Fast orthogonal forward selection algorithm for feature subset selection

IEEE Transactions on Neural Networks - Tập 13 Số 5 - Trang 1218-1224 - 2002
K.Z. Mao1
1School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

Tóm tắt

Feature selection is an important issue in pattern classification. In the presented study, we develop a fast orthogonal forward selection (FOFS) algorithm for feature subset selection. The FOFS algorithm employs an orthogonal transform to decompose correlations among candidate features, but it performs the orthogonal decomposition in an implicit way. Consequently, the fast algorithm demands less computational effort as compared with conventional orthogonal forward selection (OFS).

Từ khóa

#Feature extraction #Filters #Search methods #Parameter estimation #Multi-layer neural network #Training data #Extraterrestrial measurements #Classification algorithms #Neural networks #Pattern classification

Tài liệu tham khảo

10.1109/79.127999 10.1109/78.398734 10.1080/00207179608921662 10.1016/S0893-6080(00)00049-6 0, Plant Samples blake, 1998, UCI repository of machine learning databases devijver, 1982, Pattern Recognition a Statistical Approach 10.1109/5254.671091 korenberg, 1985, pattern recognition via nonlinear system identification, Proc 35th Midwest Symp Circuits and Systems, 1, 96 10.1016/0167-8655(94)90127-9 10.1007/BF02367385 korenberg, 1987, fast orthogonal identification of nonlinear difference equation and functional expansion models, Proc 35th Midwest Symp Circuits and Systems, 1, 270 10.1109/TC.1977.1674939 10.1016/S0004-3702(97)00043-X 10.1007/BF00204124