检索结果-内蒙古大学图书馆

Temporal pattern mining from user-generated content

Digital Communications and Networks 2022年第6期8卷 1027-1039页

作者： Adnan Ali Jinlong Li Huanhuan Chen Ali Kashif Bashir School of Computer Science and Technology University of Science and Technology of ChinaHefei230026AnhuiChina Department of Computing and Mathematics Manchester Metropolitan UniversityManchesterM156BHUnited Kingdom Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Woxsen School of Business Woxsen UniversityIndia

Faster internet, IoT, and social media have reformed the conventional web into a collaborative web resulting in enormous user-generated content. Several studies are focused on such content;however, they mainly focus on textual data, thus undermining the importance of metadata. Considering this gap, we provide a temporal pattern mining framework to model and utilize user-generated content's metadata. First, we scrap 2.1 million tweets from Twitter between Nov-2020 to Sep-2021 about 100 hashtag keywords and present these tweets into 100 User-Tweet-Hashtag (UTH) dynamic graphs. Second, we extract and identify four time-series in three timespans (Day, Hour, and Minute) from UTH dynamic graphs. Lastly, we model these four time-series with three machine learning algorithms to mine temporal patterns with the accuracy of 95.89%, 93.17%, 90.97%, and 93.73%, respectively. We demonstrate that user-generated content's metadata contains valuable information, which helps to understand the users' collective behavior and can be beneficial for business and research. Dataset and codes are publicly available;the link is given in the dataset section.

关键词： Social media analysis Collaborative computing Social data Twitter data Temporal patterns mining Dynamic graphs

来源：评论

学校读者我要写书评

暂无评论

Modelling Smart Grid Instability Against Cyber Attacks in SCADA System Networks

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data Engineering and Communications Technologies 2023年 180卷 239-250页

作者： Efiong, John E. Akinyemi, Bodunde O. Olajubu, Emmanuel A. Ibrahim, Isa A. Aderounmu, Ganiyu A. Degila, Jules Department of Computer Science and Engineering Obafemi Awolowo University Ile-Ife Nigeria Department of Cybersecurity Federal University of Technology Owerri Nigeria Department of Computer Science Institute of Mathematics and Physics University of Abomey Calavi Benin

The SCADA systems in the Smart Grid Network (SGN) are increasingly facing cyber threats and divers attacks due to their known proprietary vulnerabilities, most often leading to power instability and cascading failures in the Grid. This paper associates the SGN’s instability with cyberattacks and models intrusions into SCADA systems using the Decentral Smart Grid Control (DSGC) model on the Stability dataset. The Time-Synchronization Attack was modelled with its effects on Transmission Line Fault Detection, Voltage Stability Monitoring and Event Locating. Classification and prediction were done on WEKA using a number of Machine Learning Algorithms and performances evaluated. Random Forest (RF) classifier was found to be more promising in all the benefit metrics yielding 92.0%, 91.9%, 92.0%, and 91.9% for Accuracy, Precision, Recall and F-measure, respectively. An ensemble classifier – Bagging, performed significantly well after the RF with 90.0%, 89.9%, 90.0% and 89.9%. The ROC Area under Curve also showed RF having 97% and Bagging 96.7%. 100 trees were constructed for the RF while considering 4 random features, and the out-of-bag error was 0.0084. RF had a TPR of 92.0%, which is the highest and an FPR of 0.11. These results provide insights into identifying appropriate ML techniques and models for the Grid’s instability problem vis-à-vis modelling attacks. This is expected to help in effective security planning, threats detection, attack mitigation and risk management. © The Author(s).

