slugStudy of Euclidean and Manhattan Distance Metrics using Simple K-Means Clustering
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2014, Vol 2, Issue 5
Abstract
Clustering is the task of assigning a set of objects into groups called clusters in which objects in the same cluster are more similar to each other than to those in other clusters. Generally clustering is used to find out the similar, dissimilar and outlier items from the databases. The main idea behind the clustering is the distance between the data items. The work carried out in this paper is based on the study of two popular distance metrics viz. Euclidean and Manhattan. A series of experiments has been performed to validate the study. We use two real and one synthetic datasets on simple K-Means clustering. The theoretical analysis and experimental results show that the Euclidean method outperforms Manhattan method in terms of number of iterations performed during centroid calculation.
Authors and Affiliations
Deepak Sinwar, Rahul Kaushik
Keywords
Related Articles
- EP ID EP18115
- DOI -
- Views 291
- Downloads 13
Improvement of low energy adaptive cluster hierarchy protocol using information processing for WSN
Wireless Sensor networks (WSNs) are special type of adhoc networks which makes use of sensors (also known as motes) for gathering information. The data collected by each sensor is communicated through the network to a s...
slugObtaining an Accurate and Comprehensive Data Mining Model
It is important for shareholders and potential investors to use relevant financial information to enable them to make good investment decisions in the stock market. Predicting stock performance is certainly very complic...
slugResearch on Saliency Detection
Saliency detection means detecting visually attracted regions in images. It is an aspect of exploring visual attention from a computer vision viewpoint. The human pays unequal attention to what is seen in the world. Whe...
Forward and Backward Sweep Algorithm for Distribution Power Flow Analysis and Comparison of Different Load Flow Methods.
Power flow analysis is a very important and fundamental tool for the analysis of any electrical distribution system and is used in the operational as well as planning stages. Certain applications particularly in distrib...
Data Lineage in Malicious Environment (DLIME) for Text Data by using AES, SHA
Intentional or unintentional confidential data is leaked and it is undoubtedly one of the most severe security threats that organizations are facing in this digital era. The threats now extending to our personal lives a...