检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Yulin Sun Zheng Zhang Yang Wang Lin Wu Meng Wang School of Computer Science and Technology Soochow University Suzhou China Ministry of Education Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei China Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Dictionary learning (DL) is powerful for representation learning, while it fails to capture the deep hierarchical information hidden in data. In this paper, we propose a new generalized end-to-end mulita-layer representation learning architecture referred to as Multi-layer Dictionary Pair Learning Network (MDPL-net) for the deep sparse and hierarchical representation of images. To enable MDPL-net to conduct accurate classification, MDPL-net clearly integrates the skip connection end-to-end network and multi-layer deep sparse dictionary learning into a unified architecture. The representation learning module has several hidden DL blocks, where each hidden DL block has a dictionary pair learning (DPL) layer, a batch-norm layer and an activation function layer, and the DL blocks are connected in a feed-forward manner. To further improve the information flow and maintain the privileged features between different DL blocks, a novel skip dense connectivity pattern is deployed between hidden DL blocks, which can obtain more stable and discriminative features. The DPL layer jointly formulates the discriminative synthesis dictionary and analysis dictionary by minimizing reconstruction error within each batch over the feature maps from front layers. Extensive results on benchmark databases demonstrate the effectiveness of MDPL-net for discriminative representation and robust image classification.

关键词： Dictionaries databases Conferences Machine learning data mining Image reconstruction Image classification

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model Incorporating Knowledge Representation Vectors and Its Application in Diabetes Prediction

引用

Disease Markers 2022年第1期2022卷 7593750页

作者： Xu, He Zheng, Qunli Zhu, Jingshu Xie, Zuoling Cheng, Haitao Li, Peng Ji, Yimu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing 210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Jiangsu Province Nanjing 210023 China Institute of High Performance Computing and Big Data Nanjing University of Posts and Telecommunications Nanjing 210023 China Nanjing Center of HPC China Nanjing 210023 China Jiangsu Research Engineering of HPC and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 China Department of Endocrinology Zhongda Hospital Southeast University Nanjing 210009 China

The deep learning methods for various disease prediction tasks have become very effective and even surpass human experts. However, the lack of interpretability and medical expertise limits its clinical application. This paper combines knowledge representation learning and deep learning methods, and a disease prediction model is constructed. The model initially constructs the relationship graph between the physical indicator and the test value based on the normal range of human physical examination index. And the human physical examination index for testing value by knowledge representation learning model is encoded. Then, the patient physical examination data is represented as a vector and input into a deep learning model built with self-attention mechanism and convolutional neural network to implement disease prediction. The experimental results show that the model which is used in diabetes prediction yields an accuracy of 97.18% and the recall of 87.55%, which outperforms other machine learning methods (e.g., lasso, ridge, support vector machine, random forest, and XGBoost). Compared with the best performing random forest method, the recall is increased by 5.34%, respectively. Therefore, it can be concluded that the application of medical knowledge into deep learning through knowledge representation learning can be used in diabetes prediction for the purpose of early detection and assisting diagnosis. © 2022 He Xu et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Most Probable Transition Paths of Stochastic Dynamical Systems: A Sufficient and Necessary Characterization

arXiv

引用

arXiv 2021年

作者： Huang, Yuanfei Huang, Qiao Duan, Jinqiao School of Mathematics and Statistics Center for Mathematical Sciences Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 China Department of Statistics and Data Science National University of Singapore 6 Science Drive 2 Singapore117546 Singapore School of Data Science City University of Hong Kong Kowloon Hong Kong Department of Mathematics Faculty of Sciences University of Lisbon Campo Grande Edifício C6 LisboaPT-1749-016 Portugal Division of Mathematical Sciences School of Physical and Mathematical Sciences Nanyang Technological University 21 Nanyang Link Singapore637371 Singapore The Dongguan Key Laboratory for Data Science and Intelligent Medicine Department of Mathematics Department of Physics Great Bay University Guangdong Dongguan523000 China

