EEG-based mental workload recognition using deep learning techniques

• Main Author: Koh, Charis Hwee Ying
• Other Authors: Olga Sourina
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering; DRNTU::Engineering::Electrical and electronic engineering; DRNTU::Social sciences::Psychology::Consciousness and cognition
• Online Access: http://hdl.handle.net/10356/74601
• Institution: Nanyang Technological University

As EEG devices become more widely available in the market, they have seen increased usage in observing and tracking the brainwaves of operators. Furthermore, with their existing use in the healthcare sector, there is a need to improve the recognition of features for safety and wellbeing. This paper aims to study existing mental workload recognition techniques, as well as to demonstrate an implemented MATLAB code to execute transfer learning between two datasets and its related results. The paper also aims to compare the effectiveness of transfer learning against machine learning, and to propose suggestions for future development. In this study, results have found that while transfer learning can be applied to EEG data, much improvement has to be made before the algorithm can be used industrially or commercially.