Feature selection for neural networks using Parzen density estimator

Chulhee Lee; Jon A. Benediktsson; David A. Landgrebe

doi:10.1109/IGARSS.1992.578271

Feature selection for neural networks using Parzen density estimator

Chulhee Lee, Jon A. Benediktsson, David A. Landgrebe

Department of Electrical and Electronic Engineering

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

4 Citations (Scopus)

Abstract

In this paper, a new feature selection method for neural networks is proposed using the Parzen density estimator. A new feature set is selected employing the recently published decision boundary feature selection algorithm. The selected feature set is then used to train a neural network. Using a reduced feature set, we attempt to reduce the training time of the neural network and obtain a simpler neural network, further reducing the classification time for test data. Experiments show promising results.

Original language	English
Title of host publication	IGARSS 1992 - International Geoscience and Remote Sensing Symposium
Subtitle of host publication	International Space Year: Space Remote Sensing
Editors	Ruby Williamson, Tammy Stein
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	839-841
Number of pages	3
ISBN (Electronic)	0780301382
DOIs	https://doi.org/10.1109/IGARSS.1992.578271
Publication status	Published - 1992
Event	12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992 - Houston, United States Duration: 1992 May 26 → 1992 May 29

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2

Other

Other	12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992
Country	United States
City	Houston
Period	92/5/26 → 92/5/29

All Science Journal Classification (ASJC) codes

Computer Science Applications
Earth and Planetary Sciences(all)

Access to Document

10.1109/IGARSS.1992.578271

Fingerprint Dive into the research topics of 'Feature selection for neural networks using Parzen density estimator'. Together they form a unique fingerprint.

Cite this

Lee, C., Benediktsson, J. A., & Landgrebe, D. A. (1992). Feature selection for neural networks using Parzen density estimator. In R. Williamson, & T. Stein (Eds.), IGARSS 1992 - International Geoscience and Remote Sensing Symposium: International Space Year: Space Remote Sensing (pp. 839-841). [578271] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.1992.578271

Lee, Chulhee ; Benediktsson, Jon A. ; Landgrebe, David A. / Feature selection for neural networks using Parzen density estimator. IGARSS 1992 - International Geoscience and Remote Sensing Symposium: International Space Year: Space Remote Sensing. editor / Ruby Williamson ; Tammy Stein. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 839-841 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{a18a398469a6488696f0771d8d5b9417,

title = "Feature selection for neural networks using Parzen density estimator",

abstract = "In this paper, a new feature selection method for neural networks is proposed using the Parzen density estimator. A new feature set is selected employing the recently published decision boundary feature selection algorithm. The selected feature set is then used to train a neural network. Using a reduced feature set, we attempt to reduce the training time of the neural network and obtain a simpler neural network, further reducing the classification time for test data. Experiments show promising results.",

author = "Chulhee Lee and Benediktsson, {Jon A.} and Landgrebe, {David A.}",

year = "1992",

doi = "10.1109/IGARSS.1992.578271",

language = "English",

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

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

pages = "839--841",

editor = "Ruby Williamson and Tammy Stein",

booktitle = "IGARSS 1992 - International Geoscience and Remote Sensing Symposium",

address = "United States",

note = "12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992 ; Conference date: 26-05-1992 Through 29-05-1992",

}

Lee, C, Benediktsson, JA & Landgrebe, DA 1992, Feature selection for neural networks using Parzen density estimator. in R Williamson & T Stein (eds), IGARSS 1992 - International Geoscience and Remote Sensing Symposium: International Space Year: Space Remote Sensing., 578271, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 839-841, 12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992, Houston, United States, 92/5/26. https://doi.org/10.1109/IGARSS.1992.578271

Feature selection for neural networks using Parzen density estimator. / Lee, Chulhee; Benediktsson, Jon A.; Landgrebe, David A.

IGARSS 1992 - International Geoscience and Remote Sensing Symposium: International Space Year: Space Remote Sensing. ed. / Ruby Williamson; Tammy Stein. Institute of Electrical and Electronics Engineers Inc., 1992. p. 839-841 578271 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2).

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

TY - GEN

T1 - Feature selection for neural networks using Parzen density estimator

AU - Lee, Chulhee

AU - Benediktsson, Jon A.

AU - Landgrebe, David A.

PY - 1992

Y1 - 1992

N2 - In this paper, a new feature selection method for neural networks is proposed using the Parzen density estimator. A new feature set is selected employing the recently published decision boundary feature selection algorithm. The selected feature set is then used to train a neural network. Using a reduced feature set, we attempt to reduce the training time of the neural network and obtain a simpler neural network, further reducing the classification time for test data. Experiments show promising results.

AB - In this paper, a new feature selection method for neural networks is proposed using the Parzen density estimator. A new feature set is selected employing the recently published decision boundary feature selection algorithm. The selected feature set is then used to train a neural network. Using a reduced feature set, we attempt to reduce the training time of the neural network and obtain a simpler neural network, further reducing the classification time for test data. Experiments show promising results.

UR - http://www.scopus.com/inward/record.url?scp=84964523892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964523892&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.1992.578271

DO - 10.1109/IGARSS.1992.578271

M3 - Conference contribution

AN - SCOPUS:84964523892

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 839

EP - 841

BT - IGARSS 1992 - International Geoscience and Remote Sensing Symposium

A2 - Williamson, Ruby

A2 - Stein, Tammy

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992

Y2 - 26 May 1992 through 29 May 1992

ER -

Lee C, Benediktsson JA, Landgrebe DA. Feature selection for neural networks using Parzen density estimator. In Williamson R, Stein T, editors, IGARSS 1992 - International Geoscience and Remote Sensing Symposium: International Space Year: Space Remote Sensing. Institute of Electrical and Electronics Engineers Inc. 1992. p. 839-841. 578271. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.1992.578271