检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Cai, Wenjie Tang, Tao Balachander, J. Kong, Lingming Zhou, Ying Wang, Qingfeng Li, Jing School of Computer Science and Technology University of Science and Technology of China Hefei China School of Computer Science and Technology Southwest University of Science and Technology Mianyang China Computer Science Engineering Hindusthan College of Engineering and Technology Coimbatore India Department of General Surgery The First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Department of Radiology Mianyang Central Hospital Mianyang China

ISBN: (纸本)9798350368741

Aortic Dissection (AD) is a life-threatening disease that can be rapidly screened by using deep learning methods. However, deep learning model training requires a large amount of manual annotation of data. To improve the annotation efficiency and accuracy, we propose LABEL-SAM, a semi-automatic interactive segmentation algorithm designed to efficiently annotate AD in 3D computed tomography angiography (CTA) images. By requiring minimal user input-only points and bounding boxes on the first and last slices-LABEL-SAM automatically generates segmentation prompts for intermediate slices, reducing the manual workload. In addition, we propose a bidirectional prediction weighting method and a fine-tuning strategy tailored to AD data, further enhancing segmentation accuracy. Furthermore, LABEL-SAM is implemented as a plug-and-play plugin for the 3D Slicer software. Experimental results on both external and internal datasets demonstrate the method's superior performance, improving annotation accuracy and efficiency. The code will be available at https://***/wenjiecai/LABEL-SAM. The demonstration video is now available at https://***/watch?v=R3Fzgl1b4JQ. © 2025 IEEE.

关键词： 3D Slicer Aortic Dissection Interactive Segmentation Medical Imaging Semi-Automatic Annotation

来源：评论

学校读者我要写书评

暂无评论

Exploring A Novel Data Augmentation Strategy for Enhanced In-Vehicle Security Analysis 5

Exploring A Novel Data Augmentation Strategy for Enhanced In...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Shibly, Kabid Hassan Borhan, Rownak Akter, Lubana Based, Md. Abdul Nara Institute of Science and Technology Division of Information Science Japan Dhaka International University Dept of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350394290

In the sphere of automotive cybersecurity, navigating the complexities of behavior management within structured security databases poses significant challenges due to the heterogeneous distribution of data. This uneven data spread obscures a minority of identifiable attack instances amidst a larger pool of unlabeled data, thereby diminishing the performance of machine learning algorithms, particularly in aspects of data deterioration and equilibrium. Notwithstanding, the domain of semi-supervised learning, which leverages both labeled and unlabeled data for model development, remains relatively unexplored within the cybersecurity context. This work presents the Prototype Mixing Generative Network (PMGN), integrated with Multivariate Imputation by Chained Equations (MICE) imputation method and class conditioning, to tackle these problems. Specifically designed for semi-supervised learning, this method includes a new data augmentation technique to mitigate the inherent data imbalances found in security databases. In application across diverse security datasets, the PMGN methodology demonstrates superior performance over conventional methods, underscoring its enhanced efficacy. A major step forward in the field of semi-supervised learning for in-vehicle cybersecurity has been made with the integration of PMGN. Crucially, this research aligns with Industry 5.0 and Sustainable technology objectives by fortifying vehicular digital frameworks, a critical element in the evolution towards sustainable and intelligent transportation systems. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Cache Allocation in Multi-Tenant Edge Computing: An Online Model-Based Reinforcement Learning Approach

引用

IEEE Transactions on Cloud Computing 2025年第2期13卷 459-472页

作者： Ben-Ameur, Ayoub Araldo, Andrea Chahed, Tijani Dán, György Institut Polytechnique de Paris SAMOVAR Telecom SudParis Palaiseau91120 France KTH Royal Institute of Technology Division of Network and Systems Engineering School of Electrical Engineering and Computer Science Stockholm11428 Sweden

