Jaundice, a common condition in infants that results from high bilirubin levels in the blood, often requires early diagnosis and monitoring to prevent severe complications, especially in newborns. Traditional diagnostic methods can be time-consuming and subject to human error. This study proposes an approach for real-time jaundice detection using advanced image processing techniques and machine learning algorithms. By analyzing images captured in RGB color spaces, pixel values are extracted and processed through Otsu’s thresholding and morphological operations to detect color patterns indicative of jaundice. A classifier model is then trained to distinguish between normal and jaundiced conditions, offering an automated, accurate, and efficient diagnostic tool. The system’s potential to operate in real-time makes it particularly suited for clinical settings, providing healthcare professionals with timely insights to improve patient outcomes. The proposed method represents a significant innovation in healthcare, combining artificial intelligence and medical imaging to enhance the early detection and management of jaundice, reducing reliance on manual interventions and improving overall healthcare delivery.
โรคดีซ่าน ซึ่งเป็นภาวะทางการแพทย์ทั่วไปที่มีลักษณะการเหลืองของผิวหนังและดวงตา มักบ่งบอกถึงความผิดปกติของตับหรือเลือดที่อยู่เบื้องหลัง การตรวจพบในระยะเริ่มต้นมีความสำคัญอย่างยิ่ง โดยเฉพาะในทารกแรกเกิด ที่หากไม่ได้รับการรักษาโรคดีซ่าน อาจนำไปสู่ภาวะแทรกซ้อนร้ายแรงได้ วิธีการวินิจฉัยแบบดั้งเดิมต้องอาศัยการตรวจสอบด้วยสายตาหรือการทดสอบในห้องปฏิบัติการ ซึ่งอาจใช้เวลานานและมีข้อผิดพลาดได้ ความก้าวหน้าล่าสุดในด้านการประมวลผลภาพและแมชชีนเลิร์นนิงเสนอความเป็นไปได้ใหม่ ๆ สำหรับการตรวจจับที่แม่นยำ มีประสิทธิภาพ และแบบเรียลไทม์มากขึ้น ด้วยการวิเคราะห์รูปแบบสีผิว ปัญญาประดิษฐ์ (AI) สามารถทำให้การวินิจฉัยเป็นไปโดยอัตโนมัติ ทำให้รวดเร็วขึ้นและลดการพึ่งพาการประเมินโดยมนุษย์
คณะวิศวกรรมศาสตร์
The evaluation of mango yield and consumer behavior reflects an increasing awareness of product origins, with a growing demand for traceability to understand how the produce has been cultivated and managed. This study explores the relationship between mango characteristics and cultivation practices before harvest, using location identification to provide insights into these processes. To achieve this, a model was developed to detect and locate mangoes using 2D images via a Deep Learning approach. The study also investigates techniques to determine the real-world coordinates of mangoes from 2D images. The YOLOv8 model was employed for object detection, integrated with camera calibration and triangulation techniques to estimate the 3D positions of detected mangoes. Experiments involved 125 trials with randomized mango positions and camera placements at varying yaw and pitch angles. Parameters extracted from sequential images were compared to derive the actual 3D positions of the mangoes. The YOLOv8 model demonstrated high performance with prediction metrics of Precision (0.928), Recall (0.901), mAP50 (0.965), mAP50-95 (0.785), and F1-Score (0.914). These results indicate sufficient accuracy for predicting mango positions, with an average positional error of approximately 38 centimeters.
คณะวิทยาศาสตร์
Metallic nanoparticles embedded in cellulose nanocrystal (MNPs/CNC) films were prepared by solution casting for antimicrobial and fungus in edible peel fruit. MNPs/CNC was synthesized by ultrasonic waves. The as-synthesized was characterized by the chemical characteristics by the transmission electron microscope (TEM), X-ray photoelectron spectroscopy (XPS), X-ray diffraction analysis (XRD), Fourier transform infrared spectrometer (FT-IR), zeta potential analyzer, and UV-visible spectrophotometer. MNPs/CNC films had high potential in antimicrobial and fungus. Therefore, MNPs/CNC can be used to wrap edible peeled fruit to inhibit the growth of microorganisms, which can effectively extend the shelf life of fruits.
คณะวิทยาศาสตร์
This project presents the development of an automatic recycling machine for plastic bottles and cans, utilizing Machine Learning for packaging classification through image processing, integrated with smart sensor systems for quality inspection and operation control. The system connects to a Web Application for real-time monitoring and control. Once the packaging type is verified, the system automatically calculates the refund value and processes payment through e-wallet or issues cash vouchers. The system can be installed in public spaces to promote waste segregation at source, reduce contamination, and increase recycling efficiency. It also provides financial incentives to encourage public participation in waste management. This project demonstrates the potential of combining Machine Learning and smart sensor systems in developing accurate, convenient, and sustainable waste management solutions.