The most probable transition paths of a stochastic dynamical system are the global minimizers of the Onsager–Machlup action functional and can be described by a necessary but not sufficient condition, the Euler–Lagrange equation (a second-order differential equation with initial-terminal conditions) from a variational principle. This work is devoted to showing a sufficient and necessary characterization for the most probable transition paths of stochastic dynamical systems with Brownian noise. We prove that, under appropriate conditions, the most probable transition paths are completely determined by a first-order ordinary differential equation. The equivalence is established by showing that the Onsager–Machlup action functional of the original system can be derived from the corresponding Markovian bridge process. For linear stochastic systems and the nonlinear Hongler’s model, the first-order differential equations determining the most probable transition paths are shown analytically to imply the Euler–Lagrange equations of the Onsager–Machlup functional. For general nonlinear systems, the determining first-order differential equations can be approximated, in a short time or for the small noise case. Some numerical experiments are presented to illustrate our results. Copyright © 2021, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion

arXiv

引用

arXiv 2020年

作者： Wang, Dong Bai, Yunpeng Li, Ying School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xian China School of Computing and Information Systems University of Melbourne VIC3010 Australia

Multispectral pan-sharpening aims at producing a high resolution (HR) multispectral (MS) image in both spatial and spectral domains by fusing a panchromatic (PAN) image and a corresponding MS image. In this paper, we propose a novel dual-channel network (DCNet) framework for MS pan-sharpening. In our DCNet, the dual-channel backbone involves a spatial channel to capture spatial information with a 2D CNN, and a spectral channel to extract spectral information with a 3D CNN. This heterogeneous 2D/3D CNN architecture can minimize causing spectral information distortion, which typically happens in conventional 2D CNN models. In order to fully integrate the spatial and spectral features captured from different levels, we introduce a multi-level fusion strategy. Specifically, a spatial-spectral CLSTM (S2-CLSTM) module is proposed for fusing the hierarchical spatial and spectral features, which can effectively capture correlations among multi-level features. The S2-CLSTM module attaches two fusion ways: the intra-level fusion via bi-directional lateral connections and inter-level fusion via the cell state in the S2-CLSTM. Finally, the ideal HR-MS image is recovered by a reconstruction module. Extensive experiments have been conducted at both simulated lower scale and the original scale of real-world datasets. Compared with the state-of-the-art methods, the proposed DCNet achieves superior or competitive performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection on attributed networks via contrastive self-supervised learning

arXiv

引用

arXiv 2021年

作者： Liu, Yixin Li, Zhao Pan, Shirui Gong, Chen Zhou, Chuan Karypis, George The Department of Data Science and AI Faculty of Information Technology Monash University ClaytonVIC3800 Australia The Alibaba Group Hangzhou310000 China The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing The Hong Kong Polytechnic University Hong Kong The Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100093 China The Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States

Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. Recently, the deep learning-based anomaly detection methods have shown promising results over shallow approaches, especially on networks with high-dimensional attributes and complex structures. However, existing approaches, which employ graph autoencoder as their backbone, do not fully exploit the rich information of the network, resulting in suboptimal performance. Furthermore, these methods do not directly target anomaly detection in their learning objective and fail to scale to large networks due to the full graph training mechanism. To overcome these limitations, in this paper, we present a novel Contrastive self-supervised Learning framework for Anomaly detection on attributed networks (CoLA for abbreviation). Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way. Meanwhile, a well-designed graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure and measure the agreement of each instance pairs with its outputted scores. The multi-round predicted scores by the contrastive learning model are further used to evaluate the abnormality of each node with statistical estimation. In this way, the learning model is trained by a specific anomaly detection-aware target. Furthermore, since the input of the graph neural network module is batches of instance pairs instead of the full network, our framework can adapt to large networks flexibly. Experimental results show that our proposed framework outperforms the state-of-the-art baseline methods on all seven benchmark datasets. © 2021, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Robust Bidirectional Generative Network For Generalized Zero-Shot Learning

Robust Bidirectional Generative Network For Generalized Zero...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yun Xing Sheng Huang Luwen Huangfu Feiyu Chen Yongxin Ge Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society School of Big Data and Software Engineering at Chongqing University Chongqing P.R.China Fowler College of Business at San Diego State University San Diego USA

