EVAL Cane: Nonintrusive Monitoring Platform With a Novel Gait-Based User-Identification Scheme

Considering the particularity of fragile people with reduced mobility, we design a nonintrusive platform called EVAL cane to assist and monitor user's walking. On one hand, it has important walking-assistance functions, such as obstacle warning fall detection. other collects long-term walking data in background, which may be potential physical-health-assessment data. Compared an ordinary cane, above two functions are implemented without any burden on life. In addition, have considered authentication security for that private. To this end, propose novel user-identification scheme, leveraging user gait collected by cane. best our knowledge, is first time information used reinforcing monitoring system security. This scheme does not require remember enter identity (such password), user-friendly people. statistics-based rough feature-extraction method put forward at first. Then, order improve identification precision, performance-based feature-deletion (PFD) algorithm remove bad features. Finally, minimum Mahalanobis distance classifier used. Experimental results show rate PFD can reach high 90.48%. further improves performance about 6%, reaching excellent result 96.43%.