Classification of risks of low back disorders with support vector machines


Thesis Type: Post Graduate

Institution Of The Thesis: Gazi Üniversitesi, Fen Bilimleri Enstitüsü, Turkey

Approval Date: 2012

Student: MEHMET ERDEM

Consultant: DİYAR AKAY

Abstract:

In spite of the advanced technology, manual material handling (MMH) tasks are still done frequently. According to the surveys, MMH tasks are the leading cause of occupational low back disorders (LBDs). In the literature, the trunk motion variables and the workplace variables related to the risk of LBDs were determined. These variables were sampled for 235 MMH tasks in different manufacturing industries and were divided into high and low risk groups of LBD based on their injury and medical records. In this study, occupational LBD risks were classified with support vector machines (SVM). The results were compared with the results of studies using the same experimental data. The results obtained in this study indicate that SVM is a better classifier than the proposed methods in the literature to classify the LBD risks.