Cloud-Integrated AI-Enhanced Software IoT Framework for Real-Time Water Quality Monitoring and E. Coli Prediction via Wireless Sensor Networks
Pages : 91-98, DOI: https://doi.org/10.14741/ijmcr/v.12.1.12Download PDF
The increasing concerns over waterborne diseases highlight the necessity of real-time water quality monitoring and contamination prediction systems. This paper proposes a cloud-integrated AI-enhanced software IoT framework for real-time water quality monitoring and E. Coli prediction via wireless sensor networks. The system leverages IoT sensors to measure key water quality parameters such as TDS, pH, and dissolved oxygen, transmitting the collected data wirelessly to the cloud via LoRaWAN technology for secure storage and processing. The data undergoes pre-processing to handle missing values, normalize features, and remove outliers. The Random Forest (RF) model is then applied to predict the likelihood of E. Coli contamination based on the water quality parameters. The results are displayed on a web dashboard, providing real-time predictions and triggering alerts when contamination levels exceed safe thresholds. This integrated approach ensures scalable, accurate, and timely decision-making, allowing local authorities to take immediate action when contamination risks are identified. The framework’s novelty lies in its combination of machine learning, IoT sensors, and cloud computing to deliver continuous water safety monitoring. The performance of the proposed system is evaluated using the Water Quality Monitoring Dataset, achieving 99% accuracy, 98% precision, 97.5% recall, 98.5% F1-Score, and an AUC-ROC of 98.7%. These results demonstrate the potential of the framework to improve water quality management and public health protection.
Keywords: Real-Time Water Quality Monitoring, E. Coli Prediction, IoT Sensor Networks, Cloud Computing, Random Forest Machine Learning