A machine learning approach for localization in cellular environments

A machine learning approach is developed for localization based on received signal strength (RSS) from cellular towers. The proposed approach only assumes knowledge of RSS fingerprints of the environment, and does not require knowledge of the cellular base transceiver station (BTS) locations, nor uses any RSS mathematical model. The proposed localization scheme integrates a weighted K-nearest neighbor (WKNN) and a multilayer neural network. The integration takes advantage of the robust clustering ability of WKNN and implements a neural network that could estimate the position within each cluster. Experimental results are presented to demonstrate the proposed approach in two urban environments and one rural environment, achieving a mean distance localization error of 5.9 m and 5.1 m in the urban environments and 8.7 m in the rural environment. This constitutes an improvement of 41%, 45%, and 16%, respectively, over the WKNN-only algorithm.

[1]  Yubin Xu,et al.  Neural Network-Based Accuracy Enhancement Method for WLAN Indoor Positioning , 2012, 2012 IEEE Vehicular Technology Conference (VTC Fall).

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  Kimia Shamaei,et al.  I Hear, Therefore I Know Where I Am: Compensating for GNSS Limitations with Cellular Signals , 2017, IEEE Signal Processing Magazine.

[4]  Heinz Mathis,et al.  Positioning Using LTE Signals , 2015 .

[5]  Zaher M. Kassas,et al.  Navigation With Cellular CDMA Signals—Part I: Signal Modeling and Software-Defined Receiver Design , 2018, IEEE Transactions on Signal Processing.

[6]  Anne M. Denton,et al.  A Complete Observation Model for Tracking Vehicles from Mobile Phone Signal Strengths and Its Potential in Travel-Time Estimation , 2016, 2016 IEEE 84th Vehicular Technology Conference (VTC-Fall).

[7]  Todd E. Humphreys,et al.  Collaborative Opportunistic Navigation , 2012 .

[8]  Zaher M. Kassas,et al.  Navigation With Cellular CDMA Signals—Part II: Performance Analysis and Experimental Results , 2018, IEEE Transactions on Signal Processing.

[9]  Erik Blasch,et al.  Mobile positioning via fusion of mixed signals of opportunity , 2014, IEEE Aerospace and Electronic Systems Magazine.

[10]  Trupti M. Kodinariya,et al.  Review on determining number of Cluster in K-Means Clustering , 2013 .

[11]  Gergely V. Záruba,et al.  A Bayesian sampling approach to in-door localization of wireless devices using received signal strength indication , 2005, Third IEEE International Conference on Pervasive Computing and Communications.

[12]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[13]  Zaher M. Kassas,et al.  Exploiting LTE Signals for Navigation: Theory to Implementation , 2018, IEEE Transactions on Wireless Communications.

[14]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[15]  Paolo Crosta,et al.  Comparative results analysis on positioning with real LTE signals and low-cost hardware platforms , 2014, 2014 7th ESA Workshop on Satellite Navigation Technologies and European Workshop on GNSS Signals and Signal Processing (NAVITEC).

[16]  Markus Ulmschneider,et al.  Multipath assisted positioning for pedestrians using LTE signals , 2016, 2016 IEEE/ION Position, Location and Navigation Symposium (PLANS).

[17]  H. Howard Fan,et al.  Asynchronous differential TDOA for non-GPS navigation using signals of opportunity , 2008, IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Binghao Li,et al.  Accuracy indicator for fingerprinting localization systems , 2012, Proceedings of the 2012 IEEE/ION Position, Location and Navigation Symposium.

[19]  Steve Scheding,et al.  Comparison of Opportunistic Signals for Localisation , 2010 .

[20]  Khaled Kamal Saab,et al.  Application of an optimal stochastic Newton-Raphson technique to triangulation-based localization systems , 2016, 2016 IEEE/ION Position, Location and Navigation Symposium (PLANS).

[21]  Limin Xiao,et al.  Measurement-based RSS-multipath neural network indoor positioning technique , 2014, 2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE).

[22]  Pravin Varaiya,et al.  RSSI-Fingerprinting-Based Mobile Phone Localization With Route Constraints , 2014, IEEE Transactions on Vehicular Technology.

[23]  Kenneth M. Pesyna,et al.  Tightly-Coupled Opportunistic Navigation for Deep Urban and Indoor Positioning , 2011 .