Indoor localization through trajectory tracking using neural networks

Currently deployed wireless and cellular positioning techniques are optimized for outdoor operation and cannot provide highly accurate location information in indoor environments. Meanwhile, new applications and services for mobile devices, including the recent Enhanced 911 (E911), require accurate indoor location information up to the room/suite level. In this work, a new system for improving indoor localization of mobile users is presented by exploiting trajectory tracking techniques using neural networks (NNs). The motion trajectories of indoor mobile users are tracked using conventional positioning algorithms, then a NN is applied to identify the current room location of a mobile user based on the tracked motion trajectory. Simulation results show that the trajectory-based NN is able to provide indoor location information at the room level with much higher accuracy in different scenarios, with an enhancement of up to 49% in correct room identification, as compared to positioning techniques based only on a single-point location estimate. In addition, miss-classification of the NN system will result in selecting one of the immediate neighboring rooms instead with at least 30% probability.

[1]  Craig W. Reynolds.  Steering Behaviors For Autonomous Characters , 1999 .

[2]  Dimitrios Gunopulos,et al.  Crowdsourced Trace Similarity with Smartphones , 2013, IEEE Transactions on Knowledge and Data Engineering.

[3]  Shih-Hau Fang,et al.  Indoor Location System Based on Discriminant-Adaptive Neural Network in IEEE 802.11 Environments , 2008, IEEE Transactions on Neural Networks.

[4]  Bernard Uguen,et al.  PyLayers: An open source dynamic simulator for indoor propagation and localization , 2013, 2013 IEEE International Conference on Communications Workshops (ICC).

[5]  Petar M. Djuric,et al.  Indoor Tracking: Theory, Methods, and Technologies , 2015, IEEE Transactions on Vehicular Technology.

[6]  Betty J. Mohler,et al.  Visual flow influences gait transition speed and preferred walking speed , 2007, Experimental Brain Research.

[7]  R. Michael Buehrer,et al.  Vibration Event Localization in an Instrumented Building , 2015 .

[8]  Ah Chung Tsoi,et al.  Neural Network Classification and Prior Class Probabilities , 1996, Neural Networks: Tricks of the Trade.

[9]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[10]  Marios M. Polycarpou,et al.  Indoor Localization Using Neural Networks with Location Fingerprints , 2009, ICANN.

[11]  Ignas Niemegeers,et al.  A survey of indoor positioning systems for wireless personal networks , 2009, IEEE Communications Surveys & Tutorials.

[12]  Luca Benini,et al.  Bluetooth indoor localization with multiple neural networks , 2010, IEEE 5th International Symposium on Wireless Pervasive Computing 2010.

[13]  Ning Yu,et al.  A predictive localization algorithm based on RBF neural network for wireless sensor networks , 2015, 2015 International Conference on Wireless Communications & Signal Processing (WCSP).

[14]  R. Michael Buehrer,et al.  Improving cellular positioning indoors through trajectory matching , 2016, 2016 IEEE/ION Position, Location and Navigation Symposium (PLANS).

[15]  Tom Chau,et al.  A Review of Indoor Localization Technologies: towards Navigational Assistance for Topographical Disorientation , 2010 .

[16]  J. Holtzman,et al.  The non-line of sight problem in mobile location estimation , 1996, Proceedings of ICUPC - 5th International Conference on Universal Personal Communications.

[17]  Jim Kurose,et al.  Computer Networking: A Top-Down Approach , 1999 .

[18]  Bernard Uguen,et al.  Improved mobility modeling for indoor localization applications , 2014, 2014 11th Workshop on Positioning, Navigation and Communication (WPNC).