Machine Learning Based Localization

A vast majority of localization techniques proposed for sensor networks are based on triangulation methods in Euclidean geometry. They utilize the geometrical properties of the sensor network to infer the sensor locations. A fundamentally different approach is presented in this chapter. This approach is based on machine learning, in which we work directly on the natural (non-Euclidean) coordinate systems provided by the sensor devices. The known locations of a few nodes in the network and the sensor readings can be exploited to construct signalstrength or hop-count based function spaces that are useful for learning unknown sensor locations, as well as other extrinsic quantities of interest. We discuss the applicability of two learning methods: the classification method and the regression method. We show that these methods are especially suitable for target tracking applications.

[1]  Tian He,et al.  A high-accuracy, low-cost localization system for wireless sensor networks , 2005, SenSys '05.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  B. Thompson.  Canonical Correlation Analysis , 1984 .

[4]  Toshihisa Tanaka,et al.  Signal Processing Techniques for Knowledge Extraction and Information Fusion , 2008 .

[5]  B. R. Badrinath,et al.  DV Based Positioning in Ad Hoc Networks , 2003, Telecommun. Syst..

[6]  Anil K. Jain,et al.  Incremental nonlinear dimensionality reduction by manifold learning , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Tarek F. Abdelzaher,et al.  Range-free localization schemes for large scale sensor networks , 2003, MobiCom '03.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  Jan M. Rabaey,et al.  Location in distributed ad-hoc wireless sensor networks , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[10]  Anthony Kuh,et al.  Ad Hoc Sensor Network Localization using Distributed Kernel Regression Algorithms , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[11]  Robert A. Scholtz,et al.  Ranging in a dense multipath environment using an UWB radio link , 2002, IEEE J. Sel. Areas Commun..

[12]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[13]  Srdjan Capkun,et al.  GPS-free Positioning in Mobile Ad Hoc Networks , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.

[14]  Shotaro Akaho,et al.  A kernel method for canonical correlation analysis , 2006, ArXiv.

[15]  David C. Moore,et al.  Robust distributed network localization with noisy range measurements , 2004, SenSys '04.

[16]  L. El Ghaoui,et al.  Convex position estimation in wireless sensor networks , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[17]  S. Shankar Sastry,et al.  A Hierarchical Multiple-Target Tracking Algorithm for Sensor Networks , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[18]  Gul Agha,et al.  Resilient Localization for Sensor Networks in Outdoor Environments , 2005, ICDCS.

[19]  Ying Zhang,et al.  Localization from mere connectivity , 2003, MobiHoc '03.

[20]  Dieter Fox,et al.  Large-Scale Localization from Wireless Signal Strength , 2005, AAAI.

[21]  Mauro Brunato,et al.  Statistical learning theory for location fingerprinting in wireless LANs , 2005, Comput. Networks.

[22]  Duc A. Tran,et al.  Localization In Wireless Sensor Networks Based on Support Vector Machines , 2008, IEEE Transactions on Parallel and Distributed Systems.

[23]  Erik D. Demaine,et al.  Anchor-Free Distributed Localization in Sensor Networks , 2003 .

[24]  Qiang Yang,et al.  Online Co-Localization in Indoor Wireless Networks by Dimension Reduction , 2007, AAAI.

[25]  Seth J. Teller,et al.  The cricket compass for context-aware mobile applications , 2001, MobiCom '01.

[26]  Bodhi Priyantha,et al.  The Cricket indoor location system , 2005 .

[27]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[28]  T. Nguyen,et al.  Support Vector Classification Strategies for Localization in Sensor Networks , 2006, 2006 First International Conference on Communications and Electronics.

[29]  G.B. Giannakis,et al.  Localization via ultra-wideband radios: a look at positioning aspects for future sensor networks , 2005, IEEE Signal Processing Magazine.

[30]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

[31]  B. R. Badrinath,et al.  Ad hoc positioning system (APS) using AOA , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[32]  Yiqiang Chen,et al.  Multidimensional Vector Regression for Accurate and Low-Cost Location Estimation in Pervasive Computing , 2006, IEEE Transactions on Knowledge and Data Engineering.

[33]  Radhika Nagpal,et al.  Organizing a Global Coordinate System from Local Information on an Ad Hoc Sensor Network , 2003, IPSN.

[34]  Erik D. Demaine,et al.  Mobile-assisted localization in wireless sensor networks , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[35]  Hari Balakrishnan,et al.  6th ACM/IEEE International Conference on on Mobile Computing and Networking (ACM MOBICOM ’00) The Cricket Location-Support System , 2022 .

[36]  Bruno Sinopoli,et al.  A kernel-based learning approach to ad hoc sensor network localization , 2005, TOSN.

[37]  Mani B. Srivastava,et al.  Dynamic fine-grained localization in Ad-Hoc networks of sensors , 2001, MobiCom '01.

[38]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[39]  Deborah Estrin,et al.  Scalable, Ad Hoc Deployable, RF-Based Localization , 2002 .

[40]  Mani B. Srivastava,et al.  The bits and flops of the n-hop multilateration primitive for node localization problems , 2002, WSNA '02.

[41]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[42]  Danilo P. Mandic,et al.  Sensor Network Localization Using Least Squares Kernel Regression , 2006, KES.