检索结果-内蒙古大学图书馆

GNN-based auto-encoder for Short Linear Block Codes: A DRL Approach

IEEE Transactions on Communications 2025年

作者： Tian, Kou Yue, Chentao She, Changyang Vucetic, Branka Li, Yonghui School of Electrical and Computer Engineering University of Sydney Sydney Australia Harbin Institute of Technology (Shenzhen) School of Electronic and Information Engineering Shenzhen China

This paper presents a novel auto-encoder based end-to-end channel encoding and decoding. It integrates deep reinforcement learning (DRL) and graph neural networks (GNN) in code design by modeling the generation of code parity-check matrices as a Markov Decision Process (MDP), to optimize key coding performance metrics such as error-rates and code algebraic properties. An edge-weighted GNN (EW-GNN) decoder is proposed, which operates on the Tanner graph with an iterative message-passing structure. Once trained on a single linear block code, the EW-GNN decoder can be directly used to decode other linear block codes of different code lengths and code rates. An iterative joint training of the DRL-based code designer and the EW-GNN decoder is performed to optimize the end-end encoding and decoding process. Simulation results show the proposed auto-encoder significantly surpasses several traditional coding schemes at short block lengths, including low-density parity-check (LDPC) codes with the belief propagation (BP) decoding and the maximum-likelihood decoding (MLD), and BCH with BP decoding, offering superior error-correction capabilities while maintaining low decoding complexity. © 1972-2012 IEEE.

关键词： auto-encoder Channel coding Deep reinforcement learning GNN

来源：评论

学校读者我要写书评

暂无评论

auto-encoder based dimensionality reduction

引用

NEUROCOMPUTING 2016年第0期184卷 232-242页

作者： Wang, Yasi Yao, Hongxun Zhao, Sicheng Harbin Inst Technol Sch Comp Sci & Technol Harbin 150006 Peoples R China

auto-encoder a tricky three-layered neural network, known as auto-association before, constructs the "building block" of deep learning, which has been demonstrated to achieve good performance in various domains. In this paper, we try to investigate the dimensionality reduction ability of auto-encoder, and see if it has some kind of good property that might accumulate when being stacked and thus contribute to the success of deep learning. Based on the above idea, this paper starts from auto-encoder and focuses on its ability to reduce the dimensionality, trying to understand the difference between auto-encoder and state-of-the-art dimensionality reduction methods. Experiments are conducted both on the synthesized data for an intuitive understanding of the method, mainly on two and three-dimensional spaces for better visualization, and on some real datasets, including MNIST and Olivetti face datasets. The results show that auto-encoder can indeed learn something different from other methods. Besides, we preliminarily investigate the influence of the number of hidden layer nodes on the performance of auto-encoder and its possible relation with the intrinsic dimensionality of input data. (C) 2015 Elsevier B.V. All rights reserved.

关键词： auto-encoder Dimensionality reduction Visualization Intrinsic dimensionality Dimensionality-accuracy

来源：评论

学校读者我要写书评

暂无评论

Inverse design of GaN HEMT heterostructures via deep learning with enhanced auto-encoder framework

引用

Materials Today Communications 2025年 46卷

作者： Shu Wei Meilan Hao Lina Yu Weijun Li Linjun Sun Min Wu Yan Pang Jufeng Han AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing 100083 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing 100049 China School of Information and Electrical Engineering Hebei University of Engineering Handan 056038 China School of Integrated Circuits University of Chinese Academy of Sciences Beijing 100049 China School of Industry-education Integration University of Chinese Academy of Sciences Beijing 100049 China

The design of GaN-based heterostructure materials is critical for the performance of HEMT (High Electron Mobility Transistor) devices, determining the upper limit of the device’s capabilities. Traditional design methods mainly rely on simulation modeling based on physical properties, involving repetitive forward solving of physical models and optimization attempts within the material space, which are costly in computational resources and time. Additionally, the correlation between some physical parameters and material performance remains ambiguous, especially for novel semiconductor materials. Deep learning, empowered by data, offers a solution. It can markedly increase the efficiency of designing material structures without the need to solve complex partial differential equations. In this paper, we propose an auto-encoder framework to model the complex physical relationships between the design parameters and material performance of GaN HEMT heterostructure materials. By incorporating an annealing training methodology and conditional regularization into the loss function, our approach can predict the components and thickness of various materials within milliseconds. The materials predicted using this approach are consistently thinner than those obtained without conditional regularization, with an average thickness reduction of 76%. The proposed strategy offers promising solutions for additional material systems to achieve forward performance prediction and inverse structure design.

