Design of Water Quality Monitoring System using SVM Algorithm

Due to the fact that having access to clean and safe water is a fundamental requirement of existence, the need for basic occupations is growing as the world's population rises. One method of gathering information about water quality is by the manual collection of samples and sending them to res...

Full description

Saved in:
Bibliographic Details
Published in2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC) pp. 1196 - 1201
Main Authors Sathish, P., Reddy, A. Supraja, Teja, G. Shiva, Kiran, G. Uday, Kireeti, A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.07.2023
Subjects
Analyzing and Predicting
Automatic Controlling
Cloud
Embedded Systems
Internet of Things
Machine Learning
Monitoring
Real-time systems
Sensor systems
Support vector machines
Temperature measurement
Temperature sensors
Water quality
Water storage
Online AccessGet full text

Cover

More Information
Summary:Due to the fact that having access to clean and safe water is a fundamental requirement of existence, the need for basic occupations is growing as the world's population rises. One method of gathering information about water quality is by the manual collection of samples and sending them to research facilities for detection and analysis. Because it takes a lot of time and effort, this strategy is not long-term viable. This article explores how machine learning and the Internet of Things (IOT) may be used to improve water storage facilities. In this article, the application of machine learning and the Internet of Things (IOT) in water storage facilities is planned, tested, and evaluated. Water quality monitoring is an essential aspect of ensuring safe and sustainable water resources. In this study, a water quality monitoring system using Support Vector Machine (SVM) algorithm and Raspberry Pi is proposed. The system uses various sensors such as temperature, pH, total dissolved solids, and turbidity to measure the water quality parameters. The SVM algorithm is used to analyse the sensor data and classify the water quality into different categories such as potable, slightly contaminated, and highly contaminated. The proposed system provides real-time monitoring of water quality and alerts the user if the water quality falls below the acceptable levels. The system is cost-effective, easy to install, and can be used in remote areas where water quality monitoring is difficult. The results demonstrate the efficacy of the proposed system in accurately monitoring the water quality parameters and providing real-time alerts.
DOI:10.1109/ICESC57686.2023.10193737