检索结果-内蒙古大学图书馆

Anomaly-Guided Double autoencoders for Hyperspectral Unmixing

REMOTE SENSING 2025年第5期17卷 800-800页

作者： Liu, Hongyi Zhang, Chenyang Huang, Jianing Wei, Zhihui Nanjing Univ Sci & Technol Sch Math & Stat Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China

Deep learning has emerged as a prevalent approach for hyperspectral unmixing. However, most existing unmixing methods employ a single network, resulting in moderate estimation errors and less meaningful endmembers and abundances. To address this imitation, this paper proposes a novel double autoencoders-based unmixing method, consisting of an endmember extraction network and an abundance estimation network. In the endmember network, to improve the spectral discrimination, a logarithm spectral angle distance (SAD), integrated with anomaly-guided weight, is developed as the loss function. Specifically, the logarithm function is used to boost the reliability of a pixel based on its high SAD similarity to other pixels. Moreover, the anomaly-guided weight mitigates the influence of outliers. As for the abundance network, a spectral convolutional autoencoder combined with the channel attention module is employed to exploit the spectral features. Additionally, the decoder weight is shared between the two networks to reduce computational complexity. Extensive comparative experiments with state-of-the-art unmixing methods demonstrate that the proposed method achieves superior performance in both endmember extraction and abundance estimation.

关键词： hyperspectral unmixing autoencoder network logarithm SAD anomaly detection attention module

来源：评论

学校读者我要写书评

暂无评论

DDLA: a double deep latent autoencoder for diabetic retinopathy diagnose based on continuous glucose sensors

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2024年第10期62卷 3089-3106页

作者： Tao, Rui Li, Hongru Lu, Jingyi Huang, Youhe Wang, Yaxin Lu, Wei Shao, Xiaopeng Zhou, Jian Yu, Xia Northeastern Univ Coll Informat Sci & Engn 3-11 Wenhua Rd Shenyang 110819 Liaoning Peoples R China Shanghai Jiao Tong Univ Sch MedShanghai Peoples Hosp 6 Shanghai Clin Ctr DiabetShanghai Diabet Inst Dept Endocrinol & MetabShanghai Key Lab Diabet Me 600 Yishan Rd Shanghai 200233 Peoples R China

The current diagnosis of diabetic retinopathy is based on fundus images and clinical experience. However, considering the ineffectiveness and non-portability of medical devices, we aimed to develop a diagnostic model for diabetic retinopathy based on glucose series data from the wearable continuous glucose monitoring system. Therefore, this study developed a novel method, i.e., double deep latent autoencoder, for exploring glycemic variability influence from multi-day glucose data for diabetic retinopathy. Specifically, the model proposed in this research could encode continuous glucose sensor data with non-continuous and variable length via the integration of a data reorganization module and a novel encoding module with fragmented-missing-wise objective function. Additionally, the model implements a double deep autoencoder, which integrated convolutional neural network, long short-term memory, to jointly capturing the inter-day and intra-day glucose latent features from glucose series. The effectiveness of the proposed model is evaluated through a cross-validation method to clinical datasets of 765 type 2 diabetes patients. The proposed method achieves the highest accuracy value (0.89), precision value (0.88), and F1 score (0.73). The results suggest that our model can be used to remotely diagnose and screen for diabetic retinopathy by learning potential features of glucose series data collected by wearable continuous glucose monitoring systems.

关键词： Continuous glucose monitoring autoencoder network Diabetic retinopathy

来源：评论

学校读者我要写书评

暂无评论

Deep Embedding Clustering Based onResidual autoencoder

引用

NEURAL PROCESSING LETTERS 2024年第2期56卷 127-127页

作者： Li, Mengli Cao, Chao Li, Chungui Yang, Shuhong Guilin Univ Sch Technol Guilin Peoples R China Guangxi Univ Sci & Technol Sch Comp Sci & Technol Liuzhou Peoples R China Univ Elect Sci & Technol China Yangtze Delta Reg Inst Quzhou Quzhou Peoples R China

