This thesis presents the application of deep learning for object classification. The selected deep learning architectures studied include Convolutional Neural Networks (CNN) and ResNet18. It covers data preparation, feature extraction, parameter tuning for accuracy comparison, and performance evaluation of the selected models. The aim is to propose an efficient model for use in devices that assist visually impaired individuals in classifying indoor objects and providing sound alerts.
ในปัจจุบันปัญหาในการเคลื่อนที่และการรับรู้สภาพแวดล้อมรอบตัวสำหรับผู้บกพร่องทางสายตายังคงเป็นอุปสรรคสำคัญในสังคมส่งผลให้เกิดความเสี่ยงต่อการเดินชนสิ่งกีดขวางและได้รับอันตราย ด้วยการนำเทคโนโลยีปัญญาประดิษฐ์เข้ามาใช้ในการเรียนรู้ การวิเคราะห์ และประมวลผลข้อมูลได้อย่างรวดเร็วเพื่อจำแนกวัตถุ ปริญญานิพนธ์นี้จึงมีจุดประสงค์เพื่อสร้างอุปกรณ์สำหรับช่วยเหลือผู้บกพร่องทางสายตาที่ใช้อัลกอริทึมการเรียนรู้เชิงลึกแบบต่างๆ เพื่อนำไปจำแนกวัตถุที่เป็นอุปสรรคสำหรับผู้บกพร่องทางสายตาในการทำกิจวัตรประจำวันภายในอาคารและส่งสัญญาณเตือนให้ผู้ใช้งานทราบให้เคลื่อนที่อย่างปลอดภัย
คณะวิทยาศาสตร์
With the development of space technology, wide-field sky surveys using telescopes have expanded the range of new data available for time-domain astronomical research. Traditional data analysis methods can no longer respond quickly and accurately enough to the growing volume of data. Thus, classifying time-series data, such as light curves, has become a significant challenge in the era of big data. In modern times, analyzing light curves has become essential for using machine learning techniques to handle and filter through massive amounts of data. Machine learning algorithms can be divided into two categories: shallow learning and deep learning. Numerous researchers have proposed and developed a variety of algorithms for light curve classification. In this study, we experimented with Support Vector Machine (SVM) and XGBoost, which are shallow machine learning algorithms, as well as 1D-CNN and Long Short-Term Memory (LSTM), which are deep learning algorithms, which are branches of deep machine learning, to classify variable stars. The training and testing data used in this study were from the Optical Gravitational Lensing Experiment-III (OGLE-III), consisting of variable star data from the Large Magellanic Cloud (LMC), categorized into five main classes: Classical Cepheids, δ Scutis, eclipsing binaries, RR Lyrae stars, and Long-period variables. The results demonstrate the performance analysis of each machine learning algorithm type applied to light curve data, while also highlighting the accuracy and statistical metrics of the algorithms used in the experiments.
คณะเทคโนโลยีการเกษตร
The research aims to develop chili Thai commercial varieties for resistance to anthracnose and Pepper yellow leaf curl virus disease. The varieties allowing farmer to reduce the use of chemical pesticides for disease and pest control, also increases productivity and lowers production costs for farmers. The development new varieties are under studied of undergraduate, master's, and doctoral students by using conventional and molecular plant breeding. The new chili varieties were released to farmer and commercial companies for development for Thai commercial seed industry.
คณะเทคโนโลยีสารสนเทศ
This thesis aims to present the development of a metaverse project for the KMITL Lifelong Learning Center (KLLC) and KMITL Data Management Center (KDMC) for Public Relations at King Mongkut's Institute of Technology Ladkrabang, with the main goal of creating a metaverse prototype to promote learning and public relations through virtual reality technology for students, staff, and external individuals. In this project, the developers have created a metaverse system to simulate a virtual experience for users at the KMITL Lifelong Learning Center (KLLC) and KMITL Data Management Center (KDMC) for Public Relations at King Mongkut's Institute of Technology Ladkrabang. Users will be able to access the system through a web application developed with Unity, which is the tool used to create the metaverse system. The design allows users to visit and interact with various locations within the building to promote public relations in a more widespread virtual format. The developers used Maya and Unity software to create a metaverse system for modeling 3D objects and managing various functions, providing users with a realistic and novel experience. This project is expected to promote learning and the dissemination of information in an easily accessible modern format, creating opportunities for education and learning for those who cannot travel to see the actual locations. This makes metaverse technology an important tool for effectively developing learning and engagement in the digital age.