Latest Research Trends in Fall Detection and Prevention Using Machine Learning: A Systematic Review

Area of Science:

• Gerontology
• Computer Science
• Biomedical Engineering

Background:

• Falls pose a significant health risk to the aging population, necessitating advanced detection and prevention systems.
• Existing research often focuses on older methods, wearables, and statistical approaches with high false alarm rates.
• The increasing elderly demographic underscores the urgent need for improved fall management technologies.

Purpose of the Study:

• To present the latest research trends in fall detection and prevention systems.
• To analyze recent studies, focusing on datasets, age groups, machine learning algorithms, sensors, and location.
• To provide a comprehensive overview to guide future research and development in this field.

Main Methods:

• Systematic review of recent scientific literature on fall detection and prevention.
• Analysis of studies employing Machine Learning (ML) algorithms.
• Categorization and comparison of systems based on datasets, age groups, ML algorithms, sensors, and deployment location.

Main Results:

• Identified key trends in the application of ML for fall detection and prevention.
• Analyzed the performance and characteristics of various ML algorithms and sensor technologies.
• Highlighted limitations of current approaches, including high false alarm rates in older methods.

Conclusions:

• Machine learning offers promising advancements for fall detection and prevention systems.
• Further research is needed to address current limitations and develop more accurate and reliable solutions.
• This review provides a foundation for researchers to propose novel methodologies and improve existing systems for elderly fall safety.