www.ijemr.net ISSN (ONLINE): 2250-0758, ISSN (PRINT): 2394-6962
362 Copyright © 2011-15. Vandana Publications. All Rights Reserved.
Volume-5, Issue-6, December-2015
International Journal of Engineering and Management Research
Page Number: 362-365
An Approach for Classifying River Water Quality using Data Mining
Technique
Sanjeev Gour
1
, Dr.Anil Rajput
2
, Purushottam Sharma
3
1
Department of Computer Science, LBS College, Harda, INDIA
2
Department of Mathematics and Computer Science, Govt. P.G. College, Sehore, INDIA
3
Research Scholar, B.V.V, Bhopal, INDIA
ABSTRACT
Water is vital for life, as a water supply for people,
for the diverse ecosystems on which we depend, for
agriculture, industry and recreation. The amount of available
fresh clean water of river Narmada is changing because of
growing populations, changes in farming and the new needs
of industry. Water quality determines the ‘goodness’ of water
for particular purposes. In this paper, different water quality
parameters are selected namely, Dissolved oxygen (DO),
Nitrate (NO3), Biochemical oxygen demand (BOD),Hardness
,pH, TDS and Temperature etc. These parameters are
calculated for the Narmada River and Analyzed through
Classification and Prediction techniques of Data mining via
Software Tool ESTARD Ver. 3.1.325. The results conclude
that DO, NO3 and BOD conditions vary from good to worst
for the River Narmada at Hoshangabad district. The worst
conditions are registered for the NO3-N, where the quality
status of Water is poor due to industries sewage and also The
comparisons of these parameters are combined to provide a
water quality ranking (good[A], fair[B], poor[C],very
poor[D]) for River Water.
Keyword--- Classification, Prediction techniques
I. INTRODUCTION
Water Quality is a major concern around the
world. Water quality is affected by a wide range of natural
and human influences. The effects of human activities on
water quality are both widespread and varied in the degree
to which they disrupt the ecosystem and/or restrict water
use. Eutrophication results not only from point sources,
such as wastewater discharges with high nutrient loads, but
also from diffuse sources such as run-off from agricultural
land fertilized with organic and inorganic fertilizers. The
quality of water may be described in terms of the
concentration and state (dissolved or particulate) of some
or all the organic and inorganic material present in the
water together with certain physical characteristics of the
water. It is determined by examination of water samples
on site. The main elements of water quality monitoring
are, therefore, on-site measurements, the collection and
analysis of water samples, the study and evaluation of the
analytical results, and the reporting of the particular
location and time at which that sample was taken. Our
purpose of this study is, therefore, to gather sufficient data
to assess spatial and/or temporal variations in water
quality. In this paper various data mining techniques such
as classification and prediction are used to analyze various
water quality parameters of river Narmada [1].
II. DATA MINING
Data mining includes the use of sophisticated data
analysis tools to discover previously not known, valid
patterns and relationships in large data sets. These tools
can involve mathematical algorithms, statistical models
and machine learning methods (such as neural networks or
decision trees). As a result, data mining consists of more
managing and collecting data, it also includes analysis and
prediction. One of such Data mining tool ESTARD is used
in this study.
III. DATA SET
In this study water quality data of river Narmada
of district Hoshangabad of M.P is used. we have collected
these valuable data from the Laboratory Level-II of
Central Water Commission (CWC) State Baseline station
whose state office is located at Narmada Basin, Block-3,
G-Floor, Prayavas Bhavan, Mother Teresa Marg, Arera