检索结果-内蒙古大学图书馆

Correntropy-Induced Weighted GAN for Bridge Anomaly Detection

IEEE SENSORS JOURNAL 2024年第4期24卷 5335-5346页

作者： Tu, Jiankai Liu, Huan Li, Chunguang Liu, Pengfei Duan, Yuanfeng Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Zhejiang Univ Zhejiang Prov Key Lab Informat Proc Commun & Netw Hangzhou 310027 Peoples R China Envis Grp Co Shanghai 200001 Peoples R China Zhejiang Univ Coll Civil Engn & Architecture Hangzhou 310027 Peoples R China

Bridges play an essential role in transportation and economics. Since the loss is significant in the event of bridge damage, the monitoring of bridge structure health is important. One of the important tasks of bridge health monitoring is the bridge anomaly detection. The bridge anomaly detection is a challenging problem since the real-world bridge data collected by the sensors are usually contaminated by large non-Gaussian noises. To address this issue, we propose a correntropy-induced weighted generative adversarial network (CWGAN) for bridge anomaly detection. Specifically, we first propose a correntropy-based generator, which has an encoder-decoder structure with a memory structure, and optimize it based on the maximum correntropy criterion. Then, derived from the correntropy of the reconstruction errors, we specially design a weight module to obtain a weight variable that measures the contamination-free degree of the corresponding sample. Afterward, we take advantage of the weight module and transform the generator and discriminator modules of CWGAN into weighted versions to achieve robustness against contamination and obtain smaller reconstruction errors for noncontaminated normal data. We integrate and iteratively perform the reconstruction and weighting processes to achieve better anomaly detection performance. After the model optimization, we detect the anomalies with reconstruction errors. We conduct experiments on a model bridge to demonstrate the effectiveness of the proposed CWGAN.

关键词： Anomaly detection bridge structure health correntropy encoder-decoder generative adversarial network (GAN) memory sensor data

来源：评论

学校读者我要写书评

暂无评论

A Video Captioning Method by Semantic Topic-Guided Generation

引用

Computers, Materials & Continua 2024年第1期78卷 1071-1093页

作者： Ou Ye Xinli Wei Zhenhua Yu Yan Fu Ying Yang College of Computer Science and Technology Xi’an University of Science and TechnologyXi’an710054China

In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a ***,this kind ofmethod is dependent on a single video input source and few visual labels,and there is a problem with semantic alignment between video contents and generated natural sentences,which are not suitable for accurately comprehending and describing the video *** address this issue,this paper proposes a video captioning method by semantic topic-guided ***,a 3D convolutional neural network is utilized to extract the spatiotemporal features of videos during the ***,the semantic topics of video data are extracted using the visual labels retrieved from similar video *** the decoding,a decoder is constructed by combining a novel Enhance-TopK sampling algorithm with a Generative Pre-trained Transformer-2 deep neural network,which decreases the influence of“deviation”in the semantic mapping process between videos and texts by jointly decoding a baseline and semantic topics of video *** this process,the designed Enhance-TopK sampling algorithm can alleviate a long-tail problem by dynamically adjusting the probability distribution of the predicted ***,the experiments are conducted on two publicly used Microsoft Research Video Description andMicrosoft Research-Video to Text *** experimental results demonstrate that the proposed method outperforms several state-of-art ***,the performance indicators Bilingual Evaluation Understudy,Metric for Evaluation of Translation with Explicit Ordering,Recall Oriented Understudy for Gisting Evaluation-longest common subsequence,and Consensus-based Image Description Evaluation of the proposed method are improved by 1.2%,0.1%,0.3%,and 2.4% on the Microsoft Research Video Description dataset,and 0.1%,1.0%,0.1%,and 2.8% on the Microsoft Research-Video to Text dataset

关键词： Video captioning encoder-decoder semantic topic jointly decoding Enhance-TopK sampling

来源：评论

学校读者我要写书评

暂无评论

RVPNet: A real time unstructured road vanishing point detection algorithm using attention mechanism and global context information

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第9期83卷 28263-28280页

作者： Liu, Yu Fan, Xue Han, Shiyuan Zhou, Jin Yang, Xiaohui Li, Zhongtao Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China

