Water quality monitoring in aquaculture to increase fish growth performance based on sensor outcomes

Phang, Jun Sen (2023) Water quality monitoring in aquaculture to increase fish growth performance based on sensor outcomes. Final Year Project, UTAR.

Preview

PDF Download (7Mb) | Preview

Abstract

The increasing demand for sustainable aquafarming practices has prompted the development of advanced water quality monitoring systems. This project introduces a comprehensive Water Quality Monitoring System that encompasses four key modules: the Data Acquisition Module, Communication Module. Data Processing and User Interface Module. The project's objectives encompass analyzing existing aquafarming tools, conducting water quality analysis, developing a mobile application for data visualization, and evaluating water quality to optimize fish growth and maintain ideal conditions. An evolutionary prototyping approach was used for system development and successful implementation. In the end, the objectives are achieved when the water quality monitoring system was successfully developed and deployed in an aquaculture farm for water quality monitoring. The developed data collection module can efficiently collect and transmit data to the ThingSpeak cloud server, which stores and provides REST API for data processing and retrieval. The user interface module runs efficiently on the Android emulator and cooperates with the data processing module to provide data processing, user authentication and authorization, and machine learning data prediction to support real-time water parameter monitoring. In conclusion, this FYP report discusses the system's achievements, limitations, and recommendations for future enhancements. While the system achieved its goals, certain limitations emerged during testing, leading to suggestions for improvement. This project represents a significant step toward efficient and sustainable aquafarming practices through advanced water quality monitoring.

Actions (login required)