Investigation of evolutionary feature subset selection in multi-temporal datasets for harmful algal bloom detection

Author

Gokaraju, Balakrishna ; Durbha, Surya S. ; King, Roger L. ; Younan, Nicolas H.

Author_Institution

Center for Adv. Vehicular Syst. (CAVS), Mississippi State Univ., Starkville, MS, USA

fYear

2011

fDate

12-14 July 2011

Firstpage

149

Lastpage

152

Abstract

In the present study we investigate the evolutionary feature subset selection using wrapper based genetic algorithms on Multi-temporal datasets. Feature subset selection helps in reducing the original feature dimension and also yields high performance. The evolutionary strategy attains a global optimum by reducing the computations iteratively and by traversing intelligently in the entire feature space. This method gave a very high performance improvement up to 0.97 kappa accuracy with a best reduced feature dimension for harmful algal bloom detection.

Keywords

data mining; genetic algorithms; geophysical image processing; microorganisms; oceanographic techniques; remote sensing; support vector machines; evolutionary feature subset selection; feature space; harmful algal bloom detection; multitemporal datasets; original feature dimension reduction; wrapper based genetic algorithms; Accuracy; Computational modeling; Data mining; Feature extraction; Genetic algorithms; Indexes; Machine learning; Feature Selection; Genetic Algorithms; Multi-Temporal; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Analysis of Multi-temporal Remote Sensing Images (Multi-Temp), 2011 6th International Workshop on the

Conference_Location

Trento

Print_ISBN

978-1-4577-1202-9

Type

conf

DOI

10.1109/Multi-Temp.2011.6005070

Filename

6005070