检索结果-内蒙古大学图书馆

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Ghezaiel Hammouda, Nadia Toujani, Radhia College of Computer Science and Software Engineering University of Hail Hail Saudi Arabia ESTMOD Department Higher Institute of management University of Tunis Tunisia

Machine learning techniques, particularly fuzzy Support Vector Machines (fuzzy SVM), have demonstrated effectiveness in sentiment classification within social networks. However, the evolving complexity of social networks content and the necessity to handle diverse opinions prompt ongoing advancements in sentiment analysis methodologies. In this study, we propose an innovative approach by integrating a Convolutional Neural Network (CNN) model with fuzzy SVM. Our key contribution lies in the fusion of these two methodologies, capitalizing on the strengths of fuzzy SVM for opinion mining and CNN for extracting intricate features. Additionally, we extend this method to enable multi-class opinion classification, allowing for a finer understanding of nuances in expressed sentiments. Through evaluation on benchmark datasets, we highlight a notable improvement in performance compared to baseline methods. The results underscore the enhanced generalization capabilities and increased accuracy in opinion classification offered by our hybrid model, rendering it a promising asset for decision-making applications based on multi-opinion analysis. © 2024 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Care Assessment for Daily Living Using Machine Learning Mechanism

引用

computers, Materials & Continua 2022年第7期72卷 1747-1764页

作者： Mouazma Batool Yazeed Yasin Ghadi Suliman A.Alsuhibany Tamara al Shloul Ahmad Jalal Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Humanities and Social Science Al Ain UniversityAl Ain15551UAE Department of Computer Engineering Korea Polytechnic University237 Sangidaehak-ro Siheung-siGyeonggi-do15073Korea

Nowadays,activities of daily living(ADL)recognition system has been considered an important field of computer *** and optical sensors are widely used to assess the daily living activities in healthy people and people with certain *** conventional ADL utilizes RGB optical sensors but an RGB-D camera with features of identifying depth(distance information)and visual cues has greatly enhanced the performance of activity *** this paper,an RGB-D-based ADL recognition system has been ***,human silhouette has been extracted from the noisy background of RGB and depth images to track human movement in a *** on these silhouettes,full body features and point based features have been extracted which are further optimized with probability based incremental learning(PBIL)***,random forest classifier has been used to classify activities into different *** n-fold crossvalidation scheme has been used to measure the viability of the proposed model on the RGBD-AC benchmark dataset and has achieved an accuracy of 92.71%over other state-of-the-art methodologies.

关键词： Angular geometric features decision tree classifier human activity recognition probability based incremental learning ridge detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of Techniques for Detection and Removal of Zero-Day Attacks (ZDA) 2nd

Analysis of Techniques for Detection and Removal of Zero-Day...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Hamid, Khalid Iqbal, Muhammad Waseem Aqeel, Muhammad Liu, Xiangyong Arif, Muhammad Department of Software Engineering The Superior University Lahore54000 Pakistan Department of Computer Science The Superior University Lahore54000 Pakistan School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China

ISBN: (纸本)9789819902712

Zero-day attacks (ZDAs) are previously unknown flaws and errors in operating systems, networks, and general-purpose software. ZDAs are the cause to open security breach holes for external users or hackers for illegal operations before patches. ZDAs are different from viruses, worms and Trojans. They are very difficult to detect and remove because they are unknown to users and even programmers. Conventional defense systems are useless against such types of attacks. This paper investigates the zero-day attacks, their vulnerabilities, the intensity of these attacks and the reasons in a real-time environment. Different techniques are compared to investigate ZDAs. The hybrid technique has been used to check the behavior of data traffic coming from outside the world in the virtual environment for zero-day attacks. Static check tools (MD5 Checksum, AV-Suite, and SOPHOS) and behavioral check tools (SANDBOX) have been used for the verification and validation of results. The second comparatively best technique is Machine Learning-Based Technique which showed the best results. The results show how to choose the best solution against zero-day attacks in the real-time environment of the software. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Classification of Unbalanced Data Based on Bayesian Optimal Neural Network Model

