检索结果-内蒙古大学图书馆

Implicit Multi-Scale Swin Transformer Network for Image Denoising

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Qi Ding, Yuwei Zhang, Weiqi Zhu, Yian Zhang, Bob Lin, Jerry Chun-Wei Harbin Institute of Technology at Weihai School of Economics and Management Weihai China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Northwestern Polytechnical University School of Computer Science Xi’an China Northwestern Polytechnical University Yangtze River Delta Research Institute Taicang China University of Macau PAMI Research Group Department of Computer and Information Science Taipa China Department of Distributed Systems and IT Devices Electrical Engineering and Mathematical Sciences Silesian university of technology Poland

Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks (CNNs) and vision Transformers achieve good performance by empirically utilizing residual neural network (ResNet) as basic component. However, ResNet lacks interpretability in network design and also long-term memory of features, potentially restricting the performance of denoising networks. In this paper, we propose an Implicit Multi-scale Swin Transformer Network (IMSNet) for image denoising, which introduces the implicit Euler scheme from the feature memory perspective. Specifically, densely connected implicit feature extraction blocks (IFEBs) are designed to learn the residual mapping between noisy and clean images. The IFEB reformulates the initial skip connection of ResNet based on the implicit Euler discretization, providing both network interpretability and long-term memory. In IFEB, the multi-scale swin Transformer block (MSB) is designed as the implicit layer to capture spatial details and non-local contextual information at different scales. Additionally, a cross-layer feature fusion block (CLFF) is proposed to further improve feature reuse capabilities. Compared to existing denoising networks, the extensive experiments demonstrate the superior performance of our IMSNet in various image denoising tasks, and the flexibility in the practical applications with proposed light model on resource-restricted platforms such as consumer electronic devices. © 1975-2011 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Transforming Research with Quantum Computing

Journal of Economy and Technology

引用

Journal of Economy and Technology 2024年

作者： Sukhpal Singh Gill Rajkumar Buyya School of Electronic Engineering and Computer Science Queen Mary University of London London UK Cloud Computing and Distributed Systems (CLOUDS) Laboratory School of Computing and Information Systems The University of Melbourne Australia

Quantum computing is a novel method of computation that uses the principles of quantum mechanics to handle highly challenging situations in a very short amount of time. Quantum technology has the ability to significantly impact worldwide advancement, even prior to the complete deployment of quantum machines. Quantum technology for communication, computation, and sensors has the capacity to revolutionise many industries, and several nations are making investments in this promising field. This includes research investments from both the public and commercial sectors. This article delves into the recent quantum computing advancements and the potential opportunities made possible by quantum technology in the next few decades. We outline a vision and scientific innovation for embracing the quantum age, as well as explore the pioneering applications of quantum computing. We also highlight software tools and platforms for quantum programming to unlock the power of computing and revolutionize the world. Finally, we identify the groundbreaking impacts of quantum computing on next-generation research and discuss the benefits of unleashing its revolutionary capabilities.

关键词： Quantum Computing Quantum Technology Quantum Artificial Intelligence Quantum Machine Learning Quantum Cloud Computing Quantum Applications Quantum Programming Quantum Simulations Quantum Supermacy

来源：评论

学校读者我要写书评

暂无评论

PMU-Spill: Performance Monitor Unit Counters Leak Secrets in Transient Executions

PMU-Spill: Performance Monitor Unit Counters Leak Secrets in...

引用

IEEE Asian Hardware-Oriented Security and Trust (AsianHOST)

作者： Pengfei Qiu Qiang Gao Dongsheng Wang Yongqiang Lyu Chang Liu Xiaoyong Li Chunlu Wang Gang Qu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Tsinghua University Beijing China Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Beijing China Department of Electrical and Computer Engineering Institute for Systems Research University of Maryland Maryland USA

ISBN: (纸本)9781665461153

The processor's Performance Monitor Unit (PMU) allows the recording of architectural and microarchitectural events for profiling purposes. In this study, we reveal a security issue caused by the fact that current PMU implementations are capable of recording some events that happened during transient executions. We propose the PMU -Spill attack, a new kind of attack that enables attackers to maliciously leak the secret data in transient executions. We demonstrate on real hardware that PMU -Spill attack can leak the secret data stored in Intel Software Guard Extensions (SGX). In addition, we perform a thorough study to reveal all the vulnerable PMU counters and find that 20 of them can be used to achieve PMU -Spill attack. Our experiments suggest that the throughput of PMU -Spill attack is up to 575.3 bytes per second (Bps) with an average error rate of 1.89% when leaking the SGX-protected secret data.

关键词： Side-channel attacks Throughput Phasor measurement units Hardware Software Recording Security

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Energy-Aware Offloading in Edge-Cloud Vehicular Networks 18

Machine Learning-based Energy-Aware Offloading in Edge-Cloud...

