A Machine Learning Approach on Illegal Fishing Detection Using RNN for the Area of Bauang, La Union, Philippines

  • Thomas L. Dumpit Jr School of Graduate Studies, Ama Computer University, Philippines
  • Richard Monreal College of Computer Studies, Ama Computer University, Philippines

Abstract

Purpose—In La Union, illegal, unreported, and unregulated (IUU) fishing threatens local livelihoods and marine ecosystems. Traditional methods are not enough to monitor wide maritime areas. This study aims to apply machine learning, particularly Recurrent Neural Networks (RNN), to detect illegal fishing by analyzing fishing patterns, vessel movements, and satellite imagery. The proposed system includes a server-side geofencing feature and a mobile client for collecting GPS data.

Methodology – This research uses a mixed-methods approach, combining both quantitative and qualitative techniques. The quantitative part focuses on developing and implementing an RNN model to detect illegal fishing. The qualitative aspect involves data collection and analysis to understand the challenges and opportunities related to IUU fishing in La Union.

Result – Survey findings show a need for modern monitoring solutions. About 72% of respondents use vessel monitoring systems, 64% are aware of illegal fishing, and 66% carry mobile phones. Additionally, 80% expressed interest in training, and 44% of respondents are aged 18–24, indicating high potential for adopting digital surveillance tools.

Conclusion – The RNN model has proven effective in identifying and monitoring illegal fishing in real time. This technology supports marine conservation and promotes the long-term sustainability of local fishing communities.

Recommendation – It is recommended to implement the RNN-based monitoring system in Bauang, La Union. This solution will enhance detection and law enforcement efforts, protect marine resources, and enable quick response actions to IUU fishing.

Practical Implications – The model has the potential for broader use. It can assist agencies like BFAR is enforcing fishing regulations and improving marine conservation nationwide. Real-time data analysis will also support sustainable fishing practices and reduce the negative impact of illegal fishing.

Author Biographies

Thomas L. Dumpit Jr, School of Graduate Studies, Ama Computer University, Philippines

I am Thomas L. Dumpit Jr., a retired Colonel of the Philippine Army, former Congressman of the 2nd District of La Union, and a dedicated public servant. Currently, I am a graduating student in the Doctor of Information Technology with a strong academic background. I hold a Bachelor of Science in General Studies, a Master’s in Management from the University of the Philippines, and a Master’s in Information Technology from AMA University. Additionally, I completed a Graduate Certificate in Public Financial Management at the Harvard Kennedy School of Government. I brought the leadership, discipline, and strategic thinking I developed throughout my military experience to my work in public service. As a former congressman, I supported digital transformation, infrastructure development, and national security. Having worked in technology, finance, and government for a long time, I am still dedicated to advancing the nation's development and fostering innovation.

Richard Monreal, College of Computer Studies, Ama Computer University, Philippines

Dr. Richard N. Monreal is an Associate Professor and the Dean of the College of Computer Studies at AMA University. I have extensive experience teaching Computer Engineering, IT, and Computer Science at institutions such as TIP-QC, University of the Cordilleras, Trinity University of Asia, and Divine Word College of Legazpi. My background in research and program management has enabled me to contribute to shaping future professionals in these fields. As a Program Head, I have managed faculty, overseen course schedules, and led various academic initiatives. My expertise in contracting, coding, testing, and maintaining software systems fuels my passion for advancing education and technology.

Published
2025-05-10
How to Cite
DUMPIT JR, Thomas L.; MONREAL, Richard. A Machine Learning Approach on Illegal Fishing Detection Using RNN for the Area of Bauang, La Union, Philippines. International Journal of Computing Sciences Research, [S.l.], v. 9, p. 3647-3658, may 2025. ISSN 2546-115X. Available at: <//stepacademic.net/ijcsr/article/view/620>. Date accessed: 18 june 2025.
Citation Formats
Issue
Vol 9 (2025): Volume 9
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited.