Data Modeling
Mathematical and Computational Data Modeling
0
Citations
3.6k
Views
20
Articles
Volume 5 Number 1 2024
RESEARCH ARTICLE (Open Access)
IoT-Based Smart Aquaculture Water Quality Monitoring and Health Prediction Using Machine Learning
Kamruzzaman Mithu 1*, Md. Nesar Uddin1 ,Md. Ataur Rahman1, Sayed Rokibul Hossain1, A.K.M. Muzahidul Islam1
Data Modeling 5 (1) 1-18 https://doi.org/10.25163/data.5110759
Submitted: 10 June 2024 Revised: 13 August 2024 Accepted: 14 August 2024 Published: 16 August 2024
Abstract
Background: Maintaining stable aquatic environmental conditions remains a persistent challenge because fluctuations in water quality parameters can rapidly affect fish health, productivity, and ecosystem stability. Recent advances in Internet of Things (IoT) technologies and machine learning have created new opportunities for developing automated and predictive aquaculture monitoring systems capable of supporting more intelligent water-quality management.
Methods: In this study, a low-cost IoT-based aquaculture monitoring and prediction framework was developed using an ESP8266 microcontroller integrated with temperature, pH, total dissolved solids (TDS), and electrical conductivity (EC) sensors. Environmental data were continuously collected from aquaculture samples and transmitted through Wi-Fi communication to a cloud-hosted MySQL database. A web-based dashboard was developed for real-time visualization of environmental conditions and predictive outputs. Machine learning algorithms including Decision Tree, Support Vector Machine (SVM), Random Forest, and Logistic Regression were implemented using the Scikit-learn framework to classify aquaculture health conditions based on the collected environmental dataset.
Results: The proposed system successfully performed real-time environmental monitoring, wireless data transmission, cloud storage, and predictive analysis throughout the experimental period. Comparative evaluation demonstrated that Logistic Regression achieved the highest overall classification accuracy of approximately 91%, while Random Forest and SVM produced comparatively strong F1-score performances of 86.5% and 84.8%, respectively.
Conclusion: The findings demonstrate that integrating IoT infrastructure with machine learning techniques can provide an affordable and operationally practical framework for intelligent aquaculture monitoring.
Keywords: Internet of Things (IoT), Smart aquaculture, Water quality monitoring, Machine learning, Environmental prediction
References
Bhatnagar, A., & Devi, P. (2013). Water quality guidelines for the management of pond fish culture. International Journal of Environmental Sciences, 3(6), 1980–2009.
Bhatnagar, A., Jana, S. N., Garg, S. K., Patra, B. C., Singh, G., & Barman, U. K. (2004). Water quality management in aquaculture. In Course manual of summer school on development of sustainable aquaculture technology in fresh and saline waters (pp. 203–210). CCS Haryana Agricultural University.
Boyd, C. E. (1982). Water quality management for pond fish culture. Elsevier Scientific Publishing Company.
Delince, G. (2013). The ecology of the fish pond ecosystem: With special reference to Africa (Vol. 72). Springer Science & Business Media.
DFRobot. (n.d.-a). SEN0161-V2 analog pH meter. https://www.dfrobot.com/product-1782.html
DFRobot. (n.d.-b). DS18B20 waterproof temperature sensor. https://www.dfrobot.com/product-689.html
DFRobot. (n.d.-c). SEN0244 TDS sensor. https://www.dfrobot.com/product-1662.html
Espressif Systems. (n.d.). ESP8266 Wi-Fi MCU. https://www.espressif.com/en/products/socs/esp8266
Gondchawar, N., & Kawitkar, R. S. (2016). IoT based smart agriculture. International Journal of Advanced Research in Computer and Communication Engineering, 5(6), 838–842.
Israni, S., Meharkure, H., & Yelore, P. (2015). Application of IoT based system for advance agriculture in India. International Journal of Innovative Research in Computer and Communication Engineering, 3(11), 11586–11592.
Kayalvizhi, S., Reddy, K., Kumar, V., & Prasanth, V. (2015). Cyber aqua culture monitoring system using Arduino and Raspberry Pi. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 4, 2320–3765.
Patil, M. K., Patil, M. S., Patil, M. S., & Patil, M. V. (2015). Monitoring of turbidity, pH and temperature of water based on GSM. International Journal for Research in Emerging Science and Technology, 2(3), 16–21.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Raju, K. R. S. R., & Varma, G. H. K. (2018). Knowledge based real time monitoring system for aquaculture using IoT. In Proceedings of the International Conference on Innovations in Science, Engineering and Technology (ICISET) (pp. 318–321).
Saha, S., Rajib, R. H., & Kabir, S. (2017). IoT based automated fish farm aquaculture monitoring system. In 2017 IEEE 7th International Advance Computing Conference (IACC) (pp. 201–206). IEEE.
Simbeye, D. S., & Yang, S. F. (2014). Water quality monitoring and control for aquaculture based on wireless sensor networks. Journal of Networks, 9(4), 840–849.
United Nations Food and Agriculture Organization. (2012). The state of world fisheries and aquaculture 2012. FAO. https://www.fao.org/3/i2727e/i2727e00.htm
Varma, G. H. K., & Raju, K. R. S. R. (2018). Knowledge based real time monitoring system for aquaculture using IoT. International Conference on Innovations in Science, Engineering and Technology, 318–321.
WEMOS. (2004). LOLIN D1 mini. https://www.wemos.cc/en/latest/d1/d1_mini.html
Zhu, H.-J. (2010). Global fisheries development status and future trend analysis. Taiwan Economic Research Monthly, 33, 1–8.
Recommended articles
Fairness-Aware AI for Healthcare Supply Chain Equity: Integrating Social Determinants of Health, Causal Modeling, and Geospatial Optimization
Early Prediction of Postprandial Glycemic Response in Gestational Diabetes Using Continuous Glucose Monitoring and Gradient Boosting Models
Illuminating Biological Dark Matter: Integrating Metagenomics, Synthetic Biology, and AI to Unlock Microbial and Genomic Potential for Therapeutics and Biotechnology
1
Save
Save
0
Citation
Citation
100
View
View
0
Share
Share