An Event-Triggered Machine Learning Approach for Accelerometer-Based Fall Detection

Falls are a major health risk for the elderly. Age UK reported that falls are one of the leading causes of injury-related deaths and the main cause of disability and death for people aged over 65 in the UK [1]. The World Health Organization (WHO) also reports that falls are the second leading cause of injury-related deaths worldwide [2]. Falls can cause several types of injury, including fractures, open wounds, bruises, sprains, joint dislocations, brain injuries, or strained muscles [3]. Although fall detection systems are unable to prevent falls, they can reduce complications by ensuring that fall victims receive help quickly.