Your browser does not support JavaScript!

access icon free Measurement of walking speed from gait data using kurtosis and skewness based approximate and detailed coefficients

This study deals with the application of kurtosis and skewness based approximate and detailed coefficients in walking speed measurement. Gait data (force information of foot and positional information of ankle) are gathered through sensors during level walking on motorised treadmill of normal individuals at various speeds and features are extracted from the data using discrete wavelet tools, namely kurtosis of approximate coefficients, kurtosis of detailed coefficients, skewness of approximate coefficients, and skewness of detailed coefficients. The features corresponding to the different discrete wavelet transformation levels are analysed and results are demonstrated. Specific relations have been found between walking speeds and those parameters, where from optimisation has been done with respect to a parameter, type of sensors, and number of sensors. Finally, an algorithm is proposed accordingly for walking speed measurement using the gait data and subsequently validated through experiments.


    1. 1)
      • 23. Chattopadhyay, S., Mitra, M., Sengupta, S.: ‘Electric power quality’ (Springer, Dordrecht, 2011).
    2. 2)
      • 4. Andrie, R., Basuki, A., Arai, K.: ‘A review of Chinese Academy of Sciences (CASIA) gait database as a human gait recognition dataset’. 13th Industrial Electronics Seminar 2011 (IES 2011) Electronic Engineering Polytechnic Institute of Surabaya (EEPIS), Indonesia, 26 October 2011, pp. 267271.
    3. 3)
      • 15. Masum, H., Bhaumik, S., Ray, R.: ‘Conceptual design of a powered ankle–foot prosthesis for walking with inversion and eversion’. Second Int. Conf. Innovations in Automation and Mechatronics Engineering (ICIAME 2014) Procedia Technology, 2014, vol. 14, pp. 228235.
    4. 4)
      • 13. Gouwanda, D., Arosha Senanayake, S.M.N.: ‘Application of hybrid multi-resolution wavelet decomposition method in detecting human walking gait events’. 2009 Int. Conf. Soft Computing and Pattern Recognition, Malacca, 2009, pp. 580585.
    5. 5)
      • 20. White, S.C., Yack, H.J., Tucker, C.A., et al: ‘Comparison of vertical ground reaction forces during overground and treadmill walking’, Med. Sci. Sports Exercise, 1998, 30, (10), pp. 15371542.
    6. 6)
      • 5. Arai, K., Andrie, R.: ‘Human gait gender classification using 2D discrete wavelet transforms energy’, Int. J. Comput. Sci. Netw. Secur., 2011, 11, (12), pp. 6268.
    7. 7)
      • 17. Fan, R.E., Culjat, M.O., King, C.H., et al: ‘A haptic feedback system for lower-limb prostheses’, IEEE Trans. Neural Syst. Rehabil. Eng., 2008, 16, (3), pp. 270277.
    8. 8)
      • 10. Astephen, J.L., Deluzio, K.J.: ‘A multivariate gait data analysis technique: application to knee osteoarthritis’, Proc. Inst. Mech. Eng. J. Eng. Med., 2004, 218, (4), pp. 271279.
    9. 9)
      • 24. Karmakar, S., Chattopadhyay, S., Mitra, M., et al: ‘Induction motor fault diagnosis’ (Springer, Singapore, 2016, 1st edn.).
    10. 10)
      • 6. Arai, K., Asmara, R.A.: ‘Human gait gender classification using 3D discrete wavelet transform feature extraction’, Int. J. Adv. Res. Artif. Intell., 2014, 3, (2), pp. 1217.
    11. 11)
      • 21. Strathy, G.M., Chao, E.Y., Laughman, R.K.: ‘Changes in knee function associated with treadmill ambulation’, J. Biomech., 1983, 16, (7), pp. 517522.
    12. 12)
      • 7. Hsia, C.H., Guo, J.M., Chiang, J.S.: ‘A fast discrete wavelet transform algorithm for visual processing applications’, Signal Process., 2012, 92, (1), pp. 89106.
    13. 13)
      • 1. Phinyomark, A., Limsakul, C., Phukpattaranont, P.: ‘Application of wavelet analysis in EMG feature extraction for pattern classification’, Meas. Sci. Rev., 2011, 11, (2), pp. 4552.
    14. 14)
      • 19. Singh, A., Thakur, A.: ‘Human gait analysis using wavelet de-noising and total variation filtering’. Int. Conf. Green Computing and Internet of Things (ICGCIoT), Noida, 2015, pp. 704708.
    15. 15)
      • 16. Masum, H., Chattopadhyay, S., Bhaumik, S., et al: ‘Utilisation of skewness of wavelet-based approximate coefficient in walking speed assessment’, IET Sci. Meas. Technol., 2016, 10, (8), pp. 977982.
    16. 16)
      • 11. Khalilullah, K.M.I., Hossain, D., Hamid, M.E.: ‘DWT-DCT based individuals identification using robust gait feature images’, Int. J. Signal Process. Image Process. Pattern Recognit., 2015, 8, (4), pp. 113124.
    17. 17)
      • 2. Chang, S.L., Hsu, C.C., Lu, T.C., et al: ‘Human body tracking based on discrete wavelet transform’. Proc. 2007 WSEAS Int. Conf. Circuits, Systems, Signal and Telecommunications, Gold Coast, Australia, 17–19 January 2007, pp. 147152.
    18. 18)
      • 25. Heckert, N.A., Filliben, J.J., Croarkin, C.M., et al: ‘NIST/SEMATECH e-handbook of statistical methods’ (2002),
    19. 19)
      • 3. Atallah, L., Lo, B., Yang, G.Z., et al: ‘Detecting walking gait impairment with an ear-worn sensor’. Sixth Int. Workshop on Wearable and Implantable Body Sensor Networks, 2009, pp. 175180.
    20. 20)
      • 9. Bhatia, I., Kumar, A.: ‘Gait recognition using Hough transform and DWT’, Int. J. Adv. Res. Comput. Sci. Softw. Eng., 2014, 4, (6), pp. 889896.
    21. 21)
      • 14. Forsman, P.M, Toppila, E.M., Haeggstrom, E.O.: ‘Wavelet analysis to detect gait events’. 2009 Annual Int. Conf. IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, 2009, pp. 424427.
    22. 22)
      • 12. Ye, B., Wen, Y.M.: ‘Gait recognition based on DWT and SVM’. Int. Conf. Wavelet Analysis and Pattern Recognition (ICWAPR ‘07), Beijing, 2007, pp. 13821387.
    23. 23)
      • 18. Masum, H., Bhaumik, S., Dalmia, A., et al: ‘Development of wireless foot pressure sensor for bio-medical application’. Second Int. Conf. Advances in Mechanical Engineering and its Interdisciplinary Areas (ICAMEI-2015), Kolkata, 2015, pp. 355360.
    24. 24)
      • 22. Li, L., Van Den Bogert, E.C.H., Caldwell, G.E., et al: ‘Coordination patterns of walking and running at similar speed and stride frequency’, Hum. Mov. Sci., 1999, 18, (1), pp. 6785.
    25. 25)
      • 8. Hsia, C.H., Guo, J.M.: ‘Efficient modified directional lifting-based discrete wavelet transform for moving object detection’, Signal Process., 2014, 96, (B), pp. 138152.

Related content

This is a required field
Please enter a valid email address