检索结果-内蒙古大学图书馆

Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study

引用

Journal of Safety science and Resilience 2021年第3期2卷 146-156页

作者： Yunrong Yang Zhidong Cao Pengfei Zhao Dajun Daniel Zeng Qingpeng Zhang Yin Luo The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China Shenzhen Artificial Intelligence and Data Science Institute(Longhua) ShenzhenChina School of Data Science City University of Hong Kong-Hong Kong SARChina

The needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of *** unstructured COVID-19 publications make it challenging for policymakers to obtain relevant *** graphs(KGs)can formalize unstructured knowledge into structured form and have been used in supporting decision-making ***,we introduce a novel framework that can ex-tract the COVID-19 public health evidence knowledge graph(CPHE-KG)from papers relating to a modelling *** screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment *** define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset(CPHIE).We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++based on the *** the model on the new corpus,we construct CPHE-KG containing 60,967 entities and 51,140 ***,we seek to apply our KG to support evidence querying and evidence mapping *** SS-DYGIE++(SpanBERT)model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution *** has also shown high performance in the relation identification *** evidence querying,our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and *** evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 *** demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.

关键词： Evidence-based public health Knowledge graph COVID-19 Decision-making support

来源：评论

学校读者我要写书评

暂无评论

Joint Class-Balanced Client Selection and Bandwidth Allocation for Cost-Efficient Federated Learning in Mobile Edge Computing Networks

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5681-5698页

作者： Tang, Jian Li, Xiuhua Li, Hui Li, Penghua Wang, Xiaofei Leung, Victor C. M. Chongqing University School of Big Data & Software Engineering Chongqing400000 China Chongqing University of Posts and Telecommunications School of Automation Chongqing400065 China Tianjin University College of Intelligence and Computing Tianjin300072 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T1Z4 Canada

Federated Learning (FL) has significant potential to protect data privacy and mitigate network burden in mobile edge computing (MEC) networks. However, due to the system and data heterogeneity of mobile clients (MCs), client selection and bandwidth allocation is key for achieving cost-efficient FL in MEC networks with limited bandwidth. To address these challenges, we investigate the issue of joint client selection and bandwidth allocation for reducing the cost (i.e., latency and energy consumption) of FL training. We formulate the problem and decompose it into a holistic subproblem to reduce the number of rounds and a partial subproblem to reduce the costs of FL each round. We propose a joint class-balanced client selection and bandwidth allocation (CBCSBA) framework to address the whole problem. Specifically, for the holistic subproblem, CBCSBA combines MCs into groups, each having data distribution as close as possible to class-balanced distribution;For the partial subproblem, CBCSBA reduces costs by exploratively selecting a group and sequentially optimizing the latency and energy consumption of MCs within the group. Experimental results show that CBCSBA outperforms the baseline frameworks in reducing latency by 28.2% and energy consumption by 25.3% on average in the considered four datasets. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Collaborative Neurodynamic Approach to Distributed Global Optimization

A Discrete-Time Collaborative Neurodynamic Approach to Distr...

引用

International Conference on Intelligent Control and Information Processing (ICICIP)

作者： Haoen Huang Zhigang Zeng Jun Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science & Department of Data Science City University of Hong Kong Kowloon Hong Kong

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results.

关键词： Neurodynamics Adaptation models Adaptive systems Simulation Optimization models Neural networks Collaboration Information processing Optimization Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Image Domain Ultra-Sparse View CT Artifact Removal Via Conditional Denoising Diffusion Probability Model 23

Image Domain Ultra-Sparse View CT Artifact Removal Via Condi...

