检索结果-内蒙古大学图书馆

3rd International Conference on Blockchain Technology and Information Security, ICBCTIS 2023

作者： Ying, Zuobin Li, Wenqi Chu, Chiawei Zang, Jiawei Deng, Chen Xu, Shengmin Faculty of Data Science City University of Macau China Nanyang Technological University Singapore College of Computer and Cyber Security Fujian Normal University Fuzhou China

ISBN: (纸本)9798350340402

On-chain methods fail to improve the scalability of cryptocurrencies since they are constrained by block size and block creation rate. As a result, Payment Channel Networks (PCNs) have surfaced as a vital off-chain alternative for achieving scalability. In our prior research, we introduced a scheme called Accountable Assertions Performance Optimization (A2PO) designed to identify malicious users in PCNs while optimizing computational efficiency and maintaining security. The original A2PO scheme assumed the third-party supervisor to be trustworthy;however, the potential for malicious behavior exists in reality. Consequently, we present an improved A2PO framework that incorporates an election mechanism. Supervisors for each transaction are automatically elected by calculating user balances. We offer a thorough security analysis, as well as the results of our evaluation show that the suggested scheme keeps the original A2PO's benefits in terms of computing performance while enhancing security to thwart hostile supervisor operations. © 2023 IEEE.

关键词： Supervisory personnel

来源：评论

学校读者我要写书评

暂无评论

Empowering Diagnosis: Cutting-Edge Segmentation and Classification in Lung Cancer Analysis

引用

computers, Materials & Continua 2024年第6期79卷 4963-4977页

作者： Iftikhar Naseer Tehreem Masood Sheeraz Akram Zulfiqar Ali Awais Ahmad Shafiq Ur Rehman Arfan Jaffar Faculty of Computer Sciences&Information Technology The Superior UniversityLahore54000Pakistan Intelligent Data Visual Computing Research(IDVCR) Lahore54000Pakistan Information System Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Lung cancer is a leading cause of global mortality *** detection of pulmonary tumors can significantly enhance the survival rate of ***,various computer-Aided Diagnostic(CAD)methods have been developed to enhance the detection of pulmonary nodules with high ***,the existing method-ologies cannot obtain a high level of specificity and *** present study introduces a novel model for Lung Cancer Segmentation and Classification(LCSC),which incorporates two improved architectures,namely the improved U-Net architecture and the improved AlexNet *** LCSC model comprises two distinct *** first stage involves the utilization of an improved U-Net architecture to segment candidate nodules extracted from the lung ***,an improved AlexNet architecture is employed to classify lung *** the first stage,the proposed model demonstrates a dice accuracy of 0.855,a precision of 0.933,and a recall of 0.789 for the segmentation of candidate *** suggested improved AlexNet architecture attains 97.06%accuracy,a true positive rate of 96.36%,a true negative rate of 97.77%,a positive predictive value of 97.74%,and a negative predictive value of 96.41%for classifying pulmonary cancer as either benign or *** proposed LCSC model is tested and evaluated employing the publically available dataset furnished by the Lung Image database Consortium and Image database Resource Initiative(LIDC-IDRI).This proposed technique exhibits remarkable performance compared to the existing methods by using various evaluation parameters.

关键词： Lung cancer segmentation AlexNet U-Net classification

来源：评论

学校读者我要写书评

暂无评论

A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 790-804页

作者： Nechirvan Asaad Zebari Chira Nadheef Mohammed Dilovan Asaad Zebari Mazin Abed Mohammed Diyar Qader Zeebaree Haydar Abdulameer Marhoon Karrar Hameed Abdulkareem Seifedine Kadry Wattana Viriyasitavat Jan Nedoma Radek Martinek Department of Information Technology Lebanese French UniversityErbilIraq Department of Computer Science University of ZakhoZakhoKurdistan RegionIraq Department of Computer Science College of ScienceNawroz UniversityDuhokKurdistan RegionIraq Department of Artificial Intelligence College of Computer Science and Information TechnologyUniversity of AnbarRamadiIraq Department of Telecommunications VSB‐Technical University of OstravaOstravaCzech Republic Department of Cybernetics and Biomedical Engineering VSB‐Technical University of OstravaOstravaCzech Republic Department of Computer Network and Information Security Technical College of Informatics-AkreDuhok Polytechnic UniversityDuhokIraq Information and Communication Technology Research Group Scientific Research CenterAl‐Ayen UniversityThi‐QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq College of Agriculture Al‐Muthanna UniversitySamawahIraq Department of Applied Data Science Noroff University CollegeKristiansandNorway Faculty of Commerce and Accountancy Chulalongkorn Business SchoolChulalongkorn UniversityBangkokThailand

Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.

