An intelligent fall detection algorithm for elderly monitoring in the internet of things platform

• Published in: Multimedia tools and applications Vol. 83; no. 2; pp. 5683 - 5695
• Main Authors: Al Dujaili, Mohammed Jawas, Dhaam, Haidar Zaeer, Mezeel, Mushtaq Talib
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2024; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Caregivers; Clustering; Communication; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Deep learning; Electrocardiography; Fall detection; Health care; Health care facilities; Heart attacks; Internet of Things; Monitoring systems; Multimedia; Multimedia Information Systems; Older people; Remote searching; Special Purpose and Application-Based Systems; Track 2: Medical Applications of Multimedia; Health monitoring; Deep learning; Internet of Things (IoT); Elderly monitoring; ECG signal; Data mining; Clustering; Fall detection
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-15820-0

In recent years, the elderly population has increased, which requires more research on their health status. IoT has revolutionized device connectivity and remote access, making it an ideal solution for medical telemetry. Various plans have been presented to use the Internet of Things in the field of health. One of these plans is a fall detection system and notification to health centres and elderly families. One of the most critical requirements of fall detection algorithms is their accuracy. It is essential that the fall detection algorithm does not falsely send an alert to the elderly family, nurse or physician. Therefore, the accuracy of the fall detection algorithm should be increased by adding other techniques. In the proposed method of this research, this issue is solved by providing an intelligent framework based on clustering and ECG signal. The accuracy rate of the proposed detection algorithm is 97.1%.