| TITLE | Water Quality Monitor System using Exploratory Data Analytics and Machine Learning Model |
|---|---|
| ABSTRACT | Access to safe drinking water is a critical global challenge, directly impacting public health and well-being. Traditional water quality testing methods, while accurate, are often time-consuming, costly, and require specialized equipment. This study explores the application of machine learning (ML) and deep learning (DL) techniques to predict water potability using physicochemical properties of water samples. We utilize a publicly available dataset containing multiple water quality parameters and a binary potability label. The dataset presents challenges such as missing values and class imbalance, which we address through mean imputation and Synthetic Minority Over-sampling Technique (SMOTE), respectively. We implement and compare several ML models including Logistic Regression, Decision Trees, Random Forest, Support Vector Machines, Naive Bayes, and XGBoost, alongside a custom deep neural network architecture. Our experiments reveal that Gaussian Naive Bayes, when combined with feature discretization and hyperparameter tuning, achieves the highest accuracy of approximately 91%. Ensemble methods like Random Forest and gradient boosting with XGBoost also demonstrate strong performance. The deep learning model, while promising, requires further tuning and larger datasets for optimal results. This work highlights the importance of comprehensive data preprocessing and model selection in developing reliable water potability prediction systems, offering a scalable and cost-effective alternative to traditional testing methods. |
| AUTHOR | DR. M. Sengaliappan, Gopika S Professor, Department of Computer Applications, Nehru College of Management, Coimbatore, Tamil Nadu, India Student of II MCA, Department of Computer Applications, Nehru College of Management, Coimbatore, Tamil Nadu, India |
| PUBLICATION DATE | 2025-10-27 |
| VOLUME | 12 |
| ISSUE | 5 |
| 12_Water Quality Monitor System using Exploratory Data Analytics and Machine Learning Model.pdf | |
| KEYWORDS |
Copyright@IJARASEM