An intelligent video-monitoring system to detect falls: a proof of concept. Issue 4 (7th November 2018)

• Record Type: Journal Article
• Authors: Lapierre, Nolwenn; Meunier, Jean; St-Arnaud, Alain; Rousseau, Jacqueline
• Is Part Of: Journal of enabling technologies. Volume 12:Issue 4(2018)
• Page Start: 155
• Page End: 168
• Publication Date: 2018-11-07
• Subjects: Technology -- Older adults -- Ageing in place -- Camera -- Fall -- Video-monitoring; Self-help devices for people with disabilities -- Periodicals; Computerized self-help devices for people with disabilities -- Periodicals; People with disabilities -- Orientation and mobility -- Periodicals; People with disabilities -- Rehabilitation -- Technological innovations -- Periodicals; 617.033
• DOI: 10.1108/JET-04-2018-0022
• Languages: English
• ISSNs: 2398-6263

Abstract

Abstract : Purpose: To face the challenges raised by the high incidence of falls among older adults, the intelligent video-monitoring system (IVS), a fall detection system that respects privacy, was developed. Most fall detection systems are tested only in laboratories. The purpose of this paper is to test the IVS in a simulation context (apartment-laboratory), then at home. Design/methodology/approach: This study is a proof of concept including two phases: a simulation study to test the IVS in an apartment-laboratory (29 scenarios of activities including falls); and a 28-day pre-test at home with two young occupants. The IVS's sensitivity (Se), specificity (Sp), accuracy (A) and error rate (E) in the apartment-laboratory were calculated, and functioning at home was documented in a logbook. Findings: For phase 1, results are: Se =91.67 per cent, Sp =99.02 per cent, A=98.25 per cent, E=1.75. For phase 2, the IVS triggered four false alarms and some technical dysfunctions appeared (e.g. computer screen never turning off) that are easily overcome. Practical implications: Results show the IVS's efficacy at automatically detecting falls at home. Potential issues related to future installation in older adults' homes were identified. This proof of concept led to recommendations about the installation and calibration of a camera-based fall detection system. Originality/value: This paper highlights the potentialities of a camera-based fall detection system in real-world contexts and supports the use of the IVS to help older adults age in place.