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1427-1440页

作者： Ye, Li-Zhu Alkawaz, Mohammed Hazim Johar, Md Gapar Md School of Information Technology and Engineering Guangzhou College of Commerce Guangzhou511363 China School of Graduate Studies Management and Science University 40100 Shah Alam Selangor Malaysia Department of Computer Science College of Education for Pure Science University of Mosul Mosul41002 Iraq Software Engineering and Digital Innovation Center Management and Science University Shah Alam40100 Malaysia

Aiming at the unbalanced problem of big data classification, this paper proposes a classification method of unbalanced data on the ground of Bayesian optimal neural network model. The method firstly uses Optimized Graph Convolutional Network (OGCN) network to carry out message passing mechanism in data graph, designs neural network model with self-attention pooling and mean maximization pooling, and then uses Bayes optimization to update the posterior probability of optimization function by constantly updating the probability model and evaluating the objective function. Effectively solve the problem of speed and optimal solution of hyperparameter optimization in the neural network model. Secondly, the model is used for data set training to obtain the weight of the entire network. Secondly, the unbalanced data is mixed sampling to reduce the number of negative samples. Finally, the capability of the model was verified on the CiteSeer dataset. Experimental results showed that the accuracy rate, accuracy rate and recall rate of the proposed algorithm were 0.974, 0.982 and 0.973, respectively, which effectively improved the accuracy rate, accuracy rate and recall rate of unbalanced data classification compared with other algorithms. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Anomaly-based network intrusion detection using Transfer learning 2

Anomaly-based network intrusion detection using Transfer lea...

引用

2nd International Conference on Multidisciplinary engineering and Applied science, ICMEAS 2023

作者： Ola-Obaado, Similoluwa Suleiman, Muhammad Aliyu Nile University of Nigeria Computer Science Department Abuja Nigeria Nile University of Nigeria Software Engineering Department Abuja Nigeria

ISBN: (纸本)9798350358834

The rapid development of computer networks and network applications, along with the present global increase in hacking and computer network attacks, has increased the demand for stronger intrusion detection and prevention solutions. The intrusion detection system (IDS) is crucial in detecting irregularities and attacks on the network, which has expanded in size and pervasiveness. In this paper, we develop an intrusion detection system based on deep learning and leverage a recent security dataset, CSE-CIC-IDS2018, to implement a more realistic IDS. We proposed an approach for network intrusion detection using Transfer learning to address both the binary and multiclass classification of network attacks. Network features from the dataset are transformed into grayscale images, the images are used as input to the ResNet50 deep learning model. The dataset is imbalanced, therefore, to increase the generalization of model, the imbalance ratio is reduced by using a synthetic data generation model called Synthetic Minority Oversampling Technique (SMOTE). Experimental results show that our model achieves good performance for both binary and multiclass classification with accuracy of 92 percent for each case. The proposed approach provides a new method for intrusion detection using transfer learning and SMOTE for correcting data imbalance. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

K-Banhatti Sombor Invariants of Certain computer Networks

引用

computers, Materials & Continua 2022年第10期73卷 15-31页

作者： Khalid Hamid Muhammad Waseem Iqbal Abaid Ur Rehman Virk Muhammad Usman Ashraf Ahmed Mohammed Alghamdi Adel A.Bahaddad Khalid Ali Almarhabi Department of Computer Science Superior UniversityLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Department of Mathematics University of SialkotSialkot51013Pakistan Department of Computer Science GC Women UniversitySialkot53310Pakistan Department of Software Engineering College of Computer Science and EngineeringUniversity of Jeddah21493Saudi Arabia Department of Information System Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computing in Al-QunfudahUmm Al-Qura UniversityMakkah24381Saudi Arabia

