Currently, climate change and human activities are causing rapid deterioration of coral reefs worldwide. Monitoring coral health is essential for marine ecosystem conservation. This project focuses on developing an Artificial Intelligence (AI) model to classify coral health into four categories: Healthy, Bleached, Pale, and Dead using Deep Learning techniques. With pre-trained convolutional neural network (CNN) for image classification. To improve accuracy and mitigate overfitting, 5-fold Cross-Validation is employed during training, and the best-performing model is saved. The results of this project can be applied to monitor coral reef conditions and assist marine scientists in analyzing coral health more efficiently and accurately. This contributes to better conservation planning for marine ecosystems in the future.
ปะการังเป็นองค์ประกอบสำคัญของระบบนิเวศทางทะเล แต่กำลังเผชิญกับภาวะเสื่อมโทรมจากภาวะโลกร้อนและกิจกรรมของมนุษย์ การตรวจสอบสุขภาพของปะการังในปัจจุบันอาศัยการสำรวจภาคสนาม ซึ่งใช้เวลานานและอาจเกิดข้อผิดพลาด โครงการนี้จึงนำเทคโนโลยีปัญญาประดิษฐ์มาใช้ในการวิเคราะห์ภาพถ่ายปะการัง ช่วยให้การจำแนกสุขภาพของปะการังมีความรวดเร็วและแม่นยำยิ่งขึ้น
คณะครุศาสตร์อุตสาหกรรมและเทคโนโลยี
The Research aims to create Computer Assisted Instruction (CAI) on Kitchen Design for Residence for 20 undergraduate students at the Interior Environmental Design Division, School of Industrial Education and Technology, King Mongkut’s Institute of Technology Ladkrabang. This CAI is a self-learning program for Interior environmental design courses focused on kitchen design for residences. The program is designed to interact with students to create learner engagement and improve learning achievement by providing course content and end-of-chapter quizzes. The research hypothesis is CAI: Interior Environmental Design: Kitchen design for residence affects learners’ learning achievement and students' knowledge toward learning by this CAI. The Development testing (DT) with E1/E2 is the criterion for this instructional media to examine learning achievement. The research findings indicate that CAI is an effective instructional media, scoring 71.50/89.00, which meets the criteria of 80/80, demonstrating students’ learning achievement. Students achieved higher scores than before by using Computer-Assisted Instruction (CAI).
วิทยาเขตชุมพรเขตรอุดมศักดิ์
Study on Parasites in Blackchin Tilapia and Value-Added Processing Parasites play a crucial role in affecting fish health and the balance of marine ecosystems. The study of parasites in fish is essential for assessing fish population status and their impact on the ecosystem. This research focuses on a preliminary survey of parasites in Blackchin Tilapia (Sarotherodon melanotheron) found in the waters of Chumphon Province to determine whether this species carries parasitic infections. The findings will provide valuable insights for managing marine resources and developing strategies for processing Blackchin Tilapia into food products to help control its population in the ecosystem. One of the value-added processing approaches for Blackchin Tilapia is the "Nai Hoi Hua Fu" product. This product involves deep-frying the fish to achieve a crispy and fluffy texture before mixing it with mango salad to enhance its flavor and make it more appealing. This processing method not only adds value to the fish but also serves as a practical solution for managing the Blackchin Tilapia population, which may impact the ecosystem. The study results indicate that no parasitic infections were found in either the internal or external organs of the sampled fish, suggesting that the marine environment in the study area is favorable for fish health. However, continuous research is recommended to monitor long-term ecological changes and evaluate the impact of Blackchin Tilapia on ecosystem balance to ensure sustainable resource management.
คณะเทคโนโลยีสารสนเทศ
This research presents the development of an AI-powered system designed to automate the identification and quantification of dental surgical instruments. By leveraging deep learning-based object detection, the system ensures the completeness of instrument sets post-procedure. The system's ability to process multiple images simultaneously streamlines the inventory process, reducing manual effort and potential errors. The extracted data on instrument quantity and type can be seamlessly integrated into a database for various downstream applications.