Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
408835 | Neurocomputing | 2009 | 11 Pages |
Abstract
This work presents a novel hybrid ACO-based classifier model that combines ant colony optimization (ACO) and support vector machines (SVM) to improve classification accuracy with a small and appropriate feature subset. To simultaneously optimize the feature subset and the SVM kernel parameters, the feature importance and the pheromones are used to determine the transition probability; the classification accuracy and the weight vector of the feature provided by the SVM classifier are both considered to update the pheromone. The experimental results indicate that the hybridized approach can correctly select the discriminating input features and also achieve high classification accuracy.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Cheng-Lung Huang,