双级联合投影包络内嵌堆栈自动编码器  

Dual-stage joint projection envelope embedded stack autoencoder

作　　者：李勇明[1] 朱立志 王品[1] 马洁[1] 周传艳 Li Yongming;Zhu Lizhi;Wang Pin;Ma Jie;Zhou Chuanyan(School of Microelectronics and Communication Engineering,Chongqing University,Chongqing 400044,China)

机构地区：[1]重庆大学微电子与通信工程学院,重庆400044

出　　处：《仪器仪表学报》2025年第2期116-131,共16页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金项目(61771080);国家自然科学基金重点项目(U21A20448)资助。

摘　　要：深度堆栈自动编码器作为一种代表性的深度网络,已被广泛应用在数据科学、模式识别等领域。现有的深度堆栈自动编码器均针对原样本个体进行深度特征变换,忽略了样本之间的关联结构信息,导致其深度特征的质量往往不尽如人意。为了解决这一问题,提出一种新的深度堆栈自动编码器网络-双级联合投影包络内嵌堆栈自动编码器。与现有的深度堆栈自动编码器本质上不同的是,双级联合投影包络内嵌堆栈自动编码器针对样本间关联信息而非样本个体本身进行深度特征变换。该模型主要包括两部分:双级联合投影包络模块和内嵌式堆栈自动编码器。在双级联合投影包络模块中,流形样本对包络子模块用于提取原样本间局部关联信息,重构生成第1层包络样本;保持降维式聚类子模块用于提取样本的全局关联信息,重构生成第2层包络样本。双级间一致性保持模块用于优化第2层包络样本的表征能力。然后,在这2层包络样本上分别训练2个内嵌式堆栈自动编码器,获得2组深度特征。组织了4组实验,包括消融实验、算法比较、参数影响分析以及复杂度分析。实验结果表明,双级联合投影包络内嵌堆栈自动编码器提取的深度特征具有较高且稳定的质量。The deep stacked autoencoder,as a prominent deep learning architecture,has been widely applied in fields such as data science and pattern recognition.However,existing deep stacked autoencoders focus on transforming the features of individual samples,often overlooking the inter-sample correlation,which can lead to suboptimal feature quality.To address this limitation,this paper introduces a novel deep stacked autoencoder architecture called the dual-stage joint projection envelope embedded stacked autoencoder.Unlike traditional deep stacked autoencoders,the proposed model transforms deep features based on the correlation information between samples,rather than focusing solely on the samples themselves.The model is composed of two primary components:the dual-stage joint projection envelope and the embedded stacked autoencoder.The dual-stage joint projection envelope utilizes a manifold sample-pair envelope module to extract local correlation information from the original samples and reconstruct the first layer of enveloped samples.A descending clustering module is then employed to capture global correlations and reconstruct the second layer of enveloped samples.Additionally,the dual-stage inter-consistency maintenance module enhances the representational power of the second-layer enveloped samples.Subsequently,two sets of deep features are extracted by training two embedded stacked autoencoders on these two layers of enveloped samples.The paper concludes with four sets of experiments:ablation studies,algorithm comparisons,parameter sensitivity analysis,and complexity analysis.Experimental results demonstrate that the deep features extracted by the proposed dual-stage joint projection envelope embedded stacked autoencoder exhibit both high quality and stability.

关 键 词：内嵌堆栈自动编码器 包络学习 双级 包络样本 聚类 域适应 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TH77[自动化与计算机技术—控制科学与工程]