检索结果-内蒙古大学图书馆

IEEE Symposium (IUS) Ultrasonics

作者： Russell Thompson Umair Khan Jason Li Lauren. P. Etter Ingrid Camello Rachel. C. Pieciak Ilse. Castro-Aragon Bindu Setty Christopher. C. Gill Libertario Demi Margrit Betke University of Massachusetts Dartmouth MA USA Department of Information Engineering & Computer Science University of Trento TN Italy The Faculty of Computing & Data Sciences Boston University Boston MA USA University of Wisconsin Madison Madison WI USA Pediatric Infectious Disease Augusta University Augusta GA USA Department of Global Health Boston University School of Public Health Boston MA USA Department of Radiology Boston Medical Center Boston MA USA

Automated assessment of LUS data from adult population is an ongoing research over the last few years. To this extent, various deep learning DL-based methods have been proposed to assess lung alterations caused by pneumonia. However, no work has been done in this regard to evaluate the LUS data from children for the presence/absence of consolidations due to pneumonia. Pediatric healthcare data acquisition in a resource constraint environment is a challenging task. As a result of which limited data is acquired. This prevents the effective training of DL models for the development of reliable computer aided assessment systems. To address this challenge, we employed pre-trained DL models, previously trained on LUS data from adults, and evaluated them over LUS data from children in a transfer learning (TL) setting. Two TL strategies i.e. linear probing (LP) and fine-tuning (FT) are utilized. The models are trained and tested in a leave-one-out cross validation manner with results showing that all the pre-trained models achieved higher classification performance for FT in comparison to LP. Among the models it is found that with the addition of spatial attention and custom loss to the base CNN, the model outperformed with the highest mean F1-Score of 81.9%. While evaluating the model’s performance w.r.t age, it is found that the more accurate the model, the less impact of age has on the underlying classification performance. These findings lay down the foundation for accurate consolidation classification in LUS data from children in a resource constraint environment

关键词：

来源：评论

学校读者我要写书评

暂无评论

Free-form tumor synthesis in computed tomography images via richer generative adversarial network

arXiv

引用

arXiv 2021年

作者： Jin, Qiangguo Cui, Hui Sun, Changming Meng, Zhaopeng Su, Ran School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Csiro Data61 Sydney Australia Tianjin University of Traditional Chinese Medicine Tianjin China

The insufficiency of annotatedmedical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional feature enhanced dilated-gated generator (RicherDG) and a hybrid loss function. The RicherDG has dilated-gated convolution layers to enable tumor-painting and to enlarge perceptive fields;and it has a novel richer convolutional feature association branch to recover multi-scale convolutional features especially from uncertain boundaries between tumor and surrounding healthy tissues. The hybrid loss function, which consists of a diverse range of losses, is designed to aggregate complementary information to improve optimization. We perform a comprehensive evaluation of the synthesis results on a wide range of public CT image datasets covering the liver, kidney tumors, and lung nodules. The qualitative and quantitative evaluations and ablation study demonstrated improved synthesizing results over advanced tumor synthesis methods. Copyright © 2021, 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

G3SR: Global Graph Guided Session-based Recommendation

arXiv

引用

arXiv 2022年

作者： Deng, Zhi-Hong Wang, Chang-Dong Huang, Ling Lai, Jian-Huang Yu, Philip S. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangdong Provincial Key Laboratory of Public Finance and Taxation with Big Data Application China University of Illinois at Chicago ChicagoIL United States

Session-based recommendation tries to make use of anonymous session data to deliver high-quality recommendation under the condition that user-profiles and the complete historical behavioral data of a target user are unavailable. Previous works consider each session individually and try to capture user interests within a session. Despite their encouraging results, these models can only perceive intra-session items and cannot draw upon the massive historical relational information. To solve this problem, we propose a novel method named G3SR (Global Graph Guided Session-based Recommendation). G3SR decomposes the session-based recommendation workflow into two steps. First, a global graph is built upon all session data, from which the global item representations are learned in an unsupervised manner. Then, these representations are refined on session graphs under the graph networks, and a readout function is used to generate session representations for each session. Extensive experiments on two real-world benchmark datasets show remarkable and consistent improvements of the G3SR method over the state-of-the-art methods, especially for cold items. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A maturity model for catalogues of semantic artefacts

arXiv

引用

arXiv 2023年

作者： Corcho, Oscar Ekaputra, Fajar J. Heibi, Ivan Jonquet, Clement Micsik, Andras Peroni, Silvio Storti, Emanuele Computer Science School Universidad Politécnica de Madrid Madrid Spain Vienna Austria Data Science Research Unit TU Wien Vienna Austria Department of Classical Philology and Italian Studies University of Bologna Bologna Italy Research Centre for Open Scholarly Metadata Department of Classical Philology and Italian Studies University of Bologna Bologna Italy MISTEA University of Montpellier INRAE Institut Agro France LIRMM University of Montpellier CNRS France Budapest Hungary Department of Information Engineering Polytechnic University of Marche Ancona Italy Brussels Belgium

This work presents a maturity model for assessing catalogues of semantic artefacts, one of the keystones that permit semantic interoperability of systems. We defined the dimensions and related features to include in the maturity model by analysing the current literature and existing catalogues of semantic artefacts provided by experts. In addition, we assessed 26 different catalogues to demonstrate the effectiveness of the maturity model, which includes 12 different dimensions (Metadata, Openness, Quality, Availability, Statistics, PID, Governance, Community, Sustainability, Technology, Transparency, and Assessment) and 43 related features (or sub-criteria) associated with these dimensions. Such a maturity model is one of the first attempts to provide recommendations for governance and processes for preserving and maintaining semantic artefacts and helps assess/address interoperability challenges. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Motif Graph Neural Network

arXiv

引用

arXiv 2021年

作者： Chen, Xuexin Cai, Ruichu Fang, Yuan Wu, Min Li, Zijian Hao, Zhifeng The School of Computer Science Guangdong University of Technology Guangzhou510006 China The School of Computer Science Guangdong University of Technology Guangdong Provincial Key Laboratory of Public Finance and Taxation with Big Data Application Guangzhou China Peng Cheng Laboratory Shenzhen518066 China The School of Computing and Information Systems Singapore Management University 178902 Singapore A*STAR 138632 Singapore The College of Science Shantou University Shantou515063 China

Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations. Graph neural networks (GNNs) are currently the most popular model in graph embedding approaches. However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing high-order graph structures as opposed to low-order structures. To capture high-order structures, researchers have resorted to motifs and developed motif-based GNNs. However, existing motif-based GNNs still often suffer from less discriminative power on high-order structures. To overcome the above limitations, we propose Motif Graph Neural Network (MGNN), a novel framework to better capture high-order structures, hinging on our proposed motif redundancy minimization operator and injective motif combination. First, MGNN produces a set of node representations w.r.t. each motif. The next phase is our proposed redundancy minimization among motifs which compares the motifs with each other and distills the features unique to each motif. Finally, MGNN performs the updating of node representations by combining multiple representations from different motifs. In particular, to enhance the discriminative power, MGNN utilizes an injective function to combine the representations w.r.t. different motifs. We further show that our proposed architecture increases the expressive power of GNNs with a theoretical analysis. We demonstrate that MGNN outperforms state-of-the-art methods on seven public benchmarks on both node classification and graph classification tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing utility in the watchdog privacy mechanism

arXiv

引用

arXiv 2021年

作者： Zarrabian, Mohammad Amin Ding, Ni Sadeghi, Parastoo Rakotoarivelo, Thierry College of Engineering and Computer Science Australian National University Canberra Australia School of Computing and Information Systems University of Melbourne Melbourne Australia School of Engineering and Information Technology University of New South Wales Canberra Australia Data61 Commonwealth Scientific and Industrial Research Organisation Eveleigh Australia

This paper is concerned with enhancing data utility in the privacy watchdog method for attaining information-theoretic privacy. For a specific privacy constraint, the watchdog method filters out the high-risk data symbols through applying a uniform data regulation scheme, e.g., merging all high-risk symbols together. While this method entirely trades the symbols resolution off for privacy, we show that the data utility can be greatly improved by partitioning the high-risk symbols set and individually privatizing each subset. We further propose an agglomerative merging algorithm that finds a suitable partition of high-risk symbols: it starts with a singleton high-risk symbol, which is iteratively fused with others until the resulting subsets are private. Numerical simulations demonstrate the efficacy of this algorithm in privately achieving higher utilities in the watchdog *** Codes 68P27, © 2021, CC BY.

关键词： information theory

来源：评论

学校读者我要写书评

暂无评论

BCDAS: Blockchain-assisted Classifiable data Auditing Scheme with Dynamic Operations

引用

Blockchain: Research and Applications 2025年

作者： Yuxin Cui Chen Wang Bing Yang Wei Tong Jian Shen School of Information Science and Engineering (School of Cyber Science and Technology) Zhejiang Sci-Tech University Hangzhou 310018 Zhejiang China Zhejiang Provincial Key Laboratory of Digital Fashion and Data Governance Zhejiang Sci-Tech University Hangzhou 310018 Zhejiang China Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Zhejiang Sci-Tech University Hangzhou 310018 Zhejiang China Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing 312000 Zhejiang China School of Computer Science Nanjing University of Information Science Technology Nanjing 210044 Jiangsu China

As cloud computing gains widespread adoption, cloud storage services have become the primary means of data management for users. Authenticated data structures (ADS) are a novel computational model designed to address data authentication problems in distributed environments. With the growing demand for robust data security, vulnerability detection in storage systems has become a critical area of focus to ensure resilience against potential threats. However, traditional ADS, while ensuring consistency between cloud data and source data, have limitations in handling dynamic data operations on multiple types of files, storage space expansion, and single-point failure issues. To tackle these issues, this paper proposes a blockchain-assisted classifiable data auditing scheme with dynamic operations. First, trapdoor hash functions are used to construct a binary tree. During dynamic data operations, the impact of hash updates is confined to a subset of nodes, ensuring global stability and reducing computational resource consumption. Second, innovative data structures and verification mechanisms are introduced, reducing the risk of single-point failures by decentralizing the dependency on verification paths. Finally, data types are confirmed based on data identifiers, and corresponding path information is recorded, enabling efficient and rapid dynamic operations on specific types of files within multi-source data. Both security analysis and performance assessment demonstrate that BCDAS conducts data auditing for with reliability and efficiency.

