InFallible – Automated & Adaptive Fall Detection System

Abstract

Among the elderly population, falls are one of the most common causes of death and injury. More than 30% of people over 65 years old fall each year and the prevalence increases for people above 80 years old. Of all fall-related injuries among communitydwelling adults, 32.3% occurred among older adults, 35.3% among middle-aged adults and 32.3% among younger adults. Falls and fall-related injuries represent a significant health and safety problem for adults of all ages. The findings suggest that adult fall prevention is a serious concern and we have to consider the entire adult lifespan to ensure a greater public health benefit instead of just working with older adults. The proposed algorithm (Machine Learning algorithm) in our smartphone application does continuous monitoring of human movement, this sensing is done through internal sensors of the smartphone. The application is capable of detecting fall and sending alarms. Our focus was on data set acquisition in order to train the Machine Learning algorithm on a robust data set. After which we worked on making a better and boosted system which is adaptive. Last but the least, through real life testing we were able to achieve a userfriendly android application. Furthermore, a two week monitoring time was setup to check for false alarms. These were then further reduced to make the system highly accurate