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Straightforward Guess and Determine Analysis Based on Genetic Algorithm

引用

Journal of Systems science & Complexity 2022年第5期35卷 1988-2003页

作者： CAO Chunping CEN Zhe FENG Xiutao WANG Zhangyi ZHU Yamin Department of Computer Science and Technology University of Shanghai for Science and TechnologyShang-hai 200093China Key Laboratory of Mathematics Mechanization Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China School of Science Xi'an Technological UniversityXi'an 710021China

With the development of artificial intelligence,the genetic algorithm has been widely used in many *** cryptography,the authors find it is natural to code an individual and design its fitness in a genetic algorithm for a straightforward guess and determine analysis(SGDA,in short).Based on this observation,the authors propose an SGDA based on genetic *** it with the other three SGDAs based on exhaustive search,MILP method and CPP method respectively,the authors illustrate its effectiveness by three stream ciphers:Small scale SNOW 2.0,medium scale Enocoro-128v2 and large scale *** results show our method is significantly superior to them,especially for Trivium,the method can find a solution of 165 variables in less than one hour,while the other three methods are not applicable due to its enormous search space of size 2^(619.37).As far as we know,it is a best solution in an SGDA for Trivium so far.

关键词： Enocoro-128v2 genetic algorithm guess and determine analysis SNOW 2.0 trivium

来源：评论

学校读者我要写书评

暂无评论

Watermarking technique for copyright protection of digital images using coupled differential equations

引用

Multimedia Tools and Applications 2025年第12期84卷 11027-11039页

作者： Attaullah Javeed, Adnan Shah, Daud Shah, Tariq Department of Computer Science National University of Technology Islamabad Pakistan Government Associate College Daultala Rawalpindi Pakistan Department of Mathematics Quaid-I-Azam University Islamabad Pakistan

Advancement and expansion of the internet, along with regular software upgrades, have generated many benefits in communication patterns. This rapid growth has also had a negative impact on the security of communicated content, such as images, audio/video messages, and especially on copyright protection for important images. In this paper, a novel watermarking technique is proposed to address the challenge of copyright protection more effectively. Initially, a chaotic dynamical system presented by coupled differential equations is utilized to generate three random, as well as chaotic, sequences of numbers. These sequences are then processed on each channel (red, green, and blue) of a colored image, respectively. Subsequently, the watermark (logo image) is embedded by converting its most significant bits (MSBs) to least significant bits (LSBs). The watermark in the processed image is nearly invisible due to the presence of third-order nonlinearity in the chaotic system and the complexity of the watermarking technique. This technique has demonstrated remarkable resistance to various attacks, such as noise attacks, compression attacks, and more specifically cropping attacks, confirming its applicability in copyright protection for digital images. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Verification of the Busy-Forbidden Protocol: (using an Extension of the Cones and Foci Proof Framework) 1

引用

10th IPM International Conference on Fundamentals of Software Engineering, FSEN 2023

作者： van Spaendonck, P.H.M. Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands

ISBN: (数字)9783031424410

ISBN: (纸本)9783031424403

The busy-forbidden protocol is a new readers-writer lock with no resource contention between readers, which allows it to outperform other locks. For its verification, specifications of its implementation and its less complex external behavior are provided by the original authors but are only proven equivalent for up to 7 threads. We provide a general equivalence proof using the cones and foci proof framework, which rephrases whether two specifications are branching bisimilar as six properties on the data objects of the specifications. We provide an extension of this framework consisting of four additional properties and prove that when the additional properties hold, the two systems are divergence-preserving branching bisimilar, a stronger version of the aforementioned relation that also distinguishes livelocks. © 2023, IFIP International Federation for Information Processing.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

Group decision making based on entropy measure of Pythagorean fuzzy sets and Pythagorean fuzzy weighted arithmetic mean aggregation operator of Pythagorean fuzzy numbers

引用

Information sciences 2023年第1期624卷 361-377页

作者： Kumar, Kamal Chen, Shyi-Ming Department of Mathematics Amity University Haryana Gurugram India Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan

