检索结果-内蒙古大学图书馆

Re-quantization based binary graph neural networks

science China(Information sciences) 2024年第7期67卷 160-171页

作者： Kai-Lang YAO Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, while less attention has been paid to binary graph neural networks. A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough. In this paper, we propose a novel method, called re-quantization-based binary graph neural networks(RQBGN), for binarizing graph neural networks. Specifically, re-quantization, a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations, quantizes the results of multiplication between any two matrices during the process of multiplying three matrices. To address the challenges introduced by requantization, in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity. Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models, and RQBGN can outperform other baselines to achieve state-of-the-art performance.

关键词： graph neural networks binary neural networks mixture of experts computation-efficient algorithms

来源：评论

学校读者我要写书评

暂无评论

Stochastic normalized gradient descent with momentum for large-batch training

引用

science China(Information sciences) 2024年第11期67卷 77-91页

作者： Shen-Yi ZHAO Chang-Wei SHI Yin-Peng XIE Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the computational power of current multi-core systems such as graphics processing units(GPUs)and can reduce the number of communication rounds in distributed training settings. Thus, SGD with large-batch training has attracted considerable attention. However, existing empirical results showed that large-batch training typically leads to a drop in generalization accuracy. Hence, how to guarantee the generalization ability in large-batch training becomes a challenging task. In this paper, we propose a simple yet effective method, called stochastic normalized gradient descent with momentum(SNGM), for large-batch training. We prove that with the same number of gradient computations, SNGM can adopt a larger batch size than momentum SGD(MSGD), which is one of the most widely used variants of SGD, to converge to an?-stationary point. Empirical results on deep learning verify that when adopting the same large batch size,SNGM can achieve better test accuracy than MSGD and other state-of-the-art large-batch training methods.

关键词： non-convex problems large-batch training stochastic normalized gradient descent momentum

来源：评论

学校读者我要写书评

暂无评论

Enhanced DDoS Detection Using Advanced Machine Learning and Ensemble Techniques in Software Defined Networking

引用

computers, Materials & Continua 2024年第11期81卷 3003-3031页

作者： Hira Akhtar Butt Khoula Said Al Harthy Mumtaz Ali Shah Mudassar Hussain Rashid Amin Mujeeb Ur Rehman Department of Computer Science University of Management and TechnologySialkot51040Pakistan Department of Computer Science and Creative Technologies Global College of Engineering and TechnologyMuscat2546Sultanate of Oman Department of Computer Science University of WahWah Cantt47040Pakistan Department of Computer Science and IT University of ChakwalChakwal48800Pakistan

Detecting sophisticated cyberattacks,mainly Distributed Denial of Service(DDoS)attacks,with unexpected patterns remains challenging in modern *** detection systems often struggle to mitigate such attacks in conventional and software-defined networking(SDN)*** Machine Learning(ML)models can distinguish between benign and malicious traffic,their limited feature scope hinders the detection of new zero-day or low-rate DDoS attacks requiring frequent *** this paper,we propose a novel DDoS detection framework that combines Machine Learning(ML)and Ensemble Learning(EL)techniques to improve DDoS attack detection and mitigation in SDN *** model leverages the“DDoS SDN”dataset for training and evaluation and employs a dynamic feature selection mechanism that enhances detection accuracy by focusing on the most relevant *** adaptive approach addresses the limitations of conventional ML models and provides more accurate detection of various DDoS attack *** proposed ensemble model introduces an additional layer of detection,increasing reliability through the innovative application of ensemble *** proposed solution significantly enhances the model’s ability to identify and respond to dynamic threats in *** provides a strong foundation for proactive DDoS detection and mitigation,enhancing network defenses against evolving *** comprehensive runtime analysis of Simultaneous Multi-Threading(SMT)on identical configurations shows superior accuracy and efficiency,with significantly reduced computational time,making it ideal for real-time DDoS detection in dynamic,rapidly changing *** results demonstrate that our model achieves outstanding performance,outperforming traditional algorithms with 99%accuracy using Random Forest(RF)and K-Nearest Neighbors(KNN)and 98%accuracy using XGBoost.

