Monitoring worker fatigue using wearable devices: A case study to detect changes in gait parameters

Abstract

The goal of this case study is to answer four research questions related to fatigue through features derived from wearable sensors to measure patterns in steps: (1) How do important gait parameters change over time? (2) How do these sensor-based changes relate to the participant's subjective fatigue ratings over time? (3) Are there consistent patterns in performance across different individuals over time? and (4) Do these patterns vary systematically based on specific demographic characteristics? To answer these questions, we have combined multivariate changepoint methods with hierarchical time-series clustering and exploratory data analysis. The results improve our understanding of fatigue development.

Keywords:

• clustering
• internet of people
• median filter
• nonparametric multivariate inference
• signal processing

About the authors

Amir Baghdadi received the B.Sc. degree from the Sharif University of Technology, Tehran, Iran, in 2014, and the M.Sc. and Ph.D. degrees in mechanical engineering from the University at Buffalo, State University of New York, NY, USA, in 2017 and 2019, respectively. He currently holds a postdoctoral associate position at Project neuroArm at the Department of Clinical Neurosciences, University of Calgary. Amir's work is toward the development of novel navigation algorithms utilizing machine learning for the neuroArmPLUS robotic system for neurosurgery. Amir was an Adjunct Faculty and an Instructor at The State University of New York College, Buffalo, and a Teaching Fellow with the Department of Mechanical and Aerospace Engineering, University at Buffalo. He was also a Research Affiliate with Roswell Park Cancer Institute, Buffalo, NY, USA, where he has utilized computer vision methods to model automated assessment of surgical performance during robot-assisted surgery; and developed an automated tool for benign and malignant kidney tumor classification from computed tomography (CT) images using convolutional neural network (CNN). His research interests include the intersection of health informatics, data science, sensor fusion, computer vision, and biomechanics. Email: [email protected]

Lora A. Cavuoto received her M.S. and Ph.D. degrees in Industrial and Systems Engineering from Virginia Tech, Blacksburg, VA, USA, in 2009 and 2012, respectively. She received her M.S. degree in occupational ergonomics and safety from the University of Miami, Coral Gables, FL, USA, in 2008. She is currently an Associate Professor in the Department of Industrial and Systems Engineering, where she directs the Ergonomics and Biomechanics Laboratory. Her current research interests include quantifying physical exposures and physiological responses in the workplace to identify indicators of fatigue development. Her research work also aims to understand and model the effects of health conditions, particularly obesity and aging, on physical capacity, specifically strength, fatigue, and motor performance. She is an Associate Editor for Human Factors and Ergonomics in Manufacturing & Service Industries and a Scientific Editor for Applied Ergonomics. Email: [email protected].

Allison Jones-Farmer is the Van Andel Professor of Business Analytics at Miami University in Oxford, Ohio. Her research focuses on developing practical methods for analyzing data in industrial and business settings. She is on the editorial review board of Journal of Quality Technology and Quality Engineering and is the current Editor for the Case Study section of JQT. Her email address is [email protected].

Steven E. Rigdon is a Professor of Biostatistics in the College for Public Health and Social Justice at Saint Louis University. He is also Distinguished Research Professor Emeritus at Southern Illinois University Edwardsville. In 2017 he was elected Fellow of the American Statistical Association. From 1996 to 2006 he served on the editorial board of the Journal of Quality Technology. He was a guest editor for Quality Engineering for a special issue containing papers from the 2018 Hunter Conference. Currently, he is the editor of the Journal of Quantitative Analysis in Sports. Email: [email protected].

Ehsan T. Esfahani received the M.S. degree in electrical engineering and the Ph.D. degree in mechanical engineering from the University of California Riverside, Riverside, CA, USA, in 2012. He is currently an Associate Professor with the Department of Mechanical and Aerospace Engineering, University at Buffalo-SUNY, Buffalo, NY, USA. His main research interests include human in the loop systems, human-robot interactions, human activity monitoring, and biorobotics. Email: [email protected].

Fadel M. Megahed received his M.S. and Ph.D. degrees in Industrial and Systems Engineering from Virginia Tech, Blacksburg, VA, USA, in 2009 and 2012, respectively. He is currently the Neil R. Anderson Assistant Professor in the Farmer School of Business at Miami University located in Oxford, OH. His current research focuses on creating new tools to store, organize, analyze, model, and visualize the large heterogeneous data sets associated with modern manufacturing, healthcare and service environments. He serves on the Editorial Board for the Journal of Quality Technology and the Journal of Financial Economic Policy. He is a member of ASQ. Email: [email protected].

Supplemental Materials (Data, Code and R Markdown)

To facilitate the replication of our work and encourage future work in this area, we provide the raw data and code in the following GitHub repository: https://github.com/fmegahed/fatigue-changepoint. The repository is divided into three main folders: (a) feature-engineering, which primarily consists of the MATLAB code that we have to perform the analysis of Section 3; (b) fatigue-changepoint, which contains the data and R code used for analysis in Sections 4–6; and (c) fmegahed.github.io, where we host the HTML generated by the R Markdown documenting the code and results obtained from Sections 4–6. In addition, we have created an HTML file based on our R Markdown, which we make available at https://fmegahed.github.io/fatigue_case_jqt.html. The HTML combines our code, analysis, and results. Thus, we consider it as an important part of our work that should be examined by the readers of this case study.