0000000000073779
AUTHOR
Victor-emil Neagoe
Feature selection with Ant Colony Optimization and its applications for pattern recognition in space imagery
This paper presents a feature selection (FS) algorithm using Ant Colony Optimization (ACO). It is inspired by the particular behavior of real ants, namely by the fact that they are capable of finding the shortest path between a food source and the nest. There are considered two ACO-FS model applications for pattern recognition in remote sensing imagery: ACO Band Selection (ACO-BS) and ACO Training Label Purification (ACO-TLP). The ACO-BS reduces dimensionality of an input multispectral image data by selecting the “best” subset of bands to accomplish the classification task. The ACO-TLP selects the most informative training samples from a given set of labeled vectors in order to optimize the…
A genetic algorithm approach to purify the classifier training labels for the analysis of remote sensing imagery
This paper proposes a Genetic Algorithm (GA) approach to clean a given classifier training set for remote sensing image analysis. Starting from an initial set of training data, the new method called GA-Training Label Purifying (GA-TLP) consists of the significant training sample selection using GAs in order to maximize the classifier accuracy. This means to retain the most informative samples and to remove the uncertain, redundant, and misclassified ones. As a result of the selection process, we can obtain a purified training set. The proposed model is implemented and evaluated using a LANDSAT 7 ETM+ image. The experimental results confirm the effectiveness of the proposed approach.
Training label cleaning with ant colony optimization for classification of remote sensing imagery
This paper presents an original approach for improving performances of the supervised classifiers in remote sensing imagery by proposing a technique to refine a given training set using Ant Colony Optimization (ACO). The new method called ACO-Training Label Cleaning (ACO-TLC) applies ACO model for selection of the significant training samples from a given set of labeled vectors in order to optimize the quality of a supervised classifier. This means to retain the most informative samples and to remove the uncertain or misclassified training samples, which lead to classification errors. As a result of the selection process, we can obtain a purified training set. The proposed model is implemen…
An Artificial Bee Colony Approach for Classification of Remote Sensing Imagery
This paper presents a novel Artificial Bee Colony (ABC) approach for supervised classification of remote sensing images. One proposes to apply an ABC algorithm to optimize the coefficients of the set of polynomial discriminant functions. We have experimented the proposed ABC-based classifier algorithm for a Landsat 7 ETM+ image database, evaluating the influence of the ABC model parameters on the classifier performances. Such ABC model parameters are: numbers of employed/onlooker/scout bees, number of epochs, and polynomial degree. One has compared the best ABC classifier Overall Accuracy (OA) with the performances obtained using a set of benchmark classifiers (NN, NP, RBF, and SVM). The re…