摘要
针对武器装备体系效能评估在高维噪声小样本数据条件下准确性不高的问题,提出一种基于堆栈降噪自编码与支持向量回归机的混合模型。利用堆栈自编码神经网络对通用深层特征的自主抽取能力,通过在相似源域大数据上预训练混合模型,获得两任务间的共有特征知识,借助对该知识的迁移,在目标域微调该混合模型,从而提升支持向量回归机在小样本噪声数据上的学习预测精度。在一定作战想定背景下,结合武器装备体系仿真试验数据,对该混合模型进行验证。实验结果表明,与传统支持向量回归机等模型相比,所提模型能够更准确地评估装备效能。
In order to improve the prediction accuracy of effectiveness of weapon equipment system-of-systems which trains on high-dimensional and noisy small samples,a hybrid model based on stacked denoising autoencoder（SDA）and support vector regression（SVR）is proposed.By taking the advantage of SDA,the method extracts common features autonomously on related but different domain data.This hybrid model is pre-trained by using a large number of source domain data.Then the hybrid model is transferred as prior knowledge on target domain.By transferring these prior knowledge,the hybrid model is fine-tuned on high-dimensional and noisy small target domain data,making up for the defects of traditional SVR.In a certain battle scenario,the model with the simulation data produced by simulation testbed is validated.Experimental results demonstrate the effectiveness of the proposed model.
作者
任俊
胡晓峰
朱丰
REN Jun;HU Xiaofeng;ZHU Feng(Deparlmenl of Information Operation ＆ Command Training , National Defense University , Beijing 100091 , China;Insiiiuie of Effectiveness Evaluation of Flying Vehicle , Beijing 100091 , China)
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2017年第12期2745-2749,共5页
Systems Engineering and Electronics
基金
国家自然科学基金(61403401)
军民共用重大研究计划联合基金项目(U1435218)资助课题
关键词
深度学习
迁移学习
特征抽取
堆栈降噪自编码
deep learning
transfer learning
feature extraction
stacked denoising autoencoder（SDA）
