检索结果-内蒙古大学图书馆

Refinement modeling and verification of secure operating systems for communication in digital twins

Digital Communications and Networks 2024年第2期10卷 304-314页

作者： Zhenjiang Qian Gaofei Sun Xiaoshuang Xing Gaurav Dhiman School of Computer Science and Engineering Changshu Institute of TechnologySuzhou215500China University Centre for Research and Development Department of Computer Science and EngineeringChandigarh UniversityMohali140413India Department of Computer Science and Engineering Graphic Era Deemed to be UniversityDehradun248002India

In traditional digital twin communication system testing,we can apply test cases as completely as possible in order to ensure the correctness of the system implementation,and even then,there is no guarantee that the digital twin communication system implementation is completely *** verification is currently recognized as a method to ensure the correctness of software system for communication in digital twins because it uses rigorous mathematical methods to verify the correctness of systems for communication in digital twins and can effectively help system designers determine whether the system is designed and implemented *** this paper,we use the interactive theorem proving tool Isabelle/HOL to construct the formal model of the X86 architecture,and to model the related assembly *** verification result shows that the system states obtained after the operations of relevant assembly instructions is consistent with the expected states,indicating that the system meets the design expectations.

关键词： Theorem proving Isabelle/HOL Formal verification System modeling Correctness verification

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Head and Neck Tumors Using Dual PET/CT Imaging:Comparative Analysis of 2D,2.5D,and 3D Approaches Using UNet Transformer

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2351-2373页

作者： Mohammed A.Mahdi Shahanawaj Ahamad Sawsan A.Saad Alaa Dafhalla Alawi Alqushaibi Rizwan Qureshi Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi PetronasSeri Iskandar32610Malaysia Center for Research in Computer Vision(CRCV) University of Central FloridaOrlandoFL 32816USA

The segmentation of head and neck(H&N)tumors in dual Positron Emission Tomography/Computed Tomogra-phy(PET/CT)imaging is a critical task in medical imaging,providing essential information for diagnosis,treatment planning,and outcome *** by the need for more accurate and robust segmentation methods,this study addresses key research gaps in the application of deep learning techniques to multimodal medical ***,it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a *** primary research questions guiding this study are:(1)How can the integration of convolutional neural networks(CNNs)and transformer networks enhance segmentation accuracy in dual PET/CT imaging?(2)What are the comparative advantages of 2D,2.5D,and 3D model configurations in this context?To answer these questions,we aimed to develop and evaluate advanced deep-learning models that leverage the strengths of both CNNs and *** proposed methodology involved a comprehensive preprocessing pipeline,including normalization,contrast enhancement,and resampling,followed by segmentation using 2D,2.5D,and 3D UNet Transformer *** models were trained and tested on three diverse datasets:HeckTor2022,AutoPET2023,and *** was assessed using metrics such as Dice Similarity Coefficient,Jaccard Index,Average Surface Distance(ASD),and Relative Absolute Volume Difference(RAVD).The findings demonstrate that the 2.5D UNet Transformer model consistently outperformed the 2D and 3D models across most metrics,achieving the highest Dice and Jaccard values,indicating superior segmentation *** instance,on the HeckTor2022 dataset,the 2.5D model achieved a Dice score of 81.777 and a Jaccard index of 0.705,surpassing other model *** 3D model showed strong boundary delineation performance but exhibited variability across datasets,while the

关键词： PET/CT imaging tumor segmentation weighted fusion transformer multi-modal imaging deep learning neural networks clinical oncology

来源：评论

学校读者我要写书评

暂无评论

A new design of parity-preserving reversible multipliers based on multiple-control toffoli synthesis targeting emerging quantum circuits

引用

Frontiers of computer science 2024年第6期18卷 229-244页

作者： Mojtaba NOORALLAHZADEH Mohammad MOSLEH Kamalika DATTA Department of Computer Engineering Dezful BranchIslamic Azad UniversityDezfulIran German Research Centre for Artificial Intelligence(DFKI) Bremen 28359Germany Institute of Computer Science University of BremenBremen 28359Germany