引用

18th International Conference on Mobile systems and Pervasive Computing, MobiSPC 2021, The 16th International Conference on Future Networks and Communications, FNC 2021 and the 11th International Conference on Sustainable Energy information Technology, SEIT 2021

作者： Ismail, Leila Materwala, Huned Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. © 2021 Elsevier B.V.. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Models for Diabetes Mellitus Type 2 Prediction

Comparative Analysis of Machine Learning Models for Diabetes...

引用

2020 International Conference on Computational Science and Computational Intelligence, CSCI 2020

作者： Ismail, Leila Materwala, Huned United Arab Emirates University College of Information Technology Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering Abu-Dhabi Al-Ain15551 United Arab Emirates

ISBN: (纸本)9781728176246

Diabetes is one of the top 10 causes of death worldwide. Health professionals are aiming for machine learning models to support the prognosis of diabetes for better healthcare and to put in place an effective prevention plan. In this paper, we conduct a comparative analysis of the most used machine learning models in the literature to predict the prevalence of diabetes mellitus type 2. We evaluate the models in terms of accuracy, F-measure and execution time with and without feature selection using a real-life diabetes dataset. The detailed analysis is in the paper. © 2020 IEEE.

关键词： Medical informatics

来源：评论

学校读者我要写书评

暂无评论

AI-Driven molecule generation and bioactivity prediction: A multi-model approach combining VAE, graph and language-based neural networks

引用

Computational biology and chemistry 2025年 119卷

作者： Latefa Oulladji Mouna Saadallah Zakaria Guellil Houda Abbad Houda Bekhti Evolutionary Engineering and Distributed Information Systems Laboratory Djillali Liabes University Department of Computer Science Sidi Bel Abbes 22000 Algeria. Electronic address: latifa.oulladji@univ-sba.dz. Evolutionary Engineering and Distributed Information Systems Laboratory Djillali Liabes University Department of Computer Science Sidi Bel Abbes 22000 Algeria. Electronic address: mouna.saadallah@univ-sba.dz. Djillali Liabes University Department of Computer Science Sidi Bel Abbes 22000 Algeria. Electronic address: abdelkader.guellil.0702@univ-sba.dz. Evolutionary Engineering and Distributed Information Systems Laboratory Djillali Liabes University Department of Computer Science Sidi Bel Abbes 22000 Algeria. Electronic address: houda.abbad@univ-sba.dz. Djillali Liabes University Department of Computer Science Sidi Bel Abbes 22000 Algeria. Electronic address: bekhtinourelhoudayasmine@***.

Cancer is one of the top leading causes of death in the world according to the World Health Organization (WHO). Despite the continuous efforts, drug discovery often takes 10-15 years if done traditionally, and it costs over $2.6 billion to finally bring a single drug to market. The integration of deep learning (DL) with these traditional methods, however, is transforming the process of drug design and prediction, evolving at high speeds, often relying on the molecular data for reference. This paper explores and compares various deep learning models, presenting a multi-model for anticancer small molecule design and bioactivity (GI50%) prediction. A fine-tuned Variation Autoencoder (VAE) model is trained on a set of anticancer molecules to generate new molecules that mimic the drug. These molecules are later fed to a meta-model based on two ensemble methods: averaging and stacking, to predict their activity against different cancer cell lines; leveraging the strengths of different Graph Neural Networks (GNNs), namely: Graph Attention Networks (GATs), Graph Convolutional Networks (GCNs), and Message Passing Neural Networks (MPNNs), based on chemical structure and a pre-trained ChemBERTa model based on the attention mechanism. The experiments were conducted on a dataset of multiple compounds across the breast cancer tumour with 6 cancer cell lines, demonstrating our model's superiority against the literature, outperforming most models; the Pearson's correlation coefficients reached up to 83% using the stacking ensemble method.

关键词： Anticancer molecule Bioactivity prediction Deep learning Drug generation Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Double Deep Q Networks for Sensor Management in Space Situational Awareness

arXiv

引用

arXiv 2022年

作者： Oakes, Benedict Richards, Dominic Barr, Jordi Ralph, Jason CDT in Distributed Algorithms University of Liverpool Liverpool United Kingdom Artificial Intelligence Group STFC Hartree Centre Daresbury United Kingdom Cyber and Information Systems Division Defence Science and Technology Laboratory United Kingdom Electrical Engineering and Electronics University of Liverpool Liverpool United Kingdom

We present a novel Double Deep Q Network (DDQN) application to a sensor management problem in space situational awareness (SSA). Frequent launches of satellites into Earth orbit pose a significant sensor management challenge, whereby a limited number of sensors are required to detect and track an increasing number of objects. In this paper, we demonstrate the use of reinforcement learning to develop a sensor management policy for SSA. We simulate a controllable Earth-based telescope, which is trained to maximise the number of satellites tracked using an extended Kalman filter. The estimated state covariance matrices for satellites observed under the DDQN policy are greatly reduced compared to those generated by an alternate (random) policy. This work provides the basis for further advancements and motivates the use of reinforcement learning for SSA. Copyright © 2022, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Comprehensive information Security Evaluation Model Based on Multi-Level Decomposition Feedback for IoT

