检索结果-内蒙古大学图书馆

International Conference on Electrical engineering and computer Science (ICECOS)

作者： Majid Rahardi Muhammad Rezzha Riamrizal Arsya Afrig Aminuddin Ferian Fauzi Abdulloh Mohammad Badrul Alam Miah Heri Pratikno Faculty of Computer Science Universitas Amikom Yogyakarta Sleman Indonesia Faculty of Engineering Mawlana Bhashani Science and Technology University Tangail Bangladesh Faculty of Technology and Informatics Universitas Dinamika Surabaya Indonesia

ISBN: (数字)9798350368253

ISBN: (纸本)9798350368260

The social media of X has become a focal point for discussions on sensitive issues, including the Israeli-Palestinian conflict. This research analyzes sentiment toward tweets expressing support for Palestine on X, comparing the Support Vector Machine (SVM) and Naïve Bayes methods. Given the global attention to the conflict, sentiment analysis on this topic is crucial. The results reveal that the SVM model outperforms Naïve Bayes, achieving accuracy, precision, recall, and F1-score of 85%, 87%, 85%, and 85% for Naïve Bayes, and 91%, 92%, 90%, and 90% for SVM, respectively. It demonstrates the SVM model's capability to distinguish between positive and negative sentiments. Comparison with previous research indicates that this study surpasses the sentiment analysis results of previous SVM models, while Naïve Bayes excels in specific research. With superior performance, this research provides a new contribution to recognizing and classifying sentiments on a particular dataset related to the Israeli-Palestinian conflict on X social media.

关键词： Support vector machines Electrical engineering Sentiment analysis Analytical models Accuracy Social networking (online) Machine learning Vectors Bayes methods Reliability

来源：评论

学校读者我要写书评

暂无评论

Multiclass Stomach Diseases Classication Using Deep Learning Features Optimization

引用

computers, Materials & Continua 2021年第6期67卷 3381-3399页

作者： Muhammad Attique Khan Abdul Majid Nazar Hussain Majed Alhaisoni Yu-Dong Zhang Seifedine Kadry Yunyoung Nam Department of Computer Science HITEC UniversityTaxila47040Pakistan College of Computer Science and Engineering University of Ha’ilHa’ilSaudi Arabia Department of Informatics University of LeicesterLeicesterUK Department of Mathematics and Computer Science Faculty of ScienceBeirut Arab UniversityLebanon Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

In the area of medical image processing,stomach cancer is one of the most important cancers which need to be diagnose at the early *** this paper,an optimized deep learning method is presented for multiple stomach disease *** proposed method work in few important steps—preprocessing using the fusion of ltering images along with Ant Colony Optimization(ACO),deep transfer learning-based features extraction,optimization of deep extracted features using nature-inspired algorithms,and nally fusion of optimal vectors and classication using Multi-Layered Perceptron Neural Network(MLNN).In the feature extraction step,pretrained Inception V3 is utilized and retrained on selected stomach infection classes using the deep transfer learning *** on,the activation function is applied to Global Average Pool(GAP)for feature ***,the extracted features are optimized through two different nature-inspired algorithms—Particle Swarm Optimization(PSO)with dynamic tness function and Crow Search Algorithm(CSA).Hence,both methods’output is fused by a maximal value approach and classied the fused feature vector by *** datasets are used to evaluate the proposed method—CUI WahStomach Diseases and Combined dataset and achieved an average accuracy of 99.5%.The comparison with existing techniques,it is shown that the proposed method shows signicant performance.

关键词： Stomach infections deep features features optimization fusion classication

来源：评论

学校读者我要写书评

暂无评论

Millimeter-Wave Gap Waveguide-Based Broadband Slant-Polarized Slot Array Antenna

Millimeter-Wave Gap Waveguide-Based Broadband Slant-Polarize...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Davood Zarifi Ali Farahbakhsh Michal Mrozowski Department of Microwave and Antenna Engineering Faculty of Electronics Telecommunications and Informatics Gdansk University of Technology Gdansk Poland School of Electrical and Computer Engineering University of Kashan Kashan Iran Department of Electrical and Computer Engineering Graduate University of Kerman Kerman Iran

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This research deals with the design of a broadband, slant-polarized antenna array for 26–40 GHz frequency band. The design employs gap waveguide technology to minimize unwanted energy leakage, ensuring high gain and efficiency. In this configuration, the radiating slots are angled at 45°, and a two-layer feed network, utilizing compact folded E-plane groove gap waveguide power dividers, is used to energize the slots. Key advantages of the proposed antenna array include its low profile, low loss, wide bandwidth, and suitability for millimeter-wave applications.

关键词： Power dividers Slot antennas Millimeter wave technology Optical device fabrication Gap waveguide Bandwidth Millimeter wave propagation Broadband communication Broadband antennas Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

Attackers Can Do Better: Over- and Understated Factors of Mo...