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

In this work, we propose a novel generative approach named Robust Bidirectional Generative Network (RBGN) based on Conditional Generative Adversarial Network (CGAN) for Generalized Zero-shot Learning (GZSL). RBGN employs the adversarial attack to train a more rigorous discriminator, thus enhancing the generalizability and robustness of the feature generator under minimax strategy. Moreover, RBGN decodes the generated visual features back to their semantic representations to further improve the representational ability of generated visual features and alleviate the hubness problem. The experimental results of GZSL on four datasets, i.e. CUB, SUN, AWA1, AWA2, demonstrate that our model achieves competitive performance compared to state-of-the-art approaches and owns better generalizability to the unseen classes over conventional generative GZSL models. Further robustness analysis also validates the strong robustness of our model to the different types of semantic disturbance.

关键词： Semantics visualization Robustness Generators Training Decoding Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

A discovery of Two Slow Pulsars with FAST: "Ronin" from the Globular Cluster M15

arXiv

引用

arXiv 2023年

作者： Zhou, Dengke Wang, Pei Li, Di Fang, Jianhua Miao, Chenchen Freire, Paulo C.C. Zhang, Lei Zhang, Dandan Chen, Huaxi Feng, Yi Xiao, Yifan Xie, Jintao Zhang, Xu Jin, Chenwu Wang, Han Ke, Yinan Guo, Xuerong Zhao, Rushuang Niu, Chenhui Zhu, Weiwei Xue, Mengyao Wang, Yabiao Wu, Jiafu Gan, Zhenye Sun, Zhongyi Wang, Chengjie Zhang, Junshuo Cao, Jinhuang Lu, Wanjin Zhang, Jie Research Center for Astronomical Computing Zhejiang Laboratory Hangzhou311121 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Institute for Frontiers in Astronomy and Astrophysics Beijing Normal University Beijing102206 China University of Chinese Academy of Sciences Beijing100049 China New Cornerstone Science Laboratory Shenzhen518054 China Max Planck Institut für Radioastronomie Bonn53121 Germany Centre for Astrophysics and Supercomputing Swinburne University of Technology Hawthorn3122 Australia School of Mathematical Sciences School of Physics and Electronic Sciences Guizhou Normal University Guiyang550001 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guiyang550001 China School of Physics and Electronic Engineering Qilu Normal University Jinan250200 China School of Physics and Electronic Science Guizhou Normal University Guiyang550001 China College of Physical Science and Technology Central China Normal University Wuhan430079 China Tencent Youtu Lab Shanghai201103 China

Globular clusters harbor numerous millisecond pulsars, but long-period pulsars (P 100 ms) are rarely found. In this study, we employed a fast folding algorithm to analyze observational data from multiple globular clusters obtained by the Five-hundred-meter Aperture Spherical radio Telescope (FAST), aiming to detect the existence of long-period pulsars. We estimated the impact of the median filtering algorithm in eliminating red noise on the minimum detectable flux density (Smin) of pulsars. Subsequently, we successfully discovered two isolated long-period pulsars in M15 with periods approximately equal to 1.928451 seconds and 3.960716 seconds, respectively. On the P − P diagram, both pulsars are positioned below the spin-up line, suggesting a possible history of partial recycling in X-ray binary systems disrupted by dynamical encounters later on. According to timing results, these two pulsars exhibit remarkably strong magnetic fields. If the magnetic fields were weakened during the accretion process, then a short duration of accretion might explain the strong magnetic fields of these pulsars. © 2023, CC BY.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Machine learning for modelling unstructured grid data in computational physics: a review

