A Discrimination Analysis for Unsupervised Feature Selection via Optic Diffraction Principle

Abstract

This paper proposes an unsupervised discrimination analysis for feature selection based on a property of the Fourier transform of the probability density distribution. Each feature is evaluated on the basis of a simple observation motivated by the concept of optical diffraction, which is invariant under feature scaling. The time complexity is O(mn), where m is number of features and n is number of instances when being applied directly to the given data. This approach is also extended to deal with data orientation, which is the direction of data alignment. Therefore, the discrimination score of any transformed space can be used for evaluating the original features. The experimental results on several real-world datasets demonstrate the effectiveness of the proposed method.

Simultaneous Bayesian Clustering and Feature Selection Through Student’s ${t}$ Mixtures Model

“…Eight "noisy" features [sampled from N (0, 1)] are then appended to this data, resulting in a 10-D patterns. 800 data points are generated, and a set of outliers uniformly sampled from [− 10 30] 10 are added to the data set. Various percentages of outliers are added to the main data sets to test the performance of the algorithm on outlier detection.…”

“…Existing feature selection algorithm can be categorized as supervised feature selection (on data with full class labels) [5]- [9], unsupervised feature selection (on data without class labels) [10]- [15], and semisupervised feature selection (on data with partial labels) [14], [16], [17]. Feature selection in unsupervised context is considered to be more difficult than the other two cases, since there is no target information available for training.…”

“…In [32], embedding learning and sparse regression are jointly applied to perform feature selection. A discrimination analysis based on a property of Fourier transform of the data density distribution is applied for feature selection via optic diffraction principle [10]. A theoretically optimal criterion, namely, the discriminative optimal criterion, has been developed for feature selection in [33].…”

Effective Discriminative Feature Selection With Nontrivial Solution

“…The goal of supervised feature selection is to find the most discriminative features that can distinguish different classes. Thus discriminant analysis plays an important role in supervised feature selection [3], [20], [21]. The Fisher Score algorithm [10] is a widely applied filter-type feature selection algorithm based on linear discriminant analysis (LDA).…”

Simultaneous feature selection and weighting – An evolutionary multi-objective optimization approach

“…Mitra et al (2004) proposed an FS technique based on Feature Similarity (FSFS). Padungweang et al (2012) presented a new approach for FS, using the optical diffraction principle. Recently a non-parametric Bayesian error minimization scheme for FS was proposed by Yang and Hu (2012).…”