Sparse feature extraction for support vector data description applications

Amit Banerjee; Radford Juang; Joshua Broadwater; Philippe Burlina

doi:10.1109/IGARSS.2010.5653539

Sparse feature extraction for support vector data description applications

Amit Banerjee, Radford Juang, Joshua Broadwater, Philippe Burlina

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Support Vector Data Description (SVDD) methods have been successfully applied to hyperspectral anomaly detection. Unfortunately, the performance of SVDD methods suffers when noisy or non-informative bands are present in the data. If a set of sparse features could be identified for these techniques, the resulting data may improve SVDD performance while enjoying the benefits of decreased processing overhead. Although band selection has been investigated in previous efforts, this work builds on recent research that has resulted in the development of a theoretical framework for signal classification with sparse representation using L₁ measures.

Original language	English (US)
Title of host publication	2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4236-4239
Number of pages	4
ISBN (Print)	9781424495658, 9781424495665
DOIs	https://doi.org/10.1109/IGARSS.2010.5653539
State	Published - 2010
Externally published	Yes
Event	2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 - Honolulu, HI, United States Duration: Jul 25 2010 → Jul 30 2010

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Other

Other	2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
Country/Territory	United States
City	Honolulu, HI
Period	7/25/10 → 7/30/10

Keywords

Feature selection
Hyperspectral processing
Kernel methods

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS.2010.5653539

Cite this

Banerjee, A., Juang, R., Broadwater, J., & Burlina, P. (2010). Sparse feature extraction for support vector data description applications. In 2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 (pp. 4236-4239). Article 5653539 (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2010.5653539

Sparse feature extraction for support vector data description applications. / Banerjee, Amit; Juang, Radford; Broadwater, Joshua et al.
2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010. Institute of Electrical and Electronics Engineers Inc., 2010. p. 4236-4239 5653539 (International Geoscience and Remote Sensing Symposium (IGARSS)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Banerjee, A, Juang, R, Broadwater, J & Burlina, P 2010, Sparse feature extraction for support vector data description applications. in 2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010., 5653539, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 4236-4239, 2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010, Honolulu, HI, United States, 7/25/10. https://doi.org/10.1109/IGARSS.2010.5653539

Banerjee A, Juang R, Broadwater J, Burlina P. Sparse feature extraction for support vector data description applications. In 2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010. Institute of Electrical and Electronics Engineers Inc. 2010. p. 4236-4239. 5653539. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2010.5653539

@inproceedings{56794d53128545f996c286fed6a9371a,

title = "Sparse feature extraction for support vector data description applications",

abstract = "Support Vector Data Description (SVDD) methods have been successfully applied to hyperspectral anomaly detection. Unfortunately, the performance of SVDD methods suffers when noisy or non-informative bands are present in the data. If a set of sparse features could be identified for these techniques, the resulting data may improve SVDD performance while enjoying the benefits of decreased processing overhead. Although band selection has been investigated in previous efforts, this work builds on recent research that has resulted in the development of a theoretical framework for signal classification with sparse representation using L1 measures.",

keywords = "Feature selection, Hyperspectral processing, Kernel methods",

author = "Amit Banerjee and Radford Juang and Joshua Broadwater and Philippe Burlina",

year = "2010",

doi = "10.1109/IGARSS.2010.5653539",

language = "English (US)",

isbn = "9781424495658",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4236--4239",

booktitle = "2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010",

note = "2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 ; Conference date: 25-07-2010 Through 30-07-2010",

}

TY - GEN

T1 - Sparse feature extraction for support vector data description applications

AU - Banerjee, Amit

AU - Juang, Radford

AU - Broadwater, Joshua

AU - Burlina, Philippe

PY - 2010

Y1 - 2010

N2 - Support Vector Data Description (SVDD) methods have been successfully applied to hyperspectral anomaly detection. Unfortunately, the performance of SVDD methods suffers when noisy or non-informative bands are present in the data. If a set of sparse features could be identified for these techniques, the resulting data may improve SVDD performance while enjoying the benefits of decreased processing overhead. Although band selection has been investigated in previous efforts, this work builds on recent research that has resulted in the development of a theoretical framework for signal classification with sparse representation using L1 measures.

AB - Support Vector Data Description (SVDD) methods have been successfully applied to hyperspectral anomaly detection. Unfortunately, the performance of SVDD methods suffers when noisy or non-informative bands are present in the data. If a set of sparse features could be identified for these techniques, the resulting data may improve SVDD performance while enjoying the benefits of decreased processing overhead. Although band selection has been investigated in previous efforts, this work builds on recent research that has resulted in the development of a theoretical framework for signal classification with sparse representation using L1 measures.

KW - Feature selection

KW - Hyperspectral processing

KW - Kernel methods

UR - http://www.scopus.com/inward/record.url?scp=78650901100&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650901100&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2010.5653539

DO - 10.1109/IGARSS.2010.5653539

M3 - Conference contribution

AN - SCOPUS:78650901100

SN - 9781424495658

SN - 9781424495665

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4236

EP - 4239

BT - 2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010

Y2 - 25 July 2010 through 30 July 2010

ER -

Sparse feature extraction for support vector data description applications

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this