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.
วิทยาลัยการจัดการนวัตกรรมและอุตสาหกรรม
Air Rack is a product designed to address businesses with limited space and budget constraints for server rooms, cooling systems, and noise management. This system enables efficient use of IT equipment in open spaces, supporting both On-premise and On-cloud operations. It converts sensor data into digital information and displays it via a Dashboard, allowing users to monitor, analyze, and control the system remotely. Additionally, Air Rack significantly reduces power consumption and the costs associated with traditional server room management.
คณะเทคโนโลยีการเกษตร
The use of chemical herbicides in agriculture has raised concerns due to its adverse effects on farmers' health, environmental sustainability, and consumer safety. Paraquat, a widely used herbicide, has been banned in Thailand. In response to this issue, this research focused on the development of natural herbicide products as an alternative to conventional chemical herbicides. The study involved the extraction of bioactive compounds from selected plants with potential herbicidal properties and evaluating their effectiveness in controlling target weeds. The results indicated that the developed natural herbicide demonstrates significant weed control efficiency. Additionally, this product can be applied to organic farming systems, reducing reliance on hazardous chemicals and promoting sustainable agricultural practices. The development of this natural herbicide served as an essential step toward environmentally friendly and safe agricultural solutions.
คณะอุตสาหกรรมอาหาร
Spent coffee grounds (SCG) are a byproduct of the coffee brewing process, and their quantity continues to increase due to the growing global coffee consumption. SCG contain beneficial compounds such as polysaccharides, dietary fibers, and antioxidants, which can be utilized in various applications, including prebiotic extraction. This study focuses on extracting prebiotics from SCG using acid hydrolysis and enzymatic hydrolysis methods to evaluate their potential in promoting the growth of beneficial gut microorganisms. The expected results of this research include adding value to coffee industry waste, reducing organic waste, and providing a sustainable approach to developing prebiotic products for use in the food and health industries. Furthermore, this study aligns with sustainable resource utilization and environmentally friendly practices.