PDR/fingerprinting fusion indoor location tracking using RSS recovery and clustering

Due to the received signal strength (RSS) variation, WiFi indoor positioning techniques using RSS have difficulties to provide good location estimates. To mitigate the effect of the RSS variation, this paper presents a Kalman filter-based positioning algorithm that is combined with pedestrian dead reckoning and RSS-based fingerprinting positioning. The RSS recovery and clustering methods are also introduced to enhance the accuracy of the fingerprinting positioning. Unlike other existing algorithms, the proposed algorithm estimates biases accumulated in RSS measurements based on the recursive least square estimation and removes them from the measurements. Reference points are effectively selected with clustering using the recovered RSS measurements. Hence, a more accurate location estimate can be obtained in the existence of the RSS variation. The proposed algorithm is implemented into an Android-based smartphone for test.

[1]  H. Weinberg.  Using the ADXL202 in Pedometer and Personal Navigation Applications , 2002 .

[2]  Rui Xu,et al.  Survey of clustering algorithms , 2005, IEEE Transactions on Neural Networks.

[3]  Andreas Haeberlen,et al.  Practical robust localization over large-scale 802.11 wireless networks , 2004, MobiCom '04.

[4]  Hisashi Kobayashi,et al.  Signal strength based indoor geolocation , 2002, 2002 IEEE International Conference on Communications. Conference Proceedings. ICC 2002 (Cat. No.02CH37333).

[5]  Mikkel Baun Kjærgaard.  Automatic Mitigation of Sensor Variations for Signal Strength Based Location Systems , 2006, LoCA.

[6]  Weifeng Tian,et al.  Activity classification and dead reckoning for pedestrian navigation with wearable sensors , 2008 .

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

[8]  Hojung Cha,et al.  Smartphone-based Wi-Fi tracking system exploiting the RSS peak to overcome the RSS variance problem , 2013, Pervasive Mob. Comput..

[9]  Prashant Krishnamurthy,et al.  On clustering RSS fingerprints for improving scalability of performance prediction of indoor positioning systems , 2008, MELT '08.

[10]  Hao-Hua Chu,et al.  Unsupervised Learning for Solving RSS Hardware Variance Problem in WiFi Localization , 2009, Mob. Networks Appl..

[11]  Kaveh Pahlavan,et al.  A comparative performance evaluation of RSS-based positioning algorithms used in WLAN networks , 2005, IEEE Wireless Communications and Networking Conference, 2005.

[12]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[13]  Wei Ni,et al.  Integrated Wi-Fi fingerprinting and inertial sensing for indoor positioning , 2011, 2011 International Conference on Indoor Positioning and Indoor Navigation.

[14]  Jian Lu,et al.  Cluster filtered KNN: A WLAN-based indoor positioning scheme , 2008, 2008 International Symposium on a World of Wireless, Mobile and Multimedia Networks.

[15]  Bahram Honary,et al.  A Sensor Fusion Method for Smart phone Orientation Estimation , 2012 .

[16]  Shih-Hau Fang,et al.  A Novel Algorithm for Multipath Fingerprinting in Indoor WLAN Environments , 2008, IEEE Transactions on Wireless Communications.