Comparison of four machine learning algorithms for a pre-impact fall detection system
Authors:
- 31 May 2023
- journal article
- research article
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 61 (8) , 1961-1974
Abstract
In recent years, real-time health monitoring using wearable sensors has been an active area of research. This paper presents an efficient and low-cost fall detection system based on a pair of shoes equipped with inertial sensors and plantar pressure sensors. In addition, four machine learning algorithms (KNN, SVM, RF, and BP neural network) are compared in terms of their detection performance and suitability for pre-impact fall detection. The results show that KNN and BP neural network outperformed the other two algorithms, where KNN had 98.8% sensitivity, 99.8% specificity, and 99.7% accuracy, and BP neural network had 100% sensitivity, 99.8% specificity, and 99.9% accuracy. KNN outperformed BP neural network in terms of fitting ability, and their lead times were both 460.95 ms. The system can provide sufficient intervention time for the wearer in the pre-impact phase and together with the touchdown fall protection device can effectively prevent fall injuries. Graphical AbstractKeywords
Funding Information
- Science and Technology Innovation Plan Of Shanghai Science and Technology Commission (19DZ2203600)
This publication has 40 references indexed in Scilit:
- An individual-specific fall detection model based on the statistical process control chartSafety Science, 2014
- Pre-Impact Fall Detection: Optimal Sensor Positioning Based on a Machine Learning ParadigmPLOS ONE, 2014
- Risk factors for falls among older adults: A review of the literatureMaturitas, 2013
- A survey on fall detection: Principles and approachesNeurocomputing, 2013
- Exploration and Implementation of a Pre-Impact Fall Recognition Method Based on an Inertial Body Sensor NetworkSensors, 2012
- Growing trend in older patients with severe injuries: mortality and mechanisms of injury between 1991 and 2010 at an inner city major trauma centreAnz Journal of Surgery, 2012
- A video‐based human fall detection system for smart homesJournal of the Chinese Institute of Engineers, 2010
- A proposal for the classification and evaluation of fall detectorsIRBM, 2008
- Balance control on a moving platform in unilateral lower limb amputeesGait & Posture, 2008
- Geriatric injury: An analysis of prehospital demographics, mechanisms, and patternsAnnals of Emergency Medicine, 1990