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.
คณะศิลปศาสตร์
Layla, the hotel robot, is responsible for carrying guests’ luggage and guiding them to their accommodations. It is equipped with an internal map of the hotel, allowing it to navigate various locations efficiently. Additionally, it features an AI-powered system that enables interactive conversations in three major languages: Thai, English, and Chinese.
คณะวิทยาศาสตร์
Air pollution, particularly PM2.5, is a major environmental and public health concern in Bangkok. Instead of predicting PM2.5 levels, this project aims to identify the most significant factors influencing PM2.5 concentration. By analyzing historical air quality, weather, and other environmental data, we will determine which variables—such as temperature, humidity, wind speed, or other pollutants—have the greatest impact on PM2.5 fluctuations.
คณะวิศวกรรมศาสตร์
The production process of the food rancidity indicator label consists of three main steps: 1) preparation of the indicator solution, 2) preparation of the cellulose solution, and 3) formation of the sheet. The indicator solution includes bromothymol blue and methyl red, which act as indicators. The cellulose solution consists of hydroxypropyl methylcellulose, carboxymethyl cellulose, sodium hydroxide, polyethylene glycol 400, and the indicator solution. For the sheet formation, the cellulose solution was mixed with natural latex to increase flexibility and impart hydrophobic properties. After drying, the invention appears as a thin, dark blue label. When exposed to volatile compounds from rancid food, the label changes color from dark blue to green, and then to yellow, corresponding to the increasing amount of volatile compounds from the rancid food.