 This research has developed a novel classification algorithm to accurately identify falls, near falls, and activities of daily living, ADLs. The algorithm combines acceleration and angular velocity data from an inertial measurement unit, IMU, worn at the waist to improve the accuracy of predictions compared to individual sensor data. This can help to proactively detect falls and prevent injuries for the elderly, as well as provide quantitative rehabilitation status for those with weak balance ability. This article was offered by Unreal Choi, Taehyung Kim, Oleksandr Yuhai, and others.