检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Patch Target Guided Dual-Branch Deep Multiple Instance Learning for 3D MRI Analysis

Patch Target Guided Dual-Branch Deep Multiple Instance Learn...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingzhe Dai Xiaoshuang Shi Xiaofeng Zhu Tingrui Pan Kang Li School of Software Engineering University of Science and Technology of China Hefei China West China Biomedical Big Data Center West China Hospital of Sichuan University Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Artificial Intelligence Research Institute Yibin China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Deep multiple instance learning (MIL) has attracted considerable attention in medical image analysis, since it only requires image-level labels for model training without using fine-grained (or patch) annotations. Unfortunately, MIL-based methods might lose some significant patch features. Although pseudo-label-based methods, which assign a pre-defined label to each patch, can explore more patch-level features, they might bring label noise and make the patch-level features lose diversity, thereby possibly restricting the model performance. To overcome this issue, we propose a novel gradient-based patch target generation (PTG) module to dynamically produce a feature vector for each patch as its target. Additionally, based on the PTG module, we propose a patch-target guided dual-branch deep MIL framework for 3D MRI data analysis, where both the two branches consist of a CNN model to extract patch-level features, an attention module to interpret the significance of patches, and a bag-level classifier, while the second branch also contains the PTG module to generate patch targets of patches. Moreover, the two branches are alternatively updated in our framework, resulting in a bi-level optimization problem, and thus we design a bi-level optimization algorithm to solve our proposed objective function. Extensive experiments demonstrate the superior classification and interpretation performance of the proposed framework over recent state-of-the-art methods. Codes are available at https://***/daimz1213/mil2024.

关键词： Training Analytical models Solid modeling Three-dimensional displays Annotations Magnetic resonance imaging Feature extraction Vectors Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhou, Tong Ding, Chen Jing, Changhong Liu, Feng Hung, Kevin Pham, Hieu Mahmud, Mufti Lyu, Zhihan Qiao, Sibo Wang, Shuqiang Tsang, Kim-Fung Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100864 China Stevens Institute of Technology Department of Systems and Enterprises United States Hong Kong Metropolitan University School of Science and Technology Hong Kong Hong Kong VinUniversity College of Engineering and Computer Science VinUni-Illinois Smart Health Center Viet Nam King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Uppsala University Department of Game Design Faculty of Arts Sweden Tiangong University School of Software Tianjin300387 China

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

arXiv

引用

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

arXiv

引用

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive vision-language model for 3D segmentation of pulmonary artery and vein

arXiv

引用

arXiv 2025年

作者： Guo, Xiaotong Yang, Deqian Wang, Dan Zhao, Haochen Li, Yuan Sui, Zhilin Zhou, Tao Zhang, Lijun Meng, Yanda State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Department of Thoracic Surgery National Clinical Research Center for Cancer Cancer Hospital Shenzhen Hospital China School of Intelligent Science and Technology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China R&D Center Guangxi Huayi Artificial Intelligence Medical Technology Co. Ltd. China School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Exeter Exeter United Kingdom Department of Cardiovascular & Metabolic Medicine University of Liverpool Liverpool United Kingdom Guangzhou Jiayi Software Technology Co. Ltd. China

Accurate segmentation of pulmonary structures is crucial in clinical diagnosis, disease study, and treatment planning. Significant progress has been made in deep learning-based segmentation techniques, but most require much labeled data for training. Consequently, developing precise segmentation methods that demand fewer labeled datasets is paramount in medical image analysis. The emergence of pre-trained vision-language foundation models, such as CLIP, recently opened the door for universal computer vision tasks. Exploiting the generalization ability of these pre-trained foundation models on downstream tasks, such as segmentation, leads to unexpected performance with a relatively small amount of labeled data. However, exploring these models for pulmonary artery-vein segmentation is still limited. This paper proposes a novel framework called Language-guided self-adaptive Cross-Attention Fusion Framework. Our method adopts pre-trained CLIP as a strong feature extractor for generating the segmentation of 3D CT scans, while adaptively aggregating the cross-modality of text and image representations. We propose a s pecially designed adapter module to fine-tune pre-trained CLIP with a self-adaptive learning strategy to effectively fuse the two modalities of embeddings. We extensively validate our method on a local dataset, which is the largest pulmonary artery-vein CT dataset to date and consists of 718 labeled data in total. The experiments show that our method outperformed other state-of-the-art methods by a large margin. Our data and code will be made publicly available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

A Key-Points Based Anchor-Free Cervical Cell Detector

A Key-Points Based Anchor-Free Cervical Cell Detector

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Tong Shu Jun Shi Yushan Zheng Zhiguo Jiang Lanlan Yu School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China School of Engineering Medicine Beihang University Beijing China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China Image Processing Center School of Astronautics Beihang University Beijing China Motic (Xiamen) Medical Diagnostic Systems Co. Ltd. Xiamen China

Cervical cell detection is crucial to cervical cytology screening at early stage. Currently most cervical cell detection methods use anchor-based pipeline to achieve the localization and classification of cells, e.g. faster R-CNN and YOLOv3. However, the anchors generally need to be pre-defined before training and the detection performance is inevitably sensitive to these pre-defined hyperparameters (e.g. number of anchors, anchor size and aspect ratios). More importantly, these preset anchors fail to conform to the cells with different morphology at inference phase. In this paper, we present a key-points based anchor-free cervical cell detector based on YOLOv3. Compared with the conventional YOLOv3, the proposed method applies a key-points based anchor-free strategy to represent the cells in the initial prediction phase instead of the preset anchors. Therefore, it can generate more desirable cell localization effect through refinement. Furthermore, PAFPN is applied to enhance the feature hierarchy. GIoU loss is also introduced to optimize the small cell localization in addition to focal loss and smooth L1 loss. Experimental results on cervical cytology ROI datasets demonstrate the effectiveness of our method for cervical cell detection and the robustness to different liquid-based preparation styles (i.e. drop-slide, membrane-based and sedimentation).