引用

Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition

作者： Feixiang Zhao Jianchao Zhao Mingzhe Liu College of Nuclear Technology and Automation Engineering Chengdu University of Technology China School of Data Science and Artificial Intelligence Wenzhou University of Technology China

ISBN: (纸本)9798400707988

X-ray computed tomography (CT) scan is commonly used for pre-diagnosis and is powerful tool for ensuring accurate diagnoses. Its potential radiation damage has raised concerns in recent years. Sparse view CT scan can effectively reduce radiation exposure and improve patient comfort by shorten scanning time. However, the incomplete measurement data obtained from sparse view CT scan can only reconstruct CT images containing a large number of artifacts. To remove these artifacts and achieve a quality similar to full view CT images, numerous deep learning (DL)-based methods have been proposed, generally employing autoencoders or generative adversarial networks (GANs). Due to the high-dimensional sparse nature of artifacts, autoencoders and GANs often fail to model artifacts well. In this work, we employ a novel generative model, the denoising diffusion probability model (DDPM), to directly model full view CT images. We use ultra-sparse view CT images as the condition for generating full view CT images, guiding the reverse process of DDPM to realize artifact removal in ultra-sparse view CT images. Our method is the first to achieve artifact removal in ultra-sparse view CT in the image domain. Experiments on a public dataset demonstrate the superiority of our proposed method over existing methods.

关键词： Artifact removal Deep learning Denoising Diffusion Probability Model Sparse view CT

来源：评论

学校读者我要写书评

暂无评论

LOCAL-PROMPT: EXTENSIBLE LOCAL PROMPTS FOR FEW-SHOT OUT-OF-DISTRIBUTION DETECTION

arXiv

引用

arXiv 2024年

作者： Zeng, Fanhu Cheng, Zhen Zhu, Fei Wei, Hongxin Zhang, Xu-Yao State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong Department of Statistics and Data Science Southern University of Science and Technology China

Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce Local-Prompt, a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method comprises two integral components: global prompt guided negative augmentation and local prompt enhanced regional regularization. The former utilizes frozen, coarse global prompts as guiding cues to incorporate negative augmentation, thereby leveraging local outlier knowledge. The latter employs trainable local prompts and a regional regularization to capture local information effectively, aiding in outlier identification. We also propose regional-related metric to empower the enrichment of OOD detection. Moreover, since our approach explores enhancing local prompts only, it can be seamlessly integrated with trained global prompts during inference to boost the performance. Comprehensive experiments demonstrate the effectiveness and potential of our method. Notably, our method reduces average FPR95 by 5.17% against state-of-the-art method in 4-shot tuning on challenging ImageNet-1k dataset, even outperforming 16-shot results of previous methods. Code is released at https://***/AuroraZengfh/Local-Prompt. Copyright © 2024, 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

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition 39

Focus on Local: Finding Reliable Discriminative Regions for ...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Wang, Changwei Chen, Shunpeng Song, Yukun Xu, Rongtao Zhang, Zherui Zhang, Jiguang Yang, Haoran Zhang, Yu Fu, Kexue Du, Shide Xu, Zhiwei Gao, Longxiang Guo, Li Xu, Shibiao China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China MAIS Institute of Automation Chinese Academy of Sciences China Tongji University China College of Computer and Data Science Fuzhou University China Shandong University China

ISBN: (纸本)157735897X

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain Generalized Solar Cell Defect Segmentation Based on Shape-Aware and Multi-View Meta-Learning 42

Domain Generalized Solar Cell Defect Segmentation Based on S...

引用

42nd Chinese Control Conference, CCC 2023

作者： Liu, Kun Yang, Ying Mao, Jingkun Liu, Weipeng School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300130 China Tianjin University of Technology Department of Automation Tianjin300384 China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789887581543

Various defects are inevitably generated in the manufacturing process of solar cells. Deep learning-based methods for defect segmentation under closed situation have achieved remarkable progress. Due to the difference of imaging condition and camera parameter under different production line, there are large differences in brightness distribution of solar cell images. The model trained under closed situation cannot achieve good performance in opened situation such as multi-production lines. In this paper, a new shape-aware and multi-view meta-learning scheme is proposed to improve the model generalization performance for single-domain solar cell defect segmentation. The scheme roots in gradient-based meta-learning. Multi-brightness view information is yielded from the generated augmented images, and explicitly simulating domain shift with virtual meta-train and meta-test during training to mitigate overfitting in single-source domain train and unstable prediction. Importantly, considering tiny and faint solar cell defects are not easily identified under different image brightness conditions, shape edge constraint loss is proposed to encourage shape compactness and shape smoothness of segmentations. Experimental results show that the proposed method has high segmentation accuracy, which outperforms the state-of-the-art methods. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Solar cells

