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
This report is part of applying the knowledge gained from studying machine learning models and methods for developing a predictive model to identify customers likely to cancel their credit card services with a bank. The project was carried out during an internship at a financial institution, where the creator developed a model to predict customers likely to churn from their credit card services using real customer data through the organization's system. The focus was on building a model that can accurately predict customer churn by selecting features that are appropriate for the prediction model and the unique characteristics of the credit card industry data to ensure the highest possible accuracy and efficiency. This report also covers the integration of the model into the development of a website, which allows related departments to conveniently use the prediction model. Users can upload data for prediction and receive model results instantly. In addition, a dashboard has been created to present insights from the model's predictions, such as identifying high-risk customers likely to cancel services, as well as other important analytical information for strategic decision-making. This will help support more efficient marketing planning and customer retention efforts within the organization.
คณะศิลปศาสตร์
The innovation of aromatic and cooling inhalers stems from the widespread use of inhalers in modern times. This innovation aims to elevate the product to suit contemporary lifestyles, incorporating Thai identity in a way that resonates with the younger generation. The development focuses on enhancing scents using locally sourced Thai ingredients, adding value to Thai flowers and fruits. Various extraction methods are employed to preserve the fragrance for a longer duration. Additionally, borneol, camphor, and menthol are blended to provide a refreshing and cooling sensation. For the packaging, polymer clay is used to create the container, which is hand-molded and then baked to harden. Instead of a traditional cap, a fabric covering is used to introduce a unique and innovative alternative to conventional inhalers.
คณะสถาปัตยกรรม ศิลปะและการออกแบบ
On the path of life since we were born, we have encountered many things in life, differences and various characteristics. However, each factor of each person's life has different responsibilities, dreams, and life context differences. Everyone still has to struggle against obstacles and many burdens in life, shouldering the responsibilities of themselves and their families in order to survive. Living in different ways, with many burdens and dreams, but in real life, how many people can shoulder these burdens to reach their dreams?