With the recent demonstration of quantum computers,interests in the field of reversible logic synthesis and optimization have taken a different *** every quantum operation is inherently reversible,there is an immense motivation for exploring reversible circuit design and *** it comes to faults in circuits,the parity-preserving feature donates to the detection of permanent and temporary *** the context of reversible circuits,the parity-preserving property ensures that the input and output parities are *** this paper we suggest six parity-preserving reversible blocks(ZFATSL)with improved quantum *** reversible blocks are synthesized using an existing synthesis method that generates a netlist of multiple-control Toffoli(MCT)*** optimization rules are applied at the reversible circuit level,followed by transformation into a netlist of elementary quantum gates from the NCV *** designs of full-adder and unsigned and signed multipliers are proposed using the functional blocks that possess parity-preserving *** proposed designs are compared with state-of-the-art methods and found to be better in terms of cost of *** savings of 25.04%,20.89%,21.17%,and 51.03%,and 18.59%,13.82%,13.82%,and 27.65% respectively,are observed for 4-bit unsigned and 5-bit signed multipliers in terms of quantum cost,garbage output,constant input,and gate count as compared to recent works.

关键词： reversible circuits parity-preserving NCV library multiple-control Toffoli gates quantum circuits quantum cost

来源：评论

学校读者我要写书评

暂无评论

AdaFedProx: A Heterogeneity-Aware Federated Deep Reinforcement Learning for Medical Image Classification

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1432-1441页

作者： Sahoo, Pranab Tripathi, Ashutosh Saha, Sriparna Mondal, Samrat Singh, Jyoti Prakash Sharma, Bhisham Computer Science and Engineering Department Indian Institute of Technology Patna India Electrical and Electronics Engineering Department The Rajiv Gandhi Institute of Petroleum Technology India Indian Institute of Technology Computer Science and Engineering Department Patna India National Institute of Technology Computer Science and Engineering Department Patna India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140401 India

In the realm of smart healthcare, vast amounts of valuable patient data are generated worldwide. However, healthcare providers face challenges in data sharing due to privacy concerns. Federated learning (FL) offers a privacy-preserving solution by enabling collaborative model training without direct access to patient data. This decentralized approach utilizes data from diverse sources, resulting in a globally learned model with satisfactory performance across individual sites. However, federated training encounters challenges such as "system heterogeneity"in client specifications and "data heterogeneity"in imbalanced data distribution. Standard FL methods become unstable and require extensive hyperparameter tuning for optimal performance when facing heterogeneous clients, posing challenges in real-world applications. This research introduces a novel heterogeneity-aware federated learning approach named AdaFedProx to address the performance degradation resulting from heterogeneity. AdaFedProx utilizes a reinforcement learning-driven strategy, introducing a tailored proximal term into the objective function to incorporate partial client information in heterogeneous settings. Dynamically determining the proximal term based on individual client states, including critical characteristics like data distribution, system specification, and performance feedback, empowers AdaFedProx to make regularized decisions throughout the federated training. AdaFedProx consistently outperforms four state-of-the-art methods on three medical datasets across diverse heterogeneity settings (0%, 50%, and 75% straggler). The code can be found at https://***/Pranabiitp/AdaFedProx. © 1975-2011 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MILP Acceleration:A Survey from Perspectives of Simplex Initialization and Learning-Based Branch and Bound

引用

Journal of the Operations research Society of China 2025年第1期13卷 1-55页

作者： Meng-Yu Huang Ling-Ying Huang Yu-Xing Zhong Hui-Wen Yang Xiao-Meng Chen Wei Huo Jia-Zheng Wang Fan Zhang Bo Bai Ling Shi Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong KongChina Theory Lab Huawei Hong Kong Research CentreHong KongChina

Mixed integer linear programming(MILP)is an NP-hard problem,which can be solved by the branch and bound algorithm by dividing the original problem into several subproblems and forming a search *** each subproblem,linear programming(LP)relaxation can be solved to find the bound for making the following ***,with the increasing dimension of MILPs in different applications,how to accelerate the solution process becomes a huge *** this survey,we summarize techniques and trends to speed up MILP solving from two ***,we present different approaches in simplex initialization,which can help to accelerate the solution of LP relaxation for each ***,we introduce the learning-based technologies in branch and bound algorithms to improve decision making in tree *** also propose several potential directions and extensions to further enhance the efficiency of solving different MILP problems.

