An Effective Streams Clustering Method for Biomedical Signals

An Effective Streams Clustering Method for Biomedical Signals

Pimwadee Chaovalit (National Science and Technology Development Agency, Thailand)
DOI: 10.4018/jcmam.2010070101
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In the healthcare industry, the ability to monitor patients via biomedical signals assists healthcare professionals in detecting early signs of conditions such as blocked arteries and abnormal heart rhythms. Using data clustering, it is possible to interpret these signals to look for patterns that may indicate emerging or developing conditions. This can be accomplished by basing monitoring systems on a fast clustering algorithm that processes fast-paced streams of raw data effectively. This paper presents a clustering method, POD-Clus, which can be useful in computer-aided diagnosis. The proposed method clusters data streams in linear time and outperforms a competing algorithm in capturing changes of clusters in data streams.
Article Preview

Background

A data stream is a fast-arriving, transient sequence of data values. Data streams’ characteristics (Domingos & Hulten, 2000; Gama, Rodrigues, & Aguilar-Ruiz, 2007) are summarized as follows:

  • i)

    Data usually coming in at a detailed level

  • ii)

    Streaming data arriving at a fast pace

  • iii)

    Potentially unbounded observations of data

  • iv)

    Possibly limited storage and memory resources for processing data streams

As high-volume and high-speed data streams challenge data miners to shift data mining paradigm from mining in batches to mining incrementally. Employing the “incremental” approach allows data miners to avoid an expensive processing of potentially large-sized data at the end of the streams by processing data in a small amount at a time. The criteria for a capable data streams clustering method include (Babcock, Babu, Datar, Motwani, & Widom, 2002; Barbará, 2002; Domingos & Hulten, 2001; Golab & Özsu, 2003):

Complete Article List

Search this Journal:
Reset
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing