A. Whitney, "A direct method of non parametric measurement selection, " IEEE Trans. Computing, vol. C-20, pp. 1100--1103, 1971. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Classifier Combination and Feature Selection for Land-Cover.. - Huber (Correct)
....p( i ) i = 1 : C, the average JMD is defined by: J = C(C 1) i 1 j=1 J ik ; J ik = 2(1 e B ik ) 2) We compared two feature selection methods, the most established one, and one based on evolutionary algorithms (EAs) in our work. 3.1. Sequential Forward Selection (SFS) [14] Initialize the algorithm by setting X 0 ; Suppose k features have already been selected from the complete set of measurements Y = fy j jj = 1; 2; Dg to form feature set X k . The (k 1) st feature is then chosen from the set of available measurements, Y n X k , so that J(X k 1 ) ....
A. Wayne Whitney. A Direct Method of Nonparametric Measurement Selection. IEEE Transactions on Computers, 20:1100--1103, September 1971.
A Bayesian Pairwise Classifier for Character Recognition - Kumar, Ghosh, Crawford (2000) (3 citations) (Correct)
....feasible. For example, in the second character recognition problem considered in this chapter, there are 30 extracted features and an exhaustive search would require the examination of 2 30 10 9 possible combinations of features. Thus, greedy heuristic algorithms such as Forward selection [2] and Backward elimination [3] have been developed for feature selection. In forward selection, the feature space F is initialized to contain the single best feature with regard to the relevance measure R i.e. F 1 = fargmax f2F R(f)g. Here F denotes the set of D available features. Subsequent ....
A. W. Whitney. A direct method of nonparametric measurement selection. IEEE Transactions on Computers, 20:1100-1103, 1971. 14
Feature Selection in Unsupervised Learning via Evolutionary.. - Kim, Street, Menczer (2000) (11 citations) (Correct)
....set. The whole search space is O(2 D ) making exhaustive search impractical for data sets with even moderate dimensionality. Most research on search algorithms has used heuristic search approaches in favor of eciency rather than optimality. For instance, algorithms such as sequential search [30, 19], branch and bound [26] nonlinear optimization [5] and simulated annealing [27] have been applied. The formulation of feature selection as a combinatorial optimization problem has also lead to the use of genetic algorithms [28, 31] A recent review of these methods can be found in [8] ....
A.W. Whitney. A direct method of nonparametric measurement selection. IEEE Transactions on Computers, 20:1100-1103, 1971.
Mobile Robot Localization Using Pattern Classification Techniques - Courtney (1993) (Correct)
....still suboptimal, this straightforward approach is able to make some account of statistical dependence among the measurements. Whitney proposed the leave one out error rate of a 1 NN classifer as a criterion function for sequential forward feature selection; this is known as Whitney s method [58]. 76 5.4 Experimental Results We investigated the application of the various classifiers and techniques described above to recognize grid based maps of locales. Using our two datasets of 100 patterns, we designed and tested both K NN and MMD classifiers for room and door locale recognition. We ....
A. Whitney. A direct method of nonparametric measurement selection. IEEE Transactions on Computers, 20:100--103, September 1971.
Finding Salient Features for Personal Web Page Categories - Wulfekuhler, Punch (1997) (21 citations) (Correct)
....sets. The above classifier using all 5190 features misclassified 50 out of 85 documents, for an accuracy of 41:18 . We found we can improve the classification accuracy through feature selection techniques. Some effective conventional methods for feature selection are sequential forward selection [5, 11], sequential floating feature selection [12] and genetic algorithm search [13, 14] Sequential forward selection achieved 17 85 errors, or 80 accuracy by selecting 13 features. These features were engin, action, david, contempl, affirm, architectur, ave, osha, abund, rehabilit, notic, commerc, ....
A. Whitney, "A direct method of nonparametric measurement selection," IEEE Transactions on Computers, vol. 20, pp. 1100--1103, 1971.
Active Shape Model Segmentation with Optimal Features - van Ginneken, Frangi.. (2002) (4 citations) (Correct)
No context found.
A. Whitney, "A direct method of non parametric measurement selection, " IEEE Trans. Computing, vol. C-20, pp. 1100--1103, 1971.
A Pitfall in Determining the Optimal Feature Subset Size - Reunanen (2004) (Correct)
No context found.
A.W. Whitney. A direct method of nonparametric measurement selection. IEEE Trans. Computers, 20(9):1100--1103, 1971.
IEEE SYMPOSIUM ON BIOINFORMATICS AND BIOENGINEERING 1.. - Michael Raymer Leslie (Correct)
No context found.
A. Whitney, "A direct method of nonparametric measurement selection," IEEE Transactions on Computers, vol. 20, pp. 1100-- 1103, 1971.
Best-Bases Feature Extraction Algorithms for - Classification Of Hyperspectral (Correct)
No context found.
A. W. Whitney, "A direct method of nonparametric measurement selection, " IEEE Trans. Comput., vol. 20, pp. 1100--1103, 1971.
Classification of Hyperspectral Data using Best-bases.. - Kumar, Ghosh, Crawford (Correct)
No context found.
A. W. Whitney, \A direct method of nonparametric measurement selection," IEEE Transactions on Computers 20, pp. 1100-1103, 1971.
Multiresolution Feature Extraction for Pairwise.. - Kumar, Ghosh, Crawford (2000) (Correct)
No context found.
A. W. Whitney, \A direct method of nonparametric measurement selection," IEEE Transactions on Computers 20, pp. 1100-1103, 1971.
Texture Statistic Selective Masks - Cohen, You (1995) (Correct)
No context found.
A. W. Whitney. A direct method of nonparametric measurement selection. IEEE Trans. Commun., pages 11001103, 1971.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC