Semi-Supervised Learning Based Prediction of Musculoskeletal Disorder Risk

This study explores a semi-supervised classification approach using random forest as a baseclassifier to classify the low-back disorders (lbds) risk associated with the industrial jobs.semi-supervised classification approach uses unlabeled data together with the small number oflabelled data to create a better classifier. the results obtained by the proposed approach arecompared with those obtained by a backpropagation neural network. comparison indicates animproved performance by the semi-supervised approach over the random forest classifier aswell as neural network approach. highest classification accuracy of 78.20% was achieved bythe used semi-supervised approach with random forest as base classifier in comparison to anaccuracy of 72.4% and 74.7% obtained by random forest and back propagation neural networkapproaches respectively. thus results suggest that the proposed approach can successfullyclassify jobs into the low and high risk categories of low-back disorders based on lifting taskcharacteristics.