引用

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Daryna Oliynyk Rudolf Mayer Andreas Rauber CDL AsTra Faculty of Computer Science University of Vienna Vienna Austria SBA Research Vienna Austria Faculty of Informatics TU Wien Institute of Information Systems Engineering Vienna Austria

ISBN: (数字)9798331517113

ISBN: (纸本)9798331517120

Machine learning (ML) models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other attack methods, substitute model training is an all-encompassing attack applicable to any machine learning model whose behaviour can be approximated from input-output queries. Whereas previous works mainly focused on improving the performance of substitute models by, e.g. developing a new substitute training method, there have been only limited ablation studies that try to understand the impact the strength of an attacker has on the substitute model's performance. As a result, different authors came to diverse, sometimes contradicting, conclusions. In this work, we exhaustively examine the ambivalent influence of different factors resulting from varying the attacker's capabilities and knowledge on a substitute training attack. Our findings suggest that some of the factors that have been considered important in the past are, in fact, not that influential; instead, we discover new correlations between attack conditions and success rate. In particular, we demonstrate that better-performing target models enable higher-fidelity attacks and explain the intuition behind this phenomenon. Further, we propose to shift the focus from the complexity of target models toward the complexity of their learning tasks. Therefore, for the substitute model, rather than aiming for a higher architecture complexity, we suggest focusing on getting data of higher complexity and an appropriate architecture. Finally, we demonstrate that even in the most limited data-free scenario, there is no need to overcompensate weak knowledge with unrealistic capabilities in the form of millions of queries. Our results often exceed or match the performance of previous attacks that assume a stronger attacker, suggesting that these stronger attacks are likely endangering a model owner's intellectual property to a significantly higher degree than shown until now.

关键词： Training Correlation Query processing Focusing Intellectual property Data collection Data models Adversarial machine learning Complexity theory Tuning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Biofeedback: Enhancing Therapeutic Gaming for Stress Reduction

Harnessing Biofeedback: Enhancing Therapeutic Gaming for Str...

引用

IEEE International Conference on computer Communication and the Internet (ICCCI)

作者： Kristián Fodor Zoltán Balogh Molnár György Enikő Nagy Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary Department of Computer Science Faculty of Natural Sciences and Informatics Constantine the Philosopher University Nitra Slovakia John von Neumann Faculty of Informatics Obuda University Budapest Hungary

ISBN: (数字)9798350351767

ISBN: (纸本)9798350351774

The Internet of Things (IoT) technology has expanded in recent years and significantly influenced various areas of human activity, including healthcare and personal health. This research focuses on the application of IoT solutions for monitoring physiological functions in a virtual reality (VR) environment to create therapeutic applications for patients with phobias. Considering the developed state of IoT and its capabilities in data collection and analysis, the research focuses on the integration and use of these technologies to support physiotherapy. The importance of the work stems from the constant need for innovation in therapeutic approaches and the potential that IoT contributes to improving monitoring systems. The aim of the work is to create and implement a system for monitoring the physiological reactions of VR users and to evaluate their possible therapeutic benefits. The Samsung Galaxy Watch 5 smart watch and an Arduino microcontroller with sensors will be used. The contribution of the work lies in the development of integrated applications that help improve physiotherapy techniques and expand the understanding of human-computer interactions.

关键词： Cloud computing Databases Watches Software Real-time systems Libraries Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Network Congestion on IP and Named Data Network 16

Comparative Analysis of Network Congestion on IP and Named D...

引用

16th International Conference on Telecommunication Systems Services and Applications, TSSA 2022

作者： Arifin, Hasan Nur Syambas, Nana Rachmana Jupriyadi Sucipto, Adi Zaki Hamidi, Eki Ahmad School of Electrical and Informatics Engineering Institut Teknologi Bandung Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Uin Sunan Gunung Djati Bandung Electrical Engineering Department Bandung Indonesia

ISBN: (纸本)9781665455947

Today's data communication needs have shifted from client-server data communication to peer-to-peer. The user's focus is currently on the immediately requested data or the so-called Named Data Network (NDN). Changes to the nature of the app, user needs, and usage patterns have changed significantly, and apps on networks like YouTube, Facebook, and other social networks have revolutionized the idea of user- generated content. One of the problems in the network is network congestion or network failure. Network congestion occurs due to the need for network resources exceeding the capacity of network resources. When network congestion occurs, the NDN forwarding mechanism facilitated by FIB on the IP router cannot detect the congestion condition and will still use the same path. At the same time, the NDN router can detect congestion conditions and react by using alternative paths. The simulation results show that on the NDN router, the forwarding mechanism can maximize the use of link bandwidth faster than the forwarding mechanism on the router-based IP network. In the topology designed, NDN can achieve maximum bandwidth in the 3rd second compared to IP in the 5th second. © 2022 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

On the Improvements of Mouse Dynamics Based Continuous User Authentication

On the Improvements of Mouse Dynamics Based Continuous User ...

