An Intelligent Evaluation Model for Decision Scheme Based on Deep Learning. Issue 3 (March 2019)

• Record Type: Journal Article
• Authors: Ou, Wei; Yi, Zhaohui; Cheng, Lan; Liao, Ying
• Is Part Of: Journal of physics. Volume 1176:Issue 3(2019)
• Publication Date: 2019-03
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1176/3/032014
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Studying and constructing the intelligent decision-making model for simulation entity can effectively improve the credibility and immersion of wargaming, in which intelligent evaluation of decision scheme is the key module. To lower the reasoning complexity and shorten the decision time, an intelligent evaluation model based on Stacked Auto-Encoder (SAE) is proposed, which simulates the reasoning mode of human decision-making, and learns commander's knowledge and experience through unsupervised and supervised training. Then, to improve the robustness and generalization ability of the deep learning model, a de-noising training method and sparsity constraints are introduced. Finally, simulation experiment is carried out to verify the scientificity and effectiveness of the proposed model.