引用

Computers, Materials & Continua 2020年第10期65卷 683-704页

作者： Jinxin Zuo Yueming Lu Hui Gao Ruohan Cao Ziyv Guo Jim Feng School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China School of Information and Communication Engineering Beijing University of Posts and Telecommunica-tionsBeijing100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijing100876China Amphenol Global Interconnect Systems San JoseCA 95131USA

The development of the Internet of Things(IoT)calls for a comprehensive in-formation security evaluation framework to quantitatively measure the safety score and risk(S&R)value of the network *** this paper,we summarize the architecture and vulnerability in IoT and propose a comprehensive information security evaluation model based on multi-level decomposition *** evaluation model provides an idea for information security evaluation of IoT and guides the security decision maker for dynamic ***,we establish an overall evaluation indicator system that includes four primary indicators of threat information,asset,vulnerability,and management,*** also includes eleven secondary indicators of system protection rate,attack detection rate,confidentiality,availability,controllability,identifiability,number of vulnerabilities,vulnerability hazard level,staff organization,enterprise grading and service continuity,***,we build the core algorithm to enable the evaluation model,wherein a novel weighting technique is developed and a quantitative method is proposed to measure the S&R ***,in order to better supervise the performance of the proposed evaluation model,we present four novel indicators includes residual risk,continuous conformity of residual risk,head-to-tail consistency and decrease ratio,*** results show the advantages of the proposed model in the evaluation of information security for IoT.

关键词： IoT information security quantitative evaluation safety score residual risk

来源：评论

学校读者我要写书评

暂无评论

Work-in-Progress: Using the PerFECt Framework to Design and Implement Blended Learning Activities to Introduce the Binary System in Primary School Students

Work-in-Progress: Using the PerFECt Framework to Design and ...

引用

9th International Conference on Interactive Collaborative and Blended Learning, ICBL 2020

作者： Moumoutzis, Nektarios Rigas, Nikolaos Apostolos Xanthaki, Chara Maragkoudakis, Yiannis Christodoulakis, Christina Paneva-Marinova, Desislava Pavlova, Lilia Laboratory of Distributed Multimedia Information Systems and Applications School of Electrical and Computer Engineering Technical University of Crete Chania Crete73100 Greece Institute of Mathematics and Informatics Bulgarian Academy of Sciences Sofia1113 Bulgaria Directorate of Secondary Education Chania Crete Greece Department of Computer Science University of Toronto Toronto Canada Laboratory of Telematics Bulgarian Academy of Sciences Sofia1113 Bulgaria

ISBN: (纸本)9783030672089

This paper presents how the PerFECt framework is employed to enable innovative teaching and learning mathematics in schools using drama-based approaches. The topic addressed lies in the cross-section between mathematics and computer science: teaching and learning the binary system of arithmetic that constitutes the basis of modern computing. The work builds on previous research efforts targeting gamification of mathematics and is seen under new light offered by the Theatre in Mathematics (TIM) Methodology. The result is an engaging game to teach the binary system to children using their bodies and simple rules for interacting with each other. Following these simple rules the participants enact the operation of a calculator that is able to transform integers into their binary representations and compute the result of the four arithmetic operations (addition, subtraction, multiplication and division). The game can be combined with online activities using a simulator of the game, so that learners can explore it for themselves and discover how the arithmetic operations are done, even when they are not in the same physical space with their peers. This way, an effective blended learning approach is ultimately offered combining face-to-face and online activities. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Dfier: A Directed Vulnerability Verifier for Ethereum Smart Contracts

SSRN

引用

SSRN 2023年

作者： Wang, Zeli Dai, Weiqi Li, Ming Choo, Kim-Kwang Raymond Zou, Deqing Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing40065 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio United States

Existing smart contract vulnerability identification approaches mainly focus on complete program detection. Consequently, lots of known potentially vulnerable locations need manual verification, which is energy-exhaustive and error-prone. Fuzzing is an effective way to detect vulnerabilities. However, current fuzzers cannot effectively probe these suspicious targets because they overlook two key factors: exploring all paths toward the targets and providing high-quality directed seed inputs. This paper presents a Directed vulnerability veriFier (DFier), elaborating effective transaction sequences with directed inputs for the fuzzer, to focus on analyzing target paths and automatically detect whether the given locations are vulnerable. Specifically, DFier fuses the effectiveness of static analysis and the efficiency of fuzzing. The static analysis helps locate target paths and generate directed inputs for the fuzzer under three heuristic strategies. The first prefers inputs with the larger possibility of triggering potential vulnerabilities based on target features. The second guides the value mutation to satisfy the path constraints. The third adequately leverages execution information to help find exploits faster. Extensive experiments demonstrate that DFier is effective in verifying contract security, compared with three existing contract fuzzers (i.e., contractFuzzer, sFuzz, and conFuzzius). And the performance losses are in an acceptable range. © 2023, The Authors. All rights reserved.

关键词： Smart contract

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：