关键词： auto-encoder Deep learning GaN HEMT Heterostructure materials Inverse design

来源：评论

学校读者我要写书评

暂无评论

auto-encoder based bagging architecture for sentiment analysis

引用

JOURNAL OF VISUAL LANGUAGES AND COMPUTING 2014年第6期25卷 840-849页

作者： Rong, Wenge Nie, Yifan Ouyang, Yuanxin Peng, Baolin Xiong, Zhang Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China Beihang Univ Res Inst Shenzhen 518057 Peoples R China Beihang Univ Sinofrench Engn Sch Beijing 100191 Peoples R China

Sentiment analysis has long been a hot topic for understanding users statements online. Previously many machine learning approaches for sentiment analysis such as simple feature-oriented SVM or more complicated probabilistic models have been proposed. Though they have demonstrated capability in polarity detection, there exist one challenge called the curse of dimensionality due to the high dimensional nature of text-based documents. In this research, inspired by the dimensionality reduction and feature extraction capability of auto-encoders, an auto-encoder-based bagging prediction architecture (AEBPA) is proposed. The experimental study on commonly used datasets has shown its potential. It is believed that this method can offer the researchers in the community further insight into bagging oriented solution for sentimental analysis. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Sentiment analysis Bagging auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Residual Wide-Kernel auto-encoder With Vision Transformer for Plant Disease Detection

引用

Journal of Phytopathology 2025年第3期173卷

作者： Vamsidhar Enireddy J. Anitha N. Mahendra G. Kishore Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India Department of Computer Science and Engineering Malla Reddy Engineering College (Autonomous) Hyderabad Telangana India Miracle Educational Society Group of Institutions Visakhapatnam Andhra Pradesh India Department of Computer Science and Engineering RISE Krishna Sai Prakasam Group of Institutions Ongole Andhra Pradesh India

Plant disease diagnosis is an important aspect of managing and producing crops. Recent developments in deep-learning models provide robust performance in detecting plant disease with improved accuracy. Several methods have been devised to detect plant disease, but inaccurate disease detection and computational complexity still limit the performance. Hence, this work proposes a hybrid residual wide-kernel auto-encoder with a vision transformer (HRWKAE-VT) for Plant disease detection. The images are collected from the plant disease dataset, and pre-processing is employed based on resizing and augmentation. Then, the dimension of the leaf images is decreased by using the proposed residual wide-kernel convolutional auto-encoder. Subsequently, the healthy and unhealthy leaves are categorised by the proposed Vision transformer-based deep-learning (VT-DL) model. The VT-DL model contains an alternating multiple-head self-attention layer and a multiple-layer perceptron (MLP) block for extracting local and global features. The performance of the proposed work is evaluated over the existing models in terms of accuracy, precision, recall, f-measure and prediction loss. The proposed model achieves 99.89% accuracy and a specificity of 98.72% on the plant disease dataset. It is observed that the performance of the proposed model improved over the conventional approaches with reduced loss of prediction.

关键词： auto-encoder dimensionality reduction leaf images plant disease detection residual kernel and attention layer vision transformer

来源：评论

学校读者我要写书评

暂无评论

Wavelet Loss Function for auto-encoder

引用

IEEE ACCESS 2021年 9卷 27101-27108页

作者： Zhu, Qiuyu Wang, Hu Zhang, Ruixin Shanghai Univ Sch Commun & Informat Engn Shanghai 201900 Peoples R China

