• J. Charles
• G. Vinodhini
• R. Nagarajan

Recently, water quality monitoring becomes vital to increase protection and management of water resources. Under the related laws and regulations, environmental protection department agency monitors rivers, lakes, streams, and other kinds of water body for assessing water quality condition. The valid and high-quality data produced from the monitoring activity helps water resource manager to understand the pollution control needs, present pollution situation and energy consumption problems. In this context, this study designs a new class imbalance handling with deep belief network (CI-DBN) technique to estimate the water quality (WQ). The proposed CI-DBN model involves different processes such as pre-processing, class imbalance (CI) handling, DBN based prediction, and artificial rain drop algorithm (ARA) based hyperparameter handling. The DBN model reviews the class balanced input data and performs the prediction process. Finally, the ARA is used to optimally choose the hyperparameter values of the DBN model. A wide-ranging simulation analysis is carried out and the experimental results showcased the significate of the CI-DBN model compared to the recent WQI predictive approaches interms of various measures.

Water quality index, Deep learning, DBN model, Parameter tuning, Artificial intelligence, Soft Computing

"Deep Learning Based Optimal Deep belief network for Water Quality Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.e42-e54, September-2022, Available :http://www.jetir.org/papers/JETIR2209406.pdf

"Deep Learning Based Optimal Deep belief network for Water Quality Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppe42-e54, September-2022, Available at : http://www.jetir.org/papers/JETIR2209406.pdf