arXiv

引用

arXiv 2025年

作者： Cheng, Sibo Bocquet, Marc Ding, Weiping Finn, Tobias Sebastian Fu, Rui Fu, Jinlong Guo, Yike Johnson, Eleda Li, Siyi Liu, Che Moro, Eric Newton Pan, Jie Piggott, Matthew Quilodran, Cesar Sharma, Prakhar Wang, Kun Xiao, Dunhui Xue, Xiao Zeng, Yong Zhang, Mingrui Zhou, Hao Zhu, Kewei Arcucci, Rossella CEREA ENPC EDF R&D Institut Polytechnique de Paris Île-de-France France School of Artificial Intelligence and Computer Science Nantong University Jiangsu Nantong226019 China School of Mathematical Sciences Key Laboratory of Intelligent Computing and Applications Tongji University Shanghai200092 China School of Engineering and Materials Science Faculty of Science and Engineering Queen Mary University of London LondonE1 4NS United Kingdom Zienkiewicz Centre for Modelling Data and AI Faculty of Science and Engineering Swansea University SwanseaSA1 8EN United Kingdom Department of Computer Science and Engineering Hong Kong university of science and technology Hong Kong Department of Earth Science & Engineering Imperial College London LondonSW7 2AZ United Kingdom Tianjin Key Laboratory of Imaging and Sensing Microelectronics Technology School of Microelectronics Tianjin University Tianjin300072 China Centre for Health Informatics Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Department of Community Health Sciences Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Undaunted Grantham Institute for Climate Change and the Environment Imperial College London LondonSW7 2AZ United Kingdom Culham Campus AbingdonOX14 3DB United Kingdom Centre for Computational Science Department of Chemistry University College London LondonWC1E 6BT United Kingdom Concordia Institute for Information Systems Engineering Concordia University MontrealQCH3G 1M8 Canada School of Mechanical Medical and Process Engineering Faculty of Engineering Queensland University of Technology BrisbaneQLD Australia Department of Chemical Engineering University College London LondonWC1E 6BT United Kingdom

Unstructured grid data are essential for modelling complex geometries and dynamics in computational physics. Yet, their inherent irregularity presents significant challenges for conventional machine learning (ML) techniques. This paper provides a comprehensive review of advanced ML methodologies designed to handle unstructured grid data in high-dimensional dynamical systems. key approaches discussed include graph neural networks, transformer models with spatial attention mechanisms, interpolation-integrated ML methods, and meshless techniques such as physics-informed neural networks. These methodologies have proven effective across diverse fields, including fluid dynamics and environmental simulations. This review is intended as a guidebook for computational scientists seeking to apply ML approaches to unstructured grid data in their domains, as well as for ML researchers looking to address challenges in computational physics. It places special focus on how ML methods can overcome the inherent limitations of traditional numerical techniques and, conversely, how insights from computational physics can inform ML development. To support benchmarking, this review also provides a summary of open-access datasets of unstructured grid data in computational physics. Finally, emerging directions such as generative models with unstructured data, reinforcement learning for mesh generation, and hybrid physics-data-driven paradigms are discussed to inspire future advancements in this evolving field. © 2025, CC BY-NC-SA.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A short-term output power prediction model of wind power based on deep learning of grouped time series

引用

European Journal of Electrical engineering 2020年第1期22卷 29-38页

作者： Wang, Yongsheng Gao, Jing Xu, Zhiwei Li, Leixiao College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot010018 China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application for Agriculture and Animal Husbandry Hohhot010018 China College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service Hohhot010080 China Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China

The output power prediction of wind power plants is an important guarantee to improve the utilization rate of wind energy and reduce wind curtailment. However, due to the strong randomness of wind energy, the ultra-short-term prediction accuracy of wind power output is poor. In view of the problem above, a prediction model based on deep learning of grouped time series (LW-CLSTM) was proposed in this paper. Based on this model, the authors attempted to explore a prediction method of wind power output. For this, first the multivariate data of wind power was fused, cleaned, dimension-reduced, and standardized, and the time period characteristics of the output power itself were extracted. Afterwards, it proposes a time sliding window (TSW) algorithm, and constructs a neural network input data set. Then a deep neural network prediction model combining the Convolutional Neutral Network (CNN) and Long-Short Term Memory (LSTM) was established, and the regression evaluation criteria for output power forecast accuracy in wind power production were designed, to compare the proposed model with four other prediction models. Finally, the experiments on the TensorFlow platform using real data show that this model has better prediction accuracy than the other four models, reaching a prediction accuracy rate of 92.5%, which verified the effectiveness of this prediction method. © 2020 International Information and engineering Technology Association. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: dataset, Methods and Results

arXiv

引用

arXiv 2023年

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany ETH Zürich Switzerland The Shenzhen Campus of Sun Yat-Sen University Sun Yat-Sen University China Bigo Technology Pte. Ltd Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023, CC BY-SA.

关键词： Image enhancement

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：