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
Inventing robots for the TPA Robotics Competition Thailand Championship 2024, game “Rice Way, Thai Way to the International Way (HARVEST DAY)”
คณะสถาปัตยกรรม ศิลปะและการออกแบบ
The " Center of Invention for Future and Sustainability Project (Continuing)" serves as a continuation of a pilot initiative focused on the retrofitting of older buildings (Vach. 7), specifically a five-story structure. The primary aim of this project is to develop methodologies for enhancing the sustainability of existing buildings in order to mitigate carbon dioxide emissions. In the execution of the Future and Sustainability Innovation Development Center Project (Continuing), a comprehensive analysis of relevant data and theoretical frameworks has been undertaken, leading to the formulation of a research methodology designed to identify optimal strategies for retrofitting older buildings to reduce carbon dioxide emissions. This approach is structured into three principal phases: the combustion of fuels associated with transportation, labor, and materials; the electricity consumption during the construction process; and the accumulation of greenhouse gases from both existing and new construction materials. The project employs an experimental research design, wherein empirical data is collected to evaluate and quantify the equivalent carbon dioxide emissions arising from the construction of new buildings compared to the retrofitting of the selected case study building. Subsequent analysis of the collected data revealed that retrofitting the existing structure—through the integration of sustainable design principles—resulted in greenhouse gas emissions of 11.88 kgCO2e/sq.m. In contrast, the emissions associated with new building construction amounted to 299.35 kgCO2e/sq.m., indicating a reduction in carbon dioxide emissions by a factor of approximately 26 when compared to the construction of new buildings.
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.