Investigating the use of brain connectivity in deep transfer learning for cross-dataset EEG emotion recognition | |
| Author | Nattapat Dilokthammapan |
| Call Number | AIT Thesis no.IM-22-03 |
| Subject(s) | Electroencephalography Brain--Physiology Deep learning (Machine learning) Artificial intelligence Pattern recognition systems |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | EEG emotion recognition has received more interest from artificial intelligence researchers. However, researchers have a problem with insufficient data from the same subject to train a classifier for a subject. Therefore, we try to evaluate the use of brain connectivity on a cross-dataset for emotion recognition. We consider three types of brain connectivity. The result from this study shows that the phase lag index (PLI) has the highest accuracy, which is 99.33% and 98.19% on the SEED, and the DEAP datasets, respectively. However, when we use brain connectivity on cross-dataset, it can reach only average performance, which is 50.88% when trained on SEED dataset and used DEAP dataset to tested and 62.96% when trained on DEAP dataset and tested on SEED dataset. The result of this study show potential of brain connectivity to use in EEG emotion recognition, but it still needs fine tune in a future study. Our code: https://github.com/jaecibake/Emotion Recognition brainconnectivity |
| Year | 2022 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Chaklam Silpasuwanchai |
| Examination Committee(s) | Dailey, Matthew N.;Attaphongse Taparugssanagorn |
| Scholarship Donor(s) | Royal Thai Government Fellowship |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2022 |