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
คณะวิศวกรรมศาสตร์
The purpose of this invention is to develop a forest fire prevention agent that has the ability to prevent long-term forest fires, not only to suppress forest fires or prevent forest fires from spreading widely, but to prevent them from starting to catch fire from the beginning. It can prevent forest fires comprehensively and can be prevented for a long time during the peak forest fire period or the dry season, which is about 3-4 months. There are no residues or minimal residues without causing harm to the surrounding environment under the specified standards. Emphasis is placed on the use of raw materials, equipment, and chemicals that can be easily found in Thailand. This includes using the value of production costs as low as possible. This makes it suitable for use in large quantities for spraying and protecting forest areas in forest areas that are prone to fire. Estimated average for pollution caused by forest fires include particulate matter (PM), including PM2.5, PM10, carbon monoxide (CO), carbon dioxide, carbon dioxide, and carbon dioxide, Nitrogendioxide, VOC etc.
คณะเทคโนโลยีสารสนเทศ
This research presents a deep learning method for generating automatic captions from the segmentation of car part damage. It analyzes car images using a Unified Framework to accurately and quickly identify and describe the damage. The development is based on the research "GRiT: A Generative Region-to-text Transformer for Object Understanding," which has been adapted for car image analysis. The improvement aims to make the model generate precise descriptions for different areas of the car, from damaged parts to identifying various components. The researchers focuses on developing deep learning techniques for automatic caption generation and damage segmentation in car damage analysis. The aim is to enable precise identification and description of damages on vehicles, there by increasing speed and reducing the work load of experts in damage assessment. Traditionally, damage assessment relies solely on expert evaluations, which are costly and time-consuming. To address this issue, we propose utilizing data generation for training, automatic caption creation, and damage segmentation using an integrated framework. The researchers created a new dataset from CarDD, which is specifically designed for cardamage detection. This dataset includes labeled damages on vehicles, and the researchers have used it to feed into models for segmenting car parts and accurately labeling each part and damage category. Preliminary results from the model demonstrate its capability in automatic caption generation and damage segmentation for car damage analysis to be satisfactory. With these results, the model serves as an essential foundation for future development. This advancement aims not only to enhance performance in damage segmentation and caption generation but also to improve the model’s adaptability to a diversity of damages occurring on various surfaces and parts of vehicles. This will allow the system to be applied more broadly to different vehicle types and conditions of damage inthe future
คณะเทคโนโลยีการเกษตร
-