerprinting in wireless sensor networks. Proc IEEE 14^th Workshop on Signal Processing Advances in Wireless Communications, p.744-748.

[22]Mahfouz S, Mourad-Chehade F, Honeine P, et al., 2016. Non-parametric and semi-parametric RSSI/distance modeling for target tracking in wireless sensor networks. IEEE Sens J, 16(7):2115-2126.

[23]Niu JW, Wang BW, Shu L, et al., 2015. ZIL: an energy-efficient indoor localization system using ZigBee radio to detect WiFi fingerprints. IEEE J Sel Areas Commun, 33(7):1431-1442.

[24]Rodriguez MD, Favela J, Martinez EA, et al., 2004. Location-aware access to hospital information and services. IEEE Trans Inform Technol Biomed, 8(4):448-455.

[25]Saunders C, Gammerman A, Vovk V, 1998. Ridge regression learning algorithm in dual variables. Proc 15^th Int Conf on Machine Learning, p.515-521.

[26]Shi LF, Wang Y, Liu GX, et al., 2018. A fusion algorithm of indoor positioning based on PDR and RSS fingerprint. IEEE Sens J, 18(23):9691-9698.

[27]Wang XY, Gao LJ, Mao SW, et al., 2017. CSI-based fingerprinting for indoor localization: a deep learning approach. IEEE Trans Veh Technol, 66(1):763-776.

[28]Wu Z, Fu KC, Jedari E, et al., 2016. A fast and resource efficient method for indoor positioning using received signal strength. IEEE Trans Veh Technol, 65(12):9749-9758.

[29]Xue WX, Yu KG, Hua XH, et al., 2018. APs’ virtual positions-based reference point clustering and physical distance-based weighting for indoor Wi-Fi positioning. IEEE Intern Things J, 5(4):3031-3042.

[30]Yan J, Zhao L, Tang J, et al., 2018. Hybrid kernel based machine learning using received signal strength measurements for indoor localization. IEEE Trans Veh Technol, 67(3):2824-2829.

[31]Youssef MA, Agrawala A, Shankar AU, 2003. WLAN location determination via clustering and probability distributions. Proc 1^st IEEE Int Conf on Pervasive Computing and Communications, p.143-150.

[32]Zhang Y, Li DP, Wang YJ, 2019. An indoor passive positioning method using CSI fingerprint based on Adaboost. IEEE Sens J, 19(14):5792-5800.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Similar articles

- Go to

基于改进型分簇和核岭回归的RSS室内定位算法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference