Drinking water in almost all the locations was found to be highly contaminated, except a few locations, where it was found to be
moderately contaminated for both the monsoons. Neural provides an easy and rapid method of monitoring of water quality. It also
becomes easier to compare the quality levels in different locations and to give priority for the required treatment to the location. Data
collected by various sensors at the node side such as pH, turbidity and oxygen level is sent via WSN to the base station. Data collected
from the remote site can be displayed in visual format as well as it can be analyzed using different simulation tools at base station. The
water various parameters like pH, Dissolved oxygen, electrical conductivity, turbidity and total dissolved solids data’s are collected
that given to the neural network. A neural network usually involves a large number of processors operating in parallel, each with its
own small sphere of knowledge and access to data in its local memory. An input data are multiplexed and given to the neural network.
The various water parameter ranges are taken from water. The water ranges are input data for a neural network. An input data are
given to the multiplexer and the multiplexed output data are given to the neural network. It decides the output based on the input
range. It will give an output of the water quality. This novel system has advantages such as no carbon emission, low power
consumption, more flexible to deploy at remote site and so on. The performance of the proposed model is compared with that of fuzzy
based models, demonstrating the robustness, accuracy, and effectiveness of our method. The simulated using Matlab tool and finally
the data results are sent to the water pollution control board in the regular intervals through Matlab server.