A GPU-based harmony k-means algorithm for document clustering

Document clustering is one of the most important tasks in text mining. In clustering algorithms, high-dimensional vector is usually used to represent a document which causes that the algorithms are often computationally expensive. On the other hand, Graphic Processing Unit (GPU) is increasingly impo...

Full description

Saved in:
Bibliographic Details
Published inIET Conference Proceedings p. 3.29
Main Authors Gao, Zhanchun, Li, Enxing, Jiang, Yanjun
Format Conference Proceeding
LanguageEnglish
Published Stevenage, UK IET 2012
The Institution of Engineering & Technology
Subjects
Algebra
Document processing techniques
Knowledge engineering techniques
Parallel software
document handling
high-dimensional vector
parallel architectures
harmony k-means algorithm
data mining
graphic processing unit
document clustering
compute unified device architecture
graphics processing units
GPU
parallel programming
CUDA
vectors
pattern clustering
text mining
parallel computing
HKA
Online AccessGet full text

Cover

More Information
Summary:Document clustering is one of the most important tasks in text mining. In clustering algorithms, high-dimensional vector is usually used to represent a document which causes that the algorithms are often computationally expensive. On the other hand, Graphic Processing Unit (GPU) is increasingly important in parallel computing due to its powerful parallel capacity and high bandwidth. This paper implements a GPU-based Harmony K-means Algorithm (HKA) with NVIDIA's Compute Unified Device Architecture (CUDA), and uses it for document clustering. In our experiment, our GPU-based program can acquire a maximum 20 times speedup in contrast with CPU-based program.
ISBN:9781849196413
1849196419
DOI:10.1049/cp.2012.2426