Similar articles

Abstract: High-precision indoor positioning offers valuable information support for various services such as patient monitoring, equipment scheduling management, and laboratory safety. A traditional indoor positioning technology, fingerprint indoor positioning, often employs the K-nearest neighbor (KNN) algorithm to identify the closest K reference points (RPs) via the received signal strength (RSS) for location prediction. However, RSS is susceptible to environmental interference, leading to the selection of RPs that are not physically the closest to the user. Moreover, using a fixed K value is not the optimal strategy. In this work, we propose a novel approach, the dynamic K-nearest neighbor method based on strong access point (AP) credibility (SAPC-DKNN), for indoor positioning. In SAPC-DKNN, we leverage prior knowledge of RSS path loss and employ the RSS fluctuation area to quantify the significance of different APs. We integrate the similarity of AP sets within the range of strong APs and formulate a weighted distance metric for RSS based on the credibility of strong APs. Additionally, we introduce a dynamic K-value algorithm based on neighbor density (ND-DKA) for the automatic optimization of the K value for each test point. Experimental evaluations conducted on three datasets demonstrate that our method significantly reduces the average positioning error by 15.41%–64.74% compared to the state-of-the-art KNN methods.

基于强接入点可信度的动态K近邻室内定位方法

[1]Alitaleshi A, Jazayeriy H, Kazemitabar J, 2023. EA-CNN: a smart indoor 3D positioning scheme based on WiFi fingerprinting and deep learning. Eng Appl Artif Intell, 117: 105509.

[2]Arslantas H, Okdem S, 2024. Indoor localization with an autoencoder-based convolutional neural network. IEEE Access, (12):46059-46066.

[3]Ayinla SL, Aziz AA, Drieberg M, 2024. SALLoc: an accurate target localization in WiFi-enabled indoor environments via SAE-ALSTM. IEEE Access, 12:19694-19710.

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

[5]Bi JX, Wang YJ, Yu BG, et al., 2022. Supplementary open dataset for WiFi indoor localization based on received signal strength. Satell Navig, 3(1):25.

[6]Brunato M, Battiti R, 2005. Statistical learning theory for location fingerprinting in wireless LANs. Comput Netw, 47(6):825-845.

[7]Cha J, Lim E, 2022. A hierarchical auxiliary deep neural network architecture for large-scale indoor localization based on WiFi fingerprinting. Appl Soft Comput, 120: 108624.

[8]Chen GK, Guo XY, Liu K, et al., 2022. RWKNN: a modified WKNN algorithm specific for the indoor localization problem. IEEE Sens J, 22(7):7258-7266.

[9]Chon HD, Jun S, Jung H, et al., 2004. Using RFID for accurate positioning. J Glob Posit Syst, 3(1):32-39.

[10]Ciurana M, Cugno S, Barcelo-Arroyo F, 2007. WLAN indoor positioning based on TOA with two reference points. Proc 4^th Workshop on Positioning, Navigation and Communication, p.23-28.

[11]Costa JA, Patwari N, Hero AOIII, 2006. Distributed weighted-multidimensional scaling for node localization in sensor networks. ACM Trans Sens Netw, 2(1):39-64.

[12]Dag T, Arsan T, 2018. Received signal strength based least squares lateration algorithm for indoor localization. Comput Electr Eng, 66:114-126.

[13]Dong YH, Arslan T, Yang YJ, 2022. An encoded LSTM network model for WiFi-based indoor positioning. Proc IEEE 12^th Int Conf on Indoor Positioning and Indoor Navigation, p.1-6.

[14]Dong ZY, Xu WM, Zhuang H, 2019. Research on ZigBee indoor technology positioning based on RSSI. Proc Comput Sci, 154:424-429.

[15]Gu YY, Lo A, Niemegeers I, 2009. A survey of indoor positioning systems for wireless personal networks. IEEE Commun Surv Tut, 11(1):13-32.

[16]He SN, Chan SHG, 2016. WiFi fingerprint-based indoor positioning: recent advances and comparisons. IEEE Commun Surv Tut, 18(1):466-490.

[17]Hegarty CJ, Chatre E, 2008. Evolution of the Global Navigation Satellite System (GNSS). Proc IEEE, 96(12):1902-1917.