关键词： brain tumour deep learning feature fusion model MRI images multi‐classification

来源：评论

学校读者我要写书评

暂无评论

BlueVR: Design and Evaluation of a Virtual Reality Serious Game for Promoting Understanding towards People with Color Vision Deficiency

引用

Proceedings of the ACM on Human-computer Interaction 2023年第CHIPLAY期7卷 289–318页

作者： You, Ruoxin Zhou, Yihao Zheng, Weicheng Zuo, Yiran Barrera Machuca, Mayra Donaji Tong, Xin University College London Gower Street LondonWC1E 6BT United Kingdom School of Computer Science and Technology East China Normal University Shanghai China Duke Kunshan University Kunshan China Shanghai Yue Kong Pao Senior Secondary School Shanghai China Faculty of Computer Science Dalhousie University 6050 University Avenue HalifaxNS Canada Data Science Research Center Duke Kunshan University Kunshan China

People with color vision deficiency (CVD) often encounter color-related challenges in their daily life, which are difficult for those with non-CVD to comprehend fully. Therefore, we designed a Virtual Reality (VR) serious game, BlueVR, to simulate challenging scenarios encountered by people with CVD and facilitate understanding from people with non-CVD. We conducted an empirical study with thirty participants with non-CVD and six participants with CVD to evaluate the opportunities and challenges of BlueVR. Our findings suggest that BlueVR increased people with non-CVD's understanding, awareness, and perspective-taking abilities towards people with CVD. Moreover, interviews with participants with CVD revealed that BlueVR accurately depicts their real-life discomforts and meets their expectations to improve potential social awareness. This research contributes valuable insights into the mechanisms underlying the effectiveness of VR serious games in promoting understanding and design implications for future game development. © 2023 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Error Exponents for DNA Storage Codes with a Variable Number of Reads

arXiv

引用

arXiv 2025年

作者： Ling, Yan Hao Weinberger, Nir Scarlett, Jonathan Department of Computer Science National University of Singapore Singapore Faculty of Electrical and Computer Engineering Technion Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore Singapore

In this paper, we study error exponents for a concatataned coding based class of DNA storage codes in which the number of reads performed can be variable. That is, the decoder can sequentially perform reads and choose whether to output the final decision or take more reads, and we are interested in minimizing the average number of reads performed rather than a fixed pre-specified value. We show that this flexibility leads to a considerable reduction in the error probability compared to a fixed number of reads, not only in terms of constants in the error exponent but also in the scaling laws. This is shown via an achievability result for a suitably-designed protocol, and in certain parameter regimes we additionally establish a matching converse that holds for all protocols within a broader concatenated coding based class. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

arXiv

引用

arXiv 2024年

作者： Wang, Shang Zhu, Tianqing Ye, Dayong Zhou, Wanlei School of Computer Science University of Technology Sydney Australia Faculty of Data Science City University of Macau China

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content during training, raising significant ethical and legal concerns. To address these issues, machine unlearning has been introduced as a potential solution. While existing unlearning methods take into account the specific characteristics of LLMs, they often suffer from high computational demands, limited applicability, or the risk of catastrophic forgetting. To address these limitations, we propose a lightweight unlearning framework based on Retrieval-Augmented Generation (RAG) technology. By modifying the external knowledge base of RAG, we simulate the effects of forgetting without directly interacting with the unlearned LLM. We approach the construction of unlearned knowledge as a constrained optimization problem, deriving two key components that underpin the effectiveness of RAG-based unlearning. This RAG-based approach is particularly effective for closed-source LLMs, where existing unlearning methods often fail. We evaluate our framework through extensive experiments on both open-source and closed-source models, including ChatGPT, Gemini, Llama-2-7b-chat-hf, and PaLM 2. The results demonstrate that our approach meets five key unlearning criteria: effectiveness, universality, harmlessness, simplicity, and robustness. Meanwhile, this approach can extend to multimodal large language models and LLM-based agents. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Modal-Centric Insights Into Multimodal Federated Learning for Smart Healthcare: A Survey 24th

Modal-Centric Insights Into Multimodal Federated Learning fo...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Di Liu, Wenjian Gao, Longxiang Qu, Y. Neil. Zhang, Hu Shi, Jihong The Faculty of Data Science City University of Macau Macau China Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Medical Integration and Practice Center Shandong University Jinan China

