Abstract
The needs of computational power in geophysical prospecting system MEGA-D are discussed. The authors presents the system components which can be run in parallel and discuss preliminary results obtained on the base of real geophysical data. The feature selection procedure is described, which uses a few kinds of parallel versions of genetic algorithm. The selection of relevant features of measurement vector and features extraction processes are used as a help for hypotheses generation and verification. To make these processes fluent, high performance computing power is needed.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Almuallim, H., and Dietterich, T.,G., 1991, “Learning With Many Irrelevant Features”, Proc. of the 9-th National Conference on Artificial Intelligence (AAAI-91), 547–552.
Blasiak, J., 1996, “Parallel Realization of Mapping Algorithm Using Particles“, M.Sc. Thesis, University of Mining and Metallurgy, Cracow, Poland.
Broda, A., and Dzwinel, W., 1996, “Spatial Genetic Algorithm and its Parallel Implementation”, Lecture Notes in Computer Science PARA '96, 1184, 97–106.
Cantu-Paz E., 1995, ”A Summary of Research on Parallel Genetic Algorithms”, IlliGAL Report No. 95007, July 1995.
Dzwinel, J., 1983, “Fundamental Concept and Practical Aspects of the Cybernetic System for Direct Exploration of Mineral Deposits”, Acta Geophysica Polonica, XXXI, 3, 297.
Dzwinel, J., 1983, “The Structure and Algorithm of the Cybernetic Exploration System for Mineral Deposits”, Acta Geophysica Polonica, XXXI, 3, 306.
Dzwinel, J.,1986, “Method and System for Direct Prospecting of Hydrocarbon Deposits”, United States Patent, No.4, 633.182.Dec.30 1986.
Dzwinel, W., 1994, “How to Make Sammon's Mapping Useful for Multidimensional Data Structures Analysis?”, Pattern Recognition, 27, 7, 949–959.
Dzwinel, W., 1995, “In Search for the Global Minimum in Problems of Features Extraction and Selection”, Proc. of the 3 Congress on Intelligent Techniques and Soft Computing, EUFIT'95, 28–31 August 1995, Aachen, 3, 1326.
Dzwinel, W., and Blasiak, J., 1995, “Pattern Recognition via Molecular Dynamics on Vector Supercomputers and Networked Workstations”, Lecture Notes in Computer Science, HPCN'95, 919, 508, Springer-Verlag, Berlin 1995.
Dzwinel, J., Dzwinel, K., and Dzwinel, W., 1996, “Pattern Recognition Methods Implemented in MEGA-D — the System for Oil and Gas Prospecting”, Proc. of the Second International Conference on Application of Fuzzy Systems and Soft Computing, ICAFS'96, 25–27 June 1996, Siegen, Germany.
Goldberg, D.E., 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Publishing Company.
Manfoud, S. and Goldberg, D., 1995, “Parallel Recombinative Simulated Annealing: A Genetic Algorithm”, Parallel Computing, 21, 1.
Vafaie, H., and De Jong K., 1992, “Genetic algorithms as a Tool for Feature Selection Machine Learning”, Proc. of the 4thInternational Conference on Tools with Artificial Intelligence, Arlington, VA, November 1992.
Vafaie, H., and Imam,I.,F., 1994, “Feature Selection Methods: Genetic Algorithms vs. Greedy-like Search”, George Mason University Reports.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dzwinel, W., Dzwinel, J., Dzwinel, K. (1997). Development of parallel applications for MEGA-D — System for oil and gas prospecting. In: Hertzberger, B., Sloot, P. (eds) High-Performance Computing and Networking. HPCN-Europe 1997. Lecture Notes in Computer Science, vol 1225. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0031595
Download citation
DOI: https://doi.org/10.1007/BFb0031595
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62898-9
Online ISBN: 978-3-540-69041-2
eBook Packages: Springer Book Archive