检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Vijayaraj, A. Shreya, S. Deepana, G. Senthilvel, P. Gururama Jebakumar, R. Department of IT R.M.K Engineering College RSM Nagar Kavaraipettai Chennai601 206 India Department of Civil Engineering S.A. Engineering College Thiruverkadu Chennai600077 India Chennai602 105 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350305708

This paper suggests a new approach to enhancing waste classification performance using deep learning algorithms. Specifically, the proposed approach integrates an autoencoder network with a feature selection method in convolutional neural network models. This approach aims to identify valuable features from waste material images while reducing noise and improving the accuracy of the model. autoencoder networks are utilised to learn a compressed representation of input data, which can be used as a feature vector for classification tasks. The feature selection method is then applied to remove irrelevant features, improving the accuracy of the model. The proposed approach has the potential to provide an efficient and effective solution for waste classification tasks, contributing to sustainable waste management and environmental conservation. Experimental results demonstrate the effectiveness of the proposed approach in enhancing the accuracy of waste classification tasks. © 2023 IEEE.

关键词： autoencoder network sustainable waste management Waste classification

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

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

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

An autoencoder-based model for forest disturbance detection using Landsat time series data

引用

International Journal of Digital Earth 2021年第9期14卷 1087-1102页

作者： Gaoxiang Zhou Ming Liu Xiangnan Liu Department of Information and Engineering Engineering University of People’s Armed PoliceXi’anPeople’s Republic of China School of Land Engineering Chang’An UniversityXi’anPeople’s Republic of China School of Information and Engineering China University of GeosciencesBeijingPeople’s Republic of China

Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration *** this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal *** autoencoder network is established and trained to reconstruct intact forest ***,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest *** assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,***,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the ***,comparing three common methods,the proposed model performs better,especially for intact forest detection *** study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.

关键词： Forest disturbance detection autoencoder network Unsupervised learning Landsat time series

来源：评论

学校读者我要写书评

暂无评论

3-D Inspection Method for Industrial Product Assembly Based on Single X-Ray Projections

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2021年 70卷 1-14页

作者： Li, Xuan Wang, Sukai Chen, Ping Wang, Liming North Univ China State Key Lab Elect Testing Technol Taiyuan 030051 Peoples R China

Industrial product assembly inspection is an indispensable part of industrial production, directly affecting product performance and reliability. Due to the capsulation of many products, most of the current inspection methods are based on X-ray technologies, such as digital radiography (DR) and computed tomography (CT). The inspection methods based on DR are fast but cannot obtain the spatial distributions or interrelationships of the assembled components and are easily affected by the occlusion of internal components. The detection methods based on CT can reconstruct the 3-D volume of a product and have high detection accuracy but cannot achieve real-time inspection because of the reconstruction speed. To address the above problems, we propose an inspection method based on a single-projection reconstruction network for industrial product assembly. An improved autoencoder network is trained to learn the shared structural features in 3-D volumes from 2-D projections, realizing the reconstruction of the 3-D volume at a specific viewing angle from a single projection from any viewing angle. The 3-D volumes output by the network are used to detect the position and posture of the components in the product to judge whether the product has been assembled correctly. The feasibility of the proposed method is verified with the data of a certain fuse under different assembly conditions. The experimental results show that the proposed method can improve the inspection efficiency, reduce the inspection costs, and simplify the imaging system.

关键词： Assembly 3-D inspection autoencoder network deep learning single-projection reconstruction X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised DEnoising UltraSound network (DEUS-Net)

引用

IFAC-PapersOnLine 2024年第24期58卷 614-619页

作者： Christian Janorschke Jan Meyer Daniel Wulff

Ultrasound is one of the most widespread technologies for medical imaging. This is due to its many benefits, like being non-invasive, radiation free and portable. However, one of the biggest challenges for ultrasound is image quality due to speckle noise interfering with most image processing algorithms. Many mathematical methods are used to combat this, but modern neural networks offer new perspectives. In this paper, we propose a self-supervised neural network approach that enhances image quality for images from different anatomical domains and ultrasound systems, thus achieving domain translation, real-time computation and denoising performance on par with the best traditional algorithms.

