PROJECT TITLE :

Footstep-Identification System Based on Walking Interval

ABSTRACT:

Footsteps, as a main reasonably behavioral trait, are a universally on the market signal, but constructing an identity verification system based mostly on them remains a challenging downside: footsteps not solely replicate someone's physiological basis but conjointly depend on the person's psychological makeup, footwear, and floor. This text describes a completely unique footstep-identification system. To eliminate footwear and floor variations as limiting factors, the footstep duration and interval times are extracted from footsteps, and a timing vector is obtained as a feature. To sleek instability in footsteps, the authors developed a novel pattern-recognition method, in which the training procedure will be split into several parallel subprocedures, with every subprocedure only considering one category sample. It can be periodically retrained using several of the user's most recent successful identification footsteps. Theoretical and experimental results show this method is relatively robust to the variations of footwear, floor, and therefore the examinee's psychological makeup, and yields a higher classification performance compared with the existing ways.