On January 21, 2025, Asst. Prof. Dr. Thanapon Noraset, Assistant Dean for Academic Affairs, along with staff and students from the Faculty of Information and Communication Technology, Mahidol University (ICT Mahidol), participated in the academic showcase “120 Years of Pride: Shaping the Future with a Foundation of Quality” held at Assumption Convent School.
The academic projects presented by ICT Mahidol included:
- “Suture Bot: Development of an Automated Evaluation and Feedback System for Suture Practice Training”
This project is designed to assess and provide automatic feedback on suture practice outcomes using images of suturing results on practice kits. Data is collected through a Line Official Account and a Web Application. Machine learning techniques and image processing algorithms are applied to evaluate performance and provide suggestions to medical students. - “MASENG: Snake Identification through Image Classification”
This project integrates deep learning techniques with CNN architecture to identify snake species commonly found in Bangkok, Thailand. This innovation aims to reduce the time required for snake identification, minimize unnecessary risks, and enhance public access to accurate information about snakes. - “CAMELON: Crime and Accident Monitoring and Estimation from Large-Scale Online News Articles”
This project involves the development of a web application that provides in-depth insights into local crime rates and trends across various communities. - “eDuck: Adapting LLMs as an Educational Tool for Learning to Code”
This project is designed to assist learners in coding with Python through the integration of large language models (LLMs) into the source code editor “Visual Studio Code.” - “MOSWING: A Noise-Robust Mosquito Wingbeat Detection Model”
This project focuses on developing a sound event detection model capable of identifying mosquito species and genders effectively, even in noisy environments. It can be used to estimate mosquito populations in various areas. - “From Views to Verdicts: Simplifying Legal Case Predictions”
This research initiative proposes an efficient approach to predicting case outcomes by integrating five key components: legal document customization, machine learning, data extraction with NLP techniques, model evaluation, and the use of large language models (LLMs)
