检索结果-内蒙古大学图书馆

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Andreas Kanavos Ioannis Karamitsos Alaa Mohasseb Vassilis C. Gerogiannis Department of Informatics Ionian University Corfu Greece Department of Graduate and Research Rochester Institute of Technology Dubai UAE School of Computing University of Portsmouth Portsmouth UK Department of Digital Systems University of Thessaly Larissa Greece

The detection of fake news is a crucial task in today's society, given the widespread use of social media and online platforms. In this study, we investigate the application of Machine Learning (ML) algorithms for the detection of fake news. We consider two different datasets of categorized news articles of various sizes and apply various ML algorithms, along with two methods of text vectorization. Specifically, we examine Bag of Words and Tf-Idf, with the use of stemming and with different n-gram values. The resulting vectors are processed by Naive Bayes algorithms, Linear algorithms, Support Vector Machines, and Random Forest classifiers. F1-score and computational time for each algorithm-vectorization combination were recorded. Our results have shown that Linear Algorithms and Support Vector Machines combined with Tf-Idf vectors and n-gram value of (1,2) produced the highest accuracies, with an F1-score up to 96.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MaskViM: Domain Generalized Semantic Segmentation with State Space Models 39

MaskViM: Domain Generalized Semantic Segmentation with State...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Jiahao Lu, Yang Xie, Yuan Qu, Yanyun School of Informatics Xiamen University China Institute of Artificial Intelligence Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computer Science and Technology East China Normal University China Chongqing Institute of East China Normal University China

ISBN: (纸本)157735897X

Domain Generalized Semantic Segmentation (DGSS) aims to utilize segmentation model training on known source domains to make predictions on unknown target domains. Currently, there are two kinds of network architectures: one based on Convolutional Neural Networks (CNNs) and the other based on Visual Transformers (ViTs). However, both CNN-based and ViT-based DGSS methods face challenges: the former lacks a global receptive field, while the latter requires more computational demands. Drawing inspiration from State Space Models (SSMs), which not only possess a global receptive field but also maintain linear complexity, we propose SSM-based method for achieving DGSS. In this work, we first elucidate why does mask make sense in SSM-based DGSS and propose our mask learning mechanism. Leveraging this mechanism, we present our Mask Vision Mamba network (MaskViM), a model for SSM-based DGSS, and design our mask loss to optimize MaskViM. Our method achieves superior performance on four diverse DGSS setting, which demonstrates the effectiveness of our method. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis and Research Landscape of Artificial Intelligence in Education 14

A Bibliometric Analysis and Research Landscape of Artificial...

引用

14th IEEE International Conference on Control System, computing and Engineering, ICCSCE 2024

作者： Ajibade, Samuel-Soma M. Issa, Bayan Jasser, Muhammed Basheer Hassan, Farrukh Aldharhani, Ghassan Saleh Al-Hadi, Ismail Ahmed Al-Qasem Akintoye, Kayode Akinlekan Tabuena, Almighty Cortezo School of Engineering and Technology Sunway University Department of Computing and Information Systems No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia Istanbul Ticaret University Department of Computer Engineering Istanbul Turkey University of Aleppo Faculty of Informatics Engineering Syria Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia UKM University Faculty of Information Science and Technology Selangor Bangi Malaysia The Federal Polytechnic Department of Computer Science Ado Ekiti Ekiti State Nigeria University of the City of Valenzuela College of Arts and Sciences Philippines

ISBN: (纸本)9798350364507

This study examines the academic field of Artificial Intelligence in Education (AI-ED) by examining the publications and indexed documents in Scopus from 2010 to 2023. Consequently, we examined the publishing trends, exemplary articles, and the most engaged participants and funding institutions in the domain of AI-ED research. A bibliometric analysis was performed to examine the network of co-authorships, keywords, and citations in the domain of AIED research. The Scopus search resulted in the discovery of 10,474 published documents on AI-ED. Additionally, trends analysis indicated a significant increase of over 3,000% in publications between 2010 and 2023. Conference papers are the most often utilized document type, including 6757 publications or 64.5% of the overall amount. The ACM International Conference Proceeding Series is the primary source for published materials, accounting for 675 publications or 6.44% of the total publications on the topic. The most prolific researchers in the field of AI-ED are Breazeal, C and Chai C.S, each having published 18 documents. Additionally, the two institutions that have produced the highest number of published documents are Carnegie Mellon University (CMU) and the University of NC State University (NCSU). The output of the affiliations active in the topic is primarily attributed to the funders, specifically the National Science Foundation, which is the leading funding institution based in the United States and has contributed to 354 publications. An analysis of keyword co-occurrence revealed 6 main study areas that cover the essential tools, theories, methodologies, and socioeconomic and financial aspects of artificial intelligence in education (AIED). Future research in the field of artificial intelligence in education will focus on employing sophisticated deep learning, machine learning, and neural network algorithms to precisely predict students' learning patterns. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Non-Linear Model Predictive Speed Control of Six Phase Squirrel Cage Generator in Wind Energy System 6

