Radio received signal strength based biometric sensing for lightweight walker recognition

This article reports the findings of a radio received signal strength (RSS) based biometric sensing approach for lightweight walker recognition. A vertically deployed radio sensing network is designed to obtain the movement of walker at seven different heights. The sequential RSS at each height contributes weak distinguished feature to walker's identify. The human subjects are recognized by vector quantization (VQ) in the context of path-constrained walking. There are 12 walkers participated in this experiment, and the recognition accuracy is evaluated in line-of-sight and non-line-of-sight environments with four different sizes of codebooks. Experimental analysis shows the proposed sensing method can achieve the average recognition accuracy of 88.92% in line-of-sight environment better than the 74.41% in non-line-of-sight environment.

[1]  Biswanath Mukherjee,et al.  Wireless sensor network survey , 2008, Comput. Networks.

[2]  W. Eric L. Grimson,et al.  Gait analysis for recognition and classification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[3]  Neal Patwari,et al.  Radio Tomographic Imaging with Wireless Networks , 2010, IEEE Transactions on Mobile Computing.

[4]  Mark S. Nixon,et al.  Markerless Human Gait Analysis via Image Sequences , 2003 .

[5]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[6]  Mark S. Nixon,et al.  Using Gait as a Biometric, via Phase-weighted Magnitude Spectra , 1997, AVBPA.

[7]  Sneha Kumar Kasera,et al.  Monitoring Breathing via Signal Strength in Wireless Networks , 2011, IEEE Transactions on Mobile Computing.

[8]  Neal Patwari,et al.  Fingerprint-Based Device-Free Localization Performance in Changing Environments , 2015, IEEE Journal on Selected Areas in Communications.

[9]  Xianguo Zhang,et al.  Background-Modeling-Based Adaptive Prediction for Surveillance Video Coding , 2014, IEEE Transactions on Image Processing.

[10]  Ian F. Akyildiz,et al.  A survey on wireless multimedia sensor networks , 2007, Comput. Networks.

[11]  Sudeep Sarkar,et al.  The humanID gait challenge problem: data sets, performance, and analysis , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Bruce H. Krogh,et al.  Lightweight detection and classification for wireless sensor networks in realistic environments , 2005, SenSys '05.

[13]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[14]  A. Vasuki,et al.  A review of vector quantization techniques , 2006, IEEE Potentials.

[15]  M. P. Murray.  Gait as a total pattern of movement. , 1967, American journal of physical medicine.

[16]  Maurizio Bocca,et al.  A Fade Level-Based Spatial Model for Radio Tomographic Imaging , 2014, IEEE Transactions on Mobile Computing.

[17]  Richard K. Martin,et al.  Accuracy vs. Resolution in Radio Tomography , 2014, IEEE Transactions on Signal Processing.

[18]  Saeid Nahavandi,et al.  A Review of Vision-Based Gait Recognition Methods for Human Identification , 2010, 2010 International Conference on Digital Image Computing: Techniques and Applications.

[19]  D.R. Reddy,et al.  Speech recognition by machine: A review , 1976, Proceedings of the IEEE.

[20]  Marimuthu Palaniswami,et al.  Computational Intelligence in Gait Research: A Perspective on Current Applications and Future Challenges , 2009, IEEE Transactions on Information Technology in Biomedicine.

[21]  Neal Patwari,et al.  See-Through Walls: Motion Tracking Using Variance-Based Radio Tomography Networks , 2011, IEEE Transactions on Mobile Computing.