In the field of image generation, especially for auto-encoder models, how to extract better features and obtain better quality reconstruction samples by modifying network structure and training algorithms has always been the focus of attention. For example, Variational auto-encoder (VAE), which is a very popular auto-encoder model, is a theoretically rigorously derived image generation model. For commonly used auto-encoders, such as VAE, Regularized auto-encoder (RAE), and Wasserstein auto-encoder (WAE), the mean square error (MSE) is all used as the loss function of the reconstructed process, which makes the blur problem of the reconstruction samples unavoidable. Especially for larger-sized images, the blur phenomenon is more obvious. To solve this problem, Perceptual Loss Function is used in some cases. Although it can improve the image quality to a certain extent, the amount of calculation is large and the image quality improvement in auto-encoder is also relatively limited. For this reason, we try to propose a new loss function, Wavelet loss function, to better generate and reconstruct images. Wavelet transform is applied to the reconstructed image loss function of the auto-encoder, and the frequency characteristics of the decomposed image are used to constrain it. We conducted comparative experiments on two larger-size image datasets (FaceSrub, COIL20) and a small-size image dataset (Fashion_MNIST), and proved the effectiveness of the wavelet loss function. At the same time, we propose a new image quality index: wavelet high-frequency signal-to-noise ratio (WHF-SNR), which can better measure the quality of the reconstructed image of the auto-encoder.

关键词： Wavelet transforms Image reconstruction Training Image quality Indexes Image synthesis Feature extraction auto-encoder reconstruct generate wavelet loss function

来源：评论

学校读者我要写书评

暂无评论

Comparative study of methods to obtain the number of hidden neurons of an auto-encoder in a high-dimensionality context

引用

IEEE LATIN AMERICA TRANSACTIONS 2020年第12期18卷 2196-2203页

作者： Vega-Gutierrez, Hector R. Castorena, Carlos Alejo, Roberto Granda-Gutierrez, Everardo E. Tecnol Nacl Mexico IT Toluca Metepec 52149 Estado De Mexic Mexico Univ Autonoma Estado Mexico CU UAEM Atlacomulco Atlacomulco 50400 Estado De Mexic Mexico

Fourteen formulas from the state-of-art were used in this paper to find the optimal number of neurons in the hidden layer of an autoencoder neural network. The latter is employed to reduce the dataset dimension on high-dimensionality scenarios with not significant reduction in classification accuracy in comparison to the use of the whole dataset. A Deep Learning neural network was employed to analyze the effectiveness of the studied formulas in classification terms (accuracy). Eight high-dimensional datasets were processed in an experimental set in order to assess this proposal. Results presented in this work show that formula 13 (used to find the number of hidden neurons of the auto-encoder) is effective to reduce the data dimensionality without a statistically significant reduction of the classification performance, as it was confirmed by the Freidman test and the Holm's post-hoc test.

关键词： RNA Neurons Biological neural networks Big Data IEEE transactions Deep learning Sparks High-dimensionality data Neural Network auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Intelligent cross-machine fault diagnosis approach with deep auto-encoder and domain adaptation

引用

NEUROCOMPUTING 2020年第0期383卷 235-247页

作者： Li, Xiang Jia, Xiao-Dong Zhang, Wei Ma, Hui Luo, Zhong Li, Xu Northeastern Univ Coll Sci Shenyang 110819 Peoples R China Northeastern Univ Minist Educ Safe Min Deep Met Mines Key Lab Shenyang 110819 Liaoning Peoples R China Univ Cincinnati Dept Mech Engn NSF I UCR Ctr Intelligent Maintenance Syst Cincinnati OH 45221 USA Shenyang Aerosp Univ Sch Aerosp Engn Shenyang 110136 Peoples R China Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ Shenyang 110819 Peoples R China Northeastern Univ State Key Lab Rolling & Automat Shenyang 110819 Peoples R China

