WATER QUALITY PREDICTION

Water quality has a direct impact on public health and the environment. Water is used for various practices, such as drinking, agriculture, and industry. To evaluate the quality of rivers two approaches are considered, including measuring the water quality components and defining the mechanism of pollution transmission. Among water quality components, measuring the DO, COD, BOD, EC, pH, temperature, K, Na, Mg and etc.

Nowadays, There are many risks related to water quality prediction. Data Mining is one of the most motivating and vital area of research with the aim of extracting information from tremendous amount of accumulated data sets. Here a new model for classifying water quality prediction in waster irrigation by using Machine Learning concepts. Here we used Regression techniques to find the quality of prediction.

The previous models have high time complexity and space complexity whereas this model is constrained with the lot of advantages and with a higher accuracy than any other model already proposed. In this model we used Machine learning algorithm named Linear Regression which give an accuracy more then 80% of the previously predicted problem and there is an user friendly user interface to check water quality and lot of the previous models haven’t included the UI (User interface) which is so friendly and convenient for the users. There are some of the models that are referred for the closure below: Glorfeld and Hardgrave (2001) proposed a complete and useful systematic way to produce an optimal design of a high performance model for neural network estimating of the water quality . The neural network constructed using their design was able to classifying 75% of water applicants correctly. Michael D. Johnson, Anders Gustafsson studied broadly the usages of data mining techniques in water quality and its related impacts on several operations. They built a prediction model to predict the urban water quality using the techniques of neural network and classification. Jagielska et al investigated the abilities of neural networks in classifying water quality risk, uncertain logic genetic algorithms, rule stimulation software, he concluded that the genetic approach is more favorably than the neuron fuzzy and rough set methods.

Machine Learning( Linear Regression):

In statistics, linear regression is a linear approach to modeling the relationship between a scalar response and one or more explanatory variables. The case of one explanatory variable is called simple linear regression. For more than one explanatory variable, the process is called multiple linear regression. This term is distinct from multivariate linear regression, where multiple correlated dependent variables are predicted, rather than a single scalar variable. In linear regression, the relationships are modeled using linear predictor functions whose unknown model parameters are estimated from the data. Such models are called linear models. Most commonly, the conditional mean of the response given the values of the explanatory variables is assumed to be an affine function of those values; less commonly, the conditional median or some other quantile is used. Like all forms of regression analysis, linear regression focuses on the conditional probability distribution of the response given the values of the predictors, rather than on the joint probability distribution of all of these variables, which is the domain of multivariate analysis.

Related posts:

You came to my life as a surprise, a little color in my sky. Fell on my destiny and landed on my heart. From the day we met until the day we parted ways, I never once felt alone.

Spent the last week reviewing reams of contracts and witnessing ruthless contract negotiations first-hand. And then attempted discussing life in general with a lawyer friend over dinner just so I can…

As I sit here this morning I realize that I’m on the journey of becoming. Becoming what I am not sure but I would like to think I am evolving into a better human being; a more well rounded person…