Study of feature selection for the stored-grain insects based on artificial immune algorithm

Authors:
Hongtao Zhang;Yuxia Hu
Affiliations:
School of Electric power, North China University of Water Conservancy and Electric Power, Zhengzhou, China;School of Electrical Engineering, Zhengzhou University, Zhengzhou, China
Venue:
CAR'10 Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 2
Year:
2010

Citing 2
Cited 1

Theoretical advances in artificial immune systems

Theoretical Computer Science
Artificial immune system for multi-objective design optimization of composite structures

Engineering Applications of Artificial Intelligence

Input variable selection in time-critical knowledge integration applications: A review, analysis, and recommendation paper

Advanced Engineering Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The feature subset selection is critical for the real-time detection of the stored-grain insects based on image recognition technology. This study proposed a feature selection method based on artificial immune algorithm Immune (AIA). The single objective affinity evaluation function was developed to evaluate the feature subset by introducing the v-fold cross-validation training model accuracy and the number of the selected features. The feature subset selection for the nine species of the insects of wheat was conducted from the 17 morphological features by using AIA. Compared with the feature selection method based on genetic algorithm, AIA can further decrease the size of the feature subset and improve the classification accuracy. By using the 7 features selected based on AIA, the SVM classifier whose parameters had been optimized classified over 95.5% of the ninety image samples of the insects. The results show that it is practical and feasible.