Understanding driver behaviour relationship to precursor emotion by using EEG signals /

Driver behaviour is indeed reckoned to be one of the highest factors affecting fatal accidents. However, majority of the cases can be avoided if the driver can remain focus and make a correct decision in controlling the vehicle while driving. Decision-making ability of the driver is impeded due to d...

Full description

Saved in:
Bibliographic Details
Main Author: Norzaliza Md Nor
Format: Thesis
Language:English
Published: Kuala Lumpur : Kulliyyah of Information and Communication Technology, International Islamic University Malaysia, 2012
Subjects:
Online Access:http://studentrepo.iium.edu.my/handle/123456789/5590
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Driver behaviour is indeed reckoned to be one of the highest factors affecting fatal accidents. However, majority of the cases can be avoided if the driver can remain focus and make a correct decision in controlling the vehicle while driving. Decision-making ability of the driver is impeded due to driver behaviour which may involve precursor emotion of the driver that could lead to fatal accident. Thus, understanding and analyzing the driver behaviour and the resulting emotion can help prevent accident and reducing accident fatality rate. In this thesis, the correlation between precursor emotions to pre-post accidents using driving simulator is studied in details. This correlation between driver's behaviour and their respective emotion can be analysed based on the 2-D Affective Space Model (ASM) using four basic emotions (happy, calm, fear and sad) as stimuli. In this case, the Electroencephalogram (EEG) device is used to extract brain waves signal while the driver is driving the simulator. The EEG signals are captured through the scalp of the driver and features are extracted using Mel Frequency Cepstral Coefficient (MFCC) and Kernel Density Estimation (KDE). Neural network classifier of Multilayer Perceptron (MLP) and fuzzy neural network classifier of Adaptive Network-based Fuzzy Inference System (ANFIS) are used to classify discrete class emotions and the valence and arousal axes for the ASM. In the discrete class, result shows the possibility using the research method to identify the basic emotion is successful. Analysis of the precursor emotion for pre-post accidents using the driving simulator shows an interesting finding that complements the discrete classification. In addition, the analysis also indicates how precursor emotion can affect driver behaviour in pre-post accidents. Consequently, the understanding of pre-cursor emotion and its relationship towards driver behaviour could help the driver to control his/her emotions while driving which can prevent to fatal accident.
Item Description:Abstracts in English and Arabic.
" A thesis submitted in fulfilment of the requirement for the degree of Master of Computer Science."--On t.p.
Physical Description:xiv, 128 leaves : ill. ; 30cm.
Bibliography: Includes bibliographical references (leaves 107-116).