检索结果-内蒙古大学图书馆

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Rodrigues, Gizelle Srivastava, Neetu Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Engineering Dept. of Mathematics Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350335095

The present study utilizes the support vector regression (SVR) technique with a cubic kernel to forecast the performance of a double-pipe heat exchanger using T-W tape inserts with wing-width ratios of 0.31, 0.47, and 0.63. The SVR model that is established is applied to predict two key parameters, namely, the thermal performance (η) and the friction factor (f). Various scenarios are examined by considering the Reynolds number (Re) range from 5,500 to 14,500 and the wing-width ratio as inputs. The outcomes indicate that the SVR model accurately predicts the experimental data, as evidenced by the minimal mean square error (MSE) obtained when compared to the experimental values. Furthermore, the proposed SVR-based method predicts the thermal parameters with minimal variance. In addition, multiple regression models are utilized to evaluate the effectiveness of the proposed model, which shows that the recommended SVR technique is useful for predicting thermal parameters with minimal variance. It is noteworthy that the SVR model with the cubic kernel outperforms other modeling approaches in predicting the performance of the T-W double-pipe heat exchanger. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

GPT-Enabled Cybersecurity Training: A Tailored Approach for Effective Awareness

arXiv

引用

arXiv 2024年

作者： Al-Dhamari, Nabil Clarke, Nathan School of Engineering Computing & Mathematics University of Plymouth United Kingdom

This study explores the limitations of traditional Cybersecurity Awareness and Training (CSAT) programs and proposes an innovative solution using Generative Pre-Trained Transformers (GPT) to address these shortcomings. Traditional approaches lack personalization and adaptability to individual learning styles. To overcome these challenges, the study integrates GPT models to deliver highly tailored and dynamic cybersecurity learning experiences. Leveraging natural language processing capabilities, the proposed approach personalizes training modules based on individual trainee profiles, helping to ensure engagement and effectiveness. An experiment using a GPT model to provide a real-time and adaptive CSAT experience through generating customized training content. The findings have demonstrated a significant improvement over traditional programs, addressing issues of engagement, dynamicity, and relevance. GPT-powered CSAT programs offer a scalable and effective solution to enhance cybersecurity awareness, providing personalized training content that better prepares individuals to mitigate cybersecurity risks in their specific roles within the organization. © 2024, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Position: Epistemic Artificial Intelligence is Essential for Machine Learning Models to ‘Know When They Do Not Know’

arXiv

引用

arXiv 2025年

作者： Manchingal, Shireen Kudukkil Cuzzolin, Fabio School of Engineering Computing and Mathematics Oxford Brookes University United Kingdom

Despite the impressive achievements of AI, including advancements in generative models and large language models, there remains a significant gap in the ability of AI to handle uncertainty and generalize beyond the training data. We argue that AI models, especially in autonomous systems, fail to make robust predictions when faced with unfamiliar or adversarial data, as evidenced by incidents with autonomous vehicles. Traditional machine learning approaches struggle to address these issues due to an overemphasis on data fitting and domain adaptation. This position paper posits a paradigm shift towards epistemic artificial intelligence, emphasizing the need for models to learn not only from what they know but also from their ignorance. This approach, which focuses on recognizing and managing uncertainty, offers a potential solution to improve the resilience and robustness of AI systems, ensuring that they can better handle unpredictable real-world environments. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Anti-disturbance Anti-Saturation Tracking Control for Systems with Nonlinearity:Application to Helicopter Elevation Angle Model 41

Event-triggered Anti-disturbance Anti-Saturation Tracking Co...

引用

第41届中国控制会议

作者： Jiangtong Wang Yang Yi Yunkai Wu Weixing Zheng College of Information Engineering Yangzhou University School of Electronics and Information Jiangsu University of Science and Technology School of Computing Engineering and MathematicsUniversity of Western Sydney

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This article concerns a disturbance observer-based(DOB) event-triggered anti-disturbance tracking control strategy for CE150 Helicopter *** the same time,actuator saturation is introduced compulsively,which is expressed by convex *** the one hand,it is to verify the performance of the system in the saturated state,and on the other hand,the actuator can be avoided from being damaged by excessive ***,the purpose of introducing the event-triggered mechanism is to save communication resources and the function of DOB proportional-integral(PI) controller is to suppress the disturbance and track the trajectory of the reference ***,the feasible gain can be obtained by utilizing the convex optimization and linear matrix inequation(LMI) ***,simulation is provided to demonstrate the feasibility and validity of the proposed control method.

