Related Experiment Video
Updated: Jun 29, 2026
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
Published on: February 8, 2019
Artificial intelligence for fall detection in older adults: A comprehensive survey of machine learning, deep learning
Akshat Gattani1, Shriniket Dixit1, Mrudul Patil1
1School of Computer Science and Engineering, Vellore Institute of Technology, Vellore 632014, India.
Abstract:
Fall detection systems are crucial for ensuring the safety of older adults, given the potential for severe injuries resulting from falls. However, developing accurate and reliable detection methods faces challenges due to the rarity of fall events and limited training data. This review provides an in-depth examination of recent progress in fall detection technologies for older adults, with particular attention to addressing the scarcity of data. This review is novel in that it integrates regulatory frameworks for AI-driven systems; spans diverse fields, including engineering, computer science, and gerontology; and establishes clear connections between fall detection and conditions such as osteoporosis and neurological disorders. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines to select articles on sensor- and vision-based methodologies and machine learning (ML) algorithms for fall detection. Research findings indicate several strengths, weaknesses, and areas where accuracy can be improved, specifically for older adults. This study introduces a taxonomy that categorizes fall detection methods according to the availability of data during classifier training, thereby providing a clearer understanding of the specific challenges these methods address. Some major findings include the effectiveness achieved through sensor fusion and machine learning, aimed at improving accuracy in detecting falls, especially when sparse data are available. Future research should explore novel sensor modalities, wearable integration, and real-time enhancements to machine learning models. Moreover, this review advances the development of robust AI-based fall detection systems for older adults by addressing key technical challenges and outlining pathways toward clinical translation and regulatory approval to enhance safety and quality of life in an aging society.
