Raj Kumar PATRA, Tilendra Shishir SINHA, Ravi Prakash DUBEY

Extraction of geometric and prosodic features from human-gait-speech data for behavioral pattern detection: Part I

In this work, we extract prosodic features from subjects while they are talking while walking using humangait-speech data. These human-gait-speech data are separated into 1D data (human-speech) and 2D data (human-gait) using the adaptive-lifting scheme of wavelet transform. We carry out extraction of prosodic features from human-speech data, such as speech duration, pitch, speaking rate, and speech momentum, using five different natural languages (Hindi, Bengali, Oriya, Chhattisgarhi, and English) for the detection of behavioral patterns. These behavioral patterns form real-valued measured parameters, stored in a knowledge-based model called the human-gait-speech model. Extraction of geometrical features from human-gait data, such as step length, energy or effort, walking speed, and gait momentum, is carried out for the authentication of behavioral patterns. In this paper, the data of 25 subjects of different ages, talking in five different natural languages while walking, are analyzed for the detection of behavioral patterns.

PDF

___

[1] OShaughnessy D. Speech Communications: Human and Machine. 2nd ed. Telangana, India: Universities Press, 1987.
[2] Goldberg DE. Genetic Algorithms in Search, Optimization and Machine Learning. 1st ed. Boston, MA, USA: Addison-Wesley, 1989.
[3] Jang JSR, Sun CT, Mizutani E. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. 1st ed. Upper Saddle River, NJ, USA: Pearson Education, 1990.
[4] Hassoun MH. Fundamentals of Artificial Neural Networks. Cambridge, MA, USA: MIT Press, 1995.
[5] Cohen A. Biomedical Signal Processing Volume 2. Compression and Automatic Recognition. 1st ed. Boca Raton, FL, USA: CRC Press, 1986.
[6] Tolvi J. Genetic algorithms for outlier detection and variable selection in linear regression models. Soft Comput 2004; 8: 527-533.
[7] Sun H, Lam K, Chung S, Dong W, Gu M, Sun J. Efficient vector quantization using genetic algorithm. Neural Comput Appl 2005; 14: 203-211.
[8] Ba¸cao F, Lobo V, Painho M. Applying genetic algorithms to zone design. Soft Comput 2005; 9: 341-348.
[9] Sinha TS, Sanyal G, Mukherji A. Some aspects of modelling and simulation for the recognition of speech and speaker of Bengali language using proposed GSAMTSS algorithm. International Journal on Cybernetics & Informatics 2006: 69-75.
[10] Ghanbari Y, Karami MR. Spectral subtraction in the wavelet domain for speech enhancement. International Journal on Softwares & Information Technology 2004; 1: 26-29.
[11] Samangooei S, Nixon MS. Performing content-based retrieval of humans using gait biometrics. Semantic Multimedia 2008; 5392: 105-120.
[12] Bouchrika I, Goffredo M, Carter J, Nixon MS. On using gait in forensic biometrics. J Forensic Sci 2011; 56: 882-889.
[13] Sinha TS, Patra RK, Raja R. A comprehensive analysis of human gait for abnormal foot recognition using neurogenetic approach. International Journal of Tomography & Statistics 2011; 16: 56-73.
[14] Wang C, Zhang J, Wang L, Pu J. Human identification using temporal information preserving gait template. IEEE T Pattern Anal 2012; 34: 2164-2176.
[15] Kao E, VanMaasdam P, Sheppard J. Image-based tracking with particle swarms and probabilistic data association. In: IEEE 2008 Swarm Intelligence Symposium; 2123 September 2008; St. Louis, MO, USA. New York, NY, USA: IEEE. pp 1-8.
[16] Sinha TS, Chakravarty D, Patra RK, Raja R. Modelling and simulation for the recognition of physiological and behavioral traits through human gait and face images. In: Al-Asmari AK, editor. Discrete Wavelet Transforms: A Compendium of New Approaches and Recent Applications. Rijeka, Croatia: InTech, 2013. pp. 95-125.
[17] Cantiniaux S, Vaugoyeau M, Robert D, Horrelou-Pitek C, Mancini J, Witias T, Azulay JP. Comparative analysis of gait and speech in Parkinsons disease: hypokinetic or dysrhythmic disorders? J Neurol Neurosurg Psychiatry 2009; 81: 177-184.
[18] Janssen D, Schollhorn WI, Lubienetkzi J, Folling K, Davis K. Recognition of emotions in gait patterns by means of artificial neural nets. J Nonverbal Behav 2008; 32: 79-82.
[19] Roether CL, Omlor L, Christensen A, Giese MA. Critical features for the perception of emotion from gait. J Vis 2009; 9: 1-32.