关键词： MILP acceleration Simplex initialization Linear programming Mixed integer linear programming Machine learning

来源：评论

学校读者我要写书评

暂无评论

Detecting anomalies in blockchain transactions using machine learning classifiers and explainability analysis

引用

Blockchain(research and Applications) 2024年第3期5卷 106-122页

作者： Mohammad Hasan Mohammad Shahriar Rahman Helge Janicke Iqbal H.Sarker Department of Computer Science and Engineering Premier University4000 ChitagongBangladesh Department of Computer Science and Engineering United International University1212 DhakaBangladesh Cyber Security Cooperative Research Centre 6027 PerthAustralia Centre for Securing Digital Futures Edith Cowan University6027 PerthAustralia

As the use of blockchain for digital payments continues to rise,it becomes susceptible to various malicious *** detecting anomalies within blockchain transactions is essential for bolstering trust in digital ***,the task of anomaly detection in blockchain transaction data is challenging due to the infrequent occurrence of illicit *** several studies have been conducted in the field,a limitation persists:the lack of explanations for the model’s *** study seeks to overcome this limitation by integrating explainable artificial intelligence(XAI)techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin *** shapley additive explanation(SHAP)method is employed to measure the contribution of each feature,and it is compatible with ensemble ***,we present rules for interpreting whether a Bitcoin transaction is anomalous or ***,we introduce an under-sampling algorithm named XGBCLUS,designed to balance anomalous and non-anomalous transaction *** algorithm is compared against other commonly used under-sampling and over-sampling ***,the outcomes of various tree-based single classifiers are compared with those of stacking and voting ensemble *** experimental results demonstrate that:(i)XGBCLUS enhances true positive rate(TPR)and receiver operating characteristic-area under curve(ROC-AUC)scores compared to state-of-the-art under-sampling and over-sampling techniques,and(ii)our proposed ensemble classifiers outperform traditional single tree-based machine learning classifiers in terms of accuracy,TPR,and false positive rate(FPR)scores.

关键词： Anomaly detection Blockchain Bitcoin transactions Data imbalance Data sampling Explainable AI Machine learning Decision tree Anomaly rules

来源：评论

学校读者我要写书评

暂无评论

Life Expectancy Prediction using Machine Learning Technique - KNN 3

Life Expectancy Prediction using Machine Learning Technique ...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Narooka, Preeti Vashistha, Aarushi Mitra, Priyanka Derashri, Gulisha School of Computer Science Engineering Manipal University Department of Artificial Intelligence and Machine Learning Rajasthan Jaipur303007 India Jaipur Engineering College and Research Centre Department of Computer Science and Engineering Jaipur303905 India Jaipur Engineering College and Research Centre Department of Computer Science and Engineering Jaipur India

ISBN: (纸本)9798350384598

In the modern world, life expectancy turns out to be the most valuable factor in determining population's health. Today, it is more crucial to predict the future because life is more precarious due to a variety of circumstances, including social, economic, environmental, educational, lifestyle, and health conditions. The machine learning algorithm KNN for life expectancy is presented in this work. The dataset gathered for this study is separated into a training set (70%) and a test set (30%), and the forecasts precision is examined. To avoid misclassification, KNN needs a larger sample size, and the best K are chosen more in accordance with cross-validation experience than with strong statistical theory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

NEMESIS: NORMALIZING THE SOFT-PROMPT VECTORS OF vision-LANGUAGE MODELS 12

NEMESIS: NORMALIZING THE SOFT-PROMPT VECTORS OF VISION-LANGU...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Fu, Shuai Wang, Xiequn Huang, Qiushi Zhang, Yu Department of Computer Science and Engineering Southern University of Science and Technology China Computer Science Research Centre University of Surrey United Kingdom

With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent properties of learnable soft-prompt vectors, specifically the impact of their norms to the performance of VLMs. This motivates us to pose an unexplored research question: "Do we need to normalize the soft prompts in VLMs?" To fill this research gap, we first uncover a phenomenon, called the Low-Norm Effect by performing extensive corruption experiments, suggesting that reducing the norms of certain learned prompts occasionally enhances the performance of VLMs, while increasing them often degrades it. To harness this effect, we propose a novel method named Normalizing the soft-prompt vectors of vision-language models (Nemesis) to normalize soft-prompt vectors in VLMs. To the best of our knowledge, our work is the first to systematically investigate the role of norms of soft-prompt vector in VLMs, offering valuable insights for future research in soft-prompt tuning. The code is available at https://***/ShyFoo/Nemesis. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