In this paper, we propose a new entropy measure of Pythagorean fuzzy sets (PFSs). The proposed entropy measure of PFSs can conquer the shortcomings of the existing entropy measure of PFSs. We also propose the Pythagorean fuzzy weighted arithmetic mean (PFWAM) aggregation operator (AO) of Pythagorean fuzzy numbers (PFNs). The proposed PFWAM AO of PFNs can conquer the shortcomings of the existing sine trignometry Pythagorean fuzzy weighted averaging (ST-PFWA) AO and the existing sine trignometry Pythagorean fuzzy weighted geometric (ST-PFWG) AO of PFNs. Based on the proposed entropy measure of PFSs and the proposed PFWAM AO of PFNs, we propose a new group decision making (GDM) approach in the environment of PFNs. The proposed GDM approach can conquer the shortcomings of existing GDM approaches, where they cannot distinguish the ranking orders (ROs) of alternatives in some conditions. It offers us a very useful approach to deal with GDM problems in the environment of PFNs. © 2022 Elsevier Inc.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

Stochastic neuro-swarming intelligence paradigm for the analysis of magneto-hydrodynamic Prandtl-Eyring fluid flow with diffusive magnetic layers effect over an elongated surface

引用

Chinese Journal of Chemical Engineering 2024年第10期74卷 295-311页

作者： Zeeshan Ikram Butt Iftikhar Ahmad Muhammad Shoaib Syed Ibrar Hussain Hira Ilyas Muhammad Asif Zahoor Raja Department of Mathematics University of GujratGujrat 50700Pakistan Yuan Ze University AI CenterTaoyuanTaiwan 320China Department of Mathematics and Computer Science University of PalermoVia Archirafi 34Palermo 90123Italy Department of Mathematics University of HoustonHoustonTX 77204USA Department of Physical Sciences University of ChenabGujrat 50700Pakistan Future Technology Research Centre National Yunlin University of Science and TechnologyYunlinTaiwan 64002China

In recent years,the integration of stochastic techniques,especially those based on artificial neural networks,has emerged as a pivotal advancement in the field of computational fluid *** techniques offer a powerful framework for the analysis of complex fluid flow phenomena and address the uncertainties inherent in fluid dynamics *** this trend,the current investigation portrays the design and construction of an important technique named swarming optimized neuroheuristic intelligence with the competency of artificial neural networks to analyze nonlinear viscoelastic magneto-hydrodynamic Prandtl-Eyring fluid flow model,with diffusive magnetic layers effect along an extended *** currently designed computational technique is established using inverse multiquadric radial basis activation function through the hybridization of a well-known global searching technique of particle swarm optimization and sequential quadratic programming,a technique capable of rapid convergence *** most appropriate scaling group involved transformations that are implemented on governing equations of the suggested fluidic model to convert it from a system of nonlinear partial differential equations into a dimensionless form of a third-order nonlinear ordinary differential *** transformed/reduced fluid flow model is solved for sundry variations of physical quantities using the designed scheme and outcomes are matched consistently with Adam's numerical technique with negligible magnitude of absolute errors and mean square ***,it is revealed that the velocity of the fluid depreciates in the presence of a strong magnetic field *** efficacy of the designed solver is depicted evidently through rigorous statistical observations via exhaustive numerical experimentation of the fluidic problem.

关键词： PrandtleEyring fluid Particle swarm optimization Hydrodynamic Neural networks Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

SMNDNet for Multiple Types of Deepfake Image Detection

引用

computers, Materials & Continua 2025年第6期83卷 4607-4621页

作者： Qin Wang Xiaofeng Wang Jianghua Li Ruidong Han Zinian Liu Mingtao Guo Department of Computer Science and Engineering Xi’an University of TechnologyXi’an710048China Department of Mathematics Xi’an University of TechnologyXi’an710054China The National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan UniversityChengdu610065China

