Date of Award

8-7-2023

Publication Type

Thesis

Degree Name

M.A.Sc.

Department

Electrical and Computer Engineering

Keywords

Automation Driving Systems;Cognitive Load;Driver Monitoring System;Human Factor Engineering;Speech;Speech Features

Supervisor

Balakumar Balasingam

Supervisor

Francesco Biondi

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Driver inattention is one of the leading causes of road accidents and fatal crashes. To mitigate these risk, Driver Monitoring System (DMS) has been developed and extensively experimented by the automobile industry. An overview of DMS is presented in this thesis with specific focus on driver inattention and cognitive state of the drivers. Research on the sources of driver inattention are reviewed, and a comprehensive classification is provided. Various safety systems that measure driver inattention based on driving behavior, hybrid measures and physiological measures are investigated. In particular, a non-invasive speech-based measure of physiological signal for detecting the cognitive load of participants is investigated. The study involves 24 participants performing experiment task to stimulate cognitive load in different experiment conditions and difficulties, including visual detection response task (V-DRT) and an auditory n-back task. Speech response time (SRT) as a speech feature is calculated using voice activity detection, signal labeler software and speaker recognition techniques, resulting in a statistically significant difference in SRT in single and dual experiment condition. Furthermore, other speech features: energy, duration, mean and standard deviation are analyzed and investigated, resulting in no significant difference in cognitive load despite also considering gender as a criterion. The proposed methods offer non-invasive measures of cognitive load in DMS under different experimental conditions. The findings shows the potential of speech as a non-invasive measure of cognitive load.

Share

COinS