Unobtrusive Gait Recognition Using Smartwatches

Gait recognition is a technique that identifies or verifies people based upon their walking patterns. Smartwatches, which contain an accelerometer and gyroscope have recently been used to implement gait-based biometrics. However, this prior work relied upon data from single sessions for both training and testing, which is not realistic and can lead to overly optimistic performance results. This paper aims to remedy some of these problems by training and evaluating a smartwatch-based biometric system on data obtained from different days. Also, it proposes an advanced feature selection approach to identify optimal features for each user. Two experiments are presented under three different scenarios: Same-Day, Mixed-Day, and Cross-Day. Competitive results were achieved (best EERs of 0.13% and 3.12% by using the Same day data for accelerometer and gyroscope respectively and 0.69% and 7.97% for the same sensors under the Cross-Day evaluation. The results show that the technology is sufficiently capable and the signals captured sufficiently discriminative to be useful in performing gait recognition.

[1]  Gary M. Weiss,et al.  Cell phone-based biometric identification , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[2]  Christoph Busch,et al.  Classification of Acceleration Data for Biometric Gait Recognition on Mobile Devices , 2011, BIOSIG.

[3]  Rajesh Kumar,et al.  Authenticating users through their arm movement patterns , 2016, ArXiv.

[4]  René Mayrhofer,et al.  Orientation Independent Cell Phone Based Gait Authentication , 2014, MoMM.

[5]  Lina Yao,et al.  DeepKey: An EEG and Gait Based Dual-Authentication System , 2017, ArXiv.

[6]  Christoph Busch,et al.  Scenario test of accelerometer-based biometric gait recognition , 2011, 2011 Third International Workshop on Security and Communication Networks (IWSCN).

[7]  Christoph Busch,et al.  Classifying accelerometer data via hidden Markov models to authenticate people by the way they walk , 2013, IEEE Aerospace and Electronic Systems Magazine.

[8]  Gary M. Weiss,et al.  Smartwatch-based activity recognition: A machine learning approach , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[9]  Einar Snekkenes,et al.  Spoof Attacks on Gait Authentication System , 2007, IEEE Transactions on Information Forensics and Security.

[10]  Christoph Busch,et al.  Authentication of Smartphone Users Based on the Way They Walk Using k-NN Algorithm , 2012, 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[11]  Christoph Busch,et al.  Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition , 2010, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[12]  Edward D. Lemaire,et al.  Feature Selection for Wearable Smartphone-Based Human Activity Recognition with Able bodied, Elderly, and Stroke Patients , 2015, PloS one.

[13]  Martin Reese Hestbek,et al.  Biometric gait recognition for mobile devices using wavelet transform and support vector machines , 2012, 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP).

[14]  Nitesh Saxena,et al.  Walk-Unlock: Zero-Interaction Authentication Protected with Multi-Modal Gait Biometrics , 2016, ArXiv.

[15]  Nathan L. Clarke,et al.  Activity Recognition using wearable computing , 2016, 2016 11th International Conference for Internet Technology and Secured Transactions (ICITST).

[16]  Gary M. Weiss,et al.  Smartwatch-based biometric gait recognition , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[17]  Alessio Vecchio,et al.  Gait-based authentication using a wrist-worn device , 2016, MobiQuitous.