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.
คณะเทคโนโลยีสารสนเทศ
Nowadays, assembling a computer is considered something close to many people. Everyone has a chance to catch it. which knowledge of various components of computers and skills in assembling computers. These 2 things mentioned above are things that the general public should have basic knowledge and understanding about. For the self-assembly of computers, We therefore would like to provide knowledge to the general public who wants to learn how to assemble a computer, including information about its components. Through presentation in the form of learning media using VR technology, which will help reduce the problem of errors. and resources used in assembly Ready to create excitement for users by simulating computer assembly for users to interact within the virtual world. experience and provide knowledge before actually putting it into practice with real equipment This project was therefore created for those interested in assembling computers. Especially for people who have no experience in computer assembly. Including people who would like to have the opportunity to try building a computer by themselves.
คณะวิทยาศาสตร์
Developing a Smart Farming Simulation Utilizing LoRa Communication and Presenting Knowledge on LoRa Communication System Components
คณะวิทยาศาสตร์
Microalgae are rich in bioactive compounds that may contribute to the growth of probiotics, which require appropriate nutrients, known as prebiotics, to thrive. This study aims to evaluate the effectiveness of crude extracts from intracellular components residues of the microalga Chlorella sp. KLSc61 in promoting the growth of the probiotic bacterium Lactiplantibacillus plantarum JCM1149 under simulated gastrointestinal conditions. The intracellular extracts were obtained using 70% (v/v) ethanol, and their effects on probiotic growth were tested at concentrations of 0.1%, 0.75% and 1.5%. The growth of Lactiplantibacillus plantarum JCM1149 was assessed using the drop plate method. The findings of this study will provide insights into the potential of Chlorella sp. KLSc61 extracts in enhancing probiotic growth, which could lead to the development of synbiotic dietary supplements containing both probiotics and prebiotics. Additionally, this study may serve as a foundation for further research on the role of microalgal extracts in gut health and immune system modulation.