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.

Autorentext

Dr Hewa Balisane, Professor Waqar Ahmed and Dr Peter Twigg are based at Soran University, University of Central Lancashire and Manchester Metropolitan University respectively and have research interests in biometrics, information security, networking, human motion analysis and nanotechnology.