Automated Classification of the Phases Relevant to Work-Related Musculoskeletal Injury Risks in Residential Roof Shingle Installation Operations Using Machine Learning

Awkward kneeling in sloped shingle installation operations exposes roofers to knee musculoskeletal disorder (MSD) risks. To address the varying levels of risk associated with different phases of shingle installation, this research investigated utilizing machine learning to automatically classify seven distinct phases in a typical shingle installation task. The classification process relied on analyzing knee kinematics data and roof slope information. Nine participants were recruited and performed simulated shingle installation tasks while kneeling on a sloped wooden platform. The knee kinematics data were collected using an optical motion capture system. Three supervised machine learning classification methods (i.e., k-nearest neighbors (KNNs), decision tree (DT), and random forest (RF)) were selected for evaluation. The KNN classifier provided the best performance for overall accuracy. The results substantiated the feasibility of applying machine learning in classifying shingle installation phases from workers’ knee joint rotation and roof slope angles, which may help facilitate method and tool development for automated knee MSD risk surveillance and assessment among roofers.

[1]  M. Palaniswami,et al.  Real-time monitoring of construction sites: Sensors, methods, and applications , 2022, Automation in Construction.

[2]  Chen Yang,et al.  IoT and digital twin enabled smart tracking for safety management , 2021, Comput. Oper. Res..

[3]  Huaijun Wang,et al.  Non-Linear Chaotic Features-Based Human Activity Recognition , 2021, Electronics.

[4]  Yohan Payan,et al.  Biomechanical monitoring and machine learning for the detection of lying postures. , 2020, Clinical biomechanics.

[5]  Robert E. Carey,et al.  Effects of working posture and roof slope on activation of lower limb muscles during shingle installation , 2020, Ergonomics.

[6]  John Z. Wu,et al.  Identifying Potentially Risky Phases Leading to Knee Musculoskeletal Disorders during Shingle Installation Operations , 2020 .

[7]  Zaccaria Del Prete,et al.  Measuring Biomechanical Risk in Lifting Load Tasks Through Wearable System and Machine-Learning Approach , 2020, Sensors.

[8]  A Plamondon,et al.  A machine-learning method for classifying and analyzing foot placement: Application to manual material handling. , 2019, Journal of biomechanics.

[9]  John Z. Wu,et al.  Assessing work-related risk factors for musculoskeletal knee disorders in construction roofing tasks. , 2019, Applied ergonomics.

[10]  Robert E. Carey,et al.  Are knee savers and knee pads a viable intervention to reduce lower extremity musculoskeletal disorder risk in residential roofers? , 2019, International journal of industrial ergonomics.

[11]  Yantao Yu,et al.  Wearable insole pressure system for automated detection and classification of awkward working postures in construction workers , 2018, Automation in Construction.

[12]  Theodora Chaspari,et al.  Automated ergonomic risk monitoring using body-mounted sensors and machine learning , 2018, Adv. Eng. Informatics.

[13]  B. Hu,et al.  Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking. , 2018, Journal of biomechanics.

[14]  Ehsan T. Esfahani,et al.  A machine learning approach to detect changes in gait parameters following a fatiguing occupational task , 2018, Ergonomics.

[15]  Carl T. Haas,et al.  Identifying poses of safe and productive masons using machine learning , 2017 .

[16]  Christian Desrosiers,et al.  Wearable Devices for Classification of Inadequate Posture at Work Using Neural Networks , 2017, Sensors.

[17]  Fei Dai,et al.  Assessing Work-Related Risk Factors on Low Back Disorders among Roofing Workers. , 2017, Journal of construction engineering and management.

[18]  Jun Qiu,et al.  Construction worker's awkward posture recognition through supervised motion tensor decomposition , 2017 .

[19]  Matthew R. Hallowell,et al.  Application of machine learning to construction injury prediction , 2016 .

[20]  Xiaopeng Ning,et al.  The changes of lumbar muscle flexion-relaxation phenomenon due to antero-posteriorly slanted ground surfaces , 2016, Ergonomics.

[21]  L. Welch,et al.  Best practices for health and safety technology transfer in construction. , 2015, American journal of industrial medicine.

[22]  Fei Dai,et al.  Risk Assessment of Work-Related Musculoskeletal Disorders in Construction: State-of-the-Art Review , 2015 .

[23]  A. Nimbarte,et al.  The assessment of material-handling strategies in dealing with sudden loading: the effect of uneven ground surface on trunk biomechanical responses , 2015, Ergonomics.

[24]  Jane Labadin,et al.  Non-linear feature selection-based hybrid computational intelligence models for improved natural gas reservoir characterization , 2014 .

[25]  Sotiris B. Kotsiantis,et al.  Decision trees: a recent overview , 2011, Artificial Intelligence Review.

[26]  Jacek M. Zurada,et al.  Classifying the risk of work related low back disorders due to manual material handling tasks , 2012, Expert Syst. Appl..

[27]  José Augusto Baranauskas,et al.  How Many Trees in a Random Forest? , 2012, MLDM.

[28]  Shichao Zhang,et al.  Noisy data elimination using mutual k-nearest neighbor for classification mining , 2012, J. Syst. Softw..

[29]  M. Redfern,et al.  Forces and moments on the knee during kneeling and squatting. , 2011, Journal of applied biomechanics.

[30]  M. McGarry,et al.  Effects on tibiofemoral biomechanics from kneeling. , 2011, Clinical biomechanics.

[31]  J. Barrios,et al.  Gait retraining to reduce the knee adduction moment through real-time visual feedback of dynamic knee alignment. , 2010, Journal of biomechanics.

[32]  K. Hunting,et al.  Impact of musculoskeletal and medical conditions on disability retirement-a longitudinal study among construction roofers. , 2010, American journal of industrial medicine.

[33]  Katherine L Hunting,et al.  Musculoskeletal disorders among construction roofers--physical function and disability. , 2009, Scandinavian journal of work, environment & health.

[34]  Sang D. Choi,et al.  Postural Balance and Adaptations in Transitioning Sloped Surfaces , 2008 .

[35]  Taghi M. Khoshgoftaar,et al.  An Empirical Study of Learning from Imbalanced Data Using Random Forest , 2007, 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007).

[36]  Larry A. Lambe,et al.  Decision trees for binary classification variables grow equally with the Gini impurity measure and Pearson's chi-square test , 2007, Int. J. Bus. Intell. Data Min..

[37]  R Begg,et al.  A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. , 2005, Journal of biomechanics.

[38]  D. Gordon E. Robertson,et al.  Research Methods in Biomechanics , 2004 .

[39]  Waldemar Karwowski,et al.  Occupational Ergonomics : Design and Management of Work Systems , 2003 .

[40]  Thomas P Andriacchi,et al.  Mechanical loads at the knee joint during deep flexion , 2001, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[41]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[42]  Nick Roussopoulos,et al.  Nearest neighbor queries , 1995, SIGMOD '95.

[43]  William R Taylor,et al.  Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors , 2016, BioMed research international.

[44]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[45]  Shengyi Jiang,et al.  An improved K-nearest-neighbor algorithm for text categorization , 2012, Expert Syst. Appl..

[46]  Azriel Rosenfeld,et al.  Machine Learning and Data Mining in Pattern Recognition , 2000, Lecture Notes in Computer Science.

[47]  J. Herman.  Health , 1996, Annals of Internal Medicine.