A Surrogate-Assisted Evolutionary Algorithm with Random Feature Selection for Large-Scale Expensive Problems

2020 ◽  
pp. 125-139
Author(s):  
Guoxia Fu ◽  
Chaoli Sun ◽  
Ying Tan ◽  
Guochen Zhang ◽  
Yaochu Jin
Keyword(s):  
Feature Selection ◽  
Evolutionary Algorithm ◽  
Large Scale ◽  
Expensive Problems ◽  
Selection For

scholarly journals Large-Scale Online Feature Selection for Ultra-High Dimensional Sparse Data

2017 ◽  
Vol 11 (4) ◽  
pp. 1-22 ◽  
Author(s):  
Yue Wu ◽  
Steven C. H. Hoi ◽  
Tao Mei ◽  
Nenghai Yu
Keyword(s):  
Feature Selection ◽  
Large Scale ◽  
Sparse Data ◽  
High Dimensional ◽  
Online Feature Selection ◽  
Selection For

Evaluating the Efficiency of Radial Basis Function Classifier with Different Feature Selection for Identifying Dementia

2019 ◽  
Vol 16 (2) ◽  
pp. 627-632 ◽  
Author(s):  
S. Valarmathy ◽  
R. Ramani
Keyword(s):  
Feature Selection ◽  
Radial Basis Function ◽  
Basis Function ◽  
Large Scale ◽  
Performance Metrics ◽  
Principal Component ◽  
Specificity And Sensitivity ◽  
Radial Basis ◽  
Selection For

The Magnetic Resonance Imaging (MRI) based classification process for the classification of dementia is presented in this work. The classifier's performance may be enhanced by means of improving the extracted features that are inputted into its classifier. These MRI images are all duly segmented by making use of the wavelet. For choosing a subset that has optimal features, it may become inflexible and all issues relating to the feature selection will be shown as the NonDeterministic Polynomial (NP)-hard. The work further deals with techniques of optimization that are used in the case of feature selection for picking an optimal feature set. The Principal Component Analysis (PCA) will find an application of a large scale in signal processing. The noise estimation and the source separation are all possible. For this, the Radial Basis Function (RBF) and its classifier have been optimized to this structure by making use of the Genetic Algorithm (GA)-Artificial Immune System (AIS) algorithm. Such an optimized classifier of the RBF will classify a feature set that is provided by the GA, the AIS and the GA-AIS algorithm of feature selection. A classifier will be evaluated on the basis of its performance metrics. All classifiers will be evaluated keeping the accuracy, specificity, and sensitivity in making use of an optimized set of features. The results of the experiment have clearly demonstrated the feature selection and its effectiveness to improve the accuracy of the classification of all the images.

scholarly journals Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data

2019 ◽  
Vol 10 ◽  
Author(s):  
Mickael Leclercq ◽  
Benjamin Vittrant ◽  
Marie Laure Martin-Magniette ◽  
Marie Pier Scott Boyer ◽  
Olivier Perin ◽  
...  
Keyword(s):  
Feature Selection ◽  
Large Scale ◽  
Biomarker Discovery ◽  
High Dimensional ◽  
Omics Data ◽  
Selection For ◽  
Automatic Feature Selection

scholarly journals Feature selection for spectral clustering: to help or not to help spectral clustering when performing sense discrimination for IR?

2018 ◽  
Vol 8 (1) ◽  
pp. 218-227 ◽  
Author(s):  
Adrian-Gabriel Chifu ◽  
Florentina Hristea
Keyword(s):  
Feature Selection ◽  
Spectral Clustering ◽  
Large Scale ◽  
Word Sense Disambiguation ◽  
Large Data ◽  
Feature Weighting ◽  
Word Sense ◽  
Sense Disambiguation ◽  
Selection For ◽  
Data Collections

Abstract Whether or not word sense disambiguation (WSD) can improve information retrieval (IR) results represents a topic that has been intensely debated over the years, with many inconclusive or contradictory conclusions. The most rarely used type of WSD for this task is the unsupervised one, although it has been proven to be beneficial at a large scale. Our study builds on existing research and tries to improve the most recent unsupervised method which is based on spectral clustering. It investigates the possible benefits of “helping” spectral clustering through feature selection when it performs sense discrimination for IR. Results obtained so far, involving large data collections, encourage us to point out the importance of feature selection even in the case of this advanced, state of the art clustering technique that is known for performing its own feature weighting. By suggesting an improvement of what we consider the most promising approach to usage of WSD in IR, and by commenting on its possible extensions, we state that WSD still holds a promise for IR and hope to stimulate continuation of this line of research, perhaps at an even more successful level.

Sign in / Sign up

Export Citation Format

Share Document