A Method of Sensitivity Analysis of Complex Systems Based on BP Neural Network
- 147 Downloads
The paper proposes a method based on BP neural network to extract sensitivity information for the complex system with interrelated inputs. This method requires firstly establishing BP neural network models for each input to the others and system inputs to output, then sensitivity information is extracted from these BP network models. A procedure to obtain BP network models of the system with interrelated inputs is proposed; the question of whether for a certain sub-model to exist is explored; and a concrete approach to calculate sensitivity is presented. Simulation result demonstrates the validity of the proposed method of extracting sensitivity information.
KeywordsHide Layer Generalization Error Hide Layer Node Training Accuracy Local Importance
Unable to display preview. Download preview PDF.
- 1.Wang, H.: Partial Least Square Method and its application. National defence industrial press, Beijing (2000) (in Chinese)Google Scholar
- 4.Yuan, B., Wang, X.Z., Morris, T.: Software Analyser Design Using Data Mining Technology for Toxicity Prediction of Aqueous Effluents. Water Management 20(8), 677–686 (2000)Google Scholar
- 7.Zheng, H., Xie, L., Zhang, L.-Z.: Sensitivity Analysis of Electricity Price Based on Support Vector Machine. Proceedings of the CSEE 26(11), 134–138 (2006) (in Chinese)Google Scholar
- 9.FECIT Sci-Tech Co., Ltd. MATLAB auxiliary Neural Network Analysis and Design. Publishing House of Electronics Industry, Beijing (2003) (in Chinese)Google Scholar
- 10.Hagan, M.T., Demuth, H.B., Beale, M.: Neural Network design. China Machine Press, Beijing (2002)Google Scholar