We consider a Network Operator (NO) that owns Edge Computing (EC) resources, virtualizes them and lets third party Service Providers (SPs) run their services, using the allocated slice of resources. We focus on one specific resource, i.e., cache space, and on the problem of how to allocate it among several SPs in order to minimize the backhaul traffic. Due to confidentiality guarantees, the NO cannot observe the nature of the traffic of SPs, which is encrypted. Allocation decisions are thus challenging, since they must be taken solely based on observed monitoring information. Another challenge is that not all the traffic is cacheable. We propose a data-driven cache allocation strategy, based on Reinforcement Learning (RL). Unlike most RL applications, in which the decision policy is learned offline on a simulator, we assume no previous knowledge is available to build such a simulator. We thus apply RL in an online fashion, i.e., the model and the policy are learned by directly perturbing and monitoring the actual system. Since perturbations generate spurious traffic, we thus need to limit perturbations. This requires learning to be extremely efficient. To this aim, we devise a strategy that learns an approximation of the cost function, while interacting with the system. We then use such an approximation in a Model-Based RL (MB-RL) to speed up convergence. We prove analytically that our strategy brings cache allocation boundedly close to the optimum and stably remains in such an allocation. We show in simulations that such convergence is obtained within few minutes. We also study its fairness, its sensitivity to several scenario characteristics and compare it with a method from the state-of-the-art. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Glomerular Classification of Membranous Nephropathy Based on Deep Residual Learning with Large Resolution Images 1

Glomerular Classification of Membranous Nephropathy Based on...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Xie, Xia Liu, Xiangbao Wang, Yijie Ke, Lin Han, Min School of Computer Science and Technology Hainan University Haikou China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology Division of Nephrology Tongji Hospital Affiliated Tongji Medical College Wuhan China

ISBN: (纸本)9798350358780

Membranous nephropathy (MN) is the leading cause of nondiabetic idiopathic nephrotic syndrome in adults world-wide. The pathological changes of the glomerulus are taken as the 'gold standard' for the diagnosis of *** use the classical deep residual network ResNet as the base network to classify the glomeruli. Because the size of the obtained glomerular image can reach more than 600*600 pixels, the size of the image input to the network is increased to 672*672 to reduce the loss of image information. We add two residual downsampling blocks to reduce the size of the feature maps and further extract features. At the same time, the attention mechanism can pay attention to the features that are important for classification of high similarity images, so we also introduce the attention mechanism. Since normal glomeruli are challenging to obtain, we used minimal change disease(MCD) glomeruli to substitute normal glomeruli. For classification of the MN glomeruli and MCD glomeruli, our model achieved an accuracy of about 87.5%. Our proposed deep residual network has demonstrated promising results in processing glomerular images with higher pixel resolution in the metaverse. With further refinement and validation, this model holds potential for applications in clinical research, providing valuable assistance to physicians. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Attribute Group Decision-Making Method under Spherical Fuzzy Bipolar Soft Expert Framework with Its Application

引用

computer Modeling in Engineering & sciences 2023年第11期137卷 1891-1936页

作者： Mohammed M.Ali Al-Shamiri Ghous Ali Muhammad Zain Ul Abidin Arooj Adeel Department of Mathematics Faculty of Science and ArtsMahayl AssirKing Khalid UniversityAbhaSaudi Arabia Department of Mathematics and Computer Faculty of ScienceIbb UniversityIbbYemen Department of Mathematics Division of Science and TechnologyUniversity of EducationLahorePakistan

Spherical fuzzy soft expert set(SFSES)theory blends the perks of spherical fuzzy sets and group decision-making into a unified *** allows solutions to highly complicated uncertainties and ambiguities under the unbiased supervision and group decision-making of multiple ***,SFSES theory has some deficiencies such as the inability to interpret and portray the bipolarity of *** work highlights and overcomes these limitations by introducing the novel spherical fuzzy bipolar soft expert sets(SFBSESs)as a powerful hybridization of spherical fuzzy set theory with bipolar soft expert sets(BSESs).Followed by the development of certain set-theoretic operations and properties of the proposed model,important problems,including the selection of non-powered dam(NPD)sites for hydropower conversion are discussed and solved under the proposed *** problems mainly focus on the need for an efficient tool capable of considering the bipolarity of parameters,complicated ambiguities,and multiple *** the new approach by a detailed comparative analysis,it is concluded that the proposed model is more comprehensive and reliable for multi-attribute group decisionmaking(MAGDM)than the previous tools,particularly considering the bipolarity of parameters under SFSES environment.

