This study explores the application of deep convolutional neural networks (CNNs) for accurate pill identification, addressing the limitations of traditional human-based methods. Using a dataset of 1,250 images across 10 household remedy drugs, various CNN architectures, including YOLO models, were tested under different conditions. Results showed that natural lighting was optimal for imprinted pills, while a lightbox improved detection for plain pills. The YOLOv5-tiny model demonstrated the best detection accuracy, and efficientNet_b0 achieved the highest classification performance. While the model showed strong results, its generalization is limited by sample size and drug variability. Nonetheless, this approach holds promise for enhancing medication safety and reducing errors in outpatient care.
The increasing complexity of pharmaceutical treatments requires precise pill identification to ensure patient safety. Traditional methods for pill reconciliation rely on human experts, which are time-consuming and prone to errors. Deep Convolutional Neural Networks (CNNs), particularly effective in image processing, offer a promising solution for automating and enhancing these processes.
คณะวิศวกรรมศาสตร์
This Project has been undertaken to address the need for skill development and knowledge enhancement in pneumatic systems and automation control, which are crucial in today’s manufacturing industry. Pneumatic systems play a vital role in various production processes, including machine control, automated devices, and assembly lines. However, the Department of Measurement and Control Engineering currently lacks a laboratory dedicated to the study and experimentation of pneumatic systems due to the deterioration and lack of maintenance of the previously used equipment. This has resulted in students missing the opportunity to practice essential skills required in the industrial sector. The authors of this thesis recognize the necessity of reviving and developing a pneumatic laboratory that can effectively support teaching, learning, and research activities. This project focuses on studying and developing industrial robotic arm control systems and pneumatic systems, integrating modern technologies such as Programmable Logic Controllers (PLC) and AI Vision. These systems are intended to be applicable to real-world industrial contexts. The outcomes of this project are expected to not only enhance the understanding of relevant technologies but also aim to transform the laboratory into a vital learning hub for current and future students. Furthermore, this initiative seeks to improve the competitiveness of students in the job market and support the development of innovations in the manufacturing industry in the years to come.
คณะศิลปศาสตร์
The Herby gel are products developed to relieve stress and headaches, which often result from heavy work, a fast-paced lifestyle, or hot and humid weather. The patches are made from natural ingredients such as peppermint, neem leaves, gotu kola, aloe vera, and other herbs that effectively alleviate these symptoms. Free from alcohol, this product is safe to use and provides a cooling, soothing, and refreshing effect on the skin. It is easy to use, convenient to carry, and suitable for use in any situation, making it a practical solution for everyday discomfort.
คณะเทคโนโลยีการเกษตร
This study aimed to investigate the effects of different salinity levels on survival rate and growth performance of golden apple snail (Pomacea canaliculata). The experiment was conducted at salinity levels of 0, 5, 10, and 15 ppt, with four replicates each, over an 8-week period. The results showed that golden apple snails reared at 5-10 ppt exhibited survival rates and growth performance not significantly different (p>0.05) from those in the freshwater control group (0 ppt). These findings suggest the potential for developing golden apple snail culture in brackish water systems and the possibility of integration with other brackish water species in polyculture systems.