Fall prediction using behavioural modelling from sensor data in smart homes.

Forbes, Glenn; Massie, Stewart; Craw, Susan

Abstract

The number of methods for identifying potential fall risk is growing as the rate of elderly fallers continues to rise in the UK. Assessments for identifying risk of falling are usually performed in hospitals and other laboratory environments, however these are costly and cause inconvenience for the subject and health services. Replacing these intrusive testing methods with a passive in-home monitoring solution would provide a less time-consuming and cheaper alternative. As sensors become more readily available, machine learning models can be applied to the large amount of data they produce. This can support activity recognition, falls detection, prediction and risk determination. In this review, the growing complexity of sensor data, the required analysis, and the machine learning techniques used to determine risk of falling are explored. The current research on using passive monitoring in the home is discussed, while the viability of active monitoring using vision-based and wearable sensors is considered. Methods of fall detection, prediction and risk determination are then compared.

Citation

FORBES, G., MASSIE, S. and CRAW, S. 2020. Fall prediction using behavioural modelling from sensor data in smart homes. Artificial intelligence review [online], 53(2), pages 1071-1091. Available from: https://doi.org/10.1007/s10462-019-09687-7

• Journal Article Type: Article
• Acceptance Date: Feb 1, 2019
• Online Publication Date: Mar 16, 2019
• Publication Date: Feb 29, 2020
• Deposit Date: Feb 18, 2019
• Publicly Available Date: Feb 18, 2019
• Journal: Artificial intelligence review
• Print ISSN: 0269-2821
• Electronic ISSN: 1573-7462
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 53
• Issue: 2
• Pages: 1071-1091
• DOI: https://doi.org/10.1007/s10462-019-09687-7
• Keywords: Prediction; Sensor data; Data analytics; Health
• Public URL: http://hdl.handle.net/10059/3300
• Contract Date: Feb 18, 2019