On selecting the best features in a noisy environment
Kybernetika (1998)
- Volume: 34, Issue: 4, page [411]-416
- ISSN: 0023-5954
Access Full Article
top
Abstract
topHow to cite
topFlusser, Jan, and Suk, Tomáš. "On selecting the best features in a noisy environment." Kybernetika 34.4 (1998): [411]-416. <http://eudml.org/doc/33370>.
@article{Flusser1998,
abstract = {This paper introduces a novel method for selecting a feature subset yielding an optimal trade-off between class separability and feature space dimensionality. We assume the following feature properties: (a) the features are ordered into a sequence, (b) robustness of the features decreases with an increasing order and (c) higher-order features supply more detailed information about the objects. We present a general algorithm how to find under those assumptions the optimal feature subset. Its performance is demonstrated experimentally in the space of moment-based descriptors of 1-D signals, which are invariant to linear filtering.},
author = {Flusser, Jan, Suk, Tomáš},
journal = {Kybernetika},
keywords = {Mahalanobis distance; 1-D signals; Mahalanobis distance; 1-D signals},
language = {eng},
number = {4},
pages = {[411]-416},
publisher = {Institute of Information Theory and Automation AS CR},
title = {On selecting the best features in a noisy environment},
url = {http://eudml.org/doc/33370},
volume = {34},
year = {1998},
}
TY - JOUR
AU - Flusser, Jan
AU - Suk, Tomáš
TI - On selecting the best features in a noisy environment
JO - Kybernetika
PY - 1998
PB - Institute of Information Theory and Automation AS CR
VL - 34
IS - 4
SP - [411]
EP - 416
AB - This paper introduces a novel method for selecting a feature subset yielding an optimal trade-off between class separability and feature space dimensionality. We assume the following feature properties: (a) the features are ordered into a sequence, (b) robustness of the features decreases with an increasing order and (c) higher-order features supply more detailed information about the objects. We present a general algorithm how to find under those assumptions the optimal feature subset. Its performance is demonstrated experimentally in the space of moment-based descriptors of 1-D signals, which are invariant to linear filtering.
LA - eng
KW - Mahalanobis distance; 1-D signals; Mahalanobis distance; 1-D signals
UR - http://eudml.org/doc/33370
ER -
References
top- Fukunaga K., Introduction to Statistical Pattern Recognition, Academic Press, New York 1972 Zbl0711.62052MR1075415
- Devijver P. A., Kittler J., Pattern Recognition: A Statistical Approach, Prentice Hall, London 1982 Zbl0542.68071MR0692767
- Abu–Mostafa Y. S., Psaltis D., 10.1109/TPAMI.1984.4767594, IEEE Trans. Pattern Anal. Mach. Intell. 6 (1984), 698–706 (1984) DOI10.1109/TPAMI.1984.4767594
- Teh C. H., Chin R. T., 10.1109/34.3913, IEEE Trans. Pattern Anal. Mach. Intell. 10 (1988), 496–512 (1988) Zbl0709.94543DOI10.1109/34.3913
- Pawlak M., 10.1109/18.165444, IEEE Trans. Inform. Theory 38 (1992), 1698–1708 (1992) Zbl0761.68104MR1187813DOI10.1109/18.165444
- Liao S. X., Pawlak M., 10.1109/34.485554, IEEE Trans. Pattern Anal. Mach. Intell. 18 (1996), 254–266 (1996) DOI10.1109/34.485554
- Flusser J., Suk T., Invariants for recognition of degraded 1-D digital signals, In: Proc. 13th ICPR, Vienna 1996, vol. II, pp. 389–393 (1996)
- Flusser J., Suk T., 10.1016/S0165-1684(97)00075-3, Signal Processing 60 (1997), 243–249 (1997) Zbl1006.94512DOI10.1016/S0165-1684(97)00075-3
NotesEmbed ?
topYou must be logged in to post comments.
To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.