LOS/NLOS Identification based on Stable Distribution Feature Extraction and SVM Classifier for UWB On-body Communications

Abstract This paper presents a technique for identifying between both Line-Of-Sight (LOS) and Non-Line-Of-Sight (NLOS) propagation schemes for UWB on-body context. The wireless communications for body area networks have a great attention in the last years especially after the IEEE 802.15.6 standard. We focus in the first to extract only the pertinent information using Stable Distribution compared with statistical techniques, and secondly to classify it using Support Vector Machine (SVM) with as main goal to identify the two LOS and NLOS phenomena. We propose a technique to make the classification easy between LOS and NLOS contexts for UWB on-body communications. All simulations were applied to UWB measurements collected in 9 .

[1]  Moe Z. Win,et al.  Wideband diversity in multipath channels with nonuniform power dispersion profiles , 2006, IEEE Transactions on Wireless Communications.

[2]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[3]  Paul-Alain Rolland,et al.  α-stable interference modeling and cauchy receiver for an IR-UWB Ad Hoc network , 2010, IEEE Transactions on Communications.

[4]  Ming-Chang Lee,et al.  Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress , 2010, ArXiv.

[5]  Moe Z. Win,et al.  NLOS identification and mitigation for localization based on UWB experimental data , 2010, IEEE Journal on Selected Areas in Communications.

[6]  J. McCulloch,et al.  Simple consistent estimators of stable distribution parameters , 1986 .

[7]  R. M. Buehrer,et al.  Non-line-of-sight identification in ultra-wideband systems based on received signal statistics , 2007 .

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

[9]  Yang Hao,et al.  AN ADVANCED UWB CHANNEL MODEL FOR BODY- CENTRIC WIRELESS NETWORKS , 2013 .

[10]  Moe Z. Win,et al.  Nonparametric Obstruction Detection for UWB Localization , 2009, GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference.

[11]  Andreas F. Molisch,et al.  UWB Systems for Wireless Sensor Networks , 2009, Proceedings of the IEEE.

[12]  Yang Hao,et al.  Performance of Ultrawideband Wireless Tags for On-Body Radio Channel Characterisation , 2012 .

[13]  Aamir Saeed Malik,et al.  Survey of NLOS identification and error mitigation problems in UWB-based positioning algorithms for dense environments , 2010, Ann. des Télécommunications.

[14]  Moe Z. Win,et al.  Multipath Aided Rapid Acquisition: Optimal Search Strategies , 2007, IEEE Transactions on Information Theory.

[15]  Driss Aboutajdine,et al.  Ultra Wide-Band Channel Characterization Using Generalized Gamma Distributions , 2012, ICISP.