关键词：

来源：评论

学校读者我要写书评

暂无评论

MMST-LSTM: Leveraging Radar Echo Prediction for Emerging Consumer applications in Edge Computing

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wu, Mengjia Xiao, Bo Yang, Zhiyun Sun, Jiawei Liu, Qi Zhang, Yonghong Liu, Xiaodong Nanjing University of Information Science and Technology School of Software Nanjing210044 China Nanjing University of Information Science and Technology School of Chemistry and Materials Science Nanjing210044 China Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing210044 China Nanjing University of Information Science and Technology School of Automation Nanjing210044 China Edinburgh Napier University School of Computing EdinburghEH10 5DT United Kingdom

With the increasing frequency of extreme weather events, there is a growing demand from the public for rapid and accurate short-term heavy precipitation forecasts. This study proposes a lightweight deep learning model, MMST-LSTM, which integrates Multiscale Context Feature Fusion Mechanism (MCFFM) and Mixed-Domain Attention Fusion Mechanism (MAFUM). While maintaining high prediction accuracy, MMST-LSTM significantly improves forecast speed. The MMST-LSTM model is particularly suitable for deployment in Mobile Edge Computing (MEC) environments, enabling fast localized forecasting. Experimental results demonstrate MMST-LSTM’s excellent predictive performance on two radar echo datasets, particularly in rapid response and handling localized data. Moreover, leveraging Smart Data-Driven Modeling (SDDM) technology with consumer-generated data enhances its application potential in smart consumer electronics products, providing an efficient tool for disaster weather alerts. This study introduces an innovative meteorological forecasting method and provides robust technical support for accurate weather warning systems, offering consumers timely and reliable weather information. This enables them to make more informed decisions, effectively reducing the potential risks and economic losses caused by extreme climate events. © 1975-2011 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

New Decision-Making Technique Based on Hurwicz Criteria for Fuzzy Ranking

引用

computers, Materials & Continua 2022年第12期73卷 4595-4609页

作者： Deepak Sukheja Javaid Ahmad Shah G.Madhu K.Sandeep Kautish Fahad A.Alghamdi Ibrahim.S.Yahia El-Sayed M.El-Kenawy Ali Wagdy Mohamed Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadIndia Department of Mathematics Dr.APJ Abdul Kalam University Indore(M.P)India Department of Information Technology VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadIndia LBEF Campus Kathmandu44600Nepal Department of Management Information Systems College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia Laboratory of Nano-Smart Materials for Science and Technology(LNSMST) Department of PhysicsFaculty of ScienceKing Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Research Center for Advanced Materials Science(RCAMS) King Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Nanoscience Laboratory for Environmental and Biomedical Applications(NLEBA) Semiconductor Lab.Department of PhysicsFaculty of EducationAin Shams UniversityRoxyCairo 11757Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Department of Mathematics and Actuarial Science School of Sciences Engineering The American University in CairoEgypt

Efficient decision-making remains an open challenge in the research community,and many researchers are working to improve accuracy through the use of various computational *** this case,the fuzzification and defuzzification processes can be very *** is an effective process to get a single number from the output of a fuzzy *** defuzzification as a center point of this research paper,to analyze and understand the effect of different types of vehicles according to their *** this paper,the multi-criteria decision-making(MCDM)process under uncertainty and defuzzification is discussed by using the center of the area(COA)or ***,to find the best solution,Hurwicz criteria are used on the defuzzified ***-making technique is proposed using Hurwicz criteria for triangular and trapezoidal fuzzy *** proposed technique considers all types of decision makers’perspectives such as optimistic,neutral,and pessimistic which is crucial in solving decisionmaking problems.A simple case study is used to demonstrate and discuss the Centroid Method and Hurwicz Criteria for measuring risk attitudes among *** significance of the proposed defuzzification method is demonstrated by comparing it to previous defuzzification procedures with its application.

关键词： Defuzzification decision-making fuzzy numbers Hurwicz multicriteria decision-making ranking order

来源：评论

学校读者我要写书评

暂无评论

A Geometric Understanding of Deep Learning

引用

engineering 2020年第3期6卷 361-374页

作者： Na Lei Dongsheng An Yang Guo Kehua Su Shixia Liu Zhongxuan Luo Shing-Tung Yau Xianfeng Gu DUT-RU Co-Research Center of Advanced ICT for Active Life Dalian University of TechnologyDalian 116620China Department of Computer Science Stony Brook UniversityStony BrookNY 11794-2424USA School of Computer Science Wuhan UniversityWuhan 430072China School of Software Tsinghua UniversityBeijing 100084China Center of Mathematical Sciences and Applications Harvard UniversityCambridgeMA 02138USA

This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution of a class of data is close to a low-dimensional *** mainly accomplish two tasks:manifold learning and probability distribution *** latter can be carried out using the classical OT *** the OT perspective,the generator computes the OT map,while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution;both can be reduced to a convex geometric optimization ***,OT theory discovers the intrinsic collaborative-instead of competitive-relation between the generator and the discriminator,and the fundamental reason for mode *** also propose a novel generative model,which uses an autoencoder(AE)for manifold learning and OT map for probability distribution *** AE–OT model improves the theoretical rigor and transparency,as well as the computational stability and efficiency;in particular,it eliminates the mode *** experimental results validate our hypothesis,and demonstrate the advantages of our proposed model.

关键词： Generative Adversarial Deep learning Optimal transportation Mode collapse

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：