Lifting Activity Assessment Using Kinematic Features and Neural Networks

Work-related low-back disorders (WLBDs) can be caused by manual lifting tasks. Wearable devices used to monitor these tasks can be one possible way to assess the main risk factors for WLBDs. This study aims at analyzing the sensitivity of kinematic data to the risk level changes, and to define an instrument-based tool for risk classification by using kinematic data and artificial neural networks (ANNs). Twenty workers performed lifting tasks, designed by following the rules of the revised NIOSH lifting equation, with an increasing lifting index (LI). From the acquired kinematic data, we computed smoothness parameters together with kinetic, potential and mechanical energy. We used ANNs for mapping different set of features on LI levels to obtain an automatic risk estimation during these tasks. The results show that most of the calculated kinematic indexes are significantly affected by changes in LI and that all the lifting condition pairs can be correctly distinguished. Furthermore, using specific set of features, different topologies of ANNs can lead to a reliable classification of the biomechanical risk related to lifting tasks. In particular, the training sets and numbers of neurons in each hidden layer influence the ANNs performance, which is instead independent from the numbers of hidden layers. Reliable biomechanical risk estimation can be obtained by using training sets combining body and load kinematic features.

[1]  P G Dempsey,et al.  Influence of measurement accuracy on the application of the 1991 NIOSH equation. , 2001, Applied ergonomics.

[2]  L. Naing,et al.  Practical Issues in Calculating the Sample Size for Prevalence Studies , 2006 .

[3]  Frank Krause,et al.  Exoskeletons for industrial application and their potential effects on physical work load , 2016, Ergonomics.

[4]  P G Dempsey,et al.  A new approach to applying feedforward neural networks to the prediction of musculoskeletal disorder risk. , 2000, Applied ergonomics.

[5]  R. Fillingim,et al.  Sex, gender, and pain: a review of recent clinical and experimental findings. , 2009, The journal of pain : official journal of the American Pain Society.

[6]  A Garg,et al.  Revised NIOSH equation for the design and evaluation of manual lifting tasks. , 1993, Ergonomics.

[7]  Jose Antonio Diego-Mas,et al.  Applying generalised feedforward neural networks to classifying industrial jobs in terms of risk of low back disorders , 2010 .

[8]  T. Waters,et al.  Evaluation of the revised NIOSH lifting equation. A cross-sectional epidemiologic study. , 1999, Spine.

[9]  Andrew Merryweather,et al.  The NIOSH Lifting Equation and Low-Back Pain, Part 1 , 2014, Hum. Factors.

[10]  Patrick G Dempsey,et al.  Usability of the revised NIOSH lifting equation , 2002, Ergonomics.

[11]  Kun Liu,et al.  Nondestructive Estimation of Muscle Contributions to STS Training with Different Loadings Based on Wearable Sensor System , 2018, Sensors.

[12]  Terry R. Rakes,et al.  The effect of sample size and variability of data on the comparative performance of artificial neural networks and regression , 1998, Comput. Oper. Res..

[13]  Edward Sazonov,et al.  A Comparative Review of Footwear-Based Wearable Systems , 2016 .

[14]  D. Cole,et al.  Individual participant data meta-analysis of mechanical workplace risk factors and low back pain. , 2012, American journal of public health.

[15]  S. Taboun,et al.  An Evaluation of the NIOSH Lifting Equation: A Psychophysical and Biomechanical Investigation , 2002, International journal of occupational safety and ergonomics : JOSE.

[16]  C. Lin,et al.  Lifting speed preferences and their effects on the maximal lifting capacity , 2016, Industrial health.

[17]  Silvia Conforto,et al.  Lifting activity assessment using surface electromyographic features and neural networks , 2018, International Journal of Industrial Ergonomics.

[18]  S A Lavender,et al.  Does the asymmetry multiplier in the 1991 NIOSH lifting equation adequately control the biomechanical loading of the spine? , 2009, Ergonomics.