关键词： data auditing Dynamic operations Blockchain Trapdoor hash function

来源：评论

学校读者我要写书评

暂无评论

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

arXiv

引用

arXiv 2024年

作者： Kirchhoff, Yannick Rokuss, Maximilian R. Roy, Saikat Kovacs, Balint Ulrich, Constantin Wald, Tassilo Zenk, Maximilian Vollmuth, Philipp Kleesiek, Jens Isensee, Fabian Maier-Hein, Klaus Heidelberg Division of Medical Image Computing Germany Faculty of Mathematics and Computer Science Heidelberg University Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Heidelberg Karlsruhe Germany Medical Faculty Heidelberg Heidelberg University Heidelberg Germany Helmholtz Imaging German Cancer Research Center Heidelberg Germany Clinic for Neuroradiology University Hospital Bonn Bonn Germany Medical Faculty Bonn University of Bonn Bonn Germany University Hospital Essen Essen Germany West German Cancer Center Essen University Hospital Essen Essen Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany

Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This is particularly relevant for 3D data, rendering these losses infeasible for larger volumes as well as increasingly important multi-class segmentation problems. To mitigate this, we propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations. It demonstrates overall superior performance to current state-of-the-art approaches on five public datasets for topology-preserving segmentation, while substantially reducing computational overheads by more than 90%. In doing so, we introduce the first multi-class capable loss function for thin structure segmentation, excelling in both efficiency and efficacy for topology-preservation. Our code is available to the community, providing a foundation for further advancements, at: https://***/MIC-DKFZ/Skeleton-Recall. © 2024, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Fast Subspace Clustering Based on the Kronecker Product

Fast Subspace Clustering Based on the Kronecker Product

引用

International Conference on Pattern Recognition

作者： Lei Zhou Xiao Bai Liang Zhang Jun Zhou Edwin Hancock School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China School of Information and Communication Technology Griffith University Nathan Australia University of York York U.K.

Subspace clustering is a useful technique for many computer vision applications in which the intrinsic dimension of high-dimensional data is often smaller than the ambient dimension. Spectral clustering, as one of the main approaches to subspace clustering, often takes on a sparse representation or a low-rank representation to learn a block diagonal self-representation matrix for subspace generation. However, existing methods require solving a large scale convex optimization problem with a large set of data, with computational complexity reaches O(N³) for N data points. Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets. In this paper, we propose a subspace clustering model based on the Kronecker product. Due to the property that the Kronecker product of a block diagonal matrix with any other matrix is still a block diagonal matrix, we can efficiently learn the representation matrix which is formed by the Kronecker product of k smaller matrices. By doing so, our model significantly reduces the computational complexity to O(kN³/^k). Furthermore, our model is general in nature, and can be adapted to different regularization based subspace clustering methods. Experimental results on two public datasets show that our model significantly improves the efficiency compared with several state-of-the-art methods. Moreover, we have conducted experiments on synthetic data to verify the scalability of our model for large scale datasets.

关键词： Adaptation models Computational modeling Scalability Clustering methods Face recognition Memory management data models

来源：评论

学校读者我要写书评

暂无评论

Imperceptible diffusion modification for facial privacy protection

引用

Neurocomputing 2025年 649卷

作者： Jia Li Junhao Dong Jianhuang Lai Xiaohua Xie School of Computer Science and Engineering Sun Yat-sen University Guangzhou China College of Computing and Data Science Nanyang Technological University Singapore Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University) Ministry of Education Guangzhou China

The remarkable success of Face Recognition (FR) systems has raised significant privacy concerns, particularly the potential for unauthorized tracking of individuals on social media. To mitigate these risks, various adversarial attack methods have been proposed to protect individuals from unauthorized identification by FR systems. In this work, we propose a novel A dversarial F ace generation method via D iffusion M odification (AFDM), designed for imperceptible and transferable attacks against FR systems. The AFDM operates in the diffusion latent space of the face image, leveraging DDIM inversion and the DDIM process to achieve precise modifications. To ensure high visual fidelity, we propose a self-attention structure loss and a perceptual loss, effectively constraining the extent of diffusion-based alterations. Additionally, to enhance transferability, we introduce a face attribute loss that aligns the attribute embeddings of the protected face with those of the target face. Extensive experiments demonstrate that the proposed AFDM achieves state-of-the-art performance in attacking various FR models, with an average Protect Success Rate (PSR) of 93.32% on the CeleA-HQ and LADN datasets, while maintaining a more natural-looking protected face image with an FID score of 22.96. Through our systematic analysis, we justify the efficacy and generality of the proposed method.

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：