A Bayesian approach to joint feature selection and classifier design

2004 ◽  
Vol 26 (9) ◽  
pp. 1105-1111 ◽  
Author(s):  
B. Krishnapuram ◽  
A.J. Harternink ◽  
L. Carin ◽  
M.A.T. Figueiredo
Keyword(s):  
Feature Selection ◽  
Bayesian Approach ◽  
Classifier Design

scholarly journals Network Anomaly Intrusion Detection Using a Nonparametric Bayesian Approach and Feature Selection

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 52181-52190 ◽  
Author(s):  
Wajdi Alhakami ◽  
Abdullah ALharbi ◽  
Sami Bourouis ◽  
Roobaea Alroobaea ◽  
Nizar Bouguila
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Bayesian Approach ◽  
Nonparametric Bayesian ◽  
Anomaly Intrusion Detection

Variational Relevant Sample-Feature Machine: A fully Bayesian approach for embedded feature selection

2017 ◽  
Vol 241 ◽  
pp. 181-190 ◽  
Author(s):  
Ali Mirzaei ◽  
Yalda Mohsenzadeh ◽  
Hamid Sheikhzadeh
Keyword(s):  
Feature Selection ◽  
Bayesian Approach ◽  
Fully Bayesian

A double-layer ELM with added feature selection ability using a sparse Bayesian approach

2016 ◽  
Vol 216 ◽  
pp. 371-380 ◽  
Author(s):  
Farkhondeh Kiaee ◽  
Christian Gagné ◽  
Hamid Sheikhzadeh
Keyword(s):  
Feature Selection ◽  
Double Layer ◽  
Bayesian Approach

SOLUTION OVER-FIT CONTROL IN EVOLUTIONARY MULTIOBJECTIVE OPTIMIZATION OF PATTERN CLASSIFICATION SYSTEMS

2009 ◽  
Vol 23 (06) ◽  
pp. 1107-1127 ◽  
Author(s):  
PAULO V. W. RADTKE ◽  
TONY WONG ◽  
ROBERT SABOURIN
Keyword(s):  
Feature Selection ◽  
Pattern Classification ◽  
Control Strategy ◽  
Evolutionary Process ◽  
Memetic Algorithms ◽  
Classification Systems ◽  
Engineering Systems ◽  
Data Set ◽  
Classifier Design ◽  
Validation Procedure

The optimization of many engineering systems is challenged by the solution over-fit to the data set used to evaluate potential solutions during the evolutionary process. The solution over-fit phenomenon is hard to detect and is especially prevalent in problems involving example-based training, such as pattern feature selection and pattern classifier design. For these applications, uncontrolled over-fit can lead to biased features being extracted and degraded classifier generalization abilities. This paper details the performance of a solution over-fit control strategy used in the multiobjective evolutionary optimization of a multileveled classification system. This control, embedded within a solution validation procedure, minimizes the over-fit effects without modifying the dominance relation used in the processing of candidate solutions. Extensive experimental analysis using multiobjective genetic and memetic algorithms demonstrates both the need and the efficiency of the proposed over-fit control for pattern classification systems optimization.

Sign in / Sign up

Export Citation Format

Share Document