关键词： Spherical fuzzy sets bipolar soft expert sets group decision-making algorithm non-powered dams

来源：评论

学校读者我要写书评

暂无评论

ON THE GENERALIZED TZITZEICA CURVE EQUATION

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2023年第4期85卷 5-10页

作者： Bîlă, Nicoleta Eni, Michael Department of Mathematics and Computer Science Fayetteville State University United States Harnessing the Power of Technology for the Warfighter Special Warfare and Expeditionary Systems Department Electro-Optic Technology Division United States

The aim of this paper is to present a generalization of the Tzitzeica curve equation based on a new centro-affine invariant. The third order nonlinear ordinary differential equation of the generalized Tzitzeica curves is derived and expressed in the curve’s defining functions. A few intriguing solutions are discussed in connection with Tzitzeica curves. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Applied to Very Small Size Soccer Decision-Making, Trajectory Planning and Control In Penalty Kicks 16

Reinforcement Learning Applied to Very Small Size Soccer Dec...

引用

16th Brazilian Symposium on Robotics and 15th Workshop on Robotics in Education, SBR-WRE 2024

作者： Pires Baldão, Thayna Maximo, Marcos R.O.A. Yoneyama, Takashi Computer Science Division Aeronautics Institute of Technology São José dos Campos Brazil Electronic Engineering Division Aeronautics Institute of Technology São José dos Campos Brazil

ISBN: (纸本)9798350391084

In this work, we propose a Reinforcement Learning (RL) training methodology using Proximal Policy Optimization (PPO) and Curriculum Learning (CL) to make simulated Very Small Size Soccer robots learn to convert penalty kicks against two types of opponents: the "line follow" goalkeeper, which defends the goal by following the goal line, and the offensive goalkeeper, which uses the univector field navigation technique to attack the ball. The RL agents trained using this methodology demonstrated sophisticated penalty kick skills with high conversion rates. The best-evaluated RL agent achieved a conversion rate of over 90% against the "line follow" goalkeeper and of over 71% against the offensive goalkeeper. Comparisons with the univector agent showed that the RL agents significantly outperformed it, with conversion rates 78.71% higher against the "line follow" goalkeeper and 1997.66% higher against the offensive goalkeeper. ©2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On Error-Based Step Size Control for Discontinuous Galerkin Methods for Compressible Fluid Dynamics

引用

应用数学与计算数学学报 2025年第1期7卷 3-39页

作者： Hendrik Ranocha Andrew R.Winters Hugo Guillermo Castro Lisandro Dalcin Michael Schlottke-Lakemper Gregor J.Gassner Matteo Parsani Applied Mathematics University of HamburgBundesstr.5520146 HamburgGermany Department of Mathematics Applied Mathematics Linköping UniversityLinköpingSweden Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Applied and Computational Mathematics RWTH Aachen UniversityAachenGermany High-Performance Computing Center Stuttgart University of StuttgartStuttgartGermany Department of Mathematics and Computer Science University of CologneCologneGermany Center for Data and Simulation Science University of CologneCologneGermany Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Physical Science and Engineering Division(PSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We study a temporal step size control of explicit Runge-Kutta(RK)methods for com-pressible computational fluid dynamics(CFD),including the Navier-Stokes equations and hyperbolic systems of conservation laws such as the Euler *** demonstrate that error-based approaches are convenient in a wide range of applications and compare them to more classical step size control based on a Courant-Friedrichs-Lewy(CFL)*** numerical examples show that the error-based step size control is easy to use,robust,and efficient,e.g.,for(initial)transient periods,complex geometries,nonlinear shock captur-ing approaches,and schemes that use nonlinear entropy *** demonstrate these properties for problems ranging from well-understood academic test cases to industrially relevant large-scale computations with two disjoint code bases,the open source Julia pack-ages *** with *** and the C/Fortran code SSDC based on PETSc.

