A Survey on Recent Advances in Wearable Fall Detection Systems

Area of Science:

• Geriatric Healthcare
• Medical Technology
• Machine Learning Applications

Background:

• Increased life expectancy leads to a growing elderly population needing care.
• Falls are a significant risk for older adults, especially in care settings.
• Machine learning (ML) offers potential solutions for improving geriatric healthcare, particularly in fall detection.

Purpose of the Study:

• To examine the requirements of a typical fall detection system (FDS).
• To survey recent advancements in ML-based FDSs.
• To analyze the challenges associated with current FDS systems.

Main Methods:

• Literature review of existing fall detection systems.
• Analysis of machine learning applications in FDS.
• Examination of FDS requirements and identified challenges.

Main Results:

• The study identifies key requirements for effective fall detection systems.
• A comprehensive survey of ML techniques applied to FDS is presented.
• Significant challenges in the development and implementation of FDS were analyzed.

Conclusions:

• Machine learning plays a crucial role in the advancement of geriatric fall detection systems.
• Addressing identified challenges is essential for improving the efficacy and adoption of FDS.
• Further research is needed to optimize ML-based FDS for enhanced elderly care.