Human Gait Analysis using Wearable Sensors

Biometrics is concerned with measurement and analysis of a universal, unique and measurable physiological or behavioural characteristic. Biometric data is taken from individuals, extracting feature sets from the data and comparing it with the enrolment set in a database. Existing analyses techniques using wearable sensors are applied to gait analyses in children for biometric gait recognition. The performance degradation for children walking compared to adult walking is approximately 100%. A 6.21% Equal Error Rate (EER) for adult gait recognition was reached compared to 12.69% for children. Carrying an object showed that the performance actually improved compared to normal walking. However, faster walking was unstable resulting in a higher Equal Error Rate (EER). Age and gender differences showed significant variations in EER values. A coupled approach of statistical time-domain and frequency domain methods was employed to match biometric gait signals. Using root mean squared, crest-factor and kurtosis obtained similar matches in gait signals of children for the ages of 5-16 than for the traditional methods.