关键词： Explicit Runge-Kutta(RK)methods Step size control Compressible fluid dynamics Adaptivity in space and time Shock capturing

来源：评论

学校读者我要写书评

暂无评论

Fabrication of SiC particle dispersed AZ91D magnesium alloy composite by injection molding method and their properties

引用

Keikinzoku/Journal of Japan Institute of Light Metals 2024年第3期74卷 141-146页

作者： Hideshima, Yasutoshi Maeda, Fumiya Fukuta, Tadao Ozaki, Koichi Graduate School of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki Okayama Soja-shi719-1197 Japan Process Technology Development Department Technology Development Division Seiko Epson Co. Suwa-shi Nagano Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Soja-shi Japan

AZ91D magnesium alloy chips were coated with SiC powder using a binder, and injection molding was attempted using SiC powder coated magnesium chips as raw material. The metallurgical structure of the injection molded products showed uniform dispersion of SiC particles in the matrix, and there were no significant defects such as voids at the SiC particle-matrix interface. The hardness and 0.2% proof stress of the injection molded products tended to improve with increasing SiC content, while the elongation decreased with increasing SiC content. The Young's modulus of the injection molded products improved with increasing SiC content. It was confirmed that the specific bending rigidity of the injection molded products also improves due to the significant increase in the Young's modulus, although the addition of SiC leads to an increase in density. © 2024 The Japan Institute of Light Metals.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Modelling and Impact Analysis of Antipode Attack in Bufferless On-Chip Networks

引用

SN computer science 2023年第3期4卷 1-9页

作者： Kunthara, Rose George Josna, V.R. Neethu, K. James, Rekha K. Jose, John Division of Electronics Engineering School of Engineering Cochin University of Science and Technology Kerala Cochin 682022 India Department of Computer Science Cochin University of Science and Technology Kerala Cochin 682022 India Department of Computer Science and Engineering Indian Institute of Technology Guwahati Assam Guwahati 781039 India

With advancements in VLSI technology, Tiled Chip Multicore Processors (TCMP) with packet switching Network-on-Chip (NoC) have evolved as the backbone of modern data intensive parallel systems. Manufacturers are looking at the prospect of using several third-party Intellectual Property (IP) cores in their TCMP designs due to strict time-to-market restrictions. Outsourcing IP from vendors across the world exposes System-on-Chip (SoC) designs to malicious implants such as Hardware Trojans (HTs). The performance of entire system is adversely affected by the presence of malicious HT in NoC routers, which can negatively disrupt communication between tiles. Generally, in buffered NoC, hardware trojans affect flits when they are in input buffers. Hardware trojans in bufferless NoC is a less explored area. In this paper, we model an HT that leads to antipode attack, which can occur on Permutation Deflection Network (PDN) of a bufferless router. In a bufferless router such as CHIPPER architecture, only the highest priority flit gets productive port, while other flits may or may not get productive port depending on port availability, leading to deflections. The modelled trojan misroutes all flits of HT-infected router to non-productive ports without modifying the flit control field. We investigate the effects of such an intermittent HT and analyse its effects at NoC level in terms of performance metrics such as average flit latency, deflection rate, throughput and router link utilisation. Experimental evaluations conducted on an 8 × 8 bufferless mesh NoC indicate that the modelled HT degrades network performance due to increased flit deflections and traffic across central routers which impacts system reliability. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Antipode attack Bufferless router Deflection routing Hardware trojan NoC security

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：