检索结果-内蒙古大学图书馆

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Saragadam, Sneha Rohan, Gamidi Manideep, Thotapalli Sri Surya Jayan, Sarada Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Mathematics Bengaluru India

ISBN: (纸本)9798331518592

In an effort to increase computing efficiency, this work presents an improved spectral clustering technique that approximates the affinity matrix using Toeplitz and Circulant matrices. To preserve the quality of the clustering, we take advantage of the spectral characteristics of the similarity graph's Laplacian matrix. The Iris flower, Wine Quality, and Mushroom datasets are used to assess the approach. The following six clustering methods are contrasted: PCA combined with either spectral or K-means clustering, K-means clustering (with and without matrix approximation), and spectral clustering (with and without matrix approximation). The Silhouette Score, Fl score, precision, recall, and Adj usted Rand Index (ARI) are used to evaluate performance. The suggested method produces similar results to traditional methods with a significant reduction in computational cost, according to the results. In order to fully investigate the advantages of these matrices, architectures in spectral clustering are explored. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Stochastic Gradient Descent Method for Computational Design of Random Rough Surfaces in Solar Cells

引用

Communications in Computational Physics 2023年第10期34卷 1361-1390页

作者： Qiang Li Gang Bao Yanzhao Cao Junshan Lin Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China Department of Mathematics Zhejiang UniversityChina Department of Mathematics and Statistics Auburn UniversityAuburnAL 36849USA

In this work,we develop a stochastic gradient descent method for the computational optimal design of random rough surfaces in thin-film solar *** formulate the design problems as random PDE-constrained optimization problems and seek the optimal statistical parameters for the random *** optimizations at fixed frequency as well as at multiple frequencies and multiple incident angles are *** evaluate the gradient of the objective function,we derive the shape derivatives for the interfaces and apply the adjoint state method to perform the *** stochastic gradient descent method evaluates the gradient of the objective function only at a few samples for each iteration,which reduces the computational cost *** numerical experiments are conducted to illustrate the efficiency of the method and significant increases of the absorptance for the optimal random *** also examine the convergence of the stochastic gradient descent algorithm theoretically and prove that the numerical method is convergent under certain assumptions for the random interfaces.

关键词： Optimal design random rough surface solar cell Helmholtz equation stochastic gradient descent method

来源：评论

学校读者我要写书评

暂无评论

GAN-Guarded Fine-Tuning: Enhancing Adversarial Robustness in NLP Models 5

GAN-Guarded Fine-Tuning: Enhancing Adversarial Robustness in...

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： Ali, Tarek Eleyan, Amna Al-Khalidi, Mohammed Bejaoui, Tarek Manchester Metropolitan University Department of Computing and Mathematics Manchester United Kingdom University of Carthage Computer Engineering Department Tunisia

ISBN: (纸本)9798331519957

The increasing occurrence of assaults on Natural Language Processing (NLP) systems has sparked worry about their resilience and trustworthiness, particularly in crucial applications like sentiment analysis, machine translation and natural language deduction. To tackle these weaknesses this research presents GAN-Guarded Fine-Tuning (GAN-FT) an training structure that utilizes Generative Adversarial Networks (GANs) to bolster the resilience of extensive language models such, as BERT and RoBERTa. In contrast, training GAN with feature matching (GAN FW) uses a generative opponent to generate various and logically connected adversarial instances with less computational burden. Regular assessments on datasets such as IMDB, Yelp and SNLI indicate that GAN-FT consistently decreases the effectiveness of attacks while enhancing accuracy and adaptability across domains. This suggests its effectiveness in countering familiar and new word substitution forms of attack. This study highlights the impact of incorporating GANs into training methods and sheds light on understanding models better and making decisions effectively in this field of research. Though there are scalability and quick implementation challenges, in real-Time scenarios, GAN-FT is a starting point for looking into adversarial defence mechanisms and broadening its use in more intricate NLP assignments. The research advances the reliability and security aspects of NLP systems, which is a move towards combatting adversarial risks in the ever-changing AI domain. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Web applications testing techniques: a systematic mapping study

