Infinite ensemble of support vector machines for prediction of musculoskeletal disorders risk

Several modeling techniques have been used to classify the low-back disorders (LBDs) risk associated with the industrial jobs. Many researchers have demonstrated the use of artificial neural networks (ANNs) to predict musculoskeletal disorders risk associated with occupational exposures. In order to improve the accuracy of LBDs risk classification, this paper proposes to use the support vector machines (SVMs), a machine learning algorithm used extensively in the last decade. The results of SVMs based ensemble classification approach to classify the low-back disorders (LBDs) risk associated with the industrial jobs are presented. Four different kernels (i.e. the stump kernel, perceptron kernel, Laplacian kernel and exponential kernel) were used to create infinite ensemble of SVMs and their performance have been compared with the SVMs, AdaBoost SVMs, and a backpropagation neural network. The results suggest an increased performance by stump and Laplacian kernel in comparison to the radial basis function and polynomial kernel based SVMs, AdaBoost SVMs, and the back propagation neural network. Highest classification accuracy of 77.01% was achieved by Laplacian kernel based SVMs in comparison to 71.3% and 74.7% by radial basis function kernel based SVMs and back propagation neural network respectively.

[1]  Gunnar Rätsch,et al.  Soft Margins for AdaBoost , 2001, Machine Learning.

[2]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[3]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[4]  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.

[5]  J. M. Najeb,et al.  Efficient Parameter Selection of Support Vector Machines , 2008 .

[6]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[7]  Ignacio Méndez-Ramírez,et al.  Computer use increases the risk of musculoskeletal disorders among newspaper office workers. , 2003, Archives of medical research.

[8]  B. Bernard,et al.  Musculoskeletal disorders and workplace factors: a critical review of epidemiologic evidence for work-related musculoskeletal disorders of the neck, upper extremity, and low back , 1997 .

[9]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[10]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

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

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[13]  W. G. Allread,et al.  The Role of Dynamic Three-Dimensional Trunk Motion in Occupationally-Related Low Back Disorders: The Effects of Workplace Factors, Trunk Position, and Trunk Motion Characteristics on Risk of Injury , 1993, Spine.

[14]  S H Snook,et al.  The cost of compensable upper extremity cumulative trauma disorders. , 1994, Journal of occupational medicine. : official publication of the Industrial Medical Association.

[15]  V Putz-Anderson,et al.  Prevalence and work-relatedness of self-reported carpal tunnel syndrome among U.S. workers: analysis of the Occupational Health Supplement data of 1988 National Health Interview Survey. , 1995, American journal of industrial medicine.

[16]  Mahesh Pal,et al.  Ensemble Learning with Decision Tree for Remote Sensing Classification , 2007 .

[17]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[18]  V Putz-Anderson,et al.  Back pain among workers in the United States: national estimates and workers at high risk. , 1995, American journal of industrial medicine.

[19]  Paul M. Mather,et al.  Ensemble of support vector machines for land cover classification , 2008, ArXiv.

[20]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[21]  Ayhan Demiriz,et al.  Linear Programming Boosting via Column Generation , 2002, Machine Learning.

[22]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[23]  Patrick G. Dempsey,et al.  Developing explicit risk models for predicting low-back disability: A statistical perspective , 1997 .