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Attention Semi-Supervised Network Based on Confidence Iteration and Pseudo-Label Optimization for COVID-19 CT Segmentation 42

Multi-Scale Attention Semi-Supervised Network Based on Confi...

引用

42nd Chinese Control Conference, CCC 2023

作者： Liu, Kun Chen, Mei Xie, Junfei Mao, JingKun Liu, WeiPeng School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300130 China Tianjin University of Technology Department of Automation Tianjin300384 China Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Tianjin300401 China

ISBN: (纸本)9789887581543

Computed tomography (CT) image segmentation for COVID-19 lung infection has made great progress. However, accurate segmentation remains a major challenge due to the varying shape and size of COVID-19 infected areas, the more similar tissue of infected lung images to normal lung images, and the additional problem of a limited number of medical images annotated at the pixel level. In this paper, we propose a semi-supervised segmentation network based on confidence iteration and pseudo-label optimization for COVID-19 CT segmentation. In addition, we develop a multi-scale attention module which can achieve attentional feature fusion at different scales. The experiment evaluated on the COVID-19 CT Segmentation dataset, demonstrate our method achieves higher segmentation accuracy than the state-of-art methods. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A survey on copy-move image forgery detection based on deep-learning techniques

引用

Multimedia Tools and Applications 2024年 1-60页

作者： Samariya, Urmila Kamble, Shailesh D. Singh, Subhash Sonker, Rakesh Kumar Department of Information Technology Indira Gandhi Delhi Technical University for Women Delhi110006 India Department of Artificial Intelligence and Data Science Indira Gandhi Delhi Technical University for Women Delhi110006 India Department of Mechanical and Automation Engineering Indira Gandhi Delhi Technical University for Women Delhi110006 India Department of Physics Motilal Nehru College University of Delhi Delhi110021 India

The widespread use of digital images on social media and the internet has led to increased image forgery, which poses a significant challenge to their authenticity. It is crucial to validate the integrity of images in this digital era, where they are widely used for communication and information. This survey comprehensively reviews the existing digital image forgery detection techniques, focusing on copy-move forgery. Copy-move forgery is a common image tampering technique where a part of the image is duplicated and pasted elsewhere in the same image. Detecting such forgeries is crucial in various applications, including digital forensics, and image authentication. We discuss the different forgery detection methods, including block-based, keypoint-based, machine learning-based approaches, and various deep learning-based techniques, and a summary of benchmark datasets and evaluation measures is presented. The survey reveals that deep learning-based methods have shown promising results in detecting image forgeries, and the development of robust and efficient detection methods remains an active area of research. The study concludes with a discussion of future directions in image forgery detection. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Distributed Model Predictive Formation Control with Gait Synchronization for Multiple Quadruped Robots

Distributed Model Predictive Formation Control with Gait Syn...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Shaohang Xu Wentao Zhang Lijun Zhu Chin Pang Ho School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Data Science City University of Hong Kong HKSAR

In this paper, we present a fully distributed framework for multiple quadruped robots in environments with obstacles. Our approach utilizes Model Predictive Control (MPC) and multi-robot consensus protocol to obtain the distributed control law. It ensures that all the robots are able to avoid obstacles, navigate to the desired positions, and meanwhile synchronize the gaits. In particular, via MPC and consensus, the robots compute the optimal trajectory and the contact profile of the legs. Then an MPC-based locomotion controller is implemented to achieve the gait, stabilize the locomotion and track the desired trajectory. We present experiments in simulation and with three real quadruped robots in an environment with a static obstacle.

关键词：

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：