Scalable evolutionary computation for efficient information extraction from remote sensed imagery
Abstract
The evolutionary computation, in the form of genetic programming, is used to aid information extraction process from high-resolution satellite imagery in a semi-automatic fashion. Distributing and parallelizing the task of evaluating all candidate solutions could significantly reduce the computational cost inherent of evolving solutions composed of multi-channel large images. Therefore, the utilization of cloud-computing technology is used to enhance the existing evolutionary framework to expedite the supervised solution development stage. MapReduce programming model is used to implement a distributed version of the existed framework in cloud environment. The proposed system has three major subsystems; (i) data preparation: generation of random image band combinations, (ii) information extraction: utilization of genetic programming for spectrally distinguish the feature of interest from remaining image background of remote sensed imagery, and (iii) distributed processing: distributed implementation of genetic programming system on cloud computing environment to improve scalability. The proposed system reduces response time by leveraging the vast computational and storage resources in a cloud-computing environment. The results show that distributing the candidate solutions reduces the execution time by 91.58%. These findings allow the application of such technology to more complex problems with larger population size and number of generations.
Subject Area
Information Technology|Information science|Computer science
Recommended Citation
Laila Muthyib Almutairi,
"Scalable evolutionary computation for efficient information extraction from remote sensed imagery"
(2014).
ETD Collection for Tennessee State University.
Paper AAI1567561.
https://digitalscholarship.tnstate.edu/dissertations/AAI1567561