Journal ArticleDOI
Floating search methods in feature selection
TLDR
Sequential search methods characterized by a dynamically changing number of features included or eliminated at each step, henceforth "floating" methods, are presented and are shown to give very good results and to be computationally more effective than the branch and bound method.About:
This article is published in Pattern Recognition Letters.The article was published on 1994-11-01. It has received 3104 citations till now. The article focuses on the topics: Beam search & Jump search.read more
Citations
More filters
Book ChapterDOI
Introduction to Neonatal Facial Pain Detection Using Common and Advanced Face Classification Techniques
TL;DR: The Infant COPE project and work using face classification to detect pain in a neonate’s facial displays is described and results indicate that the application of face Classification to the problem of neonatal pain assessment is a promising area of investigation.
Journal ArticleDOI
A new maximum relevance-minimum multicollinearity (MRmMC) method for feature selection and ranking
TL;DR: A new relevancy-redundancy approach for feature selection and ranking, called the maximum relevanceminimum multicollinearity (MRmMC) method, which can overcome some shortcomings of existing criteria.
Journal ArticleDOI
Feature analysis through information granulation and fuzzy sets
TL;DR: This study revisits and generalizes an issue of feature selection by introducing a mechanism of soft (fuzzy) feature selection and reveals how such feature intervalization helps approximate fuzzy sets described by any type of membership function.
Ant Colony Optimization for Feature Subset Selection.
TL;DR: This paper presents a novel method that utilizes the ACO algorithm to implement a feature subset search procedure and initial results obtained using the classification of speech segments are very promising.
Journal ArticleDOI
A wrapper-based approach to image segmentation and classification
Michael E. Farmer,Anil K. Jain +1 more
TL;DR: A segmentation algorithm that relaxes the requirement that the object of interest to be segmented must be homogeneous in some low-level image parameter, such as texture, color, or grayscale, which represents an improvement over other segmentation methods that have used classification information only to modify the segmenter parameters.
References
More filters
Journal ArticleDOI
A Branch and Bound Algorithm for Feature Subset Selection
TL;DR: In this paper, a branch and bound-based feature subset selection algorithm is proposed to select the best subset of m features from an n-feature set without exhaustive search, which is computationally computationally unfeasible.
Journal ArticleDOI
A note on genetic algorithms for large-scale feature selection
W. Siedlecki,Jack Sklansky +1 more
TL;DR: The preliminary results suggest that GA is a powerful means of reducing the time for finding near-optimal subsets of features from large sets.
Journal ArticleDOI
A Direct Method of Nonparametric Measurement Selection
TL;DR: A direct method of measurement selection is proposed to determine the best subset of d measurements out of a set of D total measurements, using a nonparametric estimate of the probability of error given a finite design sample set.
Journal ArticleDOI
On the effectiveness of receptors in recognition systems
T. Marill,D. Green +1 more
TL;DR: Some of the theoretical problems encountered in trying to determine a more formal measure of the effectiveness of a set of tests are discussed; a measure which might be a practical substitute for the empirical evaluation.
Journal ArticleDOI
On automatic feature selection
W. Siedlecki,Jack Sklansky +1 more
TL;DR: In this paper, a review of feature selection for multidimensional pattern classification is presented, and the potential benefits of Monte Carlo approaches such as simulated annealing and genetic algorithms are compared.