TDM modelling and evaluation of different domain transforms for LSI

Tareq Jaber, Abbes Amira, Peter Milligan

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Latent semantic indexing (LSI) is a popular technique used in information retrieval (IR) applications. This paper presents a novel evaluation strategy based on the use of image processing tools. The authors evaluate the use of the discrete cosine transform (DCT) and Cohen Daubechies Feauveau 9/7 (CDF 9/7) wavelet transform as a pre-processing step for the singular value decomposition (SVD) step of the LSI system. In addition, the effect of different threshold types on the search results is examined. The results show that accuracy can be increased by applying both transforms as a pre-processing step, with better performance for the hard-threshold function. The choice of the best threshold value is a key factor in the transform process. This paper also describes the most effective structure for the database to facilitate efficient searching in the LSI system.
Original languageEnglish
Pages (from-to)2406-2417
Number of pages12
JournalNeurocomputing
Volume72
Issue number10-12
DOIs
Publication statusPublished - Jun 2009

Fingerprint

Time division multiplexing
Semantics
Wavelet Analysis
Discrete cosine transforms
Information Storage and Retrieval
Singular value decomposition
Processing
Information retrieval
Wavelet transforms
Image processing
Databases

Cite this

Jaber, Tareq ; Amira, Abbes ; Milligan, Peter. / TDM modelling and evaluation of different domain transforms for LSI. In: Neurocomputing. 2009 ; Vol. 72, No. 10-12. pp. 2406-2417.
@article{dbc25e5054594d169cfdc4f4b3aaf776,
title = "TDM modelling and evaluation of different domain transforms for LSI",
abstract = "Latent semantic indexing (LSI) is a popular technique used in information retrieval (IR) applications. This paper presents a novel evaluation strategy based on the use of image processing tools. The authors evaluate the use of the discrete cosine transform (DCT) and Cohen Daubechies Feauveau 9/7 (CDF 9/7) wavelet transform as a pre-processing step for the singular value decomposition (SVD) step of the LSI system. In addition, the effect of different threshold types on the search results is examined. The results show that accuracy can be increased by applying both transforms as a pre-processing step, with better performance for the hard-threshold function. The choice of the best threshold value is a key factor in the transform process. This paper also describes the most effective structure for the database to facilitate efficient searching in the LSI system.",
author = "Tareq Jaber and Abbes Amira and Peter Milligan",
year = "2009",
month = "6",
doi = "10.1016/j.neucom.2008.12.010",
language = "English",
volume = "72",
pages = "2406--2417",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "10-12",

}

TDM modelling and evaluation of different domain transforms for LSI. / Jaber, Tareq; Amira, Abbes; Milligan, Peter.

In: Neurocomputing, Vol. 72, No. 10-12, 06.2009, p. 2406-2417.

Research output: Contribution to journalArticle

TY - JOUR

T1 - TDM modelling and evaluation of different domain transforms for LSI

AU - Jaber, Tareq

AU - Amira, Abbes

AU - Milligan, Peter

PY - 2009/6

Y1 - 2009/6

N2 - Latent semantic indexing (LSI) is a popular technique used in information retrieval (IR) applications. This paper presents a novel evaluation strategy based on the use of image processing tools. The authors evaluate the use of the discrete cosine transform (DCT) and Cohen Daubechies Feauveau 9/7 (CDF 9/7) wavelet transform as a pre-processing step for the singular value decomposition (SVD) step of the LSI system. In addition, the effect of different threshold types on the search results is examined. The results show that accuracy can be increased by applying both transforms as a pre-processing step, with better performance for the hard-threshold function. The choice of the best threshold value is a key factor in the transform process. This paper also describes the most effective structure for the database to facilitate efficient searching in the LSI system.

AB - Latent semantic indexing (LSI) is a popular technique used in information retrieval (IR) applications. This paper presents a novel evaluation strategy based on the use of image processing tools. The authors evaluate the use of the discrete cosine transform (DCT) and Cohen Daubechies Feauveau 9/7 (CDF 9/7) wavelet transform as a pre-processing step for the singular value decomposition (SVD) step of the LSI system. In addition, the effect of different threshold types on the search results is examined. The results show that accuracy can be increased by applying both transforms as a pre-processing step, with better performance for the hard-threshold function. The choice of the best threshold value is a key factor in the transform process. This paper also describes the most effective structure for the database to facilitate efficient searching in the LSI system.

UR - http://www.scopus.com/inward/record.url?scp=67349237454&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2008.12.010

DO - 10.1016/j.neucom.2008.12.010

M3 - Article

VL - 72

SP - 2406

EP - 2417

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 10-12

ER -