A comprehensive comparison of accuracy and practicality of different types of algorithms for pre-impact fall detection using both young and old adults. (30th September 2022)

• Record Type: Journal Article
• Authors: Yu, Xiaoqun; Koo, Bummo; Jang, Jaehyuk; Kim, Youngho; Xiong, Shuping
• Is Part Of: Measurement. Volume 201(2022)
• Publication Date: 2022-09-30
• Subjects: Algorithm comparison -- Fall risk -- Inertial sensor -- Machine learning -- Pre-impact fall detection; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.111785
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Pre-impact fall detection is critical for fall injury prevention of old people. A comprehensive comparison of three pre-impact fall detection algorithms was conducted. Large-scale motion datasets from both young and old adults were used. Deep learning algorithm showed superior accuracy and high practicality. Deep learning algorithm had robust performance on external validation of old adults. Abstract: This study aims to comprehensively compare the accuracy and practicality of three different types of algorithms for pre-impact fall detection using both young and old subjects. Threshold-based, conventional machine learning (SVM) and deep learning (ConvLSTM) algorithms were compared. Results showed that ConvLSTM had an accuracy of 99.16 % (sensitivity: 99.32 %, specificity: 99.01 %) and an averaged lead time of 403 ms on young subjects, which outperformed SVM (97.16 %, 385 ms) and much superior to the threshold-based algorithm (89.06 %, 333 ms). In addition, latency tests on an embedded device showed that the Lite model of ConvLSTM had a low latency of 2.1 ms, which was comparable to the threshold-based algorithm (<1 ms) but much lower than SVM (86.9 ms). The feasibility and effectiveness of applying algorithms trained on young subjects to old subjects were also validated. These findings suggested that ConvLSTM has great potential for detecting pre-impact falls and preventing fall-related injuries.