Improvements in the Ant Colony Optimization Algorithm for Endmember Extraction From Hyperspectral Images

Spectral unmixing is a vital procedure in hyperspectral remote sensing image exploitation. The linear mixture model has been widely utilized to unmix hyperspectral images by extracting a set of pure spectral signatures, called endmembers in hyperspectral jargon, and estimating their respective fractional abundances in each pixel of the scene. Many algorithms have been proposed to extract endmembers automatically, which is a critical step in the spectral unmixing chain. In recent years, the ant colony optimization (ACO) algorithm has been developed for endmember extraction from hyperspectral data, which was regarded as a combinatorial optimization problem. Although the ACO for endmember extraction (ACOEE) can acquire accurate endmember results, its high computational complexity has limited its application in the hyperspectral data analysis. The GPUs parallel computing technique can be utilized to improve the computational performance of ACOEE, but the architecture of GPUs determines that the ACOEE should be redesigned to take full advantage of computing resources on GPUs. In this paper, a multiple sub-ant-colony-based parallel design of ACOEE was proposed, in which an innovative mechanism of local pheromone for sub-ant-colonies is utilized to enable ACOEE to be preferably executed on the multi-GPU system. The proposed method can avoid much synchronization among different GPUs to affect the computational performance improvement. The experiments on two real hyperspectral datasets demonstrated that the computational performance of ACOEE significantly benefited from the proposed methods.

Download Full-text

GPU implementation of Ant Colony Optimization algorithm for endmember extraction from hyperspectral image

2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS) ◽

10.1109/whispers.2012.6874319 ◽

2012 ◽

Cited By ~ 2

Author(s):

Jianwei Gao ◽

Lianru Gao ◽

Xu Sun ◽

Yuanfeng Wu ◽

Bing Zhang

Keyword(s):

Ant Colony Optimization ◽

Optimization Algorithm ◽

Hyperspectral Image ◽

Ant Colony ◽

Endmember Extraction ◽

Ant Colony Optimization Algorithm ◽

Gpu Implementation

Download Full-text

Modeling and optimizing logistics, information, economic and financial intercluster cooperation using the ant colony optimization algorithm

Finance and Credit ◽

10.24891/fc.26.11.2427 ◽

2020 ◽

Vol 26 (11) ◽

pp. 2427-2447

Author(s):

S.N. Yashin ◽

E.V. Koshelev ◽

S.A. Borisov

Keyword(s):

Ant Colony Optimization ◽

Optimization Algorithm ◽

Population Decline ◽

Innovation System ◽

Federal District ◽

Original Model ◽

Ant Colony ◽

Industrial Agglomeration ◽

Ant Colony Optimization Algorithm

Subject. This article discusses the issues related to the creation of a technology of modeling and optimization of economic, financial, information, and logistics cluster-cluster cooperation within a federal district. Objectives. The article aims to propose a model for determining the optimal center of industrial agglomeration for innovation and industry clusters located in a federal district. Methods. For the study, we used the ant colony optimization algorithm. Results. The article proposes an original model of cluster-cluster cooperation, showing the best version of industrial agglomeration, the cities of Samara, Ulyanovsk, and Dimitrovgrad, for the Volga Federal District as a case study. Conclusions. If the industrial agglomeration center is located in these three cities, the cutting of the overall transportation costs and natural population decline in the Volga Federal District will make it possible to qualitatively improve the foresight of evolution of the large innovation system of the district under study.

Download Full-text