SuRaksha: AI-Powered Blockchain Framework for HVAC Tamper Detection and Authentication in Smart Classrooms

引用

IEEE Internet of Things Journal 2025年第13期12卷 25568-25575页

作者： Singh, Sushil Kumar Vaghela, Krunal Khanna, Ashish Virdee, Bal Kumar, Manish Department of Computer Science and Engineering India London Metropolitan University Centre for Communications Technology Research Group Director United Kingdom Marwadi University Department of Computer Engineering Rajkot India London Metropolitan University The Center for Communications Technology United Kingdom Marwadi University Department of Computer Engineering Gujarat Rajkot India

Smart Classrooms (SCR) are reshaping the learning experience with their interactive technology and personalized knowledge, leading to improved student engagement by seamlessly integrating digital gadgets. In this rapidly evolving landscape, the integrity and efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems are essential to the futuristic student's life. This paper introduces SuRaksha: AI-Powered Blockchain Framework for HVAC Tamper Detection and Authentication in Smart Classrooms. Leveraging the power of ensemble learning (EL) at the intelligent and connection layer of the proposed framework, our approach employs IoT sensors to collect comprehensive data from HVAC appliances. The EL algorithms then analyze the collected data to detect any instances of tampering in real-time. At the security layer, robust authentication mechanisms are implemented to verify the integrity of the HVAC data before securely storing it on the cloud. This multi-layered framework enhances the detection and authentication processes and ensures the reliability and security of HVAC operations in intelligent classroom environments. Extensive experiments and validations demonstrate the efficacy of the proposed framework in identifying tampering incidents and providing a secure, authenticated, and reliable system for modern educational facilities. The validation outcomes of the proposed framework demonstrate excellent performance, with an average processing time of 3.725 Secs and 99.84% accuracy for Smart Classrooms compared to existing works. © 2025 IEEE.

关键词： HVAC

来源：评论

学校读者我要写书评

暂无评论

A Web 3.0 Integrated Blockchain Enabled Access System Augmented by Meta-Heuristic Cognitive Learning Framework for Mitigating Threats in IoT Enabled Consumer Electronic Devices

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1201-1210页

作者： Aruna, Etikala Sahayadhas, Arun Kalpana, Ponugoti Khan, Surbhi B. Quasim, Tabrez Almusharrf, Ahlam VELS Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Pallavaram Chennai India AVN Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad501510 India University of Salford School of Science Engineering and Environment SalfordM5 4WT United Kingdom Chandigarh University University Centre for Research and Development Mohali India Chitkara University Centre for Research Impact and Outcome India University of Bisha College of Computing and Information Technology Department of Computer Science and Artificial Intelligence Bisha Saudi Arabia King Khalid Univeersity Saudi Arabia

Consumer Electronic Devices have become an open network model because of the infusion of the Internet of Things (IoT) and other communication technologies such as 5G/6G. Though these devices have provided the high-end sophistication even to common person, but it has proved its darker side by triggering more security breaches and privacy problems. Hence, securing and authenticating these Internet enabled consumer devices has become a probable issue to be solved for safer and secured communication. Therefore, this paper presents a novel fusion of Web 3.0-based Blockchain (WBC) and Deep learning (DL) technique for securing consumer electronic devices in an IoT ecosystem. The proposed framework k(MTD-BCAM) is devised into two components: Multiple-Threat Detection(MTD) and Access Management Mechanism(AMM). In the first component, a DL model is applied for threat detection, whereas WBC is meant for an efficient authentication process. Furthermore, a novel residual fast-gated recurrent neural network is proposed. To reduce the complexity, the komodo Mlipir optimization (KMO) approach is used to tune the hyper-parameters of the network. The comprehensive experimental outcome study of the proposed approach employs NSL-KDD datasets in which the distinct metrics of both DL and Blockchain (BC) are measured and analyzed. Results demonstrated the superior accuracy of the model by achieving 99.78% with less computational time and higher transaction speed. Additionally, the statistical validation and security strength of the model are also analyzed and examined with the varied state-of-art models. © 2025 IEEE. All rights reserved.

关键词： Recurrent neural networks

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：