ISBN: (纸本)9789819615476

Federated Learning (FL) has progressed, providing a distributed mechanism where data need not be consolidated, thereby enhancing the privacy and security of sensitive healthcare data. Recent advancements in multimodal machine learning have empowered the development of accurate and robust AI systems in the medical domain, especially within centralized database systems. Multimodal federated learning (MFL) combines federated learning’s distributed nature with the flexibility to work with various data types. This capability is particularly relevant in medical contexts, where healthcare data can range from electronic health records (EHR) to radiology imaging, genomic data, and wearable device information. The key advantage of MFL in medical settings is the ability to create robust models without centralizing sensitive patient information. However, there are no existent research to comprehensively review the application status of MFL in smart healthcare systems from the modal-centric aspect. Motivated by this, we explore the systematization of knowledge about multimodal federated learning on medical data, find the challenges of this area and related solutions. With this research, we hope to provide a systematical review of this under-explored domain and provide insights for forthcoming researchers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees 41

FedLMT: Tackling System Heterogeneity of Federated Learning ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jiahao Zhou, Yipeng Wu, Di Hu, Miao Guizani, Mohsen Sheng, Quan Z. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Abu Dhabi United Arab Emirates

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Cooperative Task Offloading in Blockchain-Enabled MEC for Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Jing, Jinfeng Yang, Yaozong Zhou, Xiaokang Huang, Jiwei Qi, Lianyong Chen, Ying Beijing Information Science and Technology University School of Computer Science Beijing100101 China Kansai University Faculty of Business and Data Science Japan China University of Petroleum Beijing Key Laboratory of Petroleum Data Mining Beijing102249 China College of Computer Science and Technology China

The development of the Internet of Things (IoT) has made the traditional Consumer Electronics (CE) evolve into a next-generation CE with many intelligent application which generates a large number of computing-intensive tasks and is sensitive to latency. The combination of blockchain technology and multi-UAV-assisted edge computing is considered a promising technology that can process tasks near CE devices instead of sending data to remote data centers, and it has advantages in flexible deployment, differentiated services, and security assurance. This paper considers a Blockchain-enabled MEC scenario where CE devices can offload tasks to multiple-UAV-edge layers for decentralized cooperative computing, and utilize the reputation mechanism of blockchain to identify abnormal nodes in edge offloading. To solve the problem of computation offloading and resource allocation in this scenario, we jointly optimize the CPU cycle frequencies and offloading resources of UAVs and CE devices, and the decision of UAVs. Our goal is to minimize system energy consumption while ensuring the quality of service. The stochastic optimization technique is employed to transform the original stochastic optimization problem into a deterministic optimization problem, decomposing it into multiple sub-problems which can be solved in parallel. Additionally, we design a dynamic priority scoring strategy to facilitate cooperative processing among multiple UAVs and propose a Blockchain-Based Multi-UAV Cooperative Task Offloading (BMCTO) algorithm. Through theoretical analysis and simulation experiments, we demonstrate that the BMCTO algorithm can effectively reduce system energy consumption while maintaining system performance. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

On some properties of the bibasic Humbert hypergeometric functions Ξ_(1) and Ξ_(2)

引用

Applied Mathematics(A Journal of Chinese Universities) 2023年第4期38卷 614-630页

作者： CAI Qing-bo Ghazi S.Khammash Shimaa I.Moustafa Ayman Shehata Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information ProcessingSchool of Mathematics and Computer ScienceQuanzhou Normal UniversityQuanzhou 362000China Department of Mathematics Al-Aqsa UniversityGazaGaza StripPalestine Department of Mathematics Faculty of ScienceAssiut UniversityAssiut 71516Egypt Department of Mathematics Unaizah College of Science and ArtsUnaizah 56264Qassim UniversityBuraydah 52571QassimSaudi Arabia

The main object of this paper is to deduce the bibasic Humbert functions Ξ_(1) and Ξ_(2)Some interesting results and elementary summations technique that was successfully employed,q-recursion,q-derivatives relations,the q-differential recursion relations,the q-integral representations for Ξ_(1) and Ξ_(2)are *** summation formula derives a list of p-analogues of transformation formulas for bibasic Humbert functions that have been studied,also some hypergeometric functions properties of some new interesting special cases have been given.

关键词： q-calculus bibasic Humbert hypergeometric functions q-derivative

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：