检索结果-内蒙古大学图书馆

IEEE Electrical Power and Energy Conference (EPEC)

作者： Sun, Xijuan Wu, Di Zinflou, Arnaud Boulet, Benoit McGill Univ Dept Elect & Comp Engn Montreal PQ Canada Hydroquebecs Res Inst Montreal PQ Canada

ISBN: (纸本)9781665463188

Hacking and false data injection from adversaries can threaten power grids' normal operations and cause significant economic loss. Anomaly detection in power grids aims to detect and discriminate anomalies caused by the cyberattack against the power system which is essential for keeping power grids working properly and efficiently. Different types of methods have been applied for anomaly detection such as statistical methods and machine learning-based methods. For machine learning-based methods, we usually need to model the distribution of normal data. In this work, we propose a novel anomaly detection method by modeling the data distribution of normal samples via multiple encoders and decoders. Specifically, the proposed method maps input samples into a latent space and then reconstructs output samples from latent vectors. The extra encoder finally maps reconstructed samples into the latent representations. During the training phase, parameters are optimized by minimizing reconstruction loss and encoding loss. Furthermore, training samples are re-weighted to focus more on missed correlations among features of normal data. Experiment results on network intrusion and power system datasets demonstrate the effectiveness of our proposed method, where our model consistently outperforms all baselines.

关键词： Anomaly detection ensemble encoder and decoder power system one-class classification

来源：评论

学校读者我要写书评

暂无评论

Remediation of LWD data lag with hybrid real-time data using self-attention-based encoder-decoder model

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2025年 244卷

作者： Zhang, Jiafeng Liu, Ye Cao, Jie Yang, Tao Xian ShiYou Univ Sch Comp Sci Xian 710065 Shaanxi Peoples R China eDrilling AS Stavanger Rogaland Norway Equinor Stavanger Rogaland Norway

This study aims to address the lag issue in Logging While Drilling (LWD) data, which is crucial for real-time decision-making in subsurface resource exploration. The primary objective is to enhance the accuracy of LWD measurements, which suffer from a positional discrepancy due to the tools being positioned several meters behind the drill bit. This lag can lead to delayed responses and misinterpretations during drilling operations. To achieve this, we introduce a novel Self-Attention-Based encoder-decoder (SABED) model that compensates for the time/depth lag by utilizing hybrid real-time data, including drilling engineering and LWD data. Our methodology involves training and validating the SABED model using data from the Volve field in the North Sea. The model's architecture is designed to effectively capture the complex relationships between drilling data and LWD measurements. Experimental results demonstrate that the SABED model can predict gamma ray values up to 45 m ahead with a Mean Relative Error (MRE) of less than 1.5% in the primary test well (F7), outperforming conventional sequential deep learning models. Further evaluations on an auxiliary test well (F10) indicate robust performance and generalization capabilities, even with noisy drilling data. The model also meets real-time operational requirements, processing predictions in approximately 4.5 s per 300-step interval (30 m) on both CPU and GPU. Notably, the SABED model maintains predictive accuracy despite data loss, using linear interpolation for missing segments. These findings underscore the SABED model's effectiveness in mitigating LWD data lag and its potential as a valuable tool for real-time geological information prediction. This research contributes novel insights to the field by providing an advanced methodology for improving data accuracy in LWD operations, thereby enhancing decision-making in the petroleum industry.

关键词： LWD Volve field Self-attention models encoder and decoder Hybrid real-time data

来源：评论

学校读者我要写书评

暂无评论

Physically Jacobian-Informed encoder-decoder ANNs for Nonlinear Power Flow Regression

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2025年第2期61卷 2353-2362页

作者： Yang, Hao Zheng, Kai Su, Wendong Sun, Zhenglong Cai, Guowei Ding, Zhaohao Northeast Elect Power Univ Key Lab Modern Power Syst Simulat & Control & Rene Minist Educ Jilin 132012 Peoples R China North China Elect Power Univ Beijing 102206 Peoples R China