Clustering algorithm is one of the most widely used and influential analysis techniques. With the advent of deep learning, deep embedding clustering algorithms have rapidly evolved and yield promising results. Much of the success of these algorithms depends on the potential expression captured by the autoencoder network. Therefore, the quality of the potential expression directly determines the algorithm's performance. In view of this, researchers have proposed many improvements. Although the performance has been slightly improved, they all have one shortcoming, that is, too much emphasis is placed on the original data reconstruction ability during the process of feature expression, which greatly limits the further expression of potential features according to specific clustering tasks. Moreover, there is a large amount of noise in the original data, so blindly emphasizing reconstruction will only backfire. Hence, we innovatively propose a deep embedding clustering algorithm based on residual autoencoder (DECRA) after in-depth research. Specifically, a novel autoencoder network with residual structure is proposed and introduced into deep embedded clustering tasks. The network introduces an adaptive weight layer in feature representation z, which can make it have good robustness, generalization for specific tasks, and adaptive learning of better feature embeddings according to category classification. In this paper, the reasons for the validity of this structure are explained theoretically, and comprehensive experiments on six benchmark datasets including various types show that the clustering performance of the DECRA is very competitive and significantly superior to the most advanced methods.

关键词： Deepembedded clustering Residual structure autoencoder network Representationlearning

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch Subpixel-Guided network for Hyperspectral Image Classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Han, Zhu Yang, Jin Gao, Lianru Zeng, Zhiqiang Zhang, Bing Chanussot, Jocelyn Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Chinese Acad Sci Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Computat Opt Imaging Technol Beijing 100094 Peoples R China Beijing Inst Remote Sensing Equipment Beijing 100854 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China Univ Grenoble Alpes CNRS Grenoble INP IJK F-38000 Grenoble France Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China

Deep learning (DL) has been widely applied to hyperspectral image (HSI) classification, owing to its promising feature learning and representation capabilities. However, limited by the spatial resolution of sensors, existing DL-based classification approaches mainly focus on pixel-level spectral and spatial information extraction through complex network architecture design while ignoring the existence of mixed pixels in actual scenarios. To tackle this difficulty, we propose a novel dual-branch subpixel-guided network for HSI classification, called DSNet, which automatically integrates subpixel information and convolutional class features by introducing a deep autoencoder unmixing architecture to enhance classification performance. DSNet is capable of fully considering physically nonlinear properties within subpixels and adaptively generating diagnostic abundances in an unsupervised manner to achieve more reliable decision boundaries for class label distributions. The subpixel fusion module is designed to ensure high-quality information fusion across pixel and subpixel features, further promoting stable joint classification. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of DSNet compared with state-of-the-art DL-based HSI classification approaches. The codes will be available at https://***/hanzhu97702/DSNet, contributing to the remote sensing community.

关键词： Vectors Decoding Hyperspectral imaging Feature extraction Training Task analysis Spatial resolution autoencoder network deep learning (DL) hyperspectral image classification hyperspectral unmixing (HU) subpixel feature

来源：评论

学校读者我要写书评

暂无评论

NASA space station rolling bearings anomaly detection based on PARA-LSTM model

引用

INTERNATIONAL JOURNAL OF SENSOR networkS 2024年第1期44卷 49-61页

作者： Zhang, Yingqian Wu, Jiaye Xie, Hui Hua, Rongru Li, Qiang Sichuan Univ Sci & Engn Sch Civil Engn Zigong 643000 Peoples R China Southwest Petr Univ Sch Mech & Elect Engn Chengdu 610500 Peoples R China Sichuan Shengtuo Testing Technol Co Ltd Technol Ctr Chengdu 643000 Peoples R China

Anomaly detection in time series data identifies abnormal events or behaviours. Traditional methods include principal component analysis (PCA) combined with Mahalanobis distance and long short-term memory (LSTM). autoencoders and neural network techniques have been applied to the problem of anomaly detection. Still, challenges remain, such as large training data volume, network parameter initialisation, low training efficiency, and poor anomaly detection performance. This paper proposes an anomaly detection method based on parallel-long short-term memory (PARA-LSTM), which constructs two parallel processing structures. The method was tested on the rolling bearing vibration dataset collected by the NASA space station. It could detect anomalies five days ahead of the actual system destruction time, outperforming the PCA method by detecting anomalies one day earlier. PARA-LSTM has good performance, stability, and generalisation ability.