Non-Linear Model Predictive Speed Control of Six Phase Squir...

引用

6th IEEE International Conference on Electrical, Electronics and System Engineering, ICEESE 2023

作者： Umar Musa, Ibrahim Abdulwahab Sarip, Shamsul Mas'Ud, Abdullahi Abubakar Muhammad-Sukki, Firdaus Faskari, Shehu A. Mahmud, Abubakar T. Electical Engineering Ahmadu Bello University Zaria Nigeria Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Kuala Lumpur Malaysia Jubail Industrial College Department of Electical Engineering Jubail Saudi Arabia School of Computing Engineering and the Built Environment Edinburgh Napier University Scotland Edinburgh United Kingdom Electrical Engineering Baze University Abuja Nigeria Hydraulic Equipment Development Institute NASENI Abuja Nigeria

ISBN: (纸本)9781665453714

Due to the intermittent nature of wind, varying wind speed causes imbalance in the current of the six phase squirrel cage induction generator (SCIG). These changes in the input signal create inbalance in the current and therefore causes deviations in the torque and flux of the generator. Therefore, this work develops non-linear model predictive control (NMPC) scheme for the generator to ensure that uncertainties in the input of the wind energy conversion system (WECS) have little effect in the quality of output power supplied to the grid. Simulation results obtained when NMPC technique was used in controlling the generator in the WECS showed the effectiveness of the aforementioned technique. The results obtained from the developed scheme were compared with those obtained when backstepping controller was used in controlling the six phase SCIG. It was observed that the developed scheme outperformed the backstepping technique in terms of electromagnetic torque by 16.844%, while a 61.1% improvement was observed in terms of settling time for the rotor flux of the developed technique over that of the backstepping. Finally, the results obtained for the DC link voltage output showed an improvement in terms of overshoot and settling time respectively. © 2023 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Robustness modularity in complex networks

引用

Physical Review E 2022年第5期105卷 054308-054308页

作者： Filipi N. Silva Aiiad Albeshri Vijey Thayananthan Wadee Alhalabi Santo Fortunato Indiana University Network Science Institute (IUNI) Bloomington Indiana 47408 USA Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Kingdom of Saudi Arabia Luddy School of Informatics Computing and Engineering Indiana University Bloomington Indiana 47408 USA

A basic question in network community detection is how modular a given network is. This is usually addressed by evaluating the quality of partitions detected in the network. The Girvan-Newman (GN) modularity function is the standard way to make this assessment, but it has a number of drawbacks. Most importantly, it is not clearly interpretable, given that the measure can take relatively large values on partitions of random networks without communities. Here we propose a measure based on the concept of robustness: modularity is the probability to find trivial partitions when the structure of the network is randomly perturbed. This concept can be implemented for any clustering algorithm capable of telling when a group structure is absent. Tests on artificial and real graphs reveal that robustness modularity can be used to assess and compare the strength of the community structure of different networks. We also introduce two other quality functions: modularity difference, a suitably normalized version of the GN modularity, and information modularity, a measure of distance based on information compression. Both measures are strongly correlated with robustness modularity, but have lower time complexity, so they could be used on networks whose size makes the calculation of robustness modularity too costly.

关键词： Community structure Complex systems Robustness

来源：评论

学校读者我要写书评

暂无评论

K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach 39

K-hop Hypergraph Neural Network: A Comprehensive Aggregation...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xie, Linhuang Gao, Shihao Liu, Jie Yin, Ming Jin, Taisong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China School of Information Science North China University of Technology China China Language Intelligence Research Center Capital Normal University China School of Electronic Science and Engineering South China Normal University China

ISBN: (纸本)157735897X

The powerful capability of HyperGraph Neural Networks (HGNNs) in modeling intricate, high-order relationships among multiple data samples stems primarily from their ability to aggregate both the direct neighborhood features of individual nodes and those associated with hyperedges. However, the limited scope of feature propagation in existing HGNNs significantly reduces the utilization of hypergraph information, exacerbating over-squashing and over-smoothing issues. To this end, we propose a novel K-hop HyperGraph Neural Network (KHGNN) to facilitate the interactions of distant nodes and hyperedges. Specifically, the bisection nested convolution based on HyperGINE is employed to extract features from nodes, hyperedges, and structures along all shortest paths between nodes or hyperedges, providing representations of long-distance relationships. With these comprehensive path features, nodes and hyperedges are guided to aggregate distant information while learning their complex relationships. The extensive experiments, particularly on long-range graph datasets, demonstrate that the proposed method achieves SOTA performance compared to existing HGNNs and graph neural networks. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Resource-Aware Deep Collaborative Learning Towards Secure B5G-Driven IoT-Fog-Based Consumer Electronic Systems

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Tripathy, Subhranshu Sekhar Bebortta, Sujit Chakraborty, Chinmay Senapati, Dilip Pani, Subhendu Kumar Guduri, Manisha School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of Computer Science Ravenshaw University Cuttack Odisha India Department of Electronics and Communication Engineering Birla Institute of Technology Jharkhand India Department of Computer Science University of Delhi Delhi India Kausalya Ganga Bhubaneswar Odisha India School of Computing and Informatics University of Louisiana at Lafayette LA USA

The integration of Fog computing and 5G communication may enhance Cyber Physical Systems (CPSs) for effective time identification of cyber attacks among consumer electronics. An unsupervised Intrusion Detection System (IDS) based on Generative Adversarial Networks (GANs) and Recurrent Neural Networks (RNNs) is presented in this study. This system is tailored to the resource limitations of consumer electronics within CPSs. By leveraging the processing power of fog nodes and the low-latency capabilities of 5G networks, cyber attacks can be swiftly identified. The use of a trained Long Short-Term Memory (LSTM) network encoder improves detection rates by enhancing reconstruction loss computation. Experimental results demonstrate that this approach, implemented through distributed fog computing infrastructure, offers better detection rates with a 15.2% reduction in detection latency and a 24.2% decrease in overall energy consumption compared to baseline methods. This innovative system could serve as an effective alternative for securing consumer electronic devices integrated into CPSs. IEEE

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Routing of Data Between the Nodes in Mobile Adhoc Networks using Machine Learning Modelling

Routing of Data Between the Nodes in Mobile Adhoc Networks u...

引用

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Ramesh Babu, P Ranjan Nayak, Nihar Meenakshi, K Das, Saswata Selvakanmani, S. Ananda Kumar, K S Wollega University College of Engineering Technology Department of Computer Science Nekemte Ethiopia Department of Mca Andhra Pradesh Chittoor India Department of Mathematics Bengaluru India Cognizant Technology Solutions India Pvt. Ltd. West Bengal Kolkata India Velammal Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Dilla University School of Computing and Informatics College of Engineering and Technology Snnpr Dilla Ethiopia

ISBN: (纸本)9781665484251

The routing of data between the packets in mobile adhoc networks has severe limitations that involves communication and computational overhead, which has to be reduced for effective transmission of data packets. In this paper, we develop a machine learning assisted routing mechanism that has three different modules to serve the purpose of reduced overhead during routing. The study uses genetic algorithm to resolve the routing constraints between the source and destination nodes. The modelling is specifically designed to overcome the limitations associated with the generation of overheads. The simulation is conducted to test the efficacy of the models against various existing mechanisms. The results of simulation shows that the proposed method achieves higher rate of packet delivery rate, throughput and reduced delay. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Blockchain with Optimal Deep Learning Model for Smart Cities

引用

Computers, Materials & Continua 2022年第12期73卷 5299-5314页

作者： K.Pradeep Mohan Kumar Jenifer Mahilraj D.Swathi R.Rajavarman Subhi R.M.Zeebaree Rizgar RZebari Zryan Najat Rashid Ahmed Alkhayyat Department of Computing Technologies SRM Institute of Science and TechnologyKattankulathurChennai603203India Department of Computer Science and Information Technology School of Engineering and TechnologyKebridehar UniversityKebridehar250Ethiopia Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTiruchirappalli621112India Energy Department Technical College of EngineeringDuhok Polytechnic UniversityDuhokIraq Computer Science Department College of ScienceNawroz UniversityDuhokIraq Computer Network Department Technical College of InformaticsSulaimani Polytechnic UniversitySulaimaniIraq College of Technical Engineering The Islamic UniversityNajafIraq

Recently,smart cities have emerged as an effective approach to deliver high-quality services to the people through adaptive optimization of the available *** the advantages of smart cities,security remains a huge challenge to be ***,Intrusion Detection System(IDS)is the most proficient tool to accomplish security in this ***,blockchain exhibits significance in promoting smart city designing,due to its effective characteristics like immutability,transparency,and *** order to address the security problems in smart cities,the current study designs a Privacy Preserving Secure Framework using Blockchain with Optimal Deep Learning(PPSF-BODL)*** proposed PPSFBODL model includes the collection of primary data using sensing ***,z-score normalization is also utilized to transform the actual data into useful ***,Chameleon Swarm Optimization(CSO)with Attention Based Bidirectional Long Short TermMemory(ABiLSTM)model is employed for detection and classification of *** is employed for optimal hyperparameter tuning of ABiLSTM *** the same time,Blockchain(BC)is utilized for secure transmission of the data to cloud *** cloud server is a decentralized,distributed,and open digital ledger that is employed to store the transactions in different methods.A detailed experimentation of the proposed PPSF-BODL model was conducted on benchmark dataset and the outcomes established the supremacy of the proposed PPSFBODL model over recent approaches with a maximum accuracy of 97.46%.

关键词： Blockchain smart city security intrusion detection system chameleon swarm optimization deep learning parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Gradient Descent and Sea Lion Optimization Algorithm (H-GD-SLnO) to Optimize Task Scheduling in Fog computing Environment

Hybrid Gradient Descent and Sea Lion Optimization Algorithm ...

引用

Advanced computing Technologies (ICoACT), International Conference on

作者： Rakesh Premkumar N. Jagadish Kumar L Maria Michael visuwasam Gopalakrishnan Arjunan A. Vinothini C. Tharun Kumar School of informatics and computing Indiana University Bloomington USA Dept of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chennai Tamil Nadu India Dept of AI & DS RMK College of engineering and technology Puduvoyal Chennai Accenture Bangalore India Dept of CSE Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Tamil Nadu India Dept of CSBS Sri Sai Ram Engineering college Chennai Tamil Nadu India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

The architectures associated with cloud and fog computing are fundamentally important for the decentralization of computational tasks, as they facilitate the efficient processing of various user demands while simultaneously supporting extensive Internet of Things (IoT) networks that are increasingly prevalent in today's technological landscape. As the complexity and scale of computational loads continue to expand at a rapid pace, it becomes imperative to implement effective task scheduling mechanisms across these heterogeneous architectures, as this is vital for the optimization of resource utilization and the significant reduction of latency that can adversely affect system performance. This Paper centers on optimization, highlighting the novel integration of Gradient Descent (GD) and the Sea Lion Optimization Algorithm (SLnO). It proposes a harmonious methodology for addressing task scheduling challenges in Fog computing by utilizing the accuracy of GD for localized searches and the exploratory strengths of SLnO for overarching optimization. The hybrid methodology (H-GD-SLnO) was evaluated using synthetic datasets and real grid workloads, including DAS-2 and AuverGrid, as well as Hadoop tasks like Terasort. The simulation outcomes reveal that (H-GD-SLnO) surpasses numerous pre-existing algorithms, realizing reductions in mean job completion time as well as average scheduling delay and enhancements in resource utilization and throughput. These results emphasize the efficacy of our proposed methodology in meeting the rigorous task scheduling demands within cloud and fog computing environments.

关键词： Cloud computing Processor scheduling Throughput Virtual machines Scheduling Resource management Internet of Things Marine animals Optimization Edge computing

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：