Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements

Abstract

This chapter provides an overview of recent and promising Machine Learning applications, i.e. pose estimation, feature estimation, event detection, data exploration & clustering, and automated classification, in gait (walking and running) and sports biomechanics. It explores the potential of Machine Learning methods to address challenges in biomechanical workflows, highlights central limitations, i.e. data and annotation availability and explainability, that need to be addressed, and emphasises the importance of interdisciplinary approaches for fully harnessing the potential of Machine Learning in gait and sports biomechanics.

References in corpus (19)

• XGBoost: A Scalable Tree Boosting System
• A Unified Approach to Interpreting Model Predictions
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
• Explaining the Unique Nature of Individual Gait Patterns with Deep Learning
• MoVi: A Large Multipurpose Motion and Video Dataset
• On the Explanation of Machine Learning Predictions in Clinical Gait Analysis
• Measuring and modeling the motor system with machine learning
• Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning
• Automatic Classification of Functional Gait Disorders
• KAVAGait: Knowledge-Assisted Visual Analytics for Clinical Gait Analysis
• Predicting gait events from tibial acceleration in rearfoot running: a structured machine learning approach
• Explaining automated gender classification of human gait
• Explaining machine learning models for age classification in human gait analysis
• Trustworthy Visual Analytics in Clinical Gait Analysis: A Case Study for Patients with Cerebral Palsy
• Self-Expressive Subspace Clustering to Recognize Motion Dynamics of a Multi-Joint Coordination for Chronic Ankle Instability
• Bounded logit attention: Learning to explain image classifiers