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
This thesis presents the development of an IoT system that integrates various communication standards to work together seamlessly. The Core Board serves as the IoT gateway, connecting LoRa, Wi-Fi, and BLE interfaces, and is powered by the STM32H563Zi microcontroller based on the ARM Cortex M33 architecture. The system is designed with slots to support additional communication standards and includes a web platform for data monitoring.
คณะบริหารธุรกิจ
JALA is a brand that established a business around jasmine rice wax scented candles with the aim of addressing the stress people face in everyday life. The brand utilizes "Aromatherapy" to help relax the mind and alleviate stress. The scented candles made from jasmine rice wax are an innovative product, distinguished by their clean burn, safety for users and the environment, and high vitamin E content that nourishes the skin. They also retain a unique fragrance that provides true relaxation. JALA aims to offer products that blend traditional Thai elements with modern design, making their scented candles not only therapeutic but also a reflection of Thai culture and modern identity. The brand caters to health-conscious and environmentally aware consumers.
คณะวิศวกรรมศาสตร์
This research focuses on the design and development of a high-power converter to regulate energy supply from solar cells (Photovoltaic: PV) to a hydrogen production unit (Electrolyzer), which is a crucial component in advancing renewable energy in alignment with the RE100 initiative. Specifically, this study targets Green Hydrogen, which is generated through the water electrolysis process using clean energy from solar cells, ensuring zero emissions and environmental sustainability. The proposed converter includes of a Three-Level NPC Inverter, transformer, Full-Bridge Rectifier, and LC filter to enhance the power quality supplied to the electrolyzer. The system's design and simulation were conducted using MATLAB and Simulink to evaluate circuit performance and analyze operational efficiency. Simulation was conducted using MATLAB and Simulink to evaluate circuit performance and analyze operational efficiency. Additionally, a microcontroller-based control system is integrated with a gate driver circuit to optimize the electrolysis process by reducing power losses. This proposed converter effectively converts PV energy into suitable voltage and current levels for the electrolyzer while maintaining high hydrogen production efficiency.