[01] Yonghao Zhao, School of Computer Science and Technology, Nanjing University of Technology, Nanjing, China; School of Information Engineering, Yancheng Teachers University, Yancheng, China.

With the development of information technology, the basic improvement of network infrastructure and the rapid development of mobile network, the development direction of the world economy and people's thinking and way of life have undergone tremendous changes due to the rapid development of wireless technology. Nowadays, people's demand for location services is increasing. Compared with outdoor GPS navigation systems, indoor positioning technology still has a long way to go. Indoor positioning is a hot issue in navigation technology. In recent years, many indoor positioning technologies have been proposed. And location fingerprint positioning is a commonly used technology. Among them, the positioning algorithm using KNN is the most classic positioning method. Due to the complexity of the environment, the concept of weight is introduced on the basis of the KNN algorithm, which alleviates the impact of different environments to a certain extent. This paper proposes a new and improved algorithm based on the KNN algorithm. In order to fully consider the complexity of the environment, the fingerprint data is preprocessed to eliminate the interference of abnormal signal values firstly, and then a new weight method is introduced to weight the KNN algorithm. The experimental results show that this method can further improve the positioning accuracy.

Indoor Positioning, Location Fingerprint, KNN Algorithm, Improved Weighting

[01] Motte H, Wyffels J, Strycker L D, et al. Evaluating GPS Data in Indoor Environments [J]. Advances in Electrical and Computer Engineering, 2011, 11 (3): 25-28. [02] Xiaoming L, Xinglong T, Changsheng Z. PSO-LSSVR Assisted GPS/INS Positioning in Occlusion Region [J]. Sensors (Basel, Switzerland), 2019, 19 (23). [03] W. Sakpere, M. Adeyeye Oshin and N. B. Mlitwa, "A State-of-the-Art Survey of Indoor Positioning and Navigation Systems and Technologies", South African Comput. J., vol. 29, no. 3, pp. 145197, 2017. [04] Zafari F, Gkelias A, Leung K K. A Survey of Indoor Localization Systems and Technologies [J]. Communications Surveys & Tutorials, IEEE, 2019. [05] Evolution of Indoor Positioning Technologies: A Survey [J]. Journal of Sensors, 2017. [06] M. A. Al-Ammar et al., “Comparative survey of indoor positioning technologies, techniques, and algorithms,” in Proc. Int. Conf. Cyberworlds (CW), Santander, Spain, Oct. 2014, pp. 245–252. [07] Q. D. Vo and P. De, “A survey of fingerprint-based outdoor localization,” IEEE Commun. Surveys Tuts., vol. 18, no. 1, pp. 491–506, 1st Quart., 2016. [08] F. Ijaz, H. K. Yang, A. W. Ahmad, and C. Lee, “Indoor positioning: A review of indoor ultrasonic positioning systems,” in Proc. IEEE 15th Int. Conf. Adv. Commun. Technol. (ICACT), Rajampet, India, 2013, pp. 1146–1150. [09] Niculescu, D. Positioning in ad hoc sensor networks [J]. Network IEEE, 2004, 18 (4): 24-29. [10] Ma Y, Wang B, Pei S, et al. An Indoor Localization Method Based on AOA and PDOA Using Virtual Stations in Multipath and NLOS Environments for Passive UHF RFID [J]. IEEE Access, 2018: 1-1. [11] Shu Y, Huang Y, Zhang J, et al. Gradient-Based Fingerprinting for Indoor Localization and Tracking [J]. IEEE Transactions on Industrial Electronics, 2016, 63 (4): 2424-2433. [12] Janicka J, Rapinski J. Application of RSSI Based Navigation in Indoor Positioning [J]. 2016: 45-50. [13] Guan W G, Deng Z L, Ge Y T, et al. A Location Fingerprinting Algorithm Based on RSSI Statistic Parameters Matching Estimate [J]. Key Engineering Materials, 2011, 480-481: 1179-1184. [14] Mundo L B D, Ansay R L D, Festin C A M, et al. A comparison of Wireless Fidelity (Wi-Fi) fingerprinting techniques [C]// International Conference on Ict Convergence. IEEE, 2011. [15] Weixing X, Xianghong H, Qingquan L, et al. A New Weighted Algorithm Based on the Uneven Spatial Resolution of RSSI for Indoor Localization [J]. IEEE Access, 2018, 6: 26588-26595.