Abstract-Emotional engagement during mental tasks performance when the difficulty level of mental tasks increases is studied using Electroencephalogram (EEG) recorded by Emotiv Epoch device. A real-time EEG-based emotion recognition algorithm using Valence-Arousal-Dominance emotion model is applied. An experiment with 5 levels of workload is proposed and carried out with 7 subjects. The mental tasks are given to the participants to solve addition problems of increasing complexity. For each task, 3 min is given to complete additions with 2 min rest between the tasks sessions. Performance score for each participant is recorded as well. Emotions are recognized from the EEG during each task using the subjectdependent emotion recognition algorithm. The algorithm consists from feature extraction and classification parts. The classifier is trained for each participant using short calibration session with emotion induction before the experiment. The combined features obtained from the training session are used to train a SVM classifier. The following hypotheses are confirmed. Participants have mostly negative, high arousal, low dominance emotions during the mental tasks performance under the stress since high arousal can speed up the mental process and enhance information retrieval, and as the limited time is given to perform the tasks, the feeling of losing control is dominated in the participants that corresponds to low dominance on the scale of Valence-Arousal-Dominance emotion model. At the same time it is found that when the difficulty level of mental tasks increases under the stress, people tend to be more negative and more aroused.
This thesis contains material from papers published in the following peer-reviewed conferences and publication drafts under preparation for the publications in the following peer-reviewed journals where I was the first and corresponding author. Chapter 3 is prepared as W.H. Chai, and C. Quek. A novel Quasi-Newton Technique for Composite Convex Minimization. Pattern Recognition (Under revision) The contributions of the co-authors are as follows: I defined the initial project direction Assoc Prof Quek edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab. Chapter 4 is prepared as W.H. Chai, and C. Quek. Representation Recovery via -norm Minimization with Corrupted Data. Information Sciences (Submitted)The contributions of the co-authors are as follows: Assoc Prof Quek provided the initial project direction and edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.Chapter 5 is prepared as W.H. Chai, and C. Quek. Feature Selection for Dictionary Transfer.
Pattern Recognition Letters (Under preparation for publication)The contributions of the co-authors are as follows:x I defined the initial project direction Assoc Prof Quek edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.