The Design And Implementation Of The Eldly Fall Prediction System Based On ELM Algorithm

Falls and the resulting injuries in the elderly are a major public health problem,thus the early detection of falls is of great significance.The purpose of this study was to investigate the efficiency and effectiveness of a novel pre-impact fall detector System based on ELM Algorithm capable of predicting impending falls in their descending phase before the body hits the ground.A wearable tri-axial MEMS accelerometer and a tri-axis MEMS gyroscope were used to collect data of human motion information and the acceleration and angle data were transmitted to android telephone through bluetooth.Meanwhile,Elm Algorithm was used as a multi-classifier to recognize activities of daily life and falls by feature selection.The paper introduces almost all kinds of activities to make the sample more credible.The overall system was tested and results showed that all falls could be detected with an average lead-time of more than 634 ms before impact,and no false alarm occurred.The proposed system will lead to potential applications for preventing or reducing fal-related injuries.