Browsing by Author "Mique, Eusebio L."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    AQUALITICS:
    (Don Mariano Marcos Memorial State University – Mid La Union Campus, 2025-11) Gurion, Eric Brandon B.; Flores, Queenie Leanne P.; Gatchallian, Angel Laurence S.; Mamuyac Jr., Bryan D.; Hortizuela, Manny R.; Patacsil, Joseph A.; Mique, Eusebio L.; Taliman, Raygildo
    This study presents Aqualitics, an lot-based real-time monitoring system designed to assess and analyze key physical parameters of tap water,such as temperature, pH level, turbidity, total dissolved solids, and electrical conductivity, which are visualized in a web-based dashboard for efficient monitoring and analysis. The study employed the Evolutionary Prototype Model and was evaluated using the System Usability’ Scale (SUS) along with the Technology' Assessment Protocol (TAP-TEEPS), which considers the system’s technical performance, economic viability, environmental soundness, political acceptability, and social acceptability’. After testing and evaluating the usability’ and functionality of the system, it has garnered a very high validity score of 4.51, and its sensors were evaluated with high accuracy. Overall, the Aqualitics system is a practical, efficient, and user-friendly tool that supports sustainable, water quality management aligned with SDG 6: Clean Water and Sanitation.
  • No Thumbnail Available
    Publication
    Grapex:
    (Don Mariano Marcos Memorial State University – Mid La Union Campus, 2025-11) Bacani, Janverly Mhaye O.; Amparo, Arianne Therese S.; Aberin, Lexter C.; Laranang, Hardly Rianne N.; Estira, Marydel; Mique, Eusebio L.; Patacsil, Joseph A.
    This study developed GRAPEX, a digital tool for the efficient, early detection of critical fungal diseases like Black Rot and Black Measles (Esca) in grape leaves, primarily for farmers in Bauang, La Union. The methodology utilized descriptive and applied research, adhering to the CRISP-DM framework for model training and Extreme Programming (XP) for application development. Key goals included creating a validated grape leaf disease dataset, training a Convolutional Neural Network (CNN), developing a multi-platform application, and assessing system usability. The CNN model achieved a high classification accuracy of 90.3%. Furthermore, the system attained an Excellent Usability rating across all user groups (20 respondents): five (5) agricultural staff, five (5) IT Experts, and ten (10) grape farmers from Bauang, La Union, yielding an average System Usability Scale (SUS) score of 81. The GRAPEX system successfully detected Black Measles, Black Rot, and healthy conditions, proving to be a reliable, efficient, and user- friendly tool with significant potential for vineyard management.
  • Thumbnail Image
    Item
    U-Net based lung image segmentation for lung disease detection
    (International Journal of Recent Technology and Engineering (IJRTE), 2019-09) Mique, Eusebio L.; Malicdem, Alvin R.
    Lung diseases are becoming a worldwide health problem. World Health Organization estimates that by 2030, lung diseases such as Chronic Obstructive Pulmonary Disease will be one of the leading cause of mortality. Accurate and timely detection of lung diseases may prevent further death. It is therefore vital that its early detection will lead to treatment and prevention of mortality among patients. However, the scarcity of expert or well-trained radiologists reading CXR images might delay the timely diagnosis of lung diseases especially in rural areas where the scarcity is felt. In order to aid radiologist in reading CXR images, a computer aided tool is proposed for faster and more accurate reading of CXR images. To prepare the image for processing, it need to be segmented to make it easier for the computer to understand. The goal of image segmentation in medical field is to extract the region of interest in the organ. This study is focused on developing a model that will segment the lung from CXR images. Using U-Net architecture based semantic segmentation, the researchers were able to develop and train a model using a set of 562 CXR images and lung mask images, 70 percent of the images were used for training and 30 percent for testing. The developed model achieved a final training accuracy of 97.55 percent and validation accuracy of 97.37 percent. Validation loss and training loss are also low which indicates that the model can segment lung from CXR images with minimal error. The developed model can then be used in classifying lung diseases by focusing on the segmented image rather than focusing on the entire CXR image.