Feature extraction for one-class classification (2003) [3 citations — 0 self]
|
Abstract:
Abstract. Feature reduction is often an essential part of solving a classification task. One common approach for doing this, is Principal Component Analysis. There the low variance directions in the data are removed and the high variance directions are retained. It is hoped that these high variance directions contain information about the class di#erences. For one-class classification or novelty detection, the classification task contains one ill-determined class, for which (almost) no information is available. In this paper we show that for one-class classification, the low-variance directions are most informative, and that in the feature reduction a bias-variance trade-o # has to be considered which causes that retaining the high variance directions is often not optimal. 1
Citations
| 489 | Neural networks and the bias/variance dilemma – Geman, Bienenstock, et al. - 1992 |
| 397 | An Introduction to Multivariate Statistical Analysis – Anderson - 1971 |
| 90 | Basic Principles of ROC Analysis – Metz - 1978 |
| 89 | Mathematical Statistics – Wilks - 1963 |
| 47 | Learning and Example Selection for Object and Pattern Recognition – Sung - 1995 |
| 43 | A novelty detection approach to classification – Japkowicz, Myers, et al. - 1995 |
| 41 | One-class classification – Tax - 2001 |
| 25 | Bias/variance decompositions for likelihoodbased estimators – Heskes - 1998 |
| 8 | Recognition of unconstrained handwritten numerals by doubly selforganizing neural network – Cho - 1996 |
| 8 | Network contraints and multi-objective optimization for one-class classification – Moya, Hush - 1996 |
| 4 | The distribution of robust distances – Hardin, Rocke - 1999 |
| 2 | Face detection in still gray images – T, Pontil - 2000 |
| 2 | Automatic context-sensitive karyotyping of human elliptical symmetric statistical distributions – Ritter, Gallegos, et al. - 1995 |
