A comparison of machine learning classifiers for acoustic gait analysis

Gait analysis is the study of human locomotion. Such analysis can provide valuable information for low-cost analytic and classification applications in security, medical diagnostics, and biomechanics. In comparison to visual-based gait analysis, audio-based gait analysis can offer robustness to clothing variations, visibility issues, and angle complications. In this research, we consider an approach to acoustic gait analysis based on time differences between consecutive steps. For this problem, we compare several machine learning algorithms for classification, specifically, k-nearest neighbor (k-NN), support vector machines (SVM), random forests, and AdaBoost. We achieve good classification rates with highly discriminative onevs-all capabilities. The evidence provided in this research shows that our approach to acoustic gait recognition is a promising avenue for future development.

[1]  J B King,et al.  Gait Analysis. An Introduction , 1992 .

[2]  Björn Schuller,et al.  Acoustic Gait-based Person Identification using Hidden Markov Models , 2014, MAPTRAITS '14.

[3]  Douglas A. Reynolds,et al.  A Tutorial on Text-Independent Speaker Verification , 2004, EURASIP J. Adv. Signal Process..

[4]  Kamiar Aminian,et al.  Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes. , 2002, Journal of biomechanics.

[5]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

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

[7]  Joarder Kamruzzaman,et al.  Support Vector Machines and Other Pattern Recognition Approaches to the Diagnosis of Cerebral Palsy Gait , 2006, IEEE Transactions on Biomedical Engineering.

[8]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[9]  Hyeran Byun,et al.  Applications of Support Vector Machines for Pattern Recognition: A Survey , 2002, SVM.

[10]  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.

[11]  R Begg,et al.  A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. , 2005, Journal of biomechanics.

[12]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

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

[14]  Dave Tahmoush,et al.  Radar micro-doppler for long range front-view gait recognition , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[15]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[16]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[17]  A. N. Rajagopalan,et al.  Gait-based recognition of humans using continuous HMMs , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[18]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[19]  Bhiksha Raj,et al.  Acoustic Doppler sonar for gait recogination , 2007, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance.

[20]  Marimuthu Palaniswami,et al.  Support vector machines for automated gait classification , 2005, IEEE Transactions on Biomedical Engineering.

[21]  Tieniu Tan,et al.  Silhouette Analysis-Based Gait Recognition for Human Identification , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Mark Stamp,et al.  Introduction to Machine Learning with Applications in Information Security , 2017 .

[25]  Heikki Ailisto,et al.  Identifying users of portable devices from gait pattern with accelerometers , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[26]  Mark Stamp,et al.  Acoustic Gait Analysis using Support Vector Machines , 2018, ICISSP.

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  H. Yasukawa,et al.  Personal identification using footstep detection , 2004, Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, 2004. ISPACS 2004..

[29]  Robert E. Schapire,et al.  The strength of weak learnability , 1990, Mach. Learn..

[30]  Gang Qian,et al.  People Identification Using Gait Via Floor Pressure Sensing and Analysis , 2008, EuroSSC.

[31]  Jake K. Aggarwal,et al.  Human Motion Analysis: A Review , 1999, Comput. Vis. Image Underst..