关键词： Disturbance-observer-based control(BOBC) disturbance rejection convex optimization event-triggered control tracking control

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Framework for Understanding and Countering Packet-Mutation Adversarial Attacks on NIDS

A Mathematical Framework for Understanding and Countering Pa...

引用

International Conference on Computer and Information Technology (ICCIT)

作者： Md Mehedi Hasan Rafiqul Islam Quazi Mamun Md Mujibur Rahman School of Computing Mathematics and Engineering Charles Sturt University Australia

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

This paper presents a comprehensive mathematical framework for understanding and countering packet-mutation adversarial attacks on Network Intrusion Detection Systems (NIDS). We introduce the Adaptive Sequence-Aware Packet Mutation (ASAPM) algorithm for generating sophisticated adversarial examples and propose a novel defense mechanism, the Adaptive Ensemble with Perturbation Analysis (AEPA). Our approach leverages a diverse ensemble of machine learning models, including RNN-LSTM, GBDT, One-class SVM, and Transformer-based models, combined with dynamic weight adjustment and confidence calibration techniques. Experiments conducted on the UNSW-NB15 and CIC-IDS2017 datasets demonstrate the effectiveness of our methods. The ASAPM attack achieved high evasion rates of 60% and 50% respectively on these datasets with minimal perturbations. Conversely, our AEPA defense mechanism significantly outperformed baseline methods, improving the detection rate by 19.3% (from 72.4% to 91.7%) and reducing the false positive rate by 5.2% (from 8.3% to 3.1%). The adaptive nature of AEPA showed continuous improvement over time, with the detection rate increasing by 7.5% over 1000 iterations. This research contributes to the development of more resilient and adaptive NIDS, addressing the critical challenge of adversarial attacks in an evolving cybersecurity landscape.

关键词： Support vector machines Adaptation models Perturbation methods Network intrusion detection Machine learning Receivers Transformers Calibration Computer security Resilience

来源：评论

学校读者我要写书评

暂无评论

Multimodal Neuroimaging Based Alzheimer's Disease Diagnosis Using Evolutionary RVFL Classifier

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 3833-3841页

作者： Goel, Tripti Sharma, Rahul Tanveer, M. Suganthan, P.N. Maji, Krishanu Pilli, Raveendra National Institute of Technology Silchar Biomedical Imaging Lab Assam Silchar788010 India Indian Institute of Technology Indore Department of Mathematics Simrol Indore453552 India Qatar University KINDI Center for Computing Research College of Engineering Doha2713 Qatar Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore

Alzheimer's disease (AD) is one of the most known causes of dementia which can be characterized by continuous deterioration in the cognitive skills of elderly people. It is a non-reversible disorder that can only be cured if detected early, which is known as mild cognitive impairment (MCI). The most common biomarkers to diagnose AD are structural atrophy and accumulation of plaques and tangles, which can be detected using magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. Therefore, the present paper proposes wavelet transform-based multimodality fusion of MRI and PET scans to incorporate structural and metabolic information for the early detection of this life-taking neurodegenerative disease. Further, the deep learning model, ResNet-50, extracts the fused images' features. The random vector functional link (RVFL) with only one hidden layer is used to classify the extracted features. The weights and biases of the original RVFL network are being optimized by using an evolutionary algorithm to get optimum accuracy. All the experiments and comparisons are performed over the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to demonstrate the suggested algorithm's efficacy. © 2013 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Optimizing Numerical Solutions of Multi-Dimensional Itô-Volterra Stochastic Integral Equation Using Recurrent Neural Network

A Novel Method for Optimizing Numerical Solutions of Multi-D...

引用

2023 IEEE World Conference on Applied Intelligence and computing, AIC 2023

作者： Bandaru, Sumash Chandra Singh, Soumyendra Kumar, R Prasanna Chaudhary, Dharminder Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai601103 India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics Chennai601103 India

ISBN: (纸本)9798350310061

This research study proposes a deep learning approach based on a recurrent neural network and it utilizes two popular types of RNNs - Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) and Monte Carlo simulation to effectively solve multi-dimensional stochastic Itô-Volterra integral equations (MSIVIE). In numerical experiments and practical applications, the proposed approach achieves reliability and great accuracy compared to current methods. Using optimization techniques such as Adam further enhances the model's performance. The adaptability of the approach is demonstrated through various scenarios, and error analysis is conducted to validate its efficacy. The numerical computations are implemented in Python and MATLAB. Consequently, provided visualizations such as loss function and actual and predicted function value graphs for a better understanding of the solution behaviour. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

