A New Weighted Indoor Positioning Algorithm Based On the Physical Distance and Clustering

The weighted K-nearest neighbor (WKNN) algorithm is one of the most frequently used algorithms for indoor positioning. However, the traditional WKNN algorithm select the k points only based on their received signal strength (RSS), and the algorithm weights the reference points’ coordinates by the RSS, which is not accurate enough because of the exponential relationship between RSS and physical distance. Therefore, in order to improve the positioning accuracy of the traditional location algorithm, this paper proposes a new algorithm based on clustering and the physical distance of the RSS. Experiments were conducted in an office building and results demonstrate that the proposed algorithm is better than a series of indoor positioning algorithm. This proposed algorithm is based on the WKNN algorithm and the Kmeans algorithm.

[1]  Junsong Li,et al.  A Single-NN Iterative Adaptive Dynamic Programming Algorithm for Continuous-Time Nonlinear Zero-Sum Games , 2018, 2018 37th Chinese Control Conference (CCC).

[2]  Stavros Stavrou,et al.  RSS Based Localization Using a New WKNN Approach , 2015, 2015 7th International Conference on Computational Intelligence, Communication Systems and Networks.

[3]  Hsin-Piao Lin,et al.  A modified WKNN indoor Wi-Fi localization method with differential coordinates , 2017, 2017 International Conference on Applied System Innovation (ICASI).

[4]  Bo Dong,et al.  WiFi indoor localization based on K-means , 2016, 2016 International Conference on Audio, Language and Image Processing (ICALIP).

[5]  Pengfei Wang,et al.  Research on WiFi Indoor Location Algorithm Based on RSSI Ranging , 2017, 2017 4th International Conference on Information Science and Control Engineering (ICISCE).

[6]  Nadir Hakem,et al.  Path loss exponent estimation using connectivity information in wireless sensor network , 2016, 2016 IEEE International Symposium on Antennas and Propagation (APSURSI).

[7]  Qian Shi,et al.  A clustering-Based KNN improved algorithm CLKNN for text classification , 2010, 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010).

[8]  Chin-Der Wann,et al.  Hybrid TDOA/AOA Indoor Positioning and Tracking Using Extended Kalman Filters , 2006, 2006 IEEE 63rd Vehicular Technology Conference.

[9]  Abdul Halim Ali,et al.  Investigation of indoor WIFI radio signal propagation , 2010, 2010 IEEE Symposium on Industrial Electronics and Applications (ISIEA).

[10]  Xiaofeng Zhu,et al.  Efficient kNN Classification With Different Numbers of Nearest Neighbors , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Lei Shu,et al.  ZIL: An Energy-Efficient Indoor Localization System Using ZigBee Radio to Detect WiFi Fingerprints , 2015, IEEE Journal on Selected Areas in Communications.

[12]  Xinhong Hei,et al.  An improved integrated fingerprint location algorithm based on WKNN , 2017, 2017 29th Chinese Control And Decision Conference (CCDC).

[13]  Rose Qingyang Hu,et al.  Crowdsourcing and Multisource Fusion-Based Fingerprint Sensing in Smartphone Localization , 2018, IEEE Sensors Journal.

[14]  Ye Tao,et al.  A Novel System for WiFi Radio Map Automatic Adaptation and Indoor Positioning , 2018, IEEE Transactions on Vehicular Technology.

[15]  Mingyan Liu,et al.  Mitigating Large Errors in WiFi-Based Indoor Localization for Smartphones , 2017, IEEE Transactions on Vehicular Technology.