关键词： Table 1(continued)OSI layer Possible DDoS attack Data link MAC Address Flooding Physical Cable disconnection JaMMING physical impersonation

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

A Latency-Aware and Fault-Tolerant Framework for Resource Scheduling and Data Management in Fog-Enabled Smart City Transportation Systems

引用

computers, Materials & Continua 2025年第1期82卷 1377-1399页

作者： Ibrar Afzal Noor ul Amin Zulfiqar Ahmad Abdulmohsen Algarni Department of Computer Science and Information Technology Hazara UniversityMansehra21300Pakistan Department of Computer Science King Khalid UniversityAbha61421Saudi Arabia

Thedeployment of the Internet of Things(IoT)with smart sensors has facilitated the emergence of fog computing as an important technology for delivering services to smart environments such as campuses,smart cities,and smart transportation *** computing tackles a range of challenges,including processing,storage,bandwidth,latency,and reliability,by locally distributing secure information through end *** of endpoints,fog nodes,and back-end cloud infrastructure,it provides advanced capabilities beyond traditional cloud *** smart environments,particularly within smart city transportation systems,the abundance of devices and nodes poses significant challenges related to power consumption and system *** address the challenges of latency,energy consumption,and fault tolerance in these environments,this paper proposes a latency-aware,faulttolerant framework for resource scheduling and data management,referred to as the FORD framework,for smart cities in fog *** framework is designed to meet the demands of time-sensitive applications,such as those in smart transportation *** FORD framework incorporates latency-aware resource scheduling to optimize task execution in smart city environments,leveraging resources from both fog and cloud *** simulation-based executions,tasks are allocated to the nearest available nodes with minimum *** the event of execution failure,a fault-tolerantmechanism is employed to ensure the successful completion of *** successful execution,data is efficiently stored in the cloud data center,ensuring data integrity and reliability within the smart city ecosystem.

关键词： Fog computing smart cities smart transportation data management fault tolerance resource scheduling

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification in MRI Images Using VGG19 with Type-2 Fuzzy Logic

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 163-174页

作者： Dihin, Rasha Ali Hamza, Nesreen Readh Department of Computer Science College of Education for Women University of Kufa Najaf Iraq Department of Computer Science College of Computer Science and Information Technology University of Al-Qadisiyah Diwania

A Brain Tumors are highly dangerous illnesses that significantly reduce the life expectancy of patients. The classification of brain tumors plays a crucial role in clinical diagnosis and effective treatment. The misdiagnosis of brain tumors will result in wrong medical intercession and reduce chance of survival of patients Precisely diagnosing brain tumors is of utmost importance for devising suitable treatment plans that can effectively cure and improve the quality of life for patients afflicted with this condition. To tackle this challenge, present a framework that harnesses deep convolutional layers to automatically extract crucial and resilient features from the input data. Systems that use computers and with the help of convolutional neural networks have provided huge success stories in early detection of tumors. In our framework, utilize VGG19 model combined with fuzzy logic type-2 where used fuzzy logic type-2 that applied to enhancement the images brain where Type-2 fuzzy logic better handles uncertainty in medical images, improving the interpretability of image enhancement by managing noise and subtle differences with greater precision than Type-1 fuzzy logic for MRI images often contain ambiguous or low-contrast areas where noise, lighting conditions different and greatly improve accuracy. while used the VGG19 architecture to feature extraction and classify Tumor and non- Tumor. This approach enhances the accuracy of tumors classification, aiding in the development of targeted treatment strategies for patients. The method is trained on the Br35H dataset, resulting in a training accuracy of 0.9983 % and Train loss of 0.2118 while the validation accuracy of 0.9953 % validation loss of 0.2264. This demonstrates effective pattern learning and generalization capabilities. The model achieves outstanding accuracy, with a best accuracy for the model of 0.9983 %, While the test accuracy of the model reached of 99 %, and both of sensitivity and specificity at 0.9967

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cryptographic Solutions for Data Security in Cloud Computing: A Run Time Trend-based Comparison of NCS, ERSA, and EHS

引用

Journal of Cyber Security and Mobility 2024年第2期13卷 265-282页

作者： Dawson, John Kwao Twum, Frimpong Acquah, James Benjamin Hayfron Missah, Yaw Marfo Computer Science Department Sunyani Technical University Sunyani Ghana Computer Science Department Kwame Nkrumah University of Science and Technology Kumasi Ghana Ghana Department of Kwame Nkrumah University of Science and Technology Ghana

Due to the recent explosion in the amount of data being created by various social media platforms, e-commerce websites, and other businesses, a paradigm shift from on-site data centers to the cloud is required. Concerns about privacy and secrecy have been a major obstacle to the mainstream adoption of cloud computing. The best approach to protect the confidentiality and privacy of cloud data is by using cryptographic techniques. Researchers have developed several cryptographic algorithms, but they all have lengthy, linear, predictable, memory-intensive execution times. The performance of the CPU, memory, run-time trend, and throughput of the three cryptographic schemes: Enhanced RSA (ERSA), Non-Deterministic Cryptographic Scheme (NCS), and Enhanced Homomorphic Scheme (EHS) are compared using RAsys. The experiment’s results demonstrated that NCS and EHS produced non-linear and non-deterministic run times. Again, NCS and EHS produced the lowest throughput and memory consumption for text and numeric data types when data sizes of 5n∗102 (KB (∈ 1, 2, 4, 10, 20, 40) were processed. However, ERSA produced a run-time trend that was deterministic, linear, and predictable © 2024 River Publishers.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image restoration using noise gradient and dual priors under mixed noise conditions