The majority of current deepfake detection methods are constrained to identifying one or two specific types of counterfeit images,which limits their ability to keep pace with the rapid advancements in deepfake ***,in this study,we propose a novel algorithm,StereoMixture Density Network(SMNDNet),which can detect multiple types of deepfake face manipulations using a single network *** is an end-to-end CNNbased network specially designed for detecting various manipulation types of deepfake face ***,we design a Subtle Distinguishable Feature Enhancement Module to emphasize the differentiation between authentic and forged ***,we introduce aMulti-Scale Forged Region AdaptiveModule that dynamically adapts to extract forged features from images of varying synthesis ***,we integrate a Nonlinear Expression Capability Enhancement Module to augment the model’s capacity for capturing intricate nonlinear patterns across various types of ***,these modules empower our model to efficiently extract forgery features fromdiverse manipulation types,ensuring a more satisfactory performance in multiple-types deepfake *** show that the proposed method outperforms alternative approaches in detection accuracy and AUC across all four types of deepfake *** also demonstrates strong generalization on cross-dataset and cross-type detection,along with robust performance against post-processing manipulations.

关键词： Convolutional neural network deepfake detection generative adversarial network feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Group decision making based on advanced interval-valued intuitionist fuzzy weighted averaging aggregation operator and score function of interval-valued intuitionist fuzzy values

引用

Information sciences 2023年第1期624卷 908-923页

This paper proposes a new group decision making (GDM) approach in the environments of interval-valued intuitionistic fuzzy values (IVIFVs). Firstly, we propose a new score function of IVIFVs, where the proposed score function of IVIFVs can overcome the drawbacks of the existing score function of IVIFVs. The properties of the proposed score function of IVIFVs are also presented. Then, we propose the advanced interval-valued intuitionist fuzzy averaging (AIVIFA) aggregation operator of IVIFVs. We also provide the proofs of the properties of the proposed AIVIFA aggregation operator. Then, we propose the advanced interval-valued intuitionist fuzzy weighted averaging (AIVIFWA) aggregation operator of IVIFVs. Then, we propose a new GDM approach based on the proposed AIVIFWA aggregation operator of IVIFVs and the proposed score function of IVIFVs. Finally, we apply the proposed GDM approach to deal with a real-world application of cloud service selection. The proposed GDM approach can overcome the drawbacks of the existing GDM approach, which is unable to distinguish the ranking orders of alternatives in some situations. The proposed GDM approach gives us a very useful way to deal with GDM problems in the environments of IVIFVs. © 2022 Elsevier Inc.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

EMA-Affinity: A Statistical Approach for Node Affinity Prediction in Dynamic Graphs 29

EMA-Affinity: A Statistical Approach for Node Affinity Predi...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Izadifar, Emad Rahmati, Zahed Davoodi, Amirehsan Department of Mathematics and Computer Science Amirkabir University of Technology Tehran Polytechnic Tehran Iran

ISBN: (纸本)9798331523114

Dynamic graphs serve as an abstract mathematical model applicable to various real-world scenarios, allowing the integration of complex temporal, structural, and relational patterns in data. To our knowledge, while much of the literature focuses on employing dynamic graph representation learning models for dynamic node classification or link prediction, the task of node affinity prediction-aimed at estimating a node’s affinity toward other nodes over time-has shown poor performance with these dynamic graph machine learning models. One of the open challenges in addressing this problem is designing a model that effectively considers the long-term dependencies between nodes for predicting node affinities. In this work, we propose EMA-affinity, a deterministic statistical model that utilizes exponential smoothing to account for long-term correlations between nodes in its predictions, thereby addressing this challenge. We evaluate and visualize EMA-affinity using the TGBN-trade benchmark dataset and demonstrate that it outperforms the current best (implemented) model, i.e. persistent forecast, for node affinity prediction, as measured by Normalized Discounted Cumulative Gain, and test the method’s robustness. Also, we present an analytic framework for the comparison of different models’ performance on different dynamic graph machine learning tasks. © 2025 IEEE.

关键词： Statistics

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：