IoT based fall detection and ambient assisted system for the elderly

• Published in: Cluster computing 2019-01, Vol.22 (Suppl 1), p.2517-2525
• Main Authors: Chandra, I., Sivakumar, N., Gokulnath, Chandra Babu, Parthasarathy, P.
• Format: Article
• Language: English
• Subjects: Acceleration; Accelerometers; Accuracy; Algorithms; Cameras; Computer Communication Networks; Computer Science; Fall detection; Older people; Operating Systems; Processor Architectures; Sensors; Velocity
• ISSN: 1386-7857; 1573-7543
• DOI: 10.1007/s10586-018-2329-2

Falls are considered as risky for the elderly people because it may affect the health of the people. So, in the recent years many elderly fall detection methods has been developed. In the present years many fall detection method had been developed but it uses only accelerometer sensor to detect the fall. It may fail in finding in the difference between actual fall and fall like activities such as sitting fast and jumping. In the proposed approach I have suggested a fall detection algorithm to detect the fall of elderly people. Daily human activities are divided into two parts such as static position and dynamic position. With the help of tri-axis accelerometer proposed fall detection can detect four kinds of positions such as falling front, front backward, jumping and sitting fastly. Acceleration and velocity is used to determine kind of fall. Our algorithm uses accelerometer and gyroscope sensor to predict the fall correctly and reduce the false positives and false negatives and increase the accuracy. In addition to that our method is made out of low cost and it can be used in real-time.