A thesis investigating the application of wireless optical communication technologies for the advancement of Machine Learning-augmented Underwater Internet of Things. The thesis focused on exploring the possibility of using error correcting code in underwater optical communication (UWOC), developing and evaluating the performance of a multi-hop underwater wireless sensor network (UWSN), designing a prototype that utilizes relay-based diversity gain to enhance UWOC, and using data from IMU sensors to monitor the movement of aquaculture and predict the acceleration state of the target body using machine learning models. The research was conducted under the guidance of
Prof Wan-Young Chung, who is ranked among the
Top 2% Scientists Worldwide 2023 by Stanford University . I have delivered presentations at two international conferences, and the findings from these presentations have been published in four SCIE IEEE journals.