IMPROVING PRODUCTIVITY THROUGH IOT-BASED FISH POPULATION MONITORING IN INTENSIVE

Authors

  • Ravshanbekov Behruz Author
  • Mullabaev Nodirbek Author
  • Lochinbek Boboev Author

Keywords:

Internet of Things (IoT), aquaculture, fish counting, computer vision, artificial intelligence, MQTT, edge computing, smart aquaculture

Abstract

This paper presents an integrated Internet of Things (IoT)-based system designed for real-time monitoring of fish populations under intensive aquaculture conditions. Traditional methods — visual observation, manual net counting, and periodic sampling — are labor-intensive, prone to high error rates, and fail to provide real-time data, resulting in feed waste, oxygen deficiency, and increased mortality. The proposed system encompasses a complete architecture consisting of an underwater camera, ESP32/Raspberry Pi microcontrollers, an artificial intelligence model based on a convolutional neural network (YOLOv8), the MQTT protocol, a cloud database, and a user dashboard interface. The system also continuously monitors water temperature, dissolved oxygen, pH, and turbidity parameters, and automatically issues alerts when anomalies occur. Experimental results from a 40-day field trial showed that the fish-detection accuracy of the IoT-AI system reached 96.4%, compared to 71–74% for the traditional method. In ponds where the system was deployed, the feed conversion ratio (FCR) decreased from 1.42 to 1.21, fish survival rate increased by 4.6 percentage points, and labor costs were reduced by 34%. These results confirm the potential of IoT and artificial intelligence technologies for accurate fish counting, resource optimization, and improved aquaculture productivity. The paper describes in detail the system architecture, mathematical models, hardware/software specifications, and directions for future research.

References

[1] Y. Zhou, H. Yu, and Z. Wang, "A review of deep learning approaches for fish detection and classification," Computers and Electronics in Agriculture, vol. 189, p. 106379, 2021.

[2] X. Li, J. Shang, and M. Song, "Real-time underwater fish detection using YOLO-based deep learning models," Sensors, vol. 22, no. 8, p. 3013, 2022.

[3] L. Wang, F. Chen, and Y. Liu, "Wireless sensor network based water quality monitoring system for aquaculture," IEEE Internet of Things Journal, vol. 8, no. 14, pp. 11235–11247, 2021.

[4] R. Kumar and A. Singh, "NB-IoT enabled smart aquaculture monitoring for rural farms," Aquacultural Engineering, vol. 96, p. 102217, 2022.

[5] F. O'Donncha, E. Stockwell, and J. Fitzgerald, "Data driven insight into fish behaviour and their use for precision aquaculture," Frontiers in Marine Science, vol. 8, p. 754388, 2021.

[6] F. Antonucci and C. Costa, "Precision aquaculture: A short review on engineering innovations," Aquaculture International, vol. 28, no. 1, pp. 41–57, 2020.

[7] A. F. Fernandes, E. M. Turra, and R. de Alvarenga, "Deep learning image segmentation for extraction of fish body measurements and prediction of body weight," Computers and Electronics in Agriculture, vol. 170, p. 105274, 2020.

[8] L. Yang, Y. Liu, and H. Yu, "Computer vision models in intelligent aquaculture with emphasis on fish detection and behavior analysis: A review," Archives of Computational Methods in Engineering, vol. 28, pp. 2785–2816, 2021.

[9] N. Naik, "Choice of effective messaging protocols for IoT systems: MQTT, CoAP, AMQP and HTTP," in Proc. IEEE Int. Systems Engineering Symposium (ISSE), Vienna, Austria, 2017, pp. 1–7.

[10] M. Saberioon, A. Gholizadeh, and P. Cisar, "Application of machine vision systems in aquaculture with emphasis on fish: state-of-the-art and key issues," Reviews in Aquaculture, vol. 9, no. 4, pp. 369–387, 2017.

[11] M. M. Rahman, M. S. Hossain, and T. Rahman, "Low-cost Arduino based real-time water quality monitoring system," Journal of Sensors, vol. 2022, Art. no. 3183507, 2022.

[12] J. Chen, Y. Zhang, and X. Yu, "A machine learning based early warning system for water quality anomaly detection in aquaculture," Sensors, vol. 21, no. 15, p. 5019, 2021.

[13] D. V. Rao, K. Prasad, and S. Reddy, "LSTM based prediction of dissolved oxygen for intelligent aquaculture management," Computers and Electronics in Agriculture, vol. 198, p. 107070, 2022.

[14] S. Ahmed, R. Islam, and M. Karim, "AI based decision support system for feed optimization in fish farming," Aquacultural Engineering, vol. 100, p. 102305, 2023.

[15] Food and Agriculture Organization of the United Nations, The State of World Fisheries and Aquaculture 2022: Towards Blue Transformation, Rome: FAO, 2022.

[16] C. Zhao, X. Wu, and H. Han, "Application of machine vision technology in aquatic animal farming: a review," Aquaculture, vol. 542, p. 736790, 2021.

[17] P. Lopez-Vazquez, J. Lopez-Guede, and M. Marini, "Deep learning based fish abundance estimation using sonar images," Sensors, vol. 20, no. 24, p. 7085, 2020.

[18] A. Iqbal, K. Latif, and S. Aslam, "IoT based smart aquaculture monitoring and control system," in Proc. Int. Conf. on Advances in Computing and Communication Engineering, 2021, pp. 152–157.

[19] M. Tavares, R. Silva, and F. Costa, "Edge computing for real-time video analytics in aquaculture," Internet of Things, vol. 20, p. 100626, 2022.

[20] Y. Cui, Y. Guo, and X. Bai, "Fish counting in aquaculture using improved YOLOv5 with attention mechanism," Applied Sciences, vol. 13, no. 4, p. 2570, 2023.

[21] S. Palconit, R. Sybingco, and E. Dadios, "IoT and machine learning integrated smart aquaculture systems: A survey," in Proc. IEEE Region 10 Conference (TENCON), 2021, pp. 1834–1839.

[22] G. Chhetri, S. Bhandari, and R. Adhikari, "Comparative study of LoRa and Wi-Fi for long range low power IoT applications," IEEE Access, vol. 9, pp. 145611–145623, 2021.

[23] N. Ubina, S. Cheng, and C. Chang, "Evaluating fish freshness using AI and computer vision," Computers and Electronics in Agriculture, vol. 183, p. 106088, 2021.

[24] X. Zhang, S. Yang, and L. Zheng, "Cloud based intelligent aquaculture monitoring platform with predictive analytics," IEEE Access, vol. 10, pp. 45210–45222, 2022.

[25] R. Ali, M. Farooq, and S. Aslam, "A survey of edge and cloud computing based IoT architectures for smart agriculture and aquaculture," Journal of Network and Computer Applications, vol. 210, p. 103528, 2023.

[26] H. J. Vo, T. T. Nguyen, and D. H. Le, "Automatic fish counting and species classification using YOLO and deep sort," in Proc. Int. Conf. on Machine Learning and Applications, 2022, pp. 891–896.

[27] E. Odei, C. Boateng, and D. Mensah, "Smart water quality monitoring for sustainable aquaculture: A systematic review," Sustainability, vol. 15, no. 6, p. 5391, 2023.

[28] J. K. Costa, R. Oliveira, and V. Santos, "Feed conversion ratio optimization through precision aquaculture technologies," Aquaculture Reports, vol. 25, p. 101245,

Published

2026-07-30