Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198745,
        author = {Mohammed Saqib and Nitin Sharma and Mohammed Adil Hussain},
        title = {IoT-Based Smart Aquaculture Monitoring System with Cloud Integration and AI-Assisted Fish Activity Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10629-10635},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198745},
        abstract = {Water quality degradation is the leading cause of fish death in small-scale aquaculture operations, yet affordable continuous monitoring solutions remain largely unavailable to farmers who need them most. We propose a low-cost embedded monitoring platform built using the ESP32 microcontroller that measures water temperature through a DS18B20 probe, detects mechanical disturbances through an MPU6050 inertial sensor, and generates estimated values of pH levels, dissolved oxygen, turbidity, and water level. The data is then transmitted to ThingSpeak over HTTPS every sixteen seconds. A companion ESP32-CAM module runs at the same time to analyse fish behaviour. A local web dashboard serves directly from the microcontroller providing gauge-style readouts, color-coded alert badges, and a live video feed that remain fully functional during internet outages. Over a 72-hour controlled evaluation the system achieved a ThingSpeak upload success rate of 99.21%, an SD card write reliability of 99.1%, a fish activity weighted F1-score of 91.4%, and a temperature measurement error of ±0.31°C relative to a calibrated reference. The complete bill of materials totals approximately USD35, which is four to fourteen times cheaper than comparable systems reported in recent literature.},
        keywords = {Aquaculture monitoring, ESP32, IoT, ThingSpeak, TensorFlow Lite, water quality, fish behaviour classification, edge inference, dissolved oxygen, turbidity.},
        month = {April},
        }