检索结果-内蒙古大学图书馆

3rd IEEE International Conference on elec.ronic eng.neering, ICEEM 2023

作者： El-Sayed, Tharwat Mustafa, Abdallah El-Sayed, Ayman Elrashidy, Mohamed Menoufia University Faculty of Electronic Eng. Computer Science & Eng. Dept. Menouf32952 Egypt

ISBN: (纸本)9798350323511

It is becoming increasingly important for society to identify hate speech on social media. Differentiating hate speech from other instances involving offensive language is a significant difficulty for automatic hate speech tracking on social media. To distinguish between these categories, we train various classical machine learning models such as logistic regression, decision trees, random forest, naive Bayes, k-nearest neighbors, and support vector machines (SVM) - support vector classifier (SVC) on a dataset divided into three groups: those containing hate speech, those containing only offensive language, and those containing neither. From our practical trials, we found that the Logistic Regression algorithm and the SVM-SVC algorithm perform well in detecting hate speech and offensive language. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Bridging the Digital Divide: 6G Networks and Enabling Technologies for Ubiquitous Coverage

Bridging the Digital Divide: 6G Networks and Enabling Techno...

引用

2024 IEEE International Conference on Advanced Telec.mmunication and Networking Technologies, ATNT 2024

作者： Butt, Muhammad Omair Ferdouse, Lilatul Eiaz, Waleed Lakehead University Dept. of Elect. and Computer Eng. Thunder BayON Canada Wilfrid Laurier University Dept. of Physics and Computer Science WaterlooON Canada

ISBN: (纸本)9798350353501

Sixth-generation (6G) networks are expected to support an exponential increase in connected devices and address critical concerns such as capacity, coverage, and privacy. However, one significant concern is the digital divide, which refers to the difference in accessibility, availability, and usage of communication services between urban and rural areas. The COVID-19 pandemic has emphasized the need for reliable communication services in rural areas for economic inclusion in online education, remote work, and financial services. In this paper, we examine the three levels of the digital divide: coverage, access, and usage, and analyze suitable communication technologies to mitigate coverage issues and achieve ubiquitous service. Moreover, we explore enabling technologies that can help reduce global coverage gaps. Within this context, we provide a case study involving on-demand coverage and computational services provisioning in remote rural areas to demonstrate how such measures can harness the benefits of digital farming. Finally, we conclude the paper and present future research directions. © 2024 IEEE.

关键词： 6G networks coverage digital divide enabling technologies

来源：评论

学校读者我要写书评

暂无评论

GENERATIVE LEARNING FOR SIMULATION OF VEHICLE FAULTS

GENERATIVE LEARNING FOR SIMULATION OF VEHICLE FAULTS

引用

2024 Winter Simulation Conference, WSC 2024

作者： Kuiper, Patrick Lin, Sirui Blanchet, Jose Tarokh, Vahid Dept. of Electrical and Computer Eng. Duke University DurhamNC United States Dept. of Management Science and Eng. Stanford University StanfordCA United States

ISBN: (纸本)9798331534202

We develop a novel generative model to simulate vehicle health and forecast faults, conditioned on practical operational considerations. The model, trained on data from the US Army’s Predictive Logistics program, aims to support predictive maintenance. It forecasts faults far enough in advance to execute a maintenance intervention before a breakdown occurs. The model incorporates real-world factors that affect vehicle health. It also allows us to understand the vehicle’s condition by analyzing operating data, and characterizing each vehicle into discrete states. Importantly, the model predicts the time to first fault with high accuracy. We compare its performance to other models and demonstrate its successful training. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-based Trustworthy and Secure Review System for Decentralized e-Portfolio Platforms 14

A Blockchain-based Trustworthy and Secure Review System for ...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Merlec, Mpyana Mwamba Sinai, Nday Kabulo In, Hoh Peter Korea University Dept. of Computer Science and Eng. Seoul Korea Republic of

ISBN: (纸本)9798350313277

E-portfolios have emerged as powerful tools in the education and professional development fields, enabling learners to showcase their skills, achievements, and credentials in a digital format. However, ensuring the security, authenticity and reliability of e-portfolio artifacts and credentials remains a challeng.. Existing review systems face challeng.s such as lack of transparency, vulnerability to manipulation, and reliance on centralized trust. Therefore, this paper proposes B-TrustReview, a trustworthy and secure review system for decentralized e-portfolio platforms that leverages blockchain and smart contracts. By leveraging blockchain's decentralized and tamper-resistant nature, the system enhances the security, transparency, and reliability of reviews. Every review is securely recorded on the blockchain, creating an auditable and transparent record of evaluations. Smart contracts govern the execution of the review process, automating the validation and verification of reviews based on predefined criteria. This automation reduces reliance on intermediaries and minimizes the risk of biased or manipulated reviews fostering transparency, accountability, and credibility in evaluating e-portfolios. Moreover, it enables secure and efficient transactions, ensuring the confidentiality of user data and protecting against unauthorized access. © 2023 IEEE.