Any number that can be uniquely determined by a graph is called a graph *** the last twenty years’countless mathematical graph invariants have been characterized and utilized for correlation ***,no reliable examination has been embraced to decide,how much these invariants are related with a network graph or molecular *** this paper,it will discuss three different variants of bridge networks with good potential of prediction in the field of computer science,mathematics,chemistry,pharmacy,informatics and biology in context with physical and chemical structures and networks,because k-banhatti sombor invariants are freshly presented and have numerous prediction qualities for different variants of bridge graphs or *** study solved the topology of a bridge graph/networks of three different types with two invariants KBanhatti Sombor Indices and its reduced *** deduced results can be used for the modeling of computer networks like Local area network(LAN),Metropolitan area network(MAN),and Wide area network(WAN),backbone of internet and other networks/structures of computers,power generation,bio-informatics and chemical compounds synthesis.

关键词： Bridge networks invariants k-banhatti sombor indices maple network graph molecular graph

来源：评论

学校读者我要写书评

暂无评论

Secure Consumer-Centric Demand Response Management in Resilient Smart Grid as Industry 5.0 Application with Blockchain-Based Authentication

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 1370-1379页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Omar, Marwan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Illinois Institute of Technology Information Technology and Management ChicagoIL60616 United States

The development of the industrial Internet of Things and smart grid networks has emphasized the importance of secure smart grid communication for the future of electric power transmission. However, the current deployment of smart meters and wireless communication methods presents several security concerns that must be addressed to ensure sustainable and resilient smart grid networks for Industry 5.0, with a focus on consumer-centric technologies. In this context, we propose a privacy-focused authentication solution for secure consumer-centric demand response management in smart grid networks, incorporating consumer electronics. Our proposed protocol utilizes blockchain-based authentication to enhance resistance against potential attacks and ensure the integrity of demand response data. Additionally, we have incorporated a PUF to prevent physical attacks. We have conducted informal and formal security analyses to verify the effectiveness of our proposed protocol against various threats and to confirm the session key security. Our comparison study has demonstrated that our protocol provides superior security and added functionalities, with lower computation and communication costs compared to similar protocols. Furthermore, we have measured the computational time for implementing the blockchain component of our protocol while considering the impact of varying numbers of block additions and transactions per block. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations 41

Imitation Learning from Purified Demonstrations

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

引用

computer Modeling in engineering & sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu Fayez Alqahtani Amr Gafar Pradip Kumar Sharma Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangfor Technologies Inc. Shenzhen518055China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325035China College of Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of *** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model *** experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

关键词： Mobile authentication blockchain federated learning smart contract certificateless encryption VMD LSTM

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of Advance Deep Learning Architectures for Classification of Stress using Raw EEG Data

The Effectiveness of Advance Deep Learning Architectures for...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Tibrewal, Ayush Shikha Sethia, Divyashikha Delhi Technological University Department of Applied Physics Delhi India Delhi Technological University Science and Engineering Department of Computer Delhi India Delhi Technological University Department of Software Engineering Delhi India

ISBN: (纸本)9798350361537

Understanding and detecting stress in today's fast-paced world remains challenging. Previous research has explored various physiological signals, including EEG (Electroencephalography), to quantify stress. However, accurately assessing stress poses a significant challenge, particularly in preprocessing and feature extraction of EEG signals. Hence, this paper employs advanced deep learning algorithms, including ResNet18-1D, DenseNet-1D, and VGG16-1D, on raw EEG signals for automated stress classification. The study utilizes the publicly available EEG-based SAM40 dataset for stress classification and further validates the results on the EEG-based MAT dataset. The results demonstrate the efficacy of the ResNet18-1D model by achieving the highest of 98.73% and 97.24% on the SAM40 and MAT datasets, respectively. The findings pave the way for further exploration and utilization of raw EEG signals across diverse research domains beyond stress classification. © 2024 IEEE.

关键词： Electroencephalography

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：