检索结果-内蒙古大学图书馆

Neutrosophic Fuzzy Power Management (NFPM): Tackling Uncertainty in Energy Harvesting for Sensor Networks

Neutrosophic Sets and Systems 2025年 76卷 99-114页

作者： Alzubi, Musallam M. Mohamed, Mohamed A. Amer, Hanan M. Salama, A.A. Electronics and Communications Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt

This paper presents a novel approach known as Neutrosophic Fuzzy Power Management (NFPM) aimed at addressing the critical challenge of uncertain energy availability in Energy Harvesting Sensor Networks (EHWSNs). The main objective of this research is to enhance the management of energy resources within these networks, which traditional fuzzy logic methods often fail to do, leading to power failures and reduced reliability. NFPM utilizes neutrosophic logic to effectively model uncertainty by representing the degrees of truth, indeterminacy, and falsity of both harvested and residual energy levels. Through a fuzzy inference system, NFPM dynamically allocates energy budgets for each time slot based on these neutrosophic sets, resulting in more adaptive and conservative energy distribution. The results are validated through numerical examples and extensive simulations, demonstrating NFPM's superiority over traditional fuzzy logic, with significant improvements such as a 25% reduction in power failures, 95% enhanced network connectivity, a 15% increase in data transmission success rates, and overall improvements in energy efficiency and robustness to fluctuations and noise. This research establishes NFPM as a promising solution to the uncertainties inherent in EHWSNs. Future research directions include exploring the integration of NFPM with machine learning algorithms for predictive energy management, assessing its scalability in larger networks, and examining its applicability in other domains requiring energy management under uncertainty. © 2025, University of New Mexico. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Image-Based Malware Analysis Using Residual Capsule Network

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第6期52卷 2022-2038页

作者： El alaoui-Elfels, Omaima Gadi, Taoufiq Bassir, Abdelhak First University of Settat Faculty of Sciences and Techniques. Mathematics Computer Science and Engineering Laboratory Settat26000 Morocco Mathematique Department Hassan First University of Settat Faculty of Sciences and Techniques Laboratory of Mathematics Computer Science and Engineering Settat26000 Morocco

Cyberattacks and malware detection software are in a perpetual race. Researchers have developed antimalware systems that can detect and classify malicious software automatically rather than manually analyzing malware files, which is time-consuming and ineffective. On the other hand, cyber-attackers have developed approaches to avoid signature-based detectors used by antivirus software. In order to improve these detectors, deep learning has been applied by automating feature extraction and malicious pattern identification. Convolutional Neural Networks (CNNs) as a deep learning architecture have proved their effectiveness in malware classification. However, these networks require a large dataset for training, and cannot handle spatial relationships among features effectively;they lose position information on the exact location of a feature, which is critical for a malware file that contains a series of sections. In this paper, we exploit the concept of image classification in the field of computer vision to detect and classify malware images using the ELU Residual Capsule Network (ER-Caps), which goes beyond CNNs’ shortcomings and shows a high performance on a highly imbalanced malware dataset without any enhanced training strategies. The malware files are converted into grayscale images and then processed by an advanced residual subnet to extract the complex features. The resulting feature maps are grouped into capsules and then processed by the dynamic routing algorithm to classify malware. The experimental results indicate that ER-Caps achieves an F1-score of 91.97%, 94.02%, and 98.43% on classifying VIRUS-MNIST, MMCC, and Malimg datasets, respectively, and a malware detection rate of 99.24%, outperforming other deep learning models proposed for malware analysis. © (2025), (International Association of Engineers). All rights reserved.

关键词： computer viruses

来源：评论

学校读者我要写书评

暂无评论

Performance enhancement of deep neural network using fusional data assimilation and divide-and-conquer approach;case study: earthquake magnitude calculation

引用

Neural Computing and Applications 2024年第27期36卷 16899-16910页

作者： Esmaeili, Rezvan Kimiaefar, Roohollah Hajian, Alireza Soleimani-Chamkhorami, Khosro Hodhodi, Maryam Department of Physics Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Department of Mathematics Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran

The presence of "ill-posed samples" specifically in low-volume datasets leads to accuracy decrement in the learning procedure and the generalization of neural networks. Such samples can be caused by various reasons such as noise contamination, corrupted sensors, or even, the complex distribution of physical properties governing the problem. The peak ground acceleration (PGA) datasets are definitely among the last mentioned. Focusing on speed and accuracy, a method for calculating earthquake magnitude based on the PGA data recorded at a single station along with hypocentral information has been presented in this research. Here, after training a deep neural network, the regression errors of the training data samples are clustered into two groups, namely well and ill posed using the grey wolf optimization algorithm. Instead of being removed, the data samples with low learning rates are then modified using samples selected from the other cluster in a fusional form. Then, two separate models are used and trained independently for the clusters. Next, in addition to the routine procedure of network generalization, every new sample is first checked whether is more likely to belong to which group of the clustered data, and after processing, the corresponding trained model is used. The results of the experiments show that using the proposed method results in magnitude calculation with an error order of less than 0.212 units of moment magnitude with a probability of more than 99.7%, which is superior to the conventional methods some of which were reviewed in this research. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Simulation of fractional order mathematical model of robots for detection of coronavirus using Levenberg–Marquardt backpropagation neural network

引用

Neural Computing and Applications 2024年第35期36卷 22417-22428页

作者： Sabir, Zulqurnain Ali, Mohamed R. Sadat, R. Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Basic Engineering Mathematics Department Benha Faculty of Engineering Benha University Benha Egypt Faculty of Engineering Benha National University Obour Campus11835 Egypt Department of Mathematics Zagazig Faculty of Engineering Zagazig University Zagazig Egypt

This research motive is to present more realistic results through the fractional order derivatives of the Robots mathematical system (FORMS), which is used to detect the coronavirus-positive cases. This nonlinear FORMS is useful to prevent individuals from the coronavirus and its spread. The classification of mathematical system is categorized into two dynamics, infected and Robots. The designed FORMS has never been solved before through the stochastic Levenberg–Marquardt backpropagation (LBMBP) neural networks (NNs), i.e., LBMBP-NNs. The solution of three cases of the FORMS is presented along with the statistics of 76% training, 12% authorization and 12% testing. To observe the exactness of LBMBP-NNs, a reference dataset is constructed using the Adams scheme. For the validation and capability of LBMBP-NNs, the illustrations are drawn based on the state transition values, regression measures, correlation performances and error histograms. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

Science China(Information Sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

Domination based graph neural networks

引用

International Journal of computers and Applications 2024年第11期46卷 998-1005页

作者： Meybodi, Mohsen Alambardar Safari, Mahdi Davoodijam, Ensieh Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan Iran Department of Software Engineering University of Kashan Kashan Iran

Graph Neural Networks (GNNs) have emerged as a widely used and effective method across various domains for learning from graph data. Despite the abundance of GNN variants, many struggle with effectively propagating messages over long distances. This paper introduces a novel hierarchical message passing framework for graph learning, specifically designed to address the challenge of long-distance message propagation in graphs. By constructing smaller graphs from the main graph using the concept of domination, a fundamental principle in graph theory, we facilitate more efficient message passing within each subgraph. Subsequently, we employ a Graph Attention Network (GAT) to aggregate these features and propagate them to distant nodes across the graph. Experimental results on standard node classification datasets validate that the proposed architecture achieves performance comparable to or better than conventional GNNs. Additionally, our model consistently performs better on graphs with missing edges. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Edge detection using the Prewitt operator with fractional order telegraph partial differential equations (PreFOTPDE)

引用

Multimedia Tools and Applications 2025年第13期84卷 12329-12345页

作者： Tenekeci, Mehmet Emin Abdulazeez, Sadeq Taha Karadağ, Kerim Modanli, Mahmut Department of Computer Engineering Faculty of Engineering Harran University Şanlıurfa Turkey Department of Mathematics College of Basic Education University of Duhok Duhok Iraq Department of Electrical and Electronics Engineering Faculty of Engineering Harran University Şanlıurfa Turkey Depertmants of Mathematics Faculty of Arts and Sciences Harran University Sanliurfa Turkey