关键词： autoencoder bearing vibration anomaly detection Mahalanobis distance autoencoder network parallel-long short-term memory PARA-LSTM

来源：评论

学校读者我要写书评

暂无评论

STARNet: An Efficient Spatiotemporal Feature Sharing Reconstructing network for Automatic Modulation Classification

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第10期23卷 13300-13312页

作者： Zhang, Xiangli Wang, Zishuo Wang, Xuesong Luo, Tianze Xiao, Yong Fang, Bin Xiao, Fei Luo, Dapeng China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Chinese Construct Third Engn Bur Intelligent Technol Co Ltd Wuhan 430070 Peoples R China

Automatic Modulation Classification (AMC) is a crucial task in the field of wireless communication, allowing for the identification of the modulation scheme of a received radio signal without prior knowledge of the communication system. Recently, AMC approaches based on Deep Learning (DL) have achieved outstanding results. However, the majority of current DL-based AMC methods face challenges in achieving high recognition accuracy while remaining computationally efficient. Some researchers have designed autoencoder-based models to generate low-dimensional temporal feature embeddings of the radio signal, thereby reducing the number of model parameters while maintaining high performance in recognizing modulation formats. However, when further improving AMC performance via learning low-dimensional spatial-temporal feature representations, traditional autoencoder models require both a convolutional decoder and an LSTM decoder to reconstruct temporal and spatial features separately, which unavoidably raises the model parameters. In this paper, we propose a spatiotemporal feature sharing reconstructing network (STARNet) to simultaneously extract low-dimensional spatial and temporal feature representations of radio signals using a single autoencoder structure, thereby reducing the number of model parameters and improving AMC performance. Additionally, we construct a Hybrid Attentive Ghost (HA-Ghost) to automatically extract discriminative radio signal spatial information according to signal reconstruction performance. Extensive experiments on benchmark datasets demonstrate that the proposed STARNet achieves an average modulation classification accuracy of 63.64%, outperforming previous state-of-the-art models. Despite extracting more types of features, STARNet has only 14,860 parameters, which is smaller than existing spatiotemporal autoencoder-based methods.

关键词： Feature extraction Modulation Spatiotemporal phenomena Computational modeling Convolution Wireless communication Decoding Automatic modulation classification spatiotemporal feature representation autoencoder network attentive ghost sharing decoder deep learning

来源：评论

学校读者我要写书评

暂无评论

DFTI: Dual-Branch Fusion network Based on Transformer and Inception for Space Noncooperative Objects

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhang, Zhao Zhou, Dong Sun, Guanghui Hu, YuHui Deng, Runran Harbin Inst Technol Dept Control Sci & Engn Harbin 150001 Peoples R China Beijing Inst Spacecraft Syst Engn Beijing 100094 Peoples R China

Due to adverse illumination in space, noncooperative object perception based on multisource image fusion is crucial for on-orbit maintenance and orbital debris removal. In this article, we first propose a dual-branch multiscale feature extraction encoder combining Transformer block (TB) and Inception block (IB) to extract global and local features of visible and infrared images and establish high-dimensional semantic connections. Second, different from the traditional artificial design fusion strategy, we propose a feature fusion module called cross-convolution feature fusion (CCFF) module, which can achieve image feature level fusion. Based on the above, we propose a dual-branch fusion network based on Transformer and Inception (DFTI) for space noncooperative object, which is an image fusion framework based on autoencoder architecture and unsupervised learning. The fusion image can simultaneously retain the color texture details and contour energy information of space noncooperative objects. Finally, we construct a fusion dataset of infrared and visible images for space noncooperative objects (FIV-SNO) and compare DFTI with seven state-of-the-art methods. In addition, object tracking as a follow-up high-level visual task proves the effectiveness of our method. The experimental results demonstrate that compared with other advanced methods, the entropy (EN) and average gradient (AG) of the fusing images using DFTI network are increased by 0.11 and 0.06, respectively. Our method exhibits excellent performance in both quantitative measures and qualitative evaluation.

关键词： Space vehicles Feature extraction Image fusion Transformers Task analysis Visualization Training autoencoder network deep learning image fusion space noncooperative object transformer

来源：评论

学校读者我要写书评

暂无评论

Enhanced Integration of Single-Cell Multi-Omics Data Using Graph Attention networks

引用

ACS SYNTHETIC BIOLOGY 2025年第3期14卷 931-942页

作者： Liao, Xingyu Li, Yanyan Li, Shuangyi Wen, Long Li, Xingyi Yu, Bin Northwestern Polytech Univ Sch Comp Sci Xian 710129 Shaanxi Peoples R China Qingdao Univ Sci & Technol Sch Data Sci Qingdao 266061 Peoples R China

