Unsupervised Analysis of Arrhythmias using K-means Clustering
Journal Title: International Journal of Computer Science and Information Technologies - Year 2010, Vol 1, Issue 5
Abstract
The Electrocardiogram provides the valuable information regarding the cardiovascular diseases. Various methods for classification of arrhythmias have been developed by researchers. Classification can be supervised or unsupervised. Various clustering techniques have been used for arrhythmias under the unsupervised category. Clustering has been advisable technique for analysis and interpretation of long term ECG Holter records. In this paper, K-means clustering has been used. The K-means with Squared Euclidean distance has been used for the analysis. Data sets with four types of arrhythmias have been made using MIT-BIH data bases and after applying kmeans using Euclidean with ‘sample’ as seed has been used. The data is classified into five arrhythmia beats type i.e. Normal(N), Premature ventricular contraction (PVC), Paced beats(P), Left Bundle Branch Block(LBBB) and Right Bundle Branch Block(RBBB).
Authors and Affiliations
Manpreet Kaur , A. S. Arora
Keywords
Related Articles
- EP ID EP139651
- DOI -
- Views 93
- Downloads 0
A Multiobjective Genetic Algorithm for Feature Selection in Data Mining
The rapid advance of computer based highthroughput technique have provided unparalleled opportunities for humans to expand capabilities in production, services, communications, and research. Meanwhile, immense quantities...
Combined Text Watermarking
There is a vast amount of digital text data exchanged over the internet for the past few years. Such exchanges necessitate a very robust copyright protection mechanism. This paper presents a new idea on how one can effec...
Performance Enhancement of MC-CDMA System through STTC based STBC Site Diversity
The combination of multiple antennas and multicarrier code division multiple access (MC-CDMA) is a strong candidate for the downlink of future mobile communications. The study of such systems, in scenarios that model rea...
Unsupervised Analysis of Arrhythmias using K-means Clustering
The Electrocardiogram provides the valuable information regarding the cardiovascular diseases. Various methods for classification of arrhythmias have been developed by researchers. Classification can be supervised or uns...
A New Hashing and Caching Approach for Minimizing Overall Location Management Cost in Next-Generation Wireless Networks
This paper proposes a new hashing and caching strategy (NHC) in order to reduce the overall location management cost in wireless mobile networks. It uses caches whose up-to-date information is responsible for dropping th...