Feature Selection Based on Clonal Selection Algorithm

2011 ◽  
pp. 180-203
Author(s):  
Xiangrong Zhang ◽  
Fang Liu
Keyword(s):  
Feature Selection ◽  
Optimization Problem ◽  
Clonal Selection ◽  
Good Choice ◽  
Affinity Maturation ◽  
Clonal Selection Algorithm ◽  
Feature Subset ◽  
Selection Algorithm ◽  
Rapid Convergence ◽  
Optimal Feature Subset

The problem of feature selection is fundamental in various tasks like classification, data mining, image processing, conceptual learning, and so on. Feature selection is usually used to achieve the same or better performance using fewer features. It can be considered as an optimization problem and aims to find an optimal feature subset from the available features according to a certain criterion function. Clonal selection algorithm is a good choice in solving an optimization problem. It introduces the mechanisms of affinity maturation, clone, and memorization. Rapid convergence and good global searching capability characterize the performance of the corresponding operations. In this study, the property of rapid convergence to global optimum of clonal selection algorithm is made use of to speed up the searching of the most appropriate feature subset among a huge number of possible feature combinations. Compared with the traditional genetic algorithm-based feature selection, the clonal selection algorithm-based feature selection can find a better feature subset for classification. Experimental results on datasets from UCI learning repository, 16 types of Brodatz textures classification, and synthetic aperture radar (SAR) images classification demonstrated the effectiveness and good performance of the method in applications.

Modulation Recognition of Digital Multimedia Signal Based on Data Feature Selection

2017 ◽  
Vol 8 (3) ◽  
pp. 90-111 ◽  
Author(s):  
Hui Wang ◽  
Li Li Guo ◽  
Yun Lin
Keyword(s):  
Feature Selection ◽  
Information Entropy ◽  
Feature Subset ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Modulation Recognition ◽  
Signal Modulation ◽  
Digital Multimedia ◽  
Optimal Feature Subset ◽  
Optimal Feature

Automatic modulation recognition is very important for the receiver design in the broadband multimedia communication system, and the reasonable signal feature extraction and selection algorithm is the key technology of Digital multimedia signal recognition. In this paper, the information entropy is used to extract the single feature, which are power spectrum entropy, wavelet energy spectrum entropy, singular spectrum entropy and Renyi entropy. And then, the feature selection algorithm of distance measurement and Sequential Feature Selection(SFS) are presented to select the optimal feature subset. Finally, the BP neural network is used to classify the signal modulation. The simulation result shows that the four-different information entropy can be used to classify different signal modulation, and the feature selection algorithm is successfully used to choose the optimal feature subset and get the best performance.

Extracting Information in Agricultural Data Using Fuzzy-Rough Sets Hybridization and Clonal Selection Theory Inspired Algorithms

2016 ◽  
Vol 30 (09) ◽  
pp. 1660008 ◽  
Author(s):  
Ayodele Lasisi ◽  
Rozaida Ghazali ◽  
Mustafa Mat Deris ◽  
Tutut Herawan ◽  
Fola Lasisi
Keyword(s):  
Feature Selection ◽  
Artificial Immune System ◽  
Clonal Selection ◽  
Recognition System ◽  
Clonal Selection Algorithm ◽  
Immune Recognition ◽  
Selection Algorithm ◽  
Artificial Immune ◽  
Detection Rates ◽  
Clonal Selection Theory

Mining agricultural data with artificial immune system (AIS) algorithms, particularly the clonal selection algorithm (CLONALG) and artificial immune recognition system (AIRS), form the bedrock of this paper. The fuzzy-rough feature selection (FRFS) and vaguely quantified rough set (VQRS) feature selection are coupled with CLONALG and AIRS for improved detection and computational efficiencies. Comparative simulations with sequential minimal optimization and multi-layer perceptron reveal that the CLONALG and AIRS produced significant results. Their respective FRFS and VQRS upgrades namely, FRFS-CLONALG, FRFS-AIRS, VQRS-CLONALG, and VQRS-AIRS, are able to generate the highest detection rates and lowest false alarm rates. Thus, gathering useful information with the AIS models can help to enhance productivity related to agriculture.

Research on Dynamic Clonal Selection Algorithm Combined with Artificial Fish School

2011 ◽  
Vol 63-64 ◽  
pp. 552-556
Author(s):  
Yu Ling Tian ◽  
Yu Hao Liu
Keyword(s):  
Production Efficiency ◽  
Simulation Experiment ◽  
Clonal Selection ◽  
Clonal Selection Algorithm ◽  
Selection Algorithm ◽  
Rapid Convergence ◽  
Fish School ◽  
Clone Selection ◽  
Improved Algorithm

As in the dynamic clone selection algorithm, the detector use factor is low, the overall importance is bad, this article proposed that the behavior of follows, gathers which has the overall importance and the rapid convergence in the artificial school of fish algorithm applicant in the dynamic clone selection algorithm detector generation phase. Meanwhile, the efficiency of algorithm is improved, and many questions which stochastically the detector takes are solved. The simulation experiment indicated that the improved algorithm has the advantage of the artificial school fish algorithm and made up the question that earlier period to restrain slowly, the detector production efficiency low in its own system.

The Optimization of Carbon Fiber Drawing Process Based on Cooperative Immune Clonal Selection Algorithm

2013 ◽  
Vol 681 ◽  
pp. 304-308 ◽  
Author(s):  
Jia Jia Chen ◽  
Yong Sheng Ding ◽  
Kuang Rong Hao
Keyword(s):  
Carbon Fiber ◽  
Optimization Problem ◽  
Clonal Selection ◽  
Convergence Time ◽  
Clonal Selection Algorithm ◽  
Drawing Process ◽  
Multi Objective Optimization ◽  
Selection Algorithm ◽  
Elongation Ratio ◽  
Optimal Linear

Drawing is an important process during carbon fiber production. How to obtain the fittest drawing ratios distribute scheme is a typical multi-objective optimization problem. We propose a novel cooperative immune clonal selection algorithm (CICSA) to obtain the optimal linear density and breaking elongation ratio. The CICSA features in synergetic evolution, clonal operation and mutation operation. Compared with the immune algorithm and the genetic algorithm, it has the best performance in precision and convergence time.

Feature Selection Algorithm for Palm Bio-Impedance Spectroscopy Based on Immune Clone

2013 ◽  
Vol 347-350 ◽  
pp. 2712-2716
Author(s):  
Lin Tao Lü ◽  
Peng Li ◽  
Yu Xiang Yang ◽  
Fang Tan
Keyword(s):  
Feature Selection ◽  
Impedance Spectroscopy ◽  
Least Squares Method ◽  
Feature Model ◽  
Feature Subset ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Elliptical Model ◽  
Optimal Feature Subset ◽  
Optimal Feature

According to the features of Palm bio-impedance spectroscopy (BIS) data, this paper suggests a kind of effective feature model of palm BIS data elliptical model. The model combines immune clone algorithm and least squares method, establishes a palm BIS feature selection algorithm, and uses the algorithm to obtain the optimal feature subset that can completely represent the palm BIS data, and then use several classification algorithms for classification and comparison. The experimental results show that accuracy of the feature subset obtained through the algorithm in SVM classification algorithm test can reach 93.2, thereby verifying the algorithm is a valid and reliable palm BIS feature selection algorithm.

Sign in / Sign up

Export Citation Format

Share Document