Application of genetically evolved neural networks to dynamic terrain generation

• Autorzy: Chomątek L. , Rudnicki M.
• Języki publikacji: EN

Abstrakty

EN

Real time terrain generation is a vital part in the development of realistic computer simulations and games. Dynamic terrain generation influences the realism of simulation, because its participants have to adapt to the current environment conditions. Dynamically generated primary terrain is transformed in order to reflect natural phenomena, such as thermal and water erosion, avalanches or glaciers. In this article a possibility of primary terrain transformation with application of artificial neural networks is shown. The networks are trained by evolutionary algorithms to solve a problem of a water erosion phenomenon. Obtained results show that application of such neural networks to this problem can significantly reduce the processing time needed to perform the process of modeling the natural phenomena.

Słowa kluczowe

EN

evolving neural networks; water erosion

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2011
• Tom: Vol. 59, nr 1
• Strony: 3--8
• Opis fizyczny: Bibliogr. 13 poz., rys., tab.

Twórcy

autor

Chomątek L.

autor

Rudnicki M.

• Institute of Information Technology, Technical University of Lodz, 225 Wólczańska St., 90-924 Łódź, Poland,

Bibliografia

• [1] M. Gad-El-Hak, “The art and science of large-scale disasters”, Bull. Pol. Ac.: Tech. 57 (1), 3–34 (2009).
• [2] D. D’Ambrosio, S. Gregorio, S. Gabriele, and R. Gaudio, “A cellular automata model for soil erosion by water”, Physics and Chemistry of the Earth B 26, 33–39 (2001).
• [3] J. Olsen, “Realtime procedural terrain generation – realtime synthesis of eroded fractal terrain for use in computer games”, Oddlabs, available at: http://oddlabs.com/download/terrain generation.pdf (accessed 2009).
• [4] B. Beneˇs and R. Forsbach, “Visual simulation of hydraulic erosion”, J. WSCG 1, 79–86 (1994).
• [5] G. Niedbała and K. Klejna, “Analysis of forecasting possibilities of soil displacements during ploughing with the use of classic statistical methods and artificial neural networks”, Agricultural Engineering 2, 90 (2007), (in Polish).
• [6] T. Behrens, H. Forster, T. Scholten, U. Steinrucken, E. Spies, and M. Goldschmitt, “Digital soil mapping using artificial neural networks”, J. Plant Nutrition and Soil Science 168, 21–33 (2005).
• [7] P. Szczepaniak and J. Protasiewicz, “Price prediction of the electric energy – regression versus neural approach”, J. Appl. Computer Science 2 (15), 7–17 (2007).
• [8] L. Marti, “Genetically generated neural networks”, Proc. Int. Joint Conf. on Neural Networks 1, CD-ROM (1992).
• [9] V. Maniezzo, “Genetic evolution of the topology and weight distribution of neural networks”, IEEE Trans. Neural Networks 5 (1), 39–53 (1994).
• [10] D.White, “GANNET: a genetic algorithm for searching topology and weight spaces in neural network design”, Lecture Notes in Coputer Science 686, 322–327 (1993).
• [11] W. Schiffmann, M. Joost, and R. Werner, “Application of genetic algorithms to the construction of topologies for multilayer perceptrons”, Proc. Int. Conf. Artificial Neural Nets and Genetic Algorithms 1, 675–682 (1993).
• [12] C. Jacob and J. Rehder, “Evolution of neural net architectures by a hierarchical grammar-based genetic system”, Proc. Int. Conf. on Artificial Neural Networks and Genetic Algorithms 1, CD-ROM (1993).
• [13] F. Gruau, D. Whitley, and L. Pyeatt, “A comparison between cellular encoding and direct encoding for genetic neural networks”, Genetic Programming Proc. First Annual Conf. 1, 81–89 (1996).