[18]Hoang MT, Zhu YZ, Yuen B, et al., 2018. A soft range limited K-nearest neighbor algorithm for indoor localization enhancement. IEEE Sens J, 18(24):10208-10216.

[19]Hu JS, Liu HL, Liu DW, 2018. Toward a dynamic K in K-nearest neighbor fingerprint indoor positioning. Proc IEEE Int Conf on Information Reuse and Integration, p.308-314.

[20]Hu JS, Liu Dw, Yan Z, et al., 2019. Experimental analysis on weight K-nearest neighbor indoor fingerprint positioning. IEEE Int Things J, 6(1):891-897.

[21]Hu XK, Shang JG, Gu FQ, et al., 2015. Improving WiFi indoor positioning via AP sets similarity and semi-supervised affinity propagation clustering. Int J Distrib Sens Netw, 11: 109642.

[22]Jin RC, Xu H, Che ZP, et al., 2015. Experimental evaluation of reducing ranging-error based on receive signal strength indication in wireless sensor networks. IET Wirel Sens Syst, 5(5):228-234.

[23]Latif E, Parasuraman R, 2022. Online indoor localization using DOA of wireless signals. https://arxiv.org/abs/2201.05105

[24]Le YF, Zhang HN, Shi WB, et al., 2021. Received signal strength based indoor positioning algorithm using advanced clustering and kernel ridge regression. Front Inform Technol Electron Eng, 22(6):827-838.

[25]Lee I, Kwak M, Han D, 2016. A dynamic K-nearest neighbor method for WLAN-based positioning systems. J Comput Inform Syst, 56(4):295-300.

[26]Li D, Zhang BX, Li C, 2015. A feature-scaling-based K-nearest neighbor algorithm for indoor positioning systems. IEEE Int Things J, 3(4):590-597.

[27]Lin H, Purmehdi H, Fei XN, et al., 2023. Two-stage clustering for improve indoor positioning accuracy. Autom Constr, 154: 104981.

[28]Liu H, Darabi H, Banerjee P, et al., 2007. Survey of wireless indoor positioning techniques and systems. IEEE Trans Syst Man Cybern Part C (Appl Rev), 37(6):1067-1080.

[29]Liu S, Jiang YX, Striegel A, 2014. Face-to-face proximity estimation using Bluetooth on smartphones. IEEE Trans Mob Comput, 13(4):811-823.

[30]Liu SY, de Lacerda R, Fiorina J, 2022. Performance analysis of adaptive K for weighted K-nearest neighbor based indoor positioning. Proc IEEE 95^th Vehicular Technology Conf, p.1-5.

[31]Lohan ES, Torres-Sospedra J, Richter P, et al., 2017. Crowdsourced WiFi database and benchmark software for indoor positioning. Zenodo Repository.

[32]Ma J, Li XS, Tao XP, et al., 2008. Cluster filtered KNN: a WLAN-based indoor positioning scheme. Proc Int Symp on a World of Wireless, Mobile and Multimedia Networks, p.1-8.

[33]Ma R, Guo Q, Hu CZ, et al., 2015. An improved WiFi indoor positioning algorithm by weighted fusion. Sensors, 15(9):21824-21843.

[34]Madigan D, Einahrawy E, Martin RP, et al., 2005. Bayesian indoor positioning systems. Proc IEEE 24^th Annual Joint Conf of the IEEE Computer and Communications Societies, p.1217-1227.

[35]Nabati M, Ghorashi SA, 2023. A real-time fingerprint-based indoor positioning using deep learning and preceding states. Expert Syst Appl, 213: 118889.

[36]Nguyen SM, Le DV, Havinga PJM, 2023. Learning the world from its words: anchor-agnostic Transformers for fingerprint-based indoor localization. Proc IEEE Int Conf on Pervasive Computing and Communications, p.150-159.

[37]Nguyen SM, Le DV, Havinga PJM, 2024. Seeing the world from its words: all-embracing Transformers for fingerprint-based indoor localization. Perv Mob Comput, 100: 101912.

[38]Ni LM, Liu YH, Lau YC, et al., 2003. LANDMARC: indoor location sensing using active RFID. Proc 1^st IEEE Int Conf on Pervasive Computing and Communication, p.407-415.