Power flow (PF) is the basis of steady-state analysis and control of power systems. The conventional model-driven PF formulated by a set of implicated nonlinear equations is solved iteratively by using Newton-Raphson method. But, the speed and convergence of PF computation are influenced by proper initial values and the efficiency of iterative process. The data-driven PF regression method can overcome the above issues by learning an explicit mapping function from PF data set. However, it simply achieves the nonlinear map from PF input to output, overlooking the physical rules in the PF calculation, which may result in poor accuracy and generalization. This paper presents a physically jacobian-informed encoder-decoder neural networks (NNs) for PF nonlinear regression. Based on the forward and inverse PF model, a multi-task learning method with encoder-decoder NNs is constructed for data-driven PF regression. To introduce PF physical characteristics, the corresponding jacobian information is embedded into the regression model to improve the accuracy and generalization. The performance of high accuracy and generalization of the proposed method is validated by IEEE test systems.

关键词： generalization jacobian encoder and decoder neural networks neural networks physics-informed learning physics-informed learning power flow regression power flow regression physics-informed learning power flow regression

来源：评论

学校读者我要写书评

暂无评论

DMAED: Dynamic Matte Aware encoder-decoder for Shadow Removal 24

DMAED: Dynamic Matte Aware Encoder-Decoder for Shadow Remova...

引用

3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE)

作者： Zhou, Yadong Zhu, Zhenfeng Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou 450052 Henan Peoples R China

ISBN: (纸本)9798400718212

The removal of shadows in images has significant implications for research in semantic segmentation and object recognition. Although methods based on deep learning models have made important progress in shadow removal, there is still room for improvement in the simultaneous treatment of soft and hard shadows. To address these challenges and improve the robustness of the algorithms, this study introduces a dynamic matte-attention mechanism into the encoder-decoder network and proposes the DMAED (Dynamic Matte Aware encoder-decoder) model. The DMAED model first preprocesses the input data using a matte mask. Then, through iterative processes and updates of tokens and dynamic masks, it facilitates the migration of features from non-shadow to shadow regions, gradually eliminating shadow artifacts. Finally, a cascaded refinement decoder further rectifies shadowed images. Experimental results on benchmark datasets such as ISTD, ISTD+, and SRD demonstrate the significant effectiveness of the DMAED model in handling both hard and soft shadow scenarios.

关键词： Matte Shadow Removal encoder and decoder

来源：评论

学校读者我要写书评

暂无评论

Special T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography

引用

NEURAL NETWORKS 2020年 128卷 216-233页

作者： Jun, Tae Joon Kweon, Jihoon Kim, Young-Hak Kim, Daeyoung Asan Med Ctr Asan Inst Life Sci Seoul 05505 South Korea Univ Ulsan Div Cardiol Asan Med Ctr Coll Med Seoul 05505 South Korea Korea Adv Inst Sci & Technol Sch Comp Daejeon 34141 South Korea

In this paper, we proposed nested encoder-decoder architecture named T-Net. T-Net consists of several small encoder-decoders for each block constituting convolutional network. T-Net overcomes the limitation that U-Net can only have a single set of the concatenate layer between encoder and decoder block. To be more precise, the U-Net symmetrically forms the concatenate layers, so the low-level feature of the encoder is connected to the latter part of the decoder, and the high-level feature is connected to the beginning of the decoder. T-Net arranges the pooling and up-sampling appropriately during the encoding process, and likewise during the decoding process so that feature maps of various sizes are obtained in a single block. As a result, all features from the low-level to the high-level extracted from the encoder are delivered from the beginning of the decoder to predict a more accurate mask. We evaluated T-Net for the problem of segmenting three main vessels in coronary angiography images. The experiment consisted of a comparison of U-Net and T-Nets under the same conditions, and an optimized T-Net for the main vessel segmentation. As a result, T-Net recorded a Dice Similarity Coefficient score (DSC) of 83.77%, 10.69% higher than that of U-Net, and the optimized T-Net recorded a DSC of 88.97% which was 15.89% higher than that of U-Net. In addition, we visualized the weight activation of the convolutional layer of T-Net and U-Net to show that T-Net actually predicts the mask from earlier decoders. Therefore, we expect that T-Net can be effectively applied to other similar medical image segmentation problems. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Convolutional neural network Main vessel segmentation Coronary angiography encoder and decoder

