Research & Publications
Explore scholarly studies, academic journals, innovative projects, and research publications from Enverga University Candelaria.
3
Publications
2
Years Covered
14
Research Areas
(SAMPLE DATA) MicroPolluScan: A Deep Learning-Based Monitoring System for Classification of Microplastic Contamination in Fishponds
Microplastics in aquatic life are hazardous to sea life, food safety, and aquaculture. In this paper, we describe MicroPolluScan, an AI-based deep learning system which uses automated microscopic image analysis to detect, classify, and quantify microplastic contamination in fishponds. To facilitate the development, we employed an Agile Scrum-CRISP-DM paradigm, that is an architectural process based on an iterative software design methodology, along with structured data science methodology. Microscopic pictures of beads, fragments, and fibers were taken from fishponds in Lucena City, augmented with Roboflow, and trained in YOLOv5 and YOLOv8 networks on Google Colab. Comparison results demonstrated that YOLOv8 provided the best performance (precision = 0.82, recall = 0.85, F1 = 0.83, mAP = 0.89) because of the anchor-free detection head and C2f supporting mechanism. A fine-tuned model was implemented in a Flask-based web system, for real-time detection and visualization dashboards for practitioners of aquaculture. Software quality of the software evaluated following ISO/IEC 25010 has a mean of 3.80 (Strongly Agree) followed by a Cronbach's α of 0.89 indicating instrument stability and system usability. Our results show that by combining computer vision and web technologies microplastic monitoring can be automated leading to rapid decision making.
(SAMPLE DATA) Livelihood Sustainability of Small-Scale Fishermen in Coastal Communities of Quezon Province: A Mixed Methods Study
This research examines the livelihood sustainability of small-scale fishermen in five coastal barangays of Quezon Province, Philippines, using a convergent mixed-methods design. Quantitative data from 320 fisherfolk households were analyzed alongside qualitative interviews to assess income stability, food security, and adaptive capacity. Results reveal that 68% of households fall below the food poverty threshold during lean fishing months, and that access to government microfinancing and livelihood diversification programs are critical protective factors. The study proposes a community-based sustainability framework combining cooperative enterprise, skills training, and digital market access.
(SAMPLE DATA) Predictive Analytics for Student Academic Performance Using Machine Learning Algorithms in Higher Education
This study investigates the application of machine learning algorithms—specifically Random Forest, Support Vector Machine, and Gradient Boosting—to predict academic performance of university students in the Philippines. Using a dataset of 1,200 undergraduate students over three academic years, the study identified key predictors including attendance rate, midterm grades, and socioeconomic indicators. Random Forest achieved the highest accuracy at 87.3%, enabling early intervention programs. The findings suggest that data-driven approaches can substantially reduce dropout rates and improve institutional effectiveness in higher education settings.
Scholarly Works from MSEUF Candelaria
Browse and filter our complete archive of research publications, academic journals, and scholarly outputs across all disciplines.
Showing 3 publications
(SAMPLE DATA) MicroPolluScan: A Deep Learning-Based Monitoring System for Classification of Microplastic Contamination in Fishponds
Microplastics in aquatic life are hazardous to sea life, food safety, and aquaculture. In this paper, we describe MicroPolluScan, an AI-based deep learning system which uses automated microscopic image analysis to detect, classify, and quantify microplastic contamination in fishponds. To facilitate the development, we employed an Agile Scrum-CRISP-DM paradigm, that is an architectural process based on an iterative software design methodology, along with structured data science methodology. Microscopic pictures of beads, fragments, and fibers were taken from fishponds in Lucena City, augmented with Roboflow, and trained in YOLOv5 and YOLOv8 networks on Google Colab. Comparison results demonstrated that YOLOv8 provided the best performance (precision = 0.82, recall = 0.85, F1 = 0.83, mAP = 0.89) because of the anchor-free detection head and C2f supporting mechanism. A fine-tuned model was implemented in a Flask-based web system, for real-time detection and visualization dashboards for practitioners of aquaculture. Software quality of the software evaluated following ISO/IEC 25010 has a mean of 3.80 (Strongly Agree) followed by a Cronbach's α of 0.89 indicating instrument stability and system usability. Our results show that by combining computer vision and web technologies microplastic monitoring can be automated leading to rapid decision making.
(SAMPLE DATA) Livelihood Sustainability of Small-Scale Fishermen in Coastal Communities of Quezon Province: A Mixed Methods Study
This research examines the livelihood sustainability of small-scale fishermen in five coastal barangays of Quezon Province, Philippines, using a convergent mixed-methods design. Quantitative data from 320 fisherfolk households were analyzed alongside qualitative interviews to assess income stability, food security, and adaptive capacity. Results reveal that 68% of households fall below the food poverty threshold during lean fishing months, and that access to government microfinancing and livelihood diversification programs are critical protective factors. The study proposes a community-based sustainability framework combining cooperative enterprise, skills training, and digital market access.
(SAMPLE DATA) Predictive Analytics for Student Academic Performance Using Machine Learning Algorithms in Higher Education
This study investigates the application of machine learning algorithms—specifically Random Forest, Support Vector Machine, and Gradient Boosting—to predict academic performance of university students in the Philippines. Using a dataset of 1,200 undergraduate students over three academic years, the study identified key predictors including attendance rate, midterm grades, and socioeconomic indicators. Random Forest achieved the highest accuracy at 87.3%, enabling early intervention programs. The findings suggest that data-driven approaches can substantially reduce dropout rates and improve institutional effectiveness in higher education settings.