Using the SVM Algorithm to determine the weight of factors affecting Disorders among Computer Users: Universities of Medical Sciences, 2018

Background: in the past 20 years, computers and their workplaces have increased at both offices and houses, which consequently has led to saving in time, energy and resources. This study aimed to investigate risk factors of musculoskeletal disorders among computer users through support vector machine.Materials & Methods: This study was performed in seven steps on users in this university. The steps including: 1) choosing effective variables of musculoskeletal disorders on computer users. 2) Evaluating effective variables on musculoskeletal disorders by ROSA. 3) Calculating the final figure (target) of musculoskeletal disorder of computer users (by ROSA method). 4) Data preprocessing. 5) Using support vector machine (SVM) to prioritize and weighting effective variables on musculoskeletal disorders. 6) Calculating the accuracy of SVM algorithm, and at least, 7) data analysis.Results: The average of final score of ROSA, chair, telephone-monitor and mouse-keyboard were 4.36± 0.91, 3.67± 1.06, 3.68± 1.09 and 3.66± 1.18 respectively. 131 Workstation (65.5%) had a score less than 5 16 & Workstation (34.5%) had a score equal to or greater than 5. Chair variable with a normalized weighting 37%; telephone-monitor variable with a normalized weighting 34% and finally mouse-keyboard variable with a weighting 29% were respectively effective variables on disorders caused by working with computers.Conclusions: in this study, ergonomic interventions and reforms considering the effect of each variable (normalized weighting of variables), should be done first for chair; like using ergonomic adjustable chair; then for telephone-monitor; like setting their distance to the user and etc. at least reform actions should be done for mouse-keyboard; like using the ergonomic of them in proper distance .

کلیدواژه ها:

SVM ، support vector machine ، ROSA ، musculoskeletal disorders ، weighting