Empowering a Gait Feature-Rich Timed-Up-and-Go System for Complex Ecological Environments

Abstract

Identifying fall risk can prevent injuries in the elderly as well as reduce the related financial burden. A balance assessment, Timed Up and Go (TUG), has been widely applied to estimate fall risk. However, the standardized TUG usually excludes complex factors (e.g. slopes and obstacles) falling short of representing challenges in environments that many older adults navigate. Having information on the motor performance in more complex settings can better inform clinicians about an individual's risk of falling. To this end, we present Smart Insole TUG (SITUG), a cost-efficient, real-time and self-assessment system suitable for the complex environmental TUG. Based on the human stride mechanism, our SITUG educes four refined aspects in the gait feature and segments the TUG process by six detailed phases, providing accurate and advanced information for the fall risk estimation. We evaluate the system with four complex environmental TUG. The results show that the SITUG achieves mean accuracy 94.1% in extracting subcomponents within a stride and 93.13% in deriving the stride length based on the verification of estimated walking distance. Moreover, this system can distinguish six TUG phases with the correctness around 90%.