关键词： Blockchain Decentralized review system elec.ronic portfolio (e-portfolio) Reputation system Smart contract

来源：评论

学校读者我要写书评

暂无评论

Predicting DDoS Attacks: A Machine Learning Approach using ALDDoS Dataset 15

Predicting DDoS Attacks: A Machine Learning Approach using A...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shookdeb, Shantanu Muduli, Debendra Bhatta, Sandesh Adhikari, Aayush Sapkota, Aaron Chaturvedi, Prabhat C V Raman Global University Dept. of computer Science and Eng. Bhubaneswar India C V Raman Global University Dept. of computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350370249

The DDoS attack stands as Distributed Denial of Service attack refers a harmful effort to intercept on the regular traffic of a targeted web service or server. DDoS attack interferes with the normal network flow of the targeted server, potentially causing significant disruption to its *** send an incoming packet to every node except the arrived node,it used a non-adaptive routing algorithm. DDoS attacks are executed by using multiple compromised systems, which included combination of multiple computers system and other IoT device resources to make a large traffic on targeted network, rendering it inaccessible to legitimate users. In our study we experimented with various machine learning model like as RandomForest, DecisionTree, Xgbbost etc. with a high accuarcy of 99.99% to predict the DDoS attack with publicly available ALDDoS (Application-Layer DDoS) Dataset by Warda (Owner). © 2024 IEEE.

关键词： ALDDos Cyber defense DDoS RandomForest Web-proxy

来源：评论

学校读者我要写书评

暂无评论

Investigating the Performance of Different Machine Learning Models for Forecasting Li-ion Battery Core Temperature Under Dynamic Loading Conditions

Investigating the Performance of Different Machine Learning ...

引用

2024 IEEE International Conference on elec.ro Information Technology, eIT 2024

作者： Arafat, Kazi Abdullah Al Yousuf Bhuiyan, Sharif Md Mahamud, Rajib Parvez, Imtiaz Atish Dipankar Uni. of Sci. and Tech. Dept. of Computer Science and Engineering Dhaka Bangladesh Idaho State University Dept. of Mechanical Eng. PocatelloID83201 United States Utah Valley University Dept. of Computer Science and Eng. Dept. of Computer Sci. OremUT84058 United States

This study delves into the difficulties involved in managing heat, within lithium ion (Li ion) batteries for vehicles emphasizing the impact of temperature on battery performance and safety. It stresses the importance of maintaining temperatures to extend battery lifespan and boost efficiency. By employing machine learning (ML) methods to predict battery temperatures and optimize thermal management systems this research aims to enhance battery safety, performance and longevity. The study compares models like Recurrent Neural Networks (RNNs) Multi Layer Perceptrons (MLPs) and Linear Regression to evaluate their effectiveness in forecasting battery temperature under conditions. The results suggest that incorporating ML into battery management systems can result in efficient and safer operations for automotive applications. A detailed analysis of the three ML models-MLP, RNN and Linear Regression-is carried out for predicting battery temperatures. The main objective is to assess and contrast their accuracy in forecasting based on data. Simulation outcomes such as Mean Absolute Error (MAE) Coefficient of Determination (R2) and Root Mean Squared Error (RMSE) offer insights into each models performance across criteria. This study contributes towards advancing methodologies for predicting battery temperatures thereby improving decision-making processes, for energy management systems and related uses. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Gemini: Graph-based Versatile News Search eng.ne

Gemini: Graph-based Versatile News Search Engine

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Babu, Sharan Samudrala, Srikar Pulabaigari, Viswanath Padmanabha Reddy, Y.C.A. Babu, Ch.Madhu B v Raju Institute of Technology Dept. of Computer Science and Eng. NarsapurMedak Telangana India IIIT Sricity Dept. of Computer Science and Eng. Chittoor Andhra Pradesh India

ISBN: (纸本)9798350335835

Productivity and time value are always important in today's fast-paced world. It is especially true for tasks like 'News Search' where a consumer wants Fast access to events around the world, but in this event, Don't rush, be a fair and eclectic cause. This paper aims to show how the state-of-The-Art natural language processing techniques with a graph database can be used to de-duplicate redundant content from data sources and help readers to save time. A graph database uses a data model consisting of nodes, edges, and properties to store and retrieve data. In this paper, A specific schema used in this paper called the hypernode graph where the hyper-nodes connect to nodes that are relevant. These hypernodes are themselves linked by semantics. Similarity assessment offers innovative methods for modeling the News de-duplication problem in a scalable way. This work provides an extensible system that can easily extend for non-news use cases as well. © 2023 IEEE.