引用

International Journal of Web engineering and Technology 2023年第4期17卷 372-412页

作者： Hanna, Samer Ahmad, Amro Al-Said Department of Software Engineering Faculty of Information Technology Philadelphia University Jordan School of Computing and Mathematics University of Keele United Kingdom

Due to the importance of web application testing techniques for detecting faults and assessing quality attributes, many research papers were published in this field. For this reason, it became essential to analyse, classify and summarise the research in the field. To achieve this goal, this research conducted a systematic mapping study on 98 research papers in the field of web applications testing published between 2008 and 2021. The results showed that the most commonly used web applications testing techniques in literature are model-based testing and security testing. Besides, the most commonly used models in model-based testing are finite-state machines. The most targeted vulnerability in security testing is SQL injection. Test automation is the most targeted testing goal in both model-based and security testing. For other web applications testing techniques, the main goals of testing were test automation, test coverage, and assessing security quality attributes. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Leveraging A Deep Learning-Based Privacy Compliance Framework for IoT Applications 5

Leveraging A Deep Learning-Based Privacy Compliance Framewor...

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： Eleyan, Amna Ahmed, Hamza Bejaoui, Tarek Manchester Metropolitan University Department of Computing and Mathematics Manchester United Kingdom University of Carthage Computer Engineering Department Tunisia

ISBN: (纸本)9798331519957

This paper explores and investigates the development and implementation of a deep learning-based privacy compliance framework for Internet of Things (IoT) applications. The geometric growth in potentially sensitive data from the vast generations of data as IoT devices proliferate raises critical security and privacy concerns for individuals and organisations. Additionally, rising cybersecurity attacks reshape how data is handled, especially with IoT devices storing sensitive client data. Simultaneously, GDPR and CCPA which are rigorous data protection regulations have created an urgent and imperative need for automated compliance solutions. Utilising these regulatory standards, this research harnesses deep learning methodologies, specifically Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to tackle these complex challenges while employing public IoT datasets to test. Cutting-edge features are incorporated into the proposed deep-learning framework including threat characterising, anomaly detection, dynamic policy adjustment, and regulatory compliance checking/verification for IoT environments, with the additionality of a devised pipeline encompassing comprehensive data processing, model training, threat detection, compliance checking, and an intuitive user-friendly alert system. The findings concluded that the deep-learning models achieved high accuracy of 99% in threat detection, with general compliance achieving 91% and over of its IoT dataset (RT-IoT2022), concurrently while the integrated compliance checking functions effectively enforced privacy policies from a 'docx' file. This research contributes significantly to the relevant field by offering a novel, automated approach to handling privacy compliance in intricate IoT landscapes, prospectively reducing organisational resource expenditure while enhancing overall data protection measures. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

ONE-PARAMETER FINITE DIFFERENCE METHODS AND THEIR ACCELERATED SCHEMES FOR SPACE-FRACTIONAL SINE-GORDON EQUATIONS WITH DISTRIBUTED DELAY

引用

Journal of Computational mathematics 2024年第3期42卷 705-734页

作者： Tao Sun Chengjian Zhang Haiwei Sun School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China Department of Mathematics University of MacaoMacaoChina

This paper deals with numerical methods for solving one-dimensional(1D)and twodimensional(2D)initial-boundary value problems(IBVPs)of space-fractional sine-Gordon equations(SGEs)with distributed *** 1D problems,we construct a kind of oneparameter finite difference(OPFD)*** is shown that,under a suitable condition,the proposed method is convergent with second order accuracy both in time and *** implementation,the preconditioned conjugate gradient(PCG)method with the Strang circulant preconditioner is carried out to improve the computational efficiency of the OPFD *** 2D problems,we develop another kind of OPFD *** such a method,two classes of accelerated schemes are suggested,one is alternative direction implicit(ADI)scheme and the other is ADI-PCG *** particular,we prove that ADI scheme can arrive at second-order accuracy in time and *** some numerical experiments,the computational effectiveness and accuracy of the methods are further ***,for the suggested methods,a numerical comparison in computational efficiency is presented.