关键词： Ultrasound imaging Image denoising AI Machine learning autoencoder network

来源：评论

学校读者我要写书评

暂无评论

Functional connectome fingerprinting: Identifying individuals and predicting cognitive functions via autoencoder

引用

HUMAN BRAIN MAPPING 2021年第9期42卷 2691-2705页

作者： Cai, Biao Zhang, Gemeng Zhang, Aiying Xiao, Li Hu, Wenxing Stephen, Julia M. Wilson, Tony W. Calhoun, Vince D. Wang, Yu-Ping Tulane Univ Biomed Engn Dept New Orleans LA 70118 USA Mind Res Network Albuquerque NM USA Univ Nebraska Med Ctr UNMC Dept Neurol Sci Omaha NE 68182 USA Emory Univ Georgia Inst Technol Georgia State Univ Triinst Ctr Translat Res Neuroimaging & Data Sci Atlanta GA USA

Functional network connectivity has been widely acknowledged to characterize brain functions, which can be regarded as "brain fingerprinting" to identify an individual from a pool of subjects. Both common and unique information has been shown to exist in the connectomes across individuals. However, very little is known about whether and how this information can be used to predict the individual variability of the brain. In this paper, we propose to enhance the uniqueness of individual connectome based on an autoencoder network. Specifically, we hypothesize that the common neural activities shared across individuals may reduce the individual identification. By removing contributions from shared activities, inter-subject variability can be enhanced. Our experimental results on HCP data show that the refined connectomes obtained by utilizing autoencoder with sparse dictionary learning can distinguish an individual from the remaining participants with high accuracy (up to 99.5% for the rest-rest pair). Furthermore, high-level cognitive behaviors (e.g., fluid intelligence, executive function, and language comprehension) can also be better predicted with the obtained refined connectomes. We also find that high-order association cortices contribute more to both individual discrimination and behavior prediction. In summary, our proposed framework provides a promising way to leverage functional connectivity networks for cognition and behavior study, in addition to a better understanding of brain functions.

关键词： autoencoder network common connectivity patterns functional connectivity high‐ level cognition prediction individual identification refined connectomes

来源：评论

学校读者我要写书评

暂无评论

Deep Monocular Depth Estimation Based on Content and Contextual Features

引用

SENSORS 2023年第6期23卷 2919-2919页

作者： Abdulwahab, Saddam Rashwan, Hatem A. Sharaf, Najwa Khalid, Saif Puig, Domenec Univ Rovira & Virgil Dept Comp Engn & Math Campus SesceladesAvinguda dels Paisos Catalans 26 Tarragona 43007 Spain

Recently, significant progress has been achieved in developing deep learning-based approaches for estimating depth maps from monocular images. However, many existing methods rely on content and structure information extracted from RGB photographs, which often results in inaccurate depth estimation, particularly for regions with low texture or occlusions. To overcome these limitations, we propose a novel method that exploits contextual semantic information to predict precise depth maps from monocular images. Our approach leverages a deep autoencoder network incorporating high-quality semantic features from the state-of-the-art HRNet-v2 semantic segmentation model. By feeding the autoencoder network with these features, our method can effectively preserve the discontinuities of the depth images and enhance monocular depth estimation. Specifically, we exploit the semantic features related to the localization and boundaries of the objects in the image to improve the accuracy and robustness of the depth estimation. To validate the effectiveness of our approach, we tested our model on two publicly available datasets, NYU Depth v2 and SUN RGB-D. Our method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy of 85%, while minimizing the error Rel by 0.12, RMS by 0.523, and log10 by 0.0527. Our approach also demonstrated exceptional performance in preserving object boundaries and faithfully detecting small object structures in the scene.

关键词： deep learning monocular depth estimation autoencoder network contextual semantic information

来源：评论

学校读者我要写书评

暂无评论

Extended-Aggregated Strategy for Hyperspectral Unmixing Based on Dilated Convolution

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2023年 20卷 1页

作者： Gao, Yuyou Pan, Bin Song, Xinyu Xu, Xia Nankai Univ Sch Stat & Data Sci KLMDASR LEBPS Tianjin 300071 Peoples R China Nankai Univ LPMC Tianjin 300071 Peoples R China Nankai Univ Coll Comp Sci Tianjin 300071 Peoples R China

autoencoder unmixing is a popular deep learning-based spectral unmixing algorithm, which decomposes the mixed pixels into pure endmembers and their fractional proportions, but the existing methods cannot fully exploit the spatial correlation features of hyperspectral image (HIS). In this letter, we propose a dilated convolution extended-aggregated strategy (DEAS), which enhances the ability of autoencoder unmixing algorithms to extract spatial correlation features. This strategy constructs a module utilizing various combinations of dilated convolutions with different scales. DEAS extracts the spatial relationships within multiple ranges around each pixel. Compared with the full connection and convolution commonly used in the encoder layers, autoencoder algorithms with DEAS expand the acceptance domain of the network. Furthermore, DEAS aggregates the spatial information in different ranges to obtain the feature map fully acquiring the relationship between pixels, which improves the unmixing performance. In particular, DEAS can be inserted into the existing autoencoder unmixing algorithms to get more abundant spatial information, and the methods using DEAS can show better unmixing effects. We apply the DEAS to two autoencoder methods using full connection and convolution, respectively. Experiments indicate the competitiveness of the algorithms using this strategy in hyperspectral unmixing tasks.

关键词： autoencoder network dilated convolution hyperspectral unmixing spatial correlation

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：