Developing Regression Models Of Driver Fatigue Using An Ergonomics Approach

• Main Author: Ani, Mohammad Firdaus
• Format: Thesis
• Language: English; English
• Published: UTeM 2016
• Subjects: T Technology (General); TL Motor vehicles. Aeronautics. Astronautics
• Online Access: http://eprints.utem.edu.my/id/eprint/18595/1/Developing%20Regression%20Models%20Of%20Driver%20Fatigue%20Using%20An%20Ergonomics%20Approach%2024%20Pages.pdf; http://eprints.utem.edu.my/id/eprint/18595/2/Developing%20Regression%20Models%20Of%20Driver%20Fatigue%20Using%20An%20Ergonomics%20Approach.pdf; http://eprints.utem.edu.my/id/eprint/18595/; https://plh.utem.edu.my/cgi-bin/koha/opac-detail.pl?biblionumber=100610

Nowadays, driving activity has become more important as this medium being practically, faster and cheaper in connecting human from one to another places. However, driving activity can cause disaster or death to human in daily life as they get fatigued while driving. Driver fatigue is a top contributor to the road crashes. Psychophysical factors and biomechanical factors were identified as the causes of driver fatigue among Malaysian. The primary aim of this research is to develop the regression models based on psychophysical and biomechanical factors that contributes to fatigue, which the models can predict the relationship between the input parameters and output responses. Regression analysis was used, as this being practical, easy, user friendly and cost effective methods to develop a model. This research investigated the hand grip pressure force for the right hand and left hand while driving through different road conditions, study the relationship between the road conditions with hand grip pressure force and muscle fatigue, study the interaction between road condition with seat pressure distribution force and whole body vibration (WBV), heart rate monitoring, and developed the regression models of psychophysical factors and biomechanical factors for driver fatigue. The input parameters evaluated were time exposure, type of road, and gender; the output responses being muscle fatigue (voltage), heart rate (beats per minutes), hand grip pressure force (left hand), hand grip pressure force (right hand), seat pressure distribution force, and vibration (root mean square). Six regression models were successfully developed and validated. The modelling, validation runs were within the 90% prediction interval of the developed models and their residual errors compared to the predicted values were less than 10%. The significant parameters that influenced the output responses were also identified. Muscle fatigue, hand grip pressure force (left hand), and hang grip pressure force (right hand) were influenced by time exposure, type of road, gender, interaction between time exposure and type of road, and interaction between type of road and gender; heart rate was influenced by time exposure, type of road, and gender; pressure distribution force was influenced by time exposure, type of road, gender, interaction between time exposure and gender, and interaction between type of road and gender; and WBV was influenced by time exposure, type of road, gender, interaction between time exposure and type of road, and interaction between time exposure and gender.