Implementation of Machine Learning for Freshwater Fish Detection
DOI:
https://doi.org/10.56127/juit.v5i1.1427Keywords:
Android-based application, freshwater fish recognition, visual image classification, fishing assistance, artificial intelligence, TensorFlow Lite frameworkAbstract
Recent advancements in mobile technology and machine learning have enabled the development of practical tools, such as Android applications, to assist in real-time fish species identification, particularly in the context of freshwater fisheries in Indonesia. Objective: This research aims to design and implement an Android application that helps anglers accurately identify and categorize freshwater fish species native to Indonesia. The app integrates machine learning-based image recognition to provide a practical tool for fishing enthusiasts while supporting conservation efforts for Indonesia’s freshwater biodiversity. Methodology: A quantitative approach was employed, focusing on mobile application development using Kotlin for Android. The application uses a TensorFlow Lite-based image recognition model for real-time image processing on mobile devices. Data for the model were gathered from publicly available fish species datasets. The system was tested across multiple Android devices to evaluate compatibility and efficiency. Findings: The application successfully identifies and classifies various freshwater fish species in Indonesia, providing users with accurate species profiles, biological characteristics, and appropriate bait recommendations. The system operates efficiently in real-time on mobile devices without relying on cloud computing, ensuring accessibility in remote areas. Testing results across different Android devices confirm the app's robustness and user-friendly interface. Implications: This research demonstrates the integration of mobile technology and machine learning in fisheries, offering a valuable tool for both recreational and professional anglers. The app promotes awareness of freshwater fish species preservation and supports sustainable fishing practices. Additionally, it can serve educational purposes by enhancing knowledge of local biodiversity and fostering fish conservation efforts. Originality: This research introduces an innovative mobile-based solution to freshwater fish identification. Unlike previous studies, which focused on desktop-based methods, this study offers a practical mobile application that operates efficiently in real-time on-site. The originality lies in combining machine learning and mobile technology to address fish identification challenges while contributing to biodiversity conservation.
References
Balmaceda, E. T. et al. (2022). Machine Learning-Based Algorithm for Fish Kill Evaluation using Differential Changes of Input Parameters via Wireless Communication. 2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2022. https://doi.org/10.1109/HNICEM57413.2022.10109461
Borah, A. R. et al. (2024). Real-Time Monitoring of Aquarium Conditions to Ensure Optimal Fish Health. 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024, 1555–1559. https://doi.org/10.1109/IDCIoT59759.2024.10467906
Cooke, S. J., & Cowx, I. G. (2004). The role of recreational fishing in global fish crises. BioScience, 54(9), 857–859. https://doi.org/10.1641/0006-3568(2004)054[0857:TRORFI]2.0.CO;2
Corporation, I. (2021). Intel® CoreTM i7-1165G7 processor specifications. https://www.intel.com
Developers, A. (2023). Android Studio and SDK tools documentation. Google. https://developer.android.com
Fouad, M. M. et al. (2016). A fish detection approach based on BAT algorithm. Advances in Intelligent Systems and Computing, 407, 273–283. https://doi.org/10.1007/978-3-319-26690-9_25
Genymotion. (2023). Genymotion user guide: Android emulator for app testing. https://www.genymotion.com
Goodfellow, I. et al. (2016). Deep learning. MIT Press.
Hadi, S. et al. (2023). Local dataset-driven image classification for freshwater fish species using convolutional neural networks. International Journal of Intelligent Systems and Data Science, 7(3), 66–75. https://doi.org/10.1504/IJISDS.2023.132145
Hamzaoui, M. et al. (2025). An Optimized Bounding Box Technique for Enhanced Underwater Fish Detection. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 250, pp. 108–118). https://doi.org/10.1007/978-3-031-87778-0_10
Istiqomah, R. F. et al. (2024). My I-Pond : Water Quality Monitoring with IoT and Machine Learning to Reduce Pond Cultivation Failure for Farmers. Proceeding of the IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA, 2024, 150–155. https://doi.org/10.1109/ICSIMA62563.2024.10675577
Lab, G. C. (2023). Teachable Machine: Train a computer to recognize images, sounds, and poses. https://teachablemachine.withgoogle.com
Liu, S. et al. (2021). Application of mobile and image recognition technologies in fish species identification. Aquaculture and Fisheries, 6(5), 423–430. https://doi.org/10.1016/j.aaf.2020.08.003
Mustafidah, H. et al. (2025). The most optimum distance calculation method on k-nearest neighbor algorithm in image classification of freshwater fish. AIP Conference Proceedings, 3234(1). https://doi.org/10.1063/5.0259421
Nations, F. and A. O. of the U. (2020). The state of world fisheries and aquaculture 2020. FAO.
Nelson, J. S. et al. (2016). Fishes of the world (5th (ed.)). Wiley.
Pressman, R. S., & Maxim, B. R. (2020). Software engineering: A practitioner’s approach (9th (ed.)). McGraw-Hill Education.
Rahman, M. A. et al. (2021). Freshwater fish species identification using machine learning and mobile image acquisition. Journal of Computing and Informatics, 9(2), 101–110. https://doi.org/10.31289/jci.v9i2.4567
Ranjan, R. et al. (2023). Effects of image data quality on a convolutional neural network trained in-tank fish detection model for recirculating aquaculture systems. Computers and Electronics in Agriculture, 205. https://doi.org/10.1016/j.compag.2023.107644
Setiawan, R., & Lestari, D. (2022). Deep learning-based freshwater fish recognition on mobile platforms under varying illumination conditions. Journal of Artificial Intelligence Research and Applications, 4(1), 45–54. https://doi.org/10.30762/jaira.v4i1.2891
Shiam Prodhan, M. et al. (2024). Advancing Fish Species Identification in Bangladesh: Deep Learning Approaches for Accurate Freshwater Fish Recognition. Lecture Notes in Networks and Systems, 834, 113–122. https://doi.org/10.1007/978-981-99-8349-0_10
Sommerville, I. (2016). Software engineering (10th (ed.)). Pearson Education.
Wang, H. et al. (2020). Study on Freshwater Fish Image Recognition Integrating SPP and DenseNet Network. 2020 IEEE International Conference on Mechatronics and Automation, ICMA 2020, 564–569. https://doi.org/10.1109/ICMA49215.2020.9233696
Wexler, J. et al. (2019). The What-If Tool: Interactive probing of machine learning models. IEEE Transactions on Visualization and Computer Graphics, 26(1), 56–65. https://doi.org/10.1109/TVCG.2019.2934619
Zhang, L. et al. (2018). Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geoscience and Remote Sensing Magazine, 6(2), 22–40. https://doi.org/10.1109/MGRS.2018.2795608