The detection of the vanishing point (VP) in unstructured road is crucial for the advancement of autonomous vehicle technology. However, due to the inadequate fusion of intra-level features and high computational requirements of existing CNN-based road VP detection methods, a model named RVPNet is proposed in this paper. To begin, the proposed algorithm adopts the architecture of encoder-decoder combined lightweight backbone to extract unstructured road features efficiently. Second, the Simple Residual Pyramid Pooling Module (SRPPM) is designed in this model to obtain cross-path global contextual information with low computational cost. And a Dual Attention-based Feature Aggregation Module (DAFAM) is proposed to obtain better inter-level feature representations. Finally, the offset loss is introduced to compensate for the inherent offset errors caused by the output stride of the heatmap. The experimental results show that the average detection error rate of our approach is only 0.03128 on the Kong dataset, and the average processing time reaches 238 FPS. The average detection error rate of our approach based is only 0.03600 on the Moghhadam dataset. Compared with the state-of-the-art methods, the proposed approach achieves the highest detection accuracy and speed.

关键词： Vanishing point Unstructured road encoder-decoder Feature aggregation Contextual information

来源：评论

学校读者我要写书评

暂无评论

RoDAL: style generation in robot calligraphy with deep adversarial learning

引用

APPLIED INTELLIGENCE 2024年第17-18期54卷 7913-7923页

作者： Wang, Xiaoming Gong, Zhiguo Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China

Generative art has drawn increased attention in recent AI applications. Traditional approaches of robot calligraphy have faced challenges in achieving style consistency, line smoothness and high-quality structural uniformity. To address the limitation of existing methods, we propose a dual generator framework based on deep adversarial networks for robotic calligraphy reproduction. The proposed model utilizes a encoder-decoder module as one generator for style learning and a robot arm as the other generator for motion learning to optimize the networks and obtain the best robot calligraphy works. Based on the enhanced datasets, multiple evaluation metrics including coverage rate, structural similarity index measure, intersection over union and Turing test are employed to perform the experimental validation. The evaluations demonstrate that the proposed method is highly effective and applicable in robot calligraphy and achieves state-of-the-art results with the average structural similarity index measure 75.91% , coverage rate 70.25%, and intersection over union 80.68%, which provides a paradigm for evaluation in the field of art.

关键词： Robot calligraphy Style learning Dual generator Generative adversarial network encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MSE-Net: generative image inpainting with multi-scale encoder

引用

VISUAL COMPUTER 2022年第8期38卷 2647-2659页

作者： Yang, Yizhong Cheng, Zhihang Yu, Haotian Zhang, Yongqiang Cheng, Xin Zhang, Zhang Xie, Guangjun Hefei Univ Technol Sch Elect Sci & Appl Phys Hefei 230009 Peoples R China

Image inpainting methods based on deep convolutional neural networks (DCNN), especially generative adversarial networks (GAN), have made tremendous progress, due to their forceful representation capabilities. These methods can generate visually reasonable contents and textures;however, the existing deep models based on a single receptive field type usually not only cause image artifacts and content mismatches but also ignore the correlation between the hole region and long-distance spatial locations in the image. To address the above problems, in this paper, we propose a new generative model based on GAN, which is composed of a two-stage encoder-decoder with a Multi-Scale encoder Network (MSE-Net) and a new Contextual Attention Model based on the Absolute Value (CAM-AV). The former utilizes different-size convolution kernels to encode features, which improves the ability of abstract feature characterization. The latter uses a new search algorithm to enhance the matching of features in the network. Our network is a fully convolutional network that can complete holes of arbitrary size, number, and spatial location in the image. Experiments with regular and irregular inpainting on different datasets including CelebA and Places2 demonstrate that the proposed method achieves higher quality inpainting results with reasonable contents than the most existing state-of-the-art methods.

关键词： Image inpainting Generative adversarial network encoder-decoder Contextual Attention

来源：评论

学校读者我要写书评

暂无评论

Abstractive text summarization using deep learning models: a survey

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2025年 1-29页

作者： Abdul Salam, Mustafa Gamal, Mostafa Hamed, Hesham F. A. Sweidan, Sara Prince Sattam Bin Abdulaziz Univ Coll Engn Dept Comp Engn & Informat Al Kharj 16273 Saudi Arabia Benha Univ Fac Comp & Artificial Intelligence Dept Artificial Intelligence Banha 13518 Egypt Minia Univ Fac Engn Elect Engn Dept El Minia Egypt Egyptian Russian Univ Badr City Fac Artificial Intelligence Dept Artificial Intelligence Cairo 11829 Egypt New Mansoura Univ Fac Comp Sci & Engn Gamasa 35712 Egypt