关键词： Search eng.nes

来源：评论

学校读者我要写书评

暂无评论

Enhancing DDoS Attack Detection: A Hybrid SVM-Decision Tree Ensemble Approach 15

Enhancing DDoS Attack Detection: A Hybrid SVM-Decision Tree ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Muduli, Debendra Bhatta, Sandesh Shookdeb, Shantanu Adhikari, Aayush Sapkota, Aaron Chaturvedi, Prabhat C. V. Raman Global University Dept. of Computer Science and Eng. Bhubaneswar India

ISBN: (纸本)9798350370249

A DDoS attack overwhelms a network or server with an excessive amount of traffic, disrupting its normal operation and rendering it inaccessible to legitimate users. DDoS attacks involve coordinated efforts from multiple compromised devices, known as botnets, flooding the target with traffic simultaneously. This flood of data exhausts the target's resources, causing service disruptions. Machine learning aids in DDoS attack detection by analyzing network traffic patterns. It learns to differentiate between normal and malicious activity by studying features such as packet rates, traffic volume, and protocol anomalies. By training on labeled datasets containing both benign and attack traffic, machine learning algorithms can identify deviations indicative of DDoS attacks, thereby enhancing network security. The hybrid machine learning model combines the precision of Support Vector Machines with the decision-making clarity of Decision Trees to effectively combat DDoS attacks. This innovative model achieves an impressive accuracy rate of 99.98% against the CICDDoS2019 dataset, demonstrating its exceptional performance in detecting various DDoS attack vectors. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Identifying Regulation with Adversarial Surrogates Algorithm

arXiv

引用

arXiv 2024年

作者： Teichner, Ron Meir, Ron Margaliot, Michael The Viterbi Dept. of Elec. & Computer Eng. Technion Israel Institute of Technology Israel The School of Elec. Eng. Tel-Aviv University 6997801 Israel

Given a time-series of noisy measured outputs of a dynamical system {zk}Nk=1, the Identifying Regulation with Adversarial Surrogates (IRAS) algorithm aims to find a non-trivial first integral of the system, namely, a scalar function g such that g(zi) ≈ g(zj), for all i, j. IRAS has been suggested recently and was used successfully in several learning tasks in models from biology and physics. Here, we give the first rigorous analysis of this algorithm in a specific setting. We assume that the observations admit a linear first integral and that they are contaminated by Gaussian noise. We show that in this case the IRAS iterations are closely related to the self-consistent-field (SCF) iterations for solving a generalized Rayleigh quotient minimization problem. Using this approach, we derive several sufficient conditions guaranteeing local convergence of IRAS to the linear first integral. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Survivability-Based Protection for Three Phase Permanent Magnet Synchronous Motor Drives

引用

IEEE Transactions on Industry Applications 2022年 1-8页

作者： Saleh, S.A. Ozkop, E. Nahid-Mobarakeh, B. Pradhan, S. Rubaai, A. Muttaqi, K.M. Dept. of Electrical & Computer Eng. UNB Fredericton NB Canada Electrical & Electronics Eng. KTU Trabzon Turkey Dept. of Electrical & Computer Eng. McMaster University Hamilton ON Canada Electrical Eng. & Computer Science Howard University Washington DC USA School of Electrical Computer Telecommunication Engineering Univ. of Wollongong New South Wales Australia

This paper develops a survivability-based protection for three phase permanent magnet synchronous motor drives against severe dynamic events. The proposed protection is based on defining a survivability index $\Gamma _{\text{PMSM}}$that is expressed in terms of power changes resulting from a dynamic event, which is experienced by the protected motor drive. The index $\Gamma _{\text{PMSM}}$ establishes an accurate measure to detect, identify, and respond to dynamic events that a three phase permanent magnet synchronous motor drive may not survive. The validity, effectiveness, and accuracy of the survivability-based protection for three phase permanent magnet synchronous motor drives are assessed through simulation and experimental testing. Assessment tests are carried out using a 10hp laboratory three phase permanent magnet synchronous motor drive under various dynamic events. Assessment results demonstrate the efficacy and responsiveness of the survivability-based protection to unsurvivable dynamic events, and its ability to prevent damage to different components of a three phase permanent magnet synchronous motor drive. IEEE

关键词： Transient analysis

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：