[39]Oh J, Kim J, 2018. Adaptive K-nearest neighbour algorithm for WiFi fingerprint positioning. ICT Expr, 4(2):91-94.

[40]Peng YR, Fan WT, Dong X, et al., 2016. An iterative weighted KNN (IW-KNN) based indoor localization method in Bluetooth low energy (BLE) environment. Proc Int IEEE Conf on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress, p.794-800.

[41]Pu YC, You PC, 2018. Indoor positioning system based on BLE location fingerprinting with classification approach. Appl Math Modell, 62:654-663.

[42]Ren QQ, Wang Y, Liu SN, et al., 2023. FSTNet: learning spatial–temporal correlations from fingerprints for indoor positioning. Ad Hoc Netw, 149: 103244.

[43]Rusli ME, Ali M, Jamil N, et al., 2016. An improved indoor positioning algorithm based on RSSI-trilateration technique for Internet of Things (IoT). Proc Int Conf on Computer and Communication Engineering, p.72-77.

[44]Sadowski S, Spachos P, Plataniotis KN, 2020. Memoryless techniques and wireless technologies for indoor localization with the Internet of Things. IEEE Int Things J, 7(11):10996-11005.

[45]Salamah AH, Tamazin M, Sharkas MA, et al., 2016. An enhanced WiFi indoor localization system based on machine learning. Proc Int Conf on Indoor Positioning and Indoor Navigation, p.1-8.

[46]Song XD, Fan XC, Xiang CC, et al., 2019. A novel convolutional neural network based indoor localization framework with WiFi fingerprinting. IEEE Access, 7:110698-110709.

[47]Torres-Sospedra J, Montoliu R, Martónez-Usó A, et al., 2014. UJIIndoorLoc: a new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems. Proc Int Conf on Indoor Positioning and Indoor Navigation, p.261-270.

[48]Torres-Sospedra J, Montoliu R, Trilles S, et al., 2015. Comprehensive analysis of distance and similarity measures for WiFi fingerprinting indoor positioning systems. Expert Syst Appl, 42(23):9263-9278.

[49]Torres-Sospedra J, Montoliu R, Mendoza-Silva GM, et al., 2016. Providing databases for different indoor positioning technologies: pros and cons of magnetic field and WiFi based positioning. Mob Inform Syst, 2016(1): 6092618.

[50]Umair MY, Ramana KV, Yang DK, 2014. An enhanced K-nearest neighbor algorithm for indoor positioning systems in a WLAN. Proc IEEE Computers, Communications and IT Applications Conf, p.19-23.

[51]Wu D, Xu YB, Ma L, 2009. Research on RSS based indoor location method. Proc Pacific-Asia Conf on Knowledge Engineering and Software Engineering, p.205-208.

[52]Xia MZ, Chen JB, Song CL, et al., 2015. The indoor positioning algorithm research based on improved location fingerprinting. Proc 27^th Chinese Control and Decision Conf, p.5736-5739.

[53]Xie YQ, Wang Y, Nallanathan A, et al., 2016. An improved K-nearest-neighbor indoor localization method based on Spearman distance. IEEE Signal Process Lett, 23(3):351-355.

[54]Yang CC, Shao HR, 2015. WiFi-based indoor positioning. IEEE Commun Mag, 53(3):150-157.

[55]Yu XJ, Li QQ, Queralta JP, et al., 2021. Applications of UWB networks and positioning to autonomous robots and industrial systems. Proc 10^th Mediterranean Conf on Embedded Computing, p.1-6.

[56]Zhang H, Wang ZK, Xia WC, et al., 2022. Weighted adaptive KNN algorithm with historical information fusion for fingerprint positioning. IEEE Wirel Commun Lett, 11(5):1002-1006.

[57]Zhang J, Mao HQ, 2022. WKNN indoor positioning method based on spatial feature partition and basketball motion capture. Alexandr Eng J, 61(1):125-134.

[58]Zhao YM, Gong W, Li L, et al., 2024. An efficient and robust fingerprint based localization method for multifloor indoor environment. IEEE Int Things J, 11(3):3927-3941.

[59]Zou H, Jin M, Jiang H, et al., 2017. WinIPS: WiFi-based non-intrusive indoor positioning system with online radio map construction and adaptation. IEEE Trans Wirel Commun, 16(12):8118-8130.