The objective of this study was to develop an algorithm for automatically processing data collected with inertial measurement unit (IMU) wearable devices to measure lifting risk factors for low back disorders. Five IMU sensors attached to five body segments were used for developing the algorithm. The algorithm consists of two modules running in parallel for detecting the beginning and ending of a lifting event as well as the vertical height (V) of the object lifted by two hands and the horizontal (H) distance between the object and the body during the lift. The motion synchronization feature of wrists’ motion data were used to train the lifting detection module using a machine learning approach. This module achieved a training accuracy of 85%. In the second module, the forearm length and gyroscope data of four sensors are proposed for calculating trunk flexion angle, V and H during a lift.
References
1.
AttalF.MohammedS.DedabrishviliM.ChamroukhiF.OukhellouL.AmiratY. (2015). Physical human activity recognition using wearable sensors. Sensors, 15(12), 31314-31338.
2.
BattiniD.PersonaA.SgarbossaF. (2014). Innovative real-time system to integrate ergonomic evaluations into warehouse design and management. Computers & Industrial Engineering, 77, 1-10.
3.
BernardB. P. (1997). A critical review of epidemiologic evidence for work-related musculoskeletal disorders of the neck, upper extremety, and low back. U.S. Department of Health and Human Services, Center for Disease Control and Prevention, National Institute for Occupational Health and Safety.
4.
BhattacharyaA.WarrenJ.TeuschlerJ.DimovM.MedvedovicM.LemastersG. (1999). Development and evaluation of a microprocessor-based ergonomic dosimeter for evaluating carpentry tasks. Applied ergonomics, 30(6), 543-553.
5.
BullingA.BlankeU.SchieleB. (2014). A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR), 46(3), 33.
6.
CallaghanJ. P.SalewytschA. J.AndrewsD. M. (2001). An evaluation of predictive methods for estimating cumulative spinal loading. Ergonomics, 44(9), 825-837.
7.
ChaffinD.B.AnderssonG.B.J.MartinB.J. (1999). Occupational Biomechanics. New York: Wiley.
8.
da CostaB. R.VieiraE. R. (2010). Risk factors for work related musculoskeletal disorders: a systematic review of recent longitudinal studies. American journal of industrial medicine, 53(3), 285-323.
9.
DahlqvistC.HanssonG. Å.ForsmanM. (2016). Validity of a small low-cost triaxial accelerometer with integrated logger for uncomplicated measurements of postures and movements of head, upper back and upper arms. Applied ergonomics, 55, 108-116.
10.
FoxlinE. (1996, March). Inertial head-tracker sensor fusion by a complementary separate-bias Kalman filter. In Virtual Reality Annual International Symposium, (p. 185) Proceedings of the IEEE.
11.
FreivaldsA.KongY.YouH.ParkS. (2000, July). A comprehensive risk assessment model for work-related musculoskeletal disorders of the upper extremities. In Proceedings of Human Factors and Ergonomics Society Annual Meeting, (Vol. 44, No. 31, pp. 5-728). Sage CA: Los Angeles, CA: SAGE Publications.
12.
HeZ.JinL. (2009, October). Activity recognition from acceleration data based on discrete consine transform and SVM. In IEEE International Conference on Systems, Man and Cybernetics (pp. 5041-5044). IEEE.
13.
LeeH. J.JungS. (2009, February). Gyro sensor drift compensation by Kalman filter to control a mobile inverted pendulum robot system. In 2009 IEEE International Conference on Industrial Technology (pp. 1-6). IEEE.
14.
LiawA.WienerM. (2002). Classification and regression by randomForest. R news, 2(3), 18-22.
15.
Liberty Mutual Research Institute for Safety (2014). Liberty Mutual Workplace Safety Index, Liberty Mutual 175 Berkeley St., Boston, MA 02116.
16.
LuoX.PietrobonR.SunS. X.LiuG. G.HeyL. (2004). Estimates and patterns of direct health care expenditures among individuals with back pain in the United States. Spine, 29(1), 79-86.
17.
LuM. L.WatersT. R.KriegE.WerrenD. (2014). Efficacy of the revised NIOSH lifting equation to predict risk of low-back pain associated with manual lifting: a one-year prospective study. Human factors, 56(1), 73-85.
18.
LuM. L.WatersT.WerrenD. (2015). Development of human posture simulation method for assessing posture angles and spinal loads. Human Factors and Ergonomics in Manufacturing & Service Industries, 25(1), 123-136.
19.
MarrasW. S.FathallahF. A.MillerR. J.DavisS. W.MirkaG. A. (1992). Accuracy of a three-dimensional lumbar motion monitor for recording dynamic trunk motion characteristics. International Journal of Industrial Ergonomics, 9(1), 75-87.
20.
Moncada-TorresA.LeuenbergerK.GonzenbachR.LuftA.GassertR. (2014). Activity classification based on inertial and barometric pressure sensors at different anatomical locations. Physiological measurement, 35(7), 1245.
21.
National Research Council (2001). Musculoskeletal Disorders and the workplace: low back and upper extremities. Washington, DC.
22.
PowersD. M. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.
23.
RadwinR.G.LinM.L. (1993). An analytical method for characterizing repetitive motion and postural stress using spectral-analysis. Ergonomics, 36, 379-389.
24.
RigatosG.TzafestasS. (2007). Extended Kalman filtering for fuzzy modelling and multi-sensor fusion. Mathematical and computer modelling of dynamical systems, 13(3), 251-266.
25.
SpriggsE. H.DeLaTorreF.HebertM. (2009, June). Temporal segmentation and activity classification from first-person sensing. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 17-24). IEEE.
26.
WatersT.R.Putz-AndersonV.GargA. (1994) Applications Manual for the Revised NIOSH Lifting Equation. DHHS (NIOSH) Pub. No. 94–110. U. S. Department of Health and Human Services, National Institute for Occupational Safety and Health, Cincinnati, OH.
27.
YouS.NeumannU. (2001, March). Fusion of vision and gyro tracking for robust augmented reality registration. In Proceedings IEEE Virtual Reality 2001 (pp. 71-78). IEEE.
