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.