Recently, due to the rising industrial demands for intelligent machinery fault diagnosis with strong generalization, transfer learning techniques have been used to enhance adaptability of data-driven approaches. Particularly, the domain shift problem where training and testing data are sampled from different operating conditions of the same machine is well addressed. However, it is still difficult to prepare sufficient labeled data on the tested machine. Therefore, the idea of transferring fault diagnosis knowledge learned from one machine to different but related machines is motivated, and that is realized through a deep learning-based method in this paper. Features of different equipments are first projected into the same subspace using an auto-encoder structure, and cross-machine adaptation algorithm is adopted for knowledge generalization, where the distribution discrepancy between data from different machines is minimized. Experiments on three rolling bearing datasets are implemented to validate the proposed method. The results suggest it is feasible to transfer fault diagnosis knowledge across different machines, and the proposed method offers a novel and promising approach for knowledge generalization. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Deep learning Fault diagnosis Model generalization auto-encoder Rolling bearing

来源：评论

学校读者我要写书评

暂无评论

Stacked Fusion Supervised auto-encoder with an Additional Classification Layer

引用

NEURAL PROCESSING LETTERS 2020年第3期51卷 2649-2667页

作者： Li, Rui Wang, Xiaodan Quan, Wen Lei, Lei Air Force Engn Univ Coll Air & Missile Def Xian 710051 Peoples R China Air Force Engn Univ Coll Air Traff Control & Nav Xian 710051 Peoples R China

auto-encoders are unsupervised deep learning models, which try to learn hidden representations to reconstruct the inputs. While the learned representations are suitable for applications related to unsupervised reconstruction, they may not be optimal for classification. In this paper, we propose a supervised auto-encoder (SupAE) with an addition classification layer on the representation layer to jointly predict targets and reconstruct inputs, so it can learn discriminative features specifically for classification tasks. We stack several SupAE and apply a greedy layer-by-layer training approach to learn the stacked supervised auto-encoder (SSupAE). Then an adaptive weighted majority voting algorithm is proposed to fuse the prediction results of SupAE and the SSupAE, because each individual SupAE and the final SSupAE can both get the posterior probability information of samples belong to each class, we introduce Shannon entropy to measure the classification ability for different samples based on the posterior probability information, and assign high weight to sample with low entropy, thus more reasonable weights are assigned to different samples adaptively. Finally, we fuse the different results of classification layer with the proposed adaptive weighted majority voting algorithm to get the final recognition results. Experimental results on several classification datasets show that our model can learn discriminative features and improve the classification performance significantly.

关键词： Deep learning Supervised learning auto-encoder Adaptive weighted voting fusion

来源：评论

学校读者我要写书评

暂无评论

Detecting community structure and structural hole spanner simultaneously by using graph convolutional network based auto-encoder

引用

NEUROCOMPUTING 2020年 410卷 138-150页

作者： Luo, JiaXing Du, YaJun XiHua Univ Sch Comp & Sotware Chengdu 620000 Peoples R China

Both Community and Structural Hole (SH) Spanner Detection are significant research tasks in social network analysis. Due to the close topological relevance between communities and structure hole spanners, the two tasks can work out synchronously, but most studies address the two tasks independently. In recent years, deep learning has been applied in the field of community detection. However, so far no deep learning model can solve both community and SH detection at the same framework. In this paper, we first analyze why a previous model named Harmony Modularity (HAM) can working for joint community and SH spanners detection task, which is the only one previous work that solve two task synchronously. Then we discuss the deficiency of HAM. For purpose of overcoming the shortcoming of HAM, we propose a deep learning model for finding both communities and structural holes simultaneously. Because the main framework used in our model is graph convolutional neural network based auto-encoder, we shorten it for ComSHAE. Specifically, ComSHAE learn the eigenvectors of weighted Spectral Ratio-Cut Partitioning and the nonlinear representation of adjacent matrix. We infer the community assignments and top-k SH spanners from eigenvectors. Extensive experimental results on synthetic and real networks show that our model outperform the baseline HAM and some state-of-the-art methods. When compare ComSHAE with HAM on synthetic data, ComSHAE shows great effects but HAM can not work. We use Normalized Mutual Information (NMI) to measure performance on detecting communites. ComSHAE shows abort 0.05 NMI improvement than HAM on real data and abort 0.63 NMI improvement on synthetic data. We measure the cross-community transmission capacity through structural hole influence index (SHII). The SH spanners found by ComSHAE shows at lest 0.03 SHII improvement compared with SH detection methods. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Community detection Structural hole spanner auto-encoder Graph convolutional neural network Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：