Effective Falls Detection Method Using Two Tri-Axial Accelerometers
Gye Rok Jeon, Young Jae Kim, Ah Young Jeon, Sang Hoon Lee, Jae Hyung Kim, Min Seok Kim, Seong Ho Lee, Ji Hyun Kim · Advanced materials research · 2013
Falls detection systems have been developed in recent years because falls are detrimental events that can have a devastating effect on health of the elderly population. Current fall detecting methods mainly employ accelerometer to discriminate falls from activities of daily living (ADL). However, this makes it difficult to distinguish real falls from certain fall-like activities such as jogging and jumping. In this paper, an accurate fall detection system was implemented using two tri-axial accelerometers. By attaching the accelerometers on the chest and the abdomen, our system can effectively differentiate between falls and non-fall events.The Diff_Z and Sum_diff_Z parameter resulted in falls detection rate of 100%, respectively.