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 72-93页

作者： Hazique Aetesam Suman Kumar Maji V.B.Surya Prasath Computer Science and Engineering Birla Institute of Technology MesraBiharIndia Computer Science and Engineering Indian Institute of Technology PatnaBiharIndia Department of Computer Science University of CincinnatiCincinnatiOhioUSA

Images obtained from hyperspectral sensors provide information about the target area that extends beyond the visible portions of the electromagnetic ***,due to sensor limitations and imperfections during the image acquisition and transmission phases,noise is introduced into the acquired image,which can have a negative impact on downstream analyses such as classification,target tracking,and spectral *** in hyperspectral images(HSI)is modelled as a combination from several sources,including Gaussian/impulse noise,stripes,and *** HSI restoration method for such a mixed noise model is ***,a joint optimisation framework is proposed for recovering hyperspectral data corrupted by mixed Gaussian-impulse noise by estimating both the clean data as well as the sparse/impulse noise ***,a hyper-Laplacian prior is used along both the spatial and spectral dimensions to express sparsity in clean image ***,to model the sparse nature of impulse noise,anℓ_(1)−norm over the impulse noise gradient is *** the proposed methodology employs two distinct priors,the authors refer to it as the hyperspectral dual prior(HySpDualP)*** the best of authors'knowledge,this joint optimisation framework is the first attempt in this *** handle the non-smooth and nonconvex nature of the generalℓ_(p)−norm-based regularisation term,a generalised shrinkage/thresholding(GST)solver is ***,an efficient split-Bregman approach is used to solve the resulting optimisation *** results on synthetic data and real HSI datacube obtained from hyperspectral sensors demonstrate that the authors’proposed model outperforms state-of-the-art methods,both visually and in terms of various image quality assessment metrics.

关键词： hyper-laplacian prior hyperspectral images image restoration mixed noise variational approach

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approach for Automating App Review Classification:Advancing Usability Metrics Classification with an Aspect-Based Sentiment Analysis Framework

引用

computers, Materials & Continua 2025年第1期82卷 949-976页

作者： Nahed Alsaleh Reem Alnanih Nahed Alowidi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computer Science and EngineeringUniversity of HailHail81451Saudi Arabia

App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior *** research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and *** propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification *** analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,*** contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews *** advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.

关键词： Requirements Engineering(RE) app review analysis usabilitymetrics hybrid deep learning BERT-BiLSTM-CNN

来源：评论

学校读者我要写书评

暂无评论

Optimizing medical image analysis through MViTX on multiple datasets with explainable AI

引用

Neural Computing and Applications 2025年第14期37卷 8479-8507页

作者： Sheakh, Md. Alif Tahosin, Mst. Sazia Alam, Mohammad Jahangir Begum, Mahbuba Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University Tangail Bangladesh

Cancer remains a leading cause of mortality worldwide, with early detection and accurate diagnosis critical to improving patient outcomes. While computer-aided diagnosis systems powered by deep learning have shown considerable promise, their widespread clinical adoption faces significant challenges in maintaining consistent performance across diverse imaging modalities and datasets. This research addresses the critical challenge of developing robust, generalizable deep learning models by proposing a comprehensive framework utilizing seven diverse medical imaging datasets encompassing fundus photography, histopathology, endoscopy, and MRI, covering diseases such as ocular toxoplasmosis, endometrial cancer, colorectal cancer, gastrointestinal disease, breast cancer, brain tumor, and tympanic membrane conditions. Our methodology combines customized data augmentation strategies (photometric, geometric, and elastic transformations) with an optimized vision transformer with external attention (MViTX) architecture. The MViTX model demonstrated exceptional performance with test accuracies ranging from 94.1 to 99.1% across all datasets, achieving superior metrics in accuracy, precision, recall, F1-score, and AUC compared to state-of-the-art CNNs. The model's effectiveness was further validated through ablation studies and explainable AI techniques, while its practical utility was demonstrated through deployment as a user-friendly web application. Our research establishes the effectiveness of combining tailored data augmentation with attention-based transformer architectures for medical image analysis, representing a significant step toward enhancing healthcare professionals' diagnostic capabilities and ultimately improving patient care outcomes. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Magnetic resonance imaging

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：