Sensory system development to monitor operators to improve workplace safety and wellbeing

• Main Author: Poh, Yong Keat
• Other Authors: Li King Ho Holden
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Mechanical engineering
• Online Access: http://hdl.handle.net/10356/77559
• Institution: Nanyang Technological University

Mental fatigue has proved to be a persistent problem for many generations of humanity, and even till today, it is not an issue to be trifled with. In maritime transport and construction industries, crane operators continue to face the problem of fatigue at work. This poses devastating consequences due to declined performance, leading to higher error rates and inconsistent operating aptitude. Hence, early detection and prevention is an imperative measure. EEG as a bio-sensory system collects electrical neural activity at the scalp, which provides valuable insights to the inner workings of the brain. By learning EEG signals, we can uncover the complex relationship between brainwaves and fatigue. The recent popularity of deep learning techniques was sparked by their breakthroughs in areas such as Image Recognition and Natural Language Processing, leading to its widespread growth in many other applications. This study investigates various state-of-the-art deep learning techniques for detecting the onset of fatigue, and proposes a single-channel EEG system for practical usage in the crane operator setting.