[19]  Kamiar Aminian,et al.  Classification and characterization of postural transitions using instrumented shoes , 2017, Medical & Biological Engineering & Computing.

[20]  Tiwana Varrecchia,et al.  Erratum: Alberto, R. et al., Wearable Monitoring Devices for Biomechanical Risk Assessment at Work: Current Status and Future Challenges—A Systematic Review. Int. J. Environ. Res. Public Health 2018, 15, 2001 , 2018, International journal of environmental research and public health.

[21]  W S Marras,et al.  The effectiveness of commonly used lifting assessment methods to identify industrial jobs associated with elevated risk of low-back disorders. , 1999, Ergonomics.

[22]  Tiwana Varrecchia,et al.  Wearable Monitoring Devices for Biomechanical Risk Assessment at Work: Current Status and Future Challenges—A Systematic Review , 2018, International journal of environmental research and public health.

[23]  Bryan Buchholz,et al.  ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion--Part II: shoulder, elbow, wrist and hand. , 2005, Journal of biomechanics.

[24]  Patrick G. Dempsey,et al.  Application issues and theoretical concerns regarding the 1991 NIOSH equation asymmetry multiplier , 1999 .

[25]  W Karwowski,et al.  A neural network-based system for classification of industrial jobs with respect to risk of low back disorders due to workplace design. , 1997, Applied ergonomics.

[26]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[27]  T. Waters,et al.  Efficacy of the Revised NIOSH Lifting Equation to Predict Risk of Low Back Pain Due to Manual Lifting: Expanded Cross-Sectional Analysis , 2011, Journal of occupational and environmental medicine.

[28]  Donald S Bloswick,et al.  Evaluation and Quantification of Manual Materials Handling Risk Factors , 2003, International journal of occupational safety and ergonomics : JOSE.

[29]  Tadashi Masuda,et al.  Evaluation of the age-related changes in movement smoothness in the lower extremity joints during lifting. , 2010, Gait & posture.

[30]  S. Conforto,et al.  Mechanical lifting energy consumption in work activities designed by means of the “revised NIOSH lifting equation” , 2017, Industrial health.

[31]  S. Hunter,et al.  Sex differences in human fatigability: mechanisms and insight to physiological responses , 2014, Acta physiologica.

[32]  Mariano Serrao,et al.  A new muscle co-activation index for biomechanical load evaluation in work activities , 2015, Ergonomics.

[33]  Thomas R. Waters,et al.  Applications manual for the revised NIOSH lifting equation , 1994 .

[34]  Pascal Madeleine,et al.  Gender effects on the coordination of subdivisions of the trapezius muscle during a repetitive box-folding task , 2012, European Journal of Applied Physiology.

[35]  T. Lauritzen,et al.  The Association Between Physical Workload and Low Back Pain Clouded by the “Healthy Worker” Effect: Population-Based Cross-Sectional and 5-Year Prospective Questionnaire Study , 2001, Spine.

[36]  Cheng-Lung Lee,et al.  The Relationship between Low Back Discomfort Ratings and the NIOSH Lifting Index , 1998, Hum. Factors.

[37]  Silvia Conforto,et al.  Surface electromyography for risk assessment in work activities designed using the “revised NIOSH lifting equation” , 2018, International Journal of Industrial Ergonomics.

[38]  Tao Liu,et al.  A Wearable Ground Reaction Force Sensor System and Its Application to the Measurement of Extrinsic Gait Variability , 2010, Sensors.

[39]  M. Kjaer,et al.  Effect of acute resistance exercise and sex on human patellar tendon structural and regulatory mRNA expression. , 2009, Journal of applied physiology.

[40]  Thomas R. Waters,et al.  A Cross-Sectional Study of Risk Factors for Musculoskeletal Symptoms in the Workplace Using Data From the General Social Survey (GSS) , 2007, Journal of occupational and environmental medicine.