来源：评论

学校读者我要写书评

暂无评论

FST-OAM: a fast style transfer model using optimized self-attention mechanism

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第5期18卷 4191-4203页

作者： Du, Xiaozhi Jia, Ning Du, Hongyuan Xi An Jiao Tong Univ Sch Software Engn 28 West Xianning Rd Xian 710049 Shaanxi Peoples R China

Image style transfer is a remarkable research hotspot in computer image processing. However, state-of-the-art models have some drawbacks, such as low efficiency of transfer time, distorted image structure and loss of detail information. To address these key issues, this paper proposes an innovative fast style transfer model using optimized self-attention mechanism, called FST-OAM, which mainly consists of four modules: Transformer, image edge detection, fusion and postprocessing. Transformer module extracts the features of content images and style images by encoding and gets the resultant image sequence by decoding. In the Transformer, we present an improved self-attention mechanism to reduce the computational overhead. The image edge detection module is used to extract the edge features of the content and style images. The outputs of the Transformer encoder and the image edge information are input to the fusion module to generate multidimensional image features. Finally, the transferred image is generated with a three-layer convolutional neural network in the postprocessing module. Some different scenes of the content and style images were taken to evaluate our FST-OAM model. The experimental results show that our FST-OAM model outperforms state-of-the-art models. Compared with StyTr2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document}, ArtFlow and SCAIST, the training time of FST-OAM is reduced by 78%, 75%, and 81%, respectively. Compared with StyTr2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document}, ArtFlow, DFP, and SCAIST, the average transfer time of FST-OAM is redu

关键词： Style transfer Self-attention mechanism Edge detection Transformer encoder and decoder

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Enhanced decoder Network for Blind Hyperspectral Unmixing

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1页

作者： Shu, Sheng Huang, Ting-Zhu Huang, Jie Univ Elect Sci & Technol China Res Ctr Image & Vis Comp Sch Math Sci Chengdu 611731 Sichuan Peoples R China

Recently, deep learning has been widely applied in the field of blind hyperspectral unmixing (HU), which aims to simultaneously estimate constitutive endmembers and their abundances in hyperspectral images (HSIs). Generally, the HU process based on deep-learning methods consists of two parts: an encoder and a decoder. In many networks, the decoder stage uses the extracted semantic information of the HSI by the encoder, without direct access to the manifold structure of the HSI. To address this limitation and simultaneously capture both the semantic information and manifold structure of the HSI, in this letter, we propose a dual-channel enhanced decoder network (DED-Net) for the HU problem. Specifically, DED-Net redesigns a decoder by adding a dual-channel graph regularizer that establishes a physically meaningful immediate connection between the abundance and the HSI, effectively integrating both the information from the encoder and the original HSI to enhance endmembers and abundance estimation. Experimental results demonstrate the superiority of our proposed method, which leads to a more accurate unmixing performance.

关键词： Decoding Manifolds Hyperspectral imaging Transformers Semantics Feature extraction Estimation Deep learning encoder and decoder graph regularizer hyperspectral unmixing (HU) manifold structure

来源：评论

学校读者我要写书评

暂无评论

Time series cross-correlation network for wind power prediction

引用

APPLIED INTELLIGENCE 2023年第10期53卷 11403-11419页

作者： Yu, Ruiguo Sun, Yingzhou Li, Xuewei Yu, Jian Gao, Jie Liu, Zhiqiang Yu, Mei Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Tianjin Key Lab Adv Networking Tianjin 300350 Peoples R China Tianjin Univ Tianjin Int Engn Inst Tianjin 300350 Peoples R China

