Towards the Implementation of Recurrent Neural Network Schemes for WiFi Fingerprint-Based Indoor Positioning

The rapid development of Indoor Positioning System has attracted researcher to develop a robust scheme to predict the location based on Received Signal Strength Indicator (RSSI) signal. A lot of research topics presented in many journals and conferences by many researchers concern indoor positioning system as a main topic [1], [2]. Currently, the study related to find the robust algorithm for indoor positioning system becomes a high demand topic in several conferences. Our work intents to evaluate the effectiveness of Recurrent Neural Network (RNN) as a deep learning technique to be implemented in this field. In addition, LSTM as a variant of RNN scheme is also implemented. The purpose of this implementation is to explore both LSTM and original RNN to be utilized for localization in indoor positioning scheme, especially for Wifi Fingerprinting Dataset. From all evaluations, our proposed approach could get 99.7% accuracy for predicting which floor the sensor belongs to. In addition, the distance errors of our scheme are around 2.5–2.7 meters.

[1]  Lin Ma,et al.  KNN-FCM hybrid algorithm for indoor location in WLAN , 2009, 2009 2nd International Conference on Power Electronics and Intelligent Transportation System (PEITS).

[2]  Daniel Cremers,et al.  Image-Based Localization Using LSTMs for Structured Feature Correlation , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[4]  Shueng-Han Gary Chan,et al.  Wi-Fi Fingerprint-Based Indoor Positioning: Recent Advances and Comparisons , 2016, IEEE Communications Surveys & Tutorials.

[5]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[6]  Shiwen Mao,et al.  CSI-Based Fingerprinting for Indoor Localization: A Deep Learning Approach , 2016, IEEE Transactions on Vehicular Technology.

[7]  Ye Tian,et al.  A weighted least-squares method using received signal strength measurements for WLAN indoor positioning system , 2017, 2017 20th International Symposium on Wireless Personal Multimedia Communications (WPMC).

[8]  Qiang Li,et al.  Indoor Pedestrian Trajectory Detection with LSTM Network , 2017, 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC).

[9]  Lu Huang,et al.  Deep learning for weights training and indoor positioning using multi-sensor fingerprint , 2017, 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[10]  Elena Simona Lohan,et al.  Long-Term WiFi Fingerprinting Dataset for Research on Robust Indoor Positioning , 2018, Data.

[11]  Lynn Choi,et al.  Geomagnetic Field Based Indoor Localization Using Recurrent Neural Networks , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.