International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Science , Computer Science and Engineering

Volume4,December 2017,

Topic : Comparision of K-Means and Knn Algorithm in Data Mining

Authors:S.R.Kalaiselvi || C. Karpagam

Abstract:Data mining is the procedure for analyzing data from the different perspective and shortening it into helpful information. It can be used to increase income, minimize the costs. Data mining software is one of the analytical tools for analyzing data. It allows users to examine data from many different proportions, classify it, and review the relationships identified. Theoretically, data mining is the process of ruling correlations or patterns among dozens of fields in huge relational databases. Nowadays, organizations are accumulating vast and growing amounts of data in different formats and different databases. A data mining algorithm is a set of calculations which creates a data mining model from data. To build a model, the algorithm first analyzes the data and it looks for the particular type of pattern. These algorithms use the outcome of the analyzed data to define the most favorable parameters for creating the mining model. K-means is the unsupervised learning algorithm and it is an incremental approach to clustering data dynamically adds one cluster center at a time through a deterministic global search procedure. It is a simple and easy way to classify a given data set through a certain number of clusters. The k-Nearest Neighbors algorithm (or k-NN for short) is a non-parametric method used for classification and regression. In k-NN algorithm, neighbors are taken from a set of objects for which the class (for k-NN classification) otherwise the object property value (for k-NN regression) is identified. This can be considered of as the training set for the algorithm, though no explicit training step is necessary..

Keywords: Data - Information – Relationships – Analytical tools – Clustering Algorithm – groups - centroid – Data Frame – distance metrics - Prediction – Euclidean Distance – Neighbour-Dimenions–GetAccuracyfunction.

Download Paper

DOI: 01.1617/vol4/iss12/pid06592

Related Articles

Wormhole Attack Prevention and Detection Approaches in Mobile Ad hoc Networks: A Survey.

Authors: Avinash Singh || Ram Singar Verma

Doi : 01.1617/vol4/iss03/pid34591

Volume4 ,March 2017.

Developing a GIS Platform for Tourism marketing and promotion In Nigeria: Case Study Of Bauchi State

Authors: Abubakar Siddiq Ango || Abdulsalam Waheed Abdulfatah, Idrissa Djibo

Doi : 01.1617/vol3/iss09/pid91783

Volume3 ,September 2017.

Decentralized Trust Management and Trust Worthiness of Cloud Environments

Authors: Qhubaib Syed || Syed Afzal Ahmed,Syed Abdul Haq

Doi : 01.1617/vol4/iss4/pid21386

Volume4 ,April 2017.

Brain Controlled Chess Based on Virtual Reality Control for Paralyzed Patients

Authors: Sindhura Rao || Ashwini S,Kusuma Mohanchandra

Doi : 01.1617/vol4/iss4/pid82074

Volume4 ,April 2017.

Multilevel Authentication System

Authors: Nichita Silva Lobo || Beverly Rodrigues,Pavni Alluri,Prathibha Singh,Nicole Alvares

Doi : 01.1617/vol4/iss4/pid82135

Volume4 ,April 2017.

Stock Prediction Using Clustering And Regression Techniques

Authors: Shalini Lotlikar || Megha Ainapurkar

Doi : 01.1617/vol4/iss4/pid39708

Volume4 ,April 2017.

Brain Tumor Detection using Image Segmentation

Authors: Siddhi N. Nerurkar ||

Doi : 01.1617/vol4/iss4/pid02845

Volume4 ,April 2017.

Video Mining using Query by Example

Authors: Rosebud Valadares ||

Doi : 01.1617/vol4/iss4/pid89542

Volume4 ,April 2017.

Fuzzy Opinion Mining for Product Recommender System

Authors: Aarti Bandodker ||

Doi : 01.1617/vol4/iss4/pid03652

Volume4 ,April 2017.

Aadhaar and Server based Electoral system

Authors: Yugansh Garg || Sakshi Mishra

Doi : 01.1617/vol4/iss4/pid69053

Volume4 ,April 2017.



Editor Image

Dr. Allon Guez
Professor, Drexel University,

View more



Google Scholar Profile

Thomson Reuters ID : q-6288-2016.
ORCiD Research ID : 0000-0001-9540-6799

All Issues


Journal Code : IJERCSE
Electronic ISSN : 2394-2320
Impact Factor : 4.890
Frequency : monthly
Contact :