In the face of escalating volumes of textual data, the demand for advanced systems to efficiently manage this deluge is evident. Automatic summarization is a pivotal solution, continually evolving to meet the burgeoning data needs and user expectations. This paper delves into abstract text summarization, particularly focusing on utilizing neural networks-a recent breakthrough in the field. Through a comprehensive analysis of various models, we meticulously dissect critical components such as encoder-decoder design, mechanisms, training methodologies, dataset considerations, and evaluation metrics. Our primary objective is to illuminate current model landscapes, pinpoint existing challenges, and propose potential remedies. Notably, transformer-based encoder-decoder architectures emerge as state-of-the-art solutions. We suggest combining neural networks with pre-trained language models to improve abstractive summarization, making advanced techniques more accessible and effective. This approach aims to bolster the efficiency and efficacy of summarization systems, thereby facilitating superior information extraction and comprehension for users grappling with extensive textual datasets.

关键词： NLP Abstract text summarization encoder-decoder Mechanism attention Transformers

来源：评论

学校读者我要写书评

暂无评论

ARAFNet: An attribute refinement attention fusion network for advanced visual captioning

引用

DIGITAL SIGNAL PROCESSING 2025年 162卷

作者： Hossen, Md. Bipul Ye, Zhongfu Hossain, Md. Shamim Hossain, Md. Imran Begum Rokeya Univ Fac Sci Dept Stat Rangpur 5404 Bangladesh Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230027 Anhui Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Anhui Peoples R China Pabna Univ Sci & Technol Dept ICE Rajshahi 6600 Bangladesh

Visual captioning, at the nexus of computer vision and natural language processing, is one of the pivotal aspects of multimedia content understanding, demands precise and contextually fitting image descriptions. Attribute-based approaches with attention mechanisms are effective in this realm. However, many of these approaches struggle to capture semantic details due to the prediction of irrelevant attributes and reduced performance. In response to these challenges, we propose an innovative solution: the Attribute Refinement Attention Fusion Network (ARAFNet), which aims to produce significant captions by distinctly identifying major objects and background information. The model features a comprehensive Attribute Refinement Attention (ARA) module, equipped with an attribute attention mechanism, which interactively extracts the most important attributes according to the linguistic context. Diverse attributes are employed at different time steps, enhancing the model's capability to utilize semantic features effectively while also filtering out irrelevant attribute words, thereby enhancing the precision of semantic guidance. An integrated fusion mechanism is then introduced to narrow the semantic gap between visual and attribute features. Finally, this fusion mechanism combined with the language LSTM to generate precise and contextually relevant captions. Extensive experimentation demonstrates our model's superiority over advanced counterparts, achieving an average CIDEr-D score of 11.88% on the Flickr30K dataset and 11.25% on the MS-COCO dataset through cross-entropy optimization. The ARAFNet model consistently outperforms the baseline model across a diverse range of evaluation metrics and makes a significant contribution to the field of image captioning precision. The implementing code and associated materials will be published at https://***/mdbipu/ARAFNet.

关键词： Visual captioning Attribute refinement attention Integrated fusion mechanism encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MRI super-resolution reconstruction based on 3D dense connected convolutional autoencoders

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 107卷

作者： Kang, Li Song, Xinxin Huang, Jianjun Liu, Guojuan Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Peoples R China Guangdong Prov Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

High-Resolution MR (HR-MR) images provide rich structural detail to assist physicians in clinical diagnosis and detection of lesions. However, it is arduous to acquire HR-MRI due to equipment limitations, scanning time or patient comfort. Computer-aided image post-processing approaches allow indirect acquisition of HR-MRI without the requirements described above. In this paper, we propose a MRI super-resolution reconstruction method based on an image post-processing technique. Specifically, 3D densely connected convolutional neural networks are introduced to address the problem of underutilizing the spatial information in the reconstruction of 2D slices by convolutional neural networks, which can simultaneously achieve the super- resolution reconstruction of three anatomical planes: axial, coronal and sagittal. To obtain features from different sensory fields, differently sized convolution kernels are used in the shallow feature extraction module, which promotes the robustness and reliability in the deep mapping process. Furthermore, an improved densely connected high frequency module (DBHE) is built to extract high-frequency features recovered from the deep mapping to avoid the loss of detailed information, while a hybrid attention module is utilized to boost the weights of important features. Several experiments are designed to evaluate the proposed framework, and the results suggest that it could achieve favorable reconstruction performance compared with state-of-the-art methods. In addition, the experimental results on other datasets also show the proposed framework's promising generalization performance.

