Applications of Machine Learning in Human Factors and Ergonomics: A Comprehensive Review of Research From the Past Decade

This study provides a comprehensive literature review of 130 peer-reviewed journal articles published between 2015 and 2024 on the application of Machine Learning (ML) algorithms in Human Factors and Ergonomics (HFE). The selected studies cover eight key application areas, including Work-Related Musculoskeletal Disorders (WRMSDs), Mental Workload Assessment (MWLA), physical workload, and occupational safety. ML techniques examined include Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), Random Forest (RF), Decision Trees (DTs), K-Nearest Neighbors (KNN), Naive Bayes (NB), boosting algorithms, and k-means clustering. Among the reviewed articles, Artificial Neural Networks (ANNs) and Deep Learning (DL) methods were the most prevalent, at 36%, followed by Support Vector Machines (SVMs) at 22% and Random Forests (RF) at 19%. Performance benchmarks from these studies indicate classification accuracies ranging from 83% to 97.4% for tasks such as posture recognition, MWLA, and fatigue detection. For instance, ANN models for Electroencephalography (EEG)-based MWLA achieved up to 94% accuracy, while SVM classifiers reached up to 97.94% in posture classification. KNN, when optimized for k-values, yielded accuracy rates exceeding 90% in ergonomic applications. There was a marked increase in ML adoption in HFE post-2019, with 2020 publications nearly doubling compared to 2019. This review not only benchmarks algorithmic performance but also identifies research gaps and provides guidance for future machine-learning applications in human factors, ergonomics, and human-centered systems design.