Skeleton-Based Posture Classification to Promote Safer Walker-Assisted Gait in Older Adults

TL;DR

This study compares various machine learning models, including geometric, XGBoost, SVM, and deep learning, for classifying walker usage and posture to improve safety in gait assistance for older adults.

Contribution

It evaluates and identifies the most effective models for classifying walker-related postures, highlighting the potential of machine learning to enhance smart walker safety.

Findings

XGBoost achieved 99.84% accuracy in walker choice classification.

Geometric approach attained 89.9% accuracy for 8 postures.

Deep learning models achieved over 98% accuracy in binary classification.

Abstract

Falls among older adults are a significant public health concern, leading to severe injuries, loss of independence, and increased healthcare costs. This study evaluates the effectiveness of various models, including a Geometric approach, XGBoost, SVM, and several deep learning architectures, in classifying walker usage, standing vs. sitting, and posture for smart walkers used. Geometric and XGBoost were the top performers. XGBoost achieved near-perfect training accuracy in binary classification tasks, with 99.84% for walker choice and 99.69% for standing vs. sitting. For posture classification, Geometric approach attained 89.9% accuracy for 8 postures, and XGBoost obtained 99.24% during training for 17 postures. Deep learning models such as the 4-layer CNN and Encoder-Decoder CNN also demonstrated strong performance in binary classification, with accuracies above 98%. This study underscores the potential of machine learning to enhance human-robot interaction in smart walkers, particularly for fall prevention.