Wind power is an indispensable part of clean energy, but due to its inherent instability, it is necessary to predict the power generation of wind turbines after a period of time accurately. Most recent approaches are based on machine learning methods, which map time series data to a high-dimensional space, follow Markov process in the time dimension, and extract time series features following the chronological order. However, due to the time-instability and highly spatially correlated nature of wind power data, the prediction methods which follow the chronological order cannot extract all features in wind power time series. This will lose the information contained in the sequence and lack spatially relevant information. This paper proposes a TSCN-LSTM model that includes a Time Series Cross-correlation Network (TSCN) and a long short term memory (LSTM) decoder to predict wind power generation after 30 minutes. TSCN-LSTM not only collaboratively encodes the neighboring area and the neighboring time to fully tap the potential spatiotemporal correlation by TSCN, but also uses the LSTM decoder to enhance the timing relationship and to prevent the loss of timing information. At the same time, a data preprocessing method is proposed to enhance the spatial representation of the data. It makes that TSCN-LSTM can integrate the temporal and spatial feature extraction process to enhance the semantic expression of features. By establishing extensive interconnections between data in time dimension and space dimension, multiple types of cross-correlation information are generated which enables the model to distinguish different meteorological features and discover temporal and spatial correlations. A large number of experiments show that compared with the current leading SVR, LSTM, LSTM-EFG, GRU, Bi-LSTM and SATCN-LSTM methods, the wind power prediction mean square error is reduced by an average of 13.06%, 12.44%, 4.05%, 5.11%, 6.94% and 8.76%, respectively.

关键词： Wind power prediction Deep learning Attention mechanism encoder and decoder

来源：评论

学校读者我要写书评

暂无评论

Effective image tampering localization with multi-scale ConvNeXt feature fusion

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2024年 98卷

作者： Zhu, Haochen Cao, Gang Zhao, Mo Tian, Huawei Lin, Weiguo Commun Univ China Sch Comp & Cyber Sci Beijing 100024 Peoples R China Commun Univ China State Key Lab Media Convergence & Commun Beijing 100024 Peoples R China Peoples Publ Secur Univ China Beijing 100038 Peoples R China

With the widespread use of powerful image editing tools, image tampering becomes easy and realistic. Existing image forensic methods still face challenges of low generalization performance and robustness. In this letter, we propose an effective image tampering localization scheme based on ConvNeXt encoder and multi-scale Feature Fusion (ConvNeXtFF). Stacked ConvNeXt blocks are utilized as an encoder to capture hierarchical multi-scale features, which are then fused in decoder for locating tampered pixels accurately. Combined loss function and effective data augmentation strategies are adopted to further improve the model performance. Extensive experimental results show that both localization accuracy and robustness of the ConvNeXtFF scheme outperform other state-of-the-art ones. The source code is available at https://***/multimediaFor/ConvNeXtFF.

关键词： Image forensics Tampering localization encoder and decoder ConvNeXt Multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

Multi-unit stacked architecture: An urban scene segmentation network based on UNet and ShuffleNetv2

引用

APPLIED SOFT COMPUTING 2024年 165卷

作者： Liu, Dian Du, Jianchao Li, Chuhan Yu, Chenglong Zhang, Mingjin Xidian Univ Sch Telecommun Engn Xian 710071 Shaanxi Peoples R China Beijing Elect Sci & Technol Inst Beijing 100070 Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Shaanxi Peoples R China

Classic high-accuracy semantic segmentation models typically come with a large number of parameters, making them unsuitable for deployment on driverless platforms with limited computational power. To strike a balance between accuracy and limited computational budget, and enable the use of the classic segmentation model UNet in unmanned driving scenarios, this paper proposes a multi-unit stacked architecture (MSA), namely, MSA-Net, based on UNet and ShuffleNetv2. First, MSA-Net replaces the convolution blocks in the UNet encoder and decoder with stacked basic ShuffleNetv2 units, which greatly reduces computational cost while maintaining high segmentation accuracy. Second, MSA-Net designs enhanced skip connections using pointwise convolution and convolutional block attention (CBAM) to aid the decoder in selecting more relevant and valuable information. Third, MSA-Net proposes multi-scale internal connections to extend the receptive fields of encoder and decoder with little increase in model parameters. The comprehensive experiments show MSANet achieves an optimal balance on the Cityscapes dataset between accuracy and model complexity, with strong generalization on the enhanced PASCAL VOC 2012 dataset. MSA-Net achieves a mean intersection over union (mIoU) of 73.6% and an inference speed of 31.0 frames per second (FPS) on the Cityscapes test dataset. We also propose two other MSA-Net models of different sizes, providing more options for resource-constrained inference.

关键词： Unmanned driving Semantic segmentation encoder and decoder Resource-constrained inference

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

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

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：