关键词： Fractional sine-Gordon equation with distributed delay One-parameter finite difference methods Convergence analysis ADI scheme PCG method

来源：评论

学校读者我要写书评

暂无评论

Speaker Identification Using CNN-LSTM Model on RAVDESS Dataset: A Deep Learning Approach 4

Speaker Identification Using CNN-LSTM Model on RAVDESS Datas...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Suryamritha, M. Balaji, Varshini Kannan, Srinidhi Murali, K. Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Department of Mathematics Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350349900

Speaker identification is used for identifying an individual based on their voice. Signal processing and deep neural networks are used for feature extraction. This paper presents a method that combines CNN and LSTM for speaker identification. Multiple models such as GMM, CNN, SVM were compared and CNN+LSTM outperformed with an accuracy of 96.52% and F1 measure of 97%. The CNN+LSTM model combines spatial and temporal information extracted by the CNN and LSTM layers which allows to capture of both local and long-term dependencies in the audio data hence making this model very efficient. The above models were evaluated on the RAVDESS (Ryerson AudioVisual Database of Emotional Speech and Song) dataset. The results highlight their potential for practical applications within speaker identification systems. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Email Phishing Detection Using a Custom DistilBERT Model

Real-Time Email Phishing Detection Using a Custom DistilBERT...

引用

2024 International Symposium on Networks, Computers and Communications, ISNCC 2024

作者： Damatie, Edafe Maxwell Eleyan, Amna Bejaoui, Tarek Manchester Metropolitan University Department of Computing and Mathematics Manchester United Kingdom University of Carthage Computer Engineering Department Tunisia

ISBN: (纸本)9798350364910

This paper presents a real-time email phishing detection system that utilizes a custom DistilBERT model. The custom DistilBERT architecture incorporates dynamic threshold adjustment and an enhanced classifier head, optimized for analyzing email content. With detection response times of under two seconds, the system delivers real-time protection. Experimental results demonstrate 99.29% accuracy in controlled tests and 95.45% in real-world tests, surpassing current state-of-the-art methods. The system maintains high performance at low false positive rates, essential for practical deployment. An adaptive daily retraining mechanism ensures continued effectiveness against evolving phishing tactics. This research advances email security and offers insights into the use of transformer-based models in real-time cybersecurity applications. By addressing the limitations of current systems through distilled transformer models, this work significantly strengthens organizational cybersecurity against advanced phishing threats. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Accurate threat hunting in industrial internet of things edge devices

引用

Digital Communications and Networks 2023年第5期9卷 1123-1130页

作者： Abbas Yazdinejad Behrouz Zolfaghari Ali Dehghantanha Hadis Karimipour Gautam Srivastava Reza M.Parizi Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical and Software Engineering University of CalgaryAlbertaCanada Department of Mathematics and Computer Science Brandon UniversityBrandonCanada College of Computing and Software Engineering Kennesaw State UniversityGAUSA Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Department of Computer Science and Mathematics Lebanese American UniversityBeirut1102Lebanon

Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire ***,they can allow malicious software installed on end nodes to penetrate the *** paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge *** proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority *** evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.

关键词： IIoT Threat hunting Edge devices Multi-class anomalies Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

Wide and fault diameter in Kneser graphs for enhanced fault tolerance in parallel computing

引用

International Journal of Networking and Virtual Organisations 2024年第3期31卷 169-190页

作者： Sundara Rajan, R. Kirithiga Nandini, G. Lin, Yuqing Reji, Remi Mariam Department of Mathematics Hindustan Institute of Technology and Science Chennai603 103 India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai603 103 India School of Electrical Engineering and Computing The University of Newcastle CallaghanNSW2308 Australia Department of Mathematics Christian College Kerala Chengannur689 122 India

A system’s fault tolerance is its capacity to function even if one or more of its components fail. Implementing a fault-tolerant network becomes an important criterion for reliable computing. Reliability measures play a significant part in recognising the role of faulty and non-faulty processors in a parallel computing system. Parallel computing is used primarily for saving time, solving big problems, and doing multiple tasks at once at the same time. Various reliability measures have been introduced to evaluate a network’s fault-tolerance capability. We have measured the wide diameter and fault diameter of the Kneser graphs in this study. Also, we have verified the fault diameter obtained using an experimental study. Further, we have described some applications of wide diameter and fault diameter in parallel and distributed computing. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Fault tolerant computer systems

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：