Smartphone User Identity Verification Using Gait Characteristics

Smartphone-based biometrics offers a wide range of possible solutions, which could be used to authenticate users and thus to provide an extra level of security and theft prevention. We propose a method for positive identification of smartphone user’s identity using user’s gait characteristics captured by embedded smartphone sensors (gyroscopes, accelerometers). The method is based on the application of the Random Projections method for feature dimensionality reduction to just two dimensions. Then, a probability distribution function (PDF) of derived features is calculated, which is compared against known user PDF. The Jaccard distance is used to evaluate distance between two distributions, and the decision is taken based on thresholding. The results for subject recognition are at an acceptable level: we have achieved a grand mean Equal Error Rate (ERR) for subject identification of 5.7% (using the USC-HAD dataset). Our findings represent a step towards improving the performance of gait-based user identity verification technologies.

[1]  Gonzalo Bailador,et al.  Application of the computational theory of perceptions to human gait pattern recognition , 2010, Pattern Recognit..

[2]  Steven Furnell,et al.  Authentication of users on mobile telephones - A survey of attitudes and practices , 2005, Comput. Secur..

[3]  David R Bassett,et al.  2011 Compendium of Physical Activities: a second update of codes and MET values. , 2011, Medicine and science in sports and exercise.

[4]  Juha Pärkkä,et al.  Automatic feature selection for context recognition in mobile devices , 2010, Pervasive Mob. Comput..

[5]  Naranker Dulay,et al.  TRAcME: Temporal Activity Recognition Using Mobile Phone Data , 2008, 2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing.

[6]  Gerhard Tröster,et al.  Quantifying Gait Similarity: User Authentication and Real-World Challenge , 2009, ICB.

[7]  Robertas Damasevicius,et al.  Human Activity Recognition in AAL Environments Using Random Projections , 2016, Comput. Math. Methods Medicine.

[8]  B. G. Celler,et al.  Classification of basic daily movements using a triaxial accelerometer , 2004, Medical and Biological Engineering and Computing.

[9]  Matjaz B. Juric,et al.  Inertial Sensor-Based Gait Recognition: A Review , 2015, Sensors.

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

[11]  Michel Vacher,et al.  Improving Supervised Classification of Activities of Daily Living Using Prior Knowledge , 2011, Int. J. E Health Medical Commun..

[12]  Mitja Lustrek,et al.  Energy expenditure estimation with wearable accelerometers , 2012, 2012 IEEE International Symposium on Circuits and Systems.

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

[14]  A F Bobick,et al.  Movement, activity and action: the role of knowledge in the perception of motion. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[15]  Thuc Dinh Nguyen,et al.  Adaptive Cross-Device Gait Recognition Using a Mobile Accelerometer , 2013, J. Inf. Process. Syst..

[16]  Mario Baum,et al.  Handbook Of Biometrics , 2016 .

[17]  Yuting Zhang,et al.  Accelerometer-based gait recognition via voting by signature points , 2009 .

[18]  Marios Savvides,et al.  Gait-ID on the move: Pace independent human identification using cell phone accelerometer dynamics , 2012, 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[19]  Belkacem Fergani,et al.  News Schemes for Activity Recognition Systems Using PCA-WSVM, ICA-WSVM, and LDA-WSVM , 2015, Inf..

[20]  Liu Ming,et al.  A Wearable Acceleration Sensor System for Gait Recognition , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[21]  Christoph Busch,et al.  Template Protection for Biometric Gait Data , 2010, BIOSIG.

[22]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[23]  Aini Hussain,et al.  Sudden Event Recognition: A Survey , 2013, Sensors.

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

[25]  Tâm Huynh,et al.  Human activity recognition with wearable sensors , 2008 .

[26]  Miguel A. Labrador,et al.  A Survey on Human Activity Recognition using Wearable Sensors , 2013, IEEE Communications Surveys & Tutorials.

[27]  Lama Nachman,et al.  Unobtrusive gait verification for mobile phones , 2014, SEMWEB.

[28]  Yuwei Chen,et al.  Human Behavior Cognition Using Smartphone Sensors , 2013, Sensors.

[29]  Kyo Chul Kang.  FODA: Twenty Years of Perspective on Feature Modeling , 2010, VaMoS.

[30]  Cem Ersoy,et al.  A Review and Taxonomy of Activity Recognition on Mobile Phones , 2013 .

[31]  Robertas Damasevicius,et al.  Domain Ontology-Based Generative Component Design Using Feature Diagrams and Meta-programming Techniques , 2008, ECSA.

[32]  S. Sprager,et al.  A cumulant-based method for gait identification using accelerometer data with principal component analysis and support vector machine , 2009 .

[33]  Matt Wolff.  Behavioral Biometric Identification on Mobile Devices , 2013, HCI.

[34]  Shie Mannor,et al.  Activity and Gait Recognition with Time-Delay Embeddings , 2010, AAAI.

[35]  Dimitrios Tzovaras,et al.  Spatiotemporal analysis of human activities for biometric authentication , 2012, Comput. Vis. Image Underst..

[36]  Venu Govindaraju,et al.  A generative framework to investigate the underlying patterns in human activities , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[37]  Gene Eu Jan,et al.  Gait Recognition and Walking Exercise Intensity Estimation , 2014, International journal of environmental research and public health.

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

[39]  Kôiti Hasida,et al.  Rotation invariant feature extraction from 3-D acceleration signals , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[40]  Patrick Bours,et al.  Gait and activity recognition using commercial phones , 2013, Comput. Secur..

[41]  John Stillwell,et al.  Symmetry , 2000, Am. Math. Mon..

[42]  Anil K. Jain,et al.  An Introduction to Biometric Authentication Systems , 2005 .

[43]  Claudia Nickel,et al.  User Survey on Phone Security and Usage , 2010, BIOSIG.

[44]  Mi Zhang,et al.  USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors , 2012, UbiComp.

[45]  Mikko Lindholm,et al.  Identifying people from gait pattern with accelerometers , 2005, SPIE Defense + Commercial Sensing.

[46]  Guang-Zhong Yang,et al.  Sensor Positioning for Activity Recognition Using Wearable Accelerometers , 2011, IEEE Transactions on Biomedical Circuits and Systems.

[47]  Weihua Sheng,et al.  Motion- and location-based online human daily activity recognition , 2011, Pervasive Mob. Comput..

[48]  Thang Hoang,et al.  Gait identification using accelerometer on mobile phone , 2012, 2012 International Conference on Control, Automation and Information Sciences (ICCAIS).

[49]  Venu Govindaraju,et al.  Behavioural biometrics: a survey and classification , 2008, Int. J. Biom..

[50]  Faicel Chamroukhi,et al.  Physical Human Activity Recognition Using Wearable Sensors , 2015, Sensors.

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

[52]  Dimitris Achlioptas,et al.  Database-friendly random projections , 2001, PODS.

[53]  Tieniu Tan,et al.  Automatic gait recognition based on statistical shape analysis , 2003, IEEE Trans. Image Process..

[54]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .