Machine Learning Techniques for Motion Analysis of Fatigue from Manual Material Handling Operations Using 3D Motion Capture Data

Industrial Revolution 4.0 is defined as the interconnection of Information, Communications Technologies (ICT), and factory floor workers. Workers in the material handling industry are often subject to repetitive motions that cause exhaustion (or fatigue) which leads to work-related musculoskeletal disorders (WMSDs). The most common repetitive motions are lifting, pulling, pushing, carrying and walking with load. In this research data is collected as time-stamped motion data using infrared cameras at a rate of 100Hz while a subject performs one of the repetitive motions (i.e. lifting). The data is a combination of xyz-coordinates of 39 reflective markers. This results in 117 data points for each frame captured. Since these motions occur over time for a duration of time, this data is used as input to a time-series machine learning (ML) model such as Recurrent Neural Network (RNN). Using this model, this paper evaluates machine learning techniques, based on RNN, to evaluate the fatigue factor caused by repetitive motions.

[1]  Gábor Petneházi,et al.  Recurrent Neural Networks for Time Series Forecasting , 2018, ArXiv.

[2]  R. Saravanan,et al.  A State of Art Techniques on Machine Learning Algorithms: A Perspective of Supervised Learning Approaches in Data Classification , 2018, 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS).

[3]  Birgit Vogel-Heuser,et al.  Guest Editorial Industry 4.0-Prerequisites and Visions , 2016, IEEE Trans Autom. Sci. Eng..

[4]  Dragan Vuksanović,et al.  INDUSTRY 4.0: THE FUTURE CONCEPTS AND NEW VISIONS OF FACTORY OF THE FUTURE DEVELOPMENT , 2016 .

[5]  Daria Battini,et al.  Innovative real-time system to integrate ergonomic evaluations into warehouse design and management , 2014, Comput. Ind. Eng..

[6]  Wannes Meert,et al.  Fatigue Prediction in Outdoor Runners Via Machine Learning and Sensor Fusion , 2018, KDD.

[7]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[8]  B. Koes,et al.  Repetitive strain injury , 1987, The Lancet.

[9]  Zahra Sedighi Maman,et al.  A data-driven approach to modeling physical fatigue in the workplace using wearable sensors. , 2017, Applied ergonomics.

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  Fazel Naghdy,et al.  Human motion capture sensors and analysis in robotics , 2011, Ind. Robot.

[12]  Klaus Bengler,et al.  Repetitive Lifting Tasks in Logistics – Effects on Humans at Different Lifting Task Durations , 2016 .

[13]  Marcus Yung,et al.  Fatigue at the Workplace: Measurement and Temporal Development , 2016 .

[14]  D. Quarcoo,et al.  Work-related musculoskeletal disorders in the automotive industry due to repetitive work - implications for rehabilitation , 2010, Journal of occupational medicine and toxicology.

[15]  Miguel A Perez,et al.  A neural network model for predicting postures during non-repetitive manual materials handling tasks , 2008, Ergonomics.

[16]  M. Sharpe,et al.  A Report–Chronic Fatigue Syndrome: Guidelines for Research , 1991, Journal of the Royal Society of Medicine.

[17]  Franck Multon,et al.  Validation of an ergonomic assessment method using Kinect data in real workplace conditions. , 2017, Applied ergonomics.

[18]  G. Borg.  Psychophysical scaling with applications in physical work and the perception of exertion. , 1990, Scandinavian journal of work, environment & health.

[19]  Madalina Fiterau,et al.  Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities. , 2018, Journal of biomechanics.

[20]  Sunwook Kim,et al.  An evaluation of classification algorithms for manual material handling tasks based on data obtained using wearable technologies , 2014, Ergonomics.

[21]  Gabriele Bleser,et al.  Innovative system for real-time ergonomic feedback in industrial manufacturing. , 2013, Applied ergonomics.

[22]  Kolja Kuhnlenz,et al.  Expression and Automatic Recognition of Exhaustion in Natural Walking , 2008 .

[23]  Michelle Karg,et al.  Human Movement Analysis as a Measure for Fatigue: A Hidden Markov-Based Approach , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  Michael J. Black,et al.  On Human Motion Prediction Using Recurrent Neural Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Fadel M. Megahed,et al.  Understanding Fatigue and the Implications for Worker Safety , 2016 .

[26]  Andreja Rojko,et al.  Industry 4.0 Concept: Background and Overview , 2017, Int. J. Interact. Mob. Technol..

[27]  Joana Guedes,et al.  Evaluation of physical fatigue based on motion analysis , 2019 .

[28]  Silvio Savarese,et al.  Structural-RNN: Deep Learning on Spatio-Temporal Graphs , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.