The Application of SOFM Fuzzy Neural Network in Project Cost Estimate
Abstract
Applications of neural network were widely used in construct project cost estimate. Aim at handling weakness of poor convergence and insufficient forecast, an improved fuzzy neural network method based on SOFM (self-organizing feature map) was proposed to replace the fashionable T-S fuzzy neural network. The method illustrated how to apply SOFM to improve the fault such as poor convergence and insufficient forecast. After optimizing of T-S fuzzy neural network model, construct project cost estimate model had been built up. Finally, the model was set up with the purpose of comparing generalization ability by 18 examples and 2 testing samples. Comparing the simulation, a positive result was found that SOFM fuzzy neural network had a better performance in reducing the forecast error and iterating times than BP, and GA-BP. Therefore, this model is fit for handling construct project cost estimate.
Keywords
References
MATLAB Chinese forum. thirty case analysis of matlab neural network[M].Beijing University of Aeronautics and Astronautics press. April 21, 2010.
Wen-Feng Feng, Wen-Juan Zhu, Yu-Guang Zhou. Application of SOFM in building classification[J].Computer Application. June, 2010. Lan Yao. Software quality forecast research based on fuzzy neural network. April, 2007. F. H. Oscar Cordon, Frank Hoffmann,Luis Magdalena, “GENETIC FUZZY SYSTEMS: EVOLUTIONARY TUNING AND LEARNING OF FUZZY KNOWLEDGE BASES,” Advances in Fuzzy Systems — Applications and Theory vol. Vol. 19, pp. 488 pages 2001.
Xian-Ye Yang. Application of fuzzy neural network in land and water resource science. June, 2008.
M. J. S. Wen-der Yua, “A neuro-fuzzy computational approach to constructability knowledge acquisition for construction technology evaluation ” Automation in Construction, vol. 6, no. 5, pp. 539-552, 1999.
H. R. B. Donald S. Remer, “Estimating the cost for doing a cost estimate,” Int. J. Production Economics, vol. 66, no. 1, pp. 101-104, 20000.
J.-E. Y. Gwang-Hee Kim, Sung-Hoon An, Hun-Hee Cho, Kyung-In Kang, “Neural networkmodel incorporating a genetic algorithm in estimating construction costs,” building and evironment, vol. 39, no. 3, pp. 1333-1340, 2004.
Zhe-Xue Ge, “neural network and realization by matlab 2007[M],” Electronic Industry Press, 2007.
Jin Hai, and Shi-Wei Ye, “neural network theory,” machine Industry Press, 2004.
M. Zhang, Y. Hu, T. Wang et al., “An optimal predicting method based on improved genetic algorithm embedded in neural network and its application to peritoneal dialysis,” Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, vol. 26, no. 6, pp. 1186-90, Dec, 2009.
PMid:20095466
R. E. D. Randall S. Sextona, John D. Johnsonb, “Toward global optimization of neural networks: A comparison of the genetic algorithm and backpropagation ” Decision Support Systems, vol. 22, no. 2, pp. 171-185, 1998.
http://dx.doi.org/10.1016/S0167-9236(97)00040-7
Jing-Wen Tian, “artificial neural network algorithm research and application[M],” Beijing Institute of Techmology press, 2006.
Ying-Jie Lei, “matlab genetic algorithm tool-box and application[M],” Xidian University, 2006.
Xiao-Ping Wang, “genetic algorithm--theory, applicationa, and software realization,” Xi'an Jiaotong University, 2002.
L. D. David J. Montana, “Training Feedforward Neural Networks Using Genetic Algorithms,” Machine Learning, vol. 89, no. 1, pp. 762-767, 1989.
F. G. O. Cordón, F. Herrera,F. Hoffmann,and L. Magdalena, “Ten years of genetic fuzzy systems: current framework and new trends ” Fuzzy Sets and Systems, vol. 141, no. 1, pp. 5-31, 2004.
http://dx.doi.org/10.1016/S0165-0114(03)00111-8
M. J. S. Wen-der Yua, “A neuro-fuzzy computational approach to constructability knowledge acquisition for construction technology evaluation ” Automation in Construction, vol. 6, no. 5, pp. 539-552, 1999.
Zhe-Xue Ge, “neural network and realization by matlab 2007[M],” Electronic Industry Press, 2007. Jin Hai, and Shi-Wei Ye, “neural network theory[M],” machine Industry Press, 2004.
M. Zhang, Y. Hu, T. Wang et al., “[An optimal predicting method based on improved genetic algorithm embedded in neural network and its application to peritoneal dialysis],” Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, vol. 26, no. 6, pp. 1186-90, Dec, 2009.
PMid:20095466
R. E. D. Randall S. Sextona, John D. Johnsonb, “Toward global optimization of neural networks: A comparison of the genetic algorithm and backpropagation ” Decision Support Systems, vol. 22, no. 2, pp. 171-185, 1998.
http://dx.doi.org/10.1016/S0167-9236(97)00040-7
Jing-Wen Tian, “artificial neural network algorithm research and application[M],” Beijing Institute of Techmology press, 2006.
Ying-Jie Lei, “matlab genetic algorithm tool-box and application[M],” Xidian University, 2006.
Xiao-Ping Wang, “genetic algorithm--theory, applicationa, and software realization[M],” Xi'an Jiaotong University, 2002.
L. D. David J. Montana, “Training Feedforward Neural Networks Using Genetic Algorithms,” Machine Learning, vol. 89, no. 1, pp. 762-767, 1989.
F. G. O. Cordón, F. Herrera,F. Hoffmann,and L. Magdalena, “Ten years of genetic fuzzy systems: current framework and new trends ” Fuzzy Sets and Systems, vol. 141, no. 1, pp. 5-31, 2004.
http://dx.doi.org/10.1016/S0165-0114(03)00111-8
M. J. S. Wen-der Yua, “A neuro-fuzzy computational approach to constructability knowledge acquisition for construction technology evaluation ” Automation in Construction, vol. 6, no. 5, pp. 539-552, 1999.
X. YAO, “Evolving Artificial Neural Networks,” PROCEEDINGS OF THE IEEE, vol. 87, no. 9, pp. 1423-1447, 1999.
http://dx.doi.org/10.1109/5.784219
Yuan Qing, “The Study on the Application of Genetic Algorithm and Neural Network in Fault Diagnosis for Missile Ground Testing Equipment”,journal of test and measurement technology,vol 16,pp.702-706,2002.
Full Text: PDF