GPU-optimized LBM-MRT simulation of free convection and entropy generation of non-Newtonian power-law nanofluids in a porous enclosure at REV scale

引用

International Journal of Ambient Energy 2023年第1期44卷 995-1016页

作者： Islam, Mashnoon Hasan, Md Farhad Bhowmick, Sidhartha Kamrujjaman, Md. Molla, Md. Mamun Department of Mathematics and Physics North South University Dhaka Bangladesh Victoria State Government Melbourne Australia School of Computing Engineering and Mathematical Sciences La Trobe University Melbourne Australia Department of Mathematics Jagannath University Dhaka Bangladesh Department of Mathematics Dhaka University Dhaka Bangladesh North South University Dhaka Bangladesh

The present research investigates the heat transfer and entropy generation of a non-Newtonian power-law Cu-water nanofluid in a square porous enclosure at a representative elementary volume (REV) scale using the multiple-relaxation-time lattice Boltzmann method (MRT-LBM). The Graphics Processing Unit (GPU) accelerated the computations involved. The Brinkman-Forchheimer-extended Darcy model and the shear rate dependent power-law viscosity model were taken into account to characterise the non-Newtonian fluid flow in porous medium. Three types of model validations have been conducted, followed by the mandatory grid independence test, to demonstrate the precision and accuracy of the computational code. The numerical results were obtained by varying five key parameters namely, Darcy number (Da = 10−3, 10−2, 10−1);power-law index (n = 0.6–1.0);Rayleigh number (Ra = 104, 105, 106);porosity parameter (ϵ = 0.6);volume fraction of nanoparticles ( = 0.0–0.05), and the Darcy Rayleigh number (Ram = 100, 1000). The numerically simulated outcomes were presented in terms of streamlines, isotherms, velocity, and temperature profiles as well as the Nusselt (Nu) numbers. Furthermore, a correlation among the parameters to determine the average Nu was developed using the Levenberg-Marquardt (LM) algorithm. The mathematical correlation was also subject to validations, and, in general, good correlation coefficients were obtained. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Solving Ordinary Differential Equations using custom loss Convolutional Neural Network Method 11

Solving Ordinary Differential Equations using custom loss Co...

引用

11th IEEE International Conference on Cloud computing in Emerging Markets, CCEM 2023

作者： Singh, Soumyendra Rasool, Shaik Atheeq Kumar, R. Prasanna Department of Mathematics Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai601103 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai601103 India

ISBN: (纸本)9798350360059

Deep learning and machine learning are pivotal in diverse fields, particularly in mathematical problem-solving. This study introduces a novel approach for solving ordinary differential equations (ODEs) using a single-layer convolutional neural network (CNN) with a logistic sigmoid activation function. The methodology employs a control variable approach, allowing exploration of hyperparameters and optimizer choices. The primary objective is to design a CNN capable of accurately resolving ODEs, trained with the Adam optimizer and backpropagation. Extensive experiments involve custom loss functions tailored to ODE characteristics, examining the impact of varying neural network architectures on solutions. Key findings include the successful application of the CNN-based approach, adaptability assessments through control variables, and insights into the influence of network structure on ODE solutions. This research contributes to the intersection of neural networks and mathematical problem-solving, offering a promising avenue for efficiently addressing ODEs. The findings provide a foundation for enhanced mathematical problem-solving, demonstrating the potential of CNNs and custom loss functions. The implications extend to various scientific and engineering domains, opening avenues for improved efficiency and accuracy in solving ODEs in real-world applications. ©2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Numerical Solutions of Stochastic Dynamics using Convolutional Neural Network Methods 1

Numerical Solutions of Stochastic Dynamics using Convolution...

引用

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Sophiya, E. Singh, Deependra K. Singh, Soumyendra Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai601103 India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics Chennai601103 India

ISBN: (纸本)9798350328042

Deep learning and machine learning are very popular and highly interactive across many different subjects;neural networks are usually used extensively in mathematics. We introduce a convolutional neural network (CNN) approach to solving ordinary differential equations and stochastic integral equations. We use an example of a typical first-order differential equation and stochastic integral equations to briefly explain the basic ideas of CNN and gradient computing. We use the control variable approach to compare several hyperparameters and different optimizers to investigate the adaptability and viability of our model. The creation of a convolutional neural network (CNN) for resolving the equations is the key goal here. This is made possible by using a single layer back-propagation learning technique with a logistic sigmoid function and Adam optimizer. To determine which loss best fits the output, multiple losses are created and the outcomes are analyzed for varying neuron counts. © 2023 IEEE.

关键词： Stochastic 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：