引用

IEEE International Conference on Information Reuse and Integration (IRI)

作者： Hayri Durmaz Mehmet Keskinöz Department of Computer Engineering ASELSAN Inc. and ITU Turkey Ankara Turkey Faculty of Computer and Informatics ITU Turkey Istanbul Turkey

Traditional authentication methods are vulnerable when users leave their devices unattended or if their credentials are compromised. In contrast, continuous authentication offers a perpetual strategy for user validation, ensuring that only authorized users access critical information throughout their entire usage. The problem of continuous authentication boils down to a binary classification task: determining whether the usage is legal or illegal. Deep learning presents a promising solution for this problem, although the use of convolutional neural networks (CNNs) in continuous authentication still has room for improvement. In this study, we employ residual learning to train and test a user authentication model. To further enhance the accuracy of the results, we implement a realistic augmentation method and employ a superior image mapping technique compared to existing literature. As a result, we achieve significantly more accurate results than those reported in the referenced studies. On average, our tests yield a False Accept Rate of 0.45 and a False Reject Rate of 0.34, which are 6.5 times better than the referenced studies. These findings demonstrate a substantial improvement in the usability and effectiveness of real-world cybersecurity applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Datalog-based Reasoning with Heuristics over Knowledge Graphs 4

Datalog-based Reasoning with Heuristics over Knowledge Graph...

引用

4th International Workshop on the Resurgence of Datalog in Academia and Industry, Datalog-2.0 2022

作者： Baldazzi, Teodoro Benedetto, Davide Brandetti, Matteo Vlad, Adriano Bellomarini, Luigi Sallinger, Emanuel Università Roma Tre Department of Computer Science and Engineering Rome Italy TU Wien Faculty of Informatics Vienna Austria University of Oxford Department of Computer Science Oxford United Kingdom Banca d'Italia Italy

Datalog+/- has recently emerged as a family of powerful languages for ontological reasoning on knowledge graphs (KGs). Yet, performing reasoning tasks on real-world scenarios that feature large inputs and recursions, e.g., answering Boolean Conjunctive Queries (BCQs), can be very onerous even for modern Datalog-based systems. To tackle this problem, we introduce a novel reasoning technique that adopts heuristic search strategies to guide the evaluation of Datalog+/- programs and optimize BCQ answering. We apply our methodology to efficiently solve time- and space-demanding tasks on financial KGs. © 2022 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Security Framework for Metaverse: A Decentralized Approach 15

Blockchain-based Security Framework for Metaverse: A Decentr...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Rajawat, Anand Singh Goyal, S.B. Solanki, RamKumar Raboaca, Maria Simona Mihaltan, Traian Candin Illes, Zoltan Verma, Chaman School of Computer Science & Engineering Sandip University Nashik India City University Faculty of Information Technology Petaling Jaya Malaysia Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Icsi Energy Department National Valcea Romania Technical University of Cluj-Napoca Faculty of Building Services Cluj-Napoca40033 Romania Eötvös Loránd University Faculty of Informatics Department of Media and Educational Informatics Budapest Hungary

ISBN: (纸本)9798350321388

People can act out fake social exchanges in the Metaverse, which is an online community. Security has become a problem in the Metaverse because there are so many online transactions and digital assets. In this thesis, a Blockchain-based security system for the Metaverse is proposed. This would be a decentralised way to keep the virtual world safe. Our system uses Blockchain's autonomous structure to make sure that all financial transactions in the Metaverse are safe, anonymous, and true. We suggest a new consensus process that combines Proof of Stake (PoS) and Proof of Authority (PoA) to make networks safer and allow them to grow. We also have a user-focused, decentralised identity management system that keeps their information safe. We also suggest a way to process Metaverse transactions safely that is based on smart contracts. Our method makes sure that transactional proof, recording, and validation are done in a safe and reliable way. We also show a reputation system that benefits people who follow the law and punishes people who break the law. Lastly, we test how well our suggested structure works with simulations and real-world tests. The results show that our way works to reduce possible security risks in the Metaverse and create a safe, scalable environment for online business. Overall, our Blockchain-based Security Framework for Metaverse: A Decentralised Approach is a good way to keep the security and privacy of digital activities in Metaverse. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Analysis of the effectiveness of the optimization processes of trans active power system management with distributed multi-purpose energy resources

Analysis of the effectiveness of the optimization processes ...

引用

2024 International Conference on Artificial Intelligence, computer, Data Sciences, and Applications, ACDSA 2024

作者： Khilenko, Volodymyr Bielokha, Halyna Denysiuk, Serhii Stepanov, Oleksii Kotuliak, Ivan Slovak University of Technology in Bratislava Institute of Computer Engineering and Applied Informatics Faculty of Informatics and Information Technologies Bratislava Slovakia National Technical University of Ukraine "igor Sikorsky Kyiv Polytechnic Institute" Power Supply Department Kyiv Ukraine National University of Life and Environmental Sciences Ukr Article Acdsa Department of Information Technologies Khilenko ID 414 Kyiv09-02-2024 Ukraine

ISBN: (纸本)9798350394528

The article the efficiency of the Microgrid network when transitioning to a transactive power system that uses control algorithms called to optimize the distribution of power between sources of distributed generation and to minimize the time of decision-making about mode switching and at the corresponding change of the power system architecture. Tables and graphs of the conducted modeling are presented and the efficiency of this control-optimized system is calculated in comparison with the power system where uniform distribution of load power is used. © 2024 IEEE.

关键词： Distributed power generation

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：