Indoor localization at 5GHz using Dynamic machine learning approach (DMLA)

In recent years, Wi-Fi based indoor localization using received signal strength (RSS) gets considerable attention. However, RSS based Wi-Fi localization at 2.4GHz is highly susceptible and unstable. We proposed dynamic machine learning approach (DMLA) at 5GHz to effectively localize Wi-Fi users by means of feed-forward neural network algorithm. The simulation result shows that 90% of tested result has less than 0.4m estimation error, and no result shows greater than 0.47m location estimation errors.

[1]  Serkan Günal,et al.  A comparative study on machine learning algorithms for indoor positioning , 2015, 2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA).

[2]  Bernard K.-S. Cheung,et al.  An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning , 2013, ISPRS Int. J. Geo Inf..

[3]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[4]  Wang-Chien Lee,et al.  Rule-Based WiFi Localization Methods , 2008, 2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing.

[5]  Ding-Bing Lin,et al.  Indoor Human Localization System Based on RF and PIR Sensors , 2014 .

[6]  K. J. Ray Liu,et al.  Achieving Centimeter-Accuracy Indoor Localization on WiFi Platforms: A Frequency Hopping Approach , 2016, IEEE Internet of Things Journal.

[7]  Hao Jiang,et al.  An online sequential extreme learning machine approach to WiFi based indoor positioning , 2014, 2014 IEEE World Forum on Internet of Things (WF-IoT).

[8]  Mu Zhou,et al.  Fingerprint indoor positioning algorithm based on affinity propagation clustering , 2013, EURASIP Journal on Wireless Communications and Networking.

[9]  Xiao Qin,et al.  Expansion RSS-based Indoor Localization Using 5G WiFi Signal , 2014, 2014 International Conference on Computational Intelligence and Communication Networks.

[10]  Ding-Bing Lin,et al.  Hybrid Indoor Human Localization System for Addressing the Issue of RSS Variation in Fingerprinting , 2015, Int. J. Distributed Sens. Networks.

[11]  Rongke Liu,et al.  Wi-Fi-Based Localization in Dynamic Indoor Environment Using a Dynamic Neural Network , 2013 .

[12]  Nadeem Akhtar,et al.  LTE - Wi-Fi coexistence in 5 GHz band , 2015, 2015 IEEE International Conference on Advanced Networks and Telecommuncations Systems (ANTS).