Detecting edges in image processing is an important process in image analysis or enhancement. Many methods detected edge information based on the differences in brightness values. Prewitt, the most widely used edge detection method, performs the extraction of edges by partial differential calculation. This study performed fractional order partial differential calculation with the Telegraph equation in the Prewitt method calculation. Filter coefficients are determined by using Grumwald-Letnikov series expansion for fractional partial differential equation calculation. To determine the most appropriate fraction value, five different coefficients were tried. The proposed method is compared with the conventional edge detection methods Sobel, Canny and standard Prewitt. The obtained result showed that the proposed method detects the edges more accurately. In addition, it has been compared with Prewitt fractional order edge detection (FOED) and edge detection method based on ant colony optimization (ACO) methods developed in recent years. Pratt's figure of merit (FOM) metric was used to compare these studies. It was realized that the FOM values calculated with the proposed method were more accurate than the others methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Finite Difference Method for Neutrosophic Fuzzy Second Order Differential Equation under Generalized Hukuhara Differentiability

引用

Neutrosophic Sets and Systems 2023年 58卷 311-329页

作者： Kamal, Bassem Khalid, Huda E. Salama, A.A. El-Baghdady, Galal I. Department of Mathematics and Engineering Physics Faculty of Engineering Delta University for Science and Technology Egypt Telafer University Telafer Iraq Department of Mathematics and Computer Science Faculty of Science Port Saied University Egypt Department of Mathematics and Engineering Physics Faculty of Engineering Mansoura University Egypt

This paper solves the boundary value problem of the second-order differential equation under the neutrosophic fuzzy boundary condition. The proposed solution is approximated using the finite difference method but deneutrosophication utilizing strongly generalized Hukuhara differentiability. The error calculation is then processed by comparing the proposed numerical solution with the analytical solution presented in our earlier work [20]. © (2023). All Rights Reserved.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters 38

Equivariant Machine Learning on Graphs with Nonlinear Spectr...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lin, Ya-Wei Eileen Talmon, Ronen Levie, Ron Viterbi Faculty of Electrical and Computer Engineering Technion Israel Faculty of Mathematics Technion Israel

Equivariant machine learning is an approach for designing deep learning models that respect the symmetries of the problem, with the aim of reducing model complexity and improving generalization. In this paper, we focus on an extension of shift equivariance, which is the basis of convolution networks on images, to general graphs. Unlike images, graphs do not have a natural notion of domain translation. Therefore, we consider the graph functional shifts as the symmetry group: the unitary operators that commute with the graph shift operator. Notably, such symmetries operate in the signal space rather than directly in the spatial space. We remark that each linear filter layer of a standard spectral graph neural network (GNN) commutes with graph functional shifts, but the activation function breaks this symmetry. Instead, we propose nonlinear spectral filters (NLSFs) that are fully equivariant to graph functional shifts and show that they have universal approximation properties. The proposed NLSFs are based on a new form of spectral domain that is transferable between graphs. We demonstrate the superior performance of NLSFs over existing spectral GNNs in node and graph classification benchmarks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainable AI model for PDFMal detection based on gradient boosting model

引用

Neural Computing and Applications 2024年第34期36卷 21607-21622页

作者： Elattar, Mona Younes, Ahmed Gad, Ibrahim Elkabani, Islam Department of Computer Science Faculty of Science Tanta University Tanta31527 Egypt Department of Mathematics and Computer Science Faculty of Science Alexandria University Alexandria21511 Egypt Faculty of Computer Science and Engineering Al Alamein International University Alamein51718 Egypt

Portable document formats (PDFs) are widely used for document exchange due to their widespread usage and versatility. However, PDFs are highly vulnerable to malware attacks, which pose significant security risks. Existing defense mechanisms often struggle to effectively detect and mitigate these threats, highlighting the need for more robust solutions. This paper introduces a robust framework that uses advanced tree-based ensemble models to detect malicious PDFs using the Evasive-PDFMal2022 dataset. The proposed model achieves a recall rate of 100%, an accuracy rate of 99.95%, and a fast inference time of 0.1723 s. Furthermore, the framework exhibits minimal false positive and false negative rates, ensuring a high level of precision in distinguishing between malicious and benign PDFs. Shapley additive explanations are used to improve the interpretability and reliability of the model’s predictions. The results highlight the effectiveness of the proposed model in improving PDF document security and addressing the challenges posed by malware attacks. © The Author(s) 2024.

关键词： Explainable artificial intelligence (XAI) Malicious PDF Malware detection Tree-based ensemble models

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：