Abstract
The Bhattacharyya distance provides a valuable information in determining the effectiveness of a feature set and has been used as separability measure for feature selection. Recently, it is shown that it is feasible to predict the classification error accurately using the Bhattacharyya distance. The new formula makes it possible to estimate classification error between two classes within 1-2% margin. In this paper, we propose a new feature extraction method utilizing the result. Initially, we start with an arbitrary feature vector. Assuming that the feature vector is used for classification, we estimate the classification error using the error estimation formula. Then we move the feature vector slightly in the direction so that the estimated classification error is decreased most rapidly. This can be done by taking gradient. Experiments show that the proposed method compare favorably with the conventional methods.
| Original language | English |
|---|---|
| Pages (from-to) | 2147-2150 |
| Number of pages | 4 |
| Journal | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
| Volume | 3 |
| Publication status | Published - 1997 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Hardware and Architecture
- Control and Systems Engineering
Cite this
}
Feature extraction using the Bhattacharyya distance. / Lee, Chulhee; Hong, Daesik.
In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol. 3, 01.12.1997, p. 2147-2150.Research output: Contribution to journal › Conference article
TY - JOUR
T1 - Feature extraction using the Bhattacharyya distance
AU - Lee, Chulhee
AU - Hong, Daesik
PY - 1997/12/1
Y1 - 1997/12/1
N2 - The Bhattacharyya distance provides a valuable information in determining the effectiveness of a feature set and has been used as separability measure for feature selection. Recently, it is shown that it is feasible to predict the classification error accurately using the Bhattacharyya distance. The new formula makes it possible to estimate classification error between two classes within 1-2% margin. In this paper, we propose a new feature extraction method utilizing the result. Initially, we start with an arbitrary feature vector. Assuming that the feature vector is used for classification, we estimate the classification error using the error estimation formula. Then we move the feature vector slightly in the direction so that the estimated classification error is decreased most rapidly. This can be done by taking gradient. Experiments show that the proposed method compare favorably with the conventional methods.
AB - The Bhattacharyya distance provides a valuable information in determining the effectiveness of a feature set and has been used as separability measure for feature selection. Recently, it is shown that it is feasible to predict the classification error accurately using the Bhattacharyya distance. The new formula makes it possible to estimate classification error between two classes within 1-2% margin. In this paper, we propose a new feature extraction method utilizing the result. Initially, we start with an arbitrary feature vector. Assuming that the feature vector is used for classification, we estimate the classification error using the error estimation formula. Then we move the feature vector slightly in the direction so that the estimated classification error is decreased most rapidly. This can be done by taking gradient. Experiments show that the proposed method compare favorably with the conventional methods.
UR - http://www.scopus.com/inward/record.url?scp=0031333236&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031333236&partnerID=8YFLogxK
M3 - Conference article
VL - 3
SP - 2147
EP - 2150
JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
SN - 0884-3627
ER -