The continuous advancement of single-cell multimodal omics (scMulti-omics) technologies offers unprecedented opportunities to measure various modalities, including RNA expression, protein abundance, gene perturbation, DNA methylation, and chromatin accessibility at single-cell resolution. These advances hold significant potential for breakthroughs by integrating diverse omics modalities. However, the data generated from different omics layers often face challenges due to high dimensionality, heterogeneity, and sparsity, which can adversely impact the accuracy and efficiency of data integration analyses. To address these challenges, we propose a high-precision analysis method called scMGAT (single-cell multiomics data analysis based on multihead graph attention networks). This method effectively coordinates reliable information across multiomics data sets using a multihead attention mechanism, allowing for better management of the heterogeneous characteristics inherent in scMulti-omics data. We evaluated scMGAT's performance on eight sets of real scMulti-omics data, including samples from both human and mouse. The experimental results demonstrate that scMGAT significantly enhances the quality of multiomics data and improves the accuracy of cell-type annotation compared to state-of-the-art methods. scMGAT is now freely accessible at https://***/Xingyu-Liao/scMGAT.

关键词： single-cell multiomics integration analysis autoencoder network multihead graph attention mechanism high dimensionality cell type annotation

来源：评论

学校读者我要写书评

暂无评论

FGR-Net: Interpretable fundus image gradeability classification based on deep reconstruction learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期238卷

作者： Khalid, Saif Rashwan, Hatem A. Abdulwahab, Saddam Abdel-Nasser, Mohamed Quiroga, Facundo Manuel Puig, Domenec Rovira & Virgili Univ Dept Comp Engn & Math Tarragona Spain Univ Al Qadisiyah Al Diwaniyah 58002 Iraq Aswan Univ Dept Elect Engn Aswan 81528 Egypt Univ Nacl La Plata Fac Informat Inst Invest Informat LIDI La Plata Buenos Aires Argentina

The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called "FGR-Net"to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of > 89% and an F1-score of > 87%. The code is publicly available at https://***/saifalkh/FGR-Net.

关键词： Retinal image Quality assessment autoencoder network Ocular diseases Deep learning Intepretability Explainability Gradability

来源：评论

学校读者我要写书评

暂无评论

scBKAP: A Clustering Model for Single-Cell RNA-Seq Data Based on Bisecting K-Means

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第3期20卷 2007-2015页

作者： Wang, Xiaolin Gao, Hongli Qi, Ren Zheng, Ruiqing Gao, Xin Yu, Bin Qingdao Univ Sci & Technol Coll Math & Phys Qingdao 266061 Shandong Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Cent South Univ Sch Informat Sci & Engn Changsha 410083 Hunan Peoples R China King Abdullah Univ Sci & Technol KAUST Computat Biosci Res Ctr CBRC Thuwal 23955 Saudi Arabia Qingdao Univ Sci & Technol Coll Informat Sci & Technol Sch Data Sci Qingdao 266061 Shandong Peoples R China Univ Sci & Technol China Sch Data Sci Hefei 230027 Anhui Peoples R China

Advances in single-cell RNA sequencing (scRNA-seq) technologies allow researchers to analyze the genome-wide transcription profile and to solve biological problems at the individual-cell resolution. However, existing clustering methods on scRNA-seq suffer from high dropout rate and curse of dimensionality in the data. Here, we propose a novel pipeline, scBKAP, the cornerstone of which is a single-cell bisecting K-means clustering method based on an autoencoder network and a dimensionality reduction model MPDR. Specially, scBKAP utilizes an autoencoder network to reconstruct gene expression values from scRNA-seq data to alleviate the dropout issue, and the MPDR model composed of the M3Drop feature selection algorithm and the PHATE dimensionality reduction algorithm to reduce the dimensions of reconstructed data. The dimensionality-reduced data are then fed into the bisecting K-means clustering algorithm to identify the clusters of cells. Comprehensive experiments demonstrate scBKAP's superior performance over nine state-of-the-art single-cell clustering methods on 21 public scRNA-seq datasets and simulated datasets. The source codes and datasets are available at https://***/YuBinLab-QUST/scBKAP/ and https://***/10.24433/CO.4592131.v1.

关键词： Clustering algorithms Data models Pipelines Dimensionality reduction Clustering methods Standards Sequential analysis autoencoder network bisecting K-means clustering Index Terms MPDR dimensionality reduction scRNA-seq

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：