关键词： CNN MRI encoder-decoder Attention

来源：评论

学校读者我要写书评

暂无评论

MSPFusion: A feature transformer for multidimensional spectral-polarization image fusion

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 275卷

作者： Tong, Geng Yao, Xinling Li, Ben Fu, Jiaye Wang, Yan Hao, Jia Karim, Shahid Yu, Yiting Northwestern Polytech Univ Ningbo Inst Coll Mech Engn Xian 710072 Peoples R China Northwestern Polytech Univ Key Lab Micro Nano Syst Aerosp Minist Educ Shaanxi Prov Key Lab Micro & Nano Electromech Syst Xian 710072 Peoples R China Northwestern Polytech Univ Shenzhen Res & Dev Inst Shenzhen 518057 Peoples R China Xian Polytech Univ Coll Comp Sci & Engn Xian 710021 Peoples R China

Spectral images capture reflection characteristics, texture, and spatial details, while polarimetric images provide insights into surface roughness, morphology, and material structure. Fusing these complementary sensing modalities overcomes the limitations of individual perception techniques, offering a richer understanding of the scene. However, traditional fusion methods are typically designed for dual-modal inputs and lack robustness when handling multimodal data. To address this, we propose MSPFusion, a novel feature transformer network for multidimensional spectral-polarization image fusion. Our approach leverages a Feature Multi-head Self- attention (F-MSA) mechanism in the encoder to enhance feature extraction and introduces an entropy-based fusion layer to adaptively integrate spectral and polarization information by maximizing information content. The F-MSA decoder further refines the fused features to produce high-quality integration and visualization of spectral-polarization data. We constructed a hyperspectral-polarization dataset, NWPU-SP, to validate our method. Experimental results show that MSPFusion achieves state-of-the-art performance, ranking first in the following metrics, i.e., entropy (EN), information (MI), standard deviation (SD), quality of saliency (QS), and quality of gradient (QG). All these metrics show a better preservation of information, along with improved clarity and contrast in the fusion results of our proposed method. Additionally, MSPFusion demonstrates strong robustness in infrared-visible image fusion tasks, proving its adaptability across various scenarios. The source code and NWPU-SP dataset are available at https://***/tgg-77/MSPFusion.

关键词： Image fusion encoder-decoder Transformer Spectral-polarization image

来源：评论

学校读者我要写书评

暂无评论

Improving ultra-short-term photovoltaic power forecasting using advanced deep-learning approach

引用

MEASUREMENT 2025年 239卷

作者： Su, Zhongyuan Gu, Shengyan Wang, Jun Lund, Peter D. Southeast Univ Sch Energy & Environm Jiangsu Prov Key Lab Solar Energy Sci & Technol Nanjing 210096 Peoples R China Geol & Mineral Resources Res Inst Jiangsu Prov Nanjing 210008 Peoples R China Aalto Univ Sch Sci POB 15100 FI-00076 Espoo Finland

Forecasting photovoltaic (PV) power output is of high importance to optimal operation, scheduling and planning of power systems with much PV due to the weather uncertainty. Here, an advanced deep-learning method employing Gated Recurrent Unit (GRU) network with dual attention (DA) mechanism and encoder-decoder framework is applied to improve ultra-short-term PV output forecasting up to a 2-hour time range. The novel DA-GRU model showed better forecasting accuracy over other models such as neural networks and machine learning under single and multi-step forecasting. The mean absolute percentage error of 1-step (15 min), 4-step (1 h) and 8-step (2 h) forecasting with DA-GRU was 12.4%, 20 % and 22 %, respectively. Increasing the number of forecast steps and time range improved the accuracy of DA-GRU over the other forecasting models. The better feature extraction ability based on feature and time attention has greater impact on the forecasting results at different time points yielding a better prediction accuracy.

关键词： Photovoltaics Forecasting Deep learning Gated Recurrent Unit encoder-decoder Attention mechanism

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：