检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Acs, Judit Hamerlik, Endre Schwartz, Roy Smith, Noah A. Kornai, Andras Budapest Hungary Budapest University of Technology and Economics Budapest Hungary Department of Applied Informatics Comenius University in Bratislava Faculty of Mathematics Physics and Informatics Bratislava Slovakia Hebrew University of Jerusalem Jerusalem Israel Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Allen Institute for Artificial Intelligence SeattleWA United States

We introduce an extensive dataset for multilingual probing of morphological information in language models (247 tasks across 42 languages from 10 families), each consisting of a sentence with a target word and a morphological tag as the desired label, derived from the Universal Dependencies treebanks. We find that pre-trained Transformer models (mBERT and XLM-RoBERTa) learn features that attain strong performance across these tasks. We then apply two methods to locate, for each probing task, where the disambiguating information resides in the input. The first is a new perturbation method that "masks" various parts of context;the second is the classical method of Shapley values. The most intriguing finding that emerges is a strong tendency for the preceding context to hold more information relevant to the prediction than the following context. © 2023, CC BY.

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy Protection with Group Onion Routing based on AI-based URL Classification

Differential Privacy Protection with Group Onion Routing bas...

引用

2020 ACM International Conference on Intelligent Computing and its Emerging Applications, ICEA 2020

作者： Liu, I-Hsien Chang, Yung-Lin Li, Jung-Shian Liu, Chuan-Gang Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Tainan Taiwan Department of Applied Informatics and Multimedia Chia-Nan University of Pharmacy and Science Tainan Taiwan

ISBN: (纸本)9781450383042

Due to the rapid spread of tablet computers, smartphones, and other mobile information devices, wireless communication technology is fully developed and deployed widely. Mobile Internet access has been a main and important way to communicate the world in daily and it privacy protection also catches much attentions. The Onion Router, better known as Tor, is a technique for anonymous communication over internet without regional restrictions for privacy protection. Apart from this, Tor can reach sites that normal search engine cannot search. As the opinion of Tor, the transmitted data has been encrypted layer by layer, just like onion, before it reaching server. Our research proposed a system predicting URL's category with the use of machine learning technique before visiting. According to the category prediction, we represent different privacy level with three kinds of RSA key lengths on onion routing. Depending on various situations, our system can obtain the balance between security and time cost. Hence, our proposed scheme can make onion routing more flexible and efficiently. © 2020 ACM.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of fem solvers on practical electromagnetic problems

Periodica polytechnica Electrical engineering and computer s...

引用

Periodica polytechnica Electrical engineering and computer science 2021年第2期65卷 113-122页

作者： Kiss, Gergely Máté Kaska, Jan De Oliveira, Roberto André Henrique Rubanenko, Olena Tóth, Balázs AVL List GmbH Alte Poststraße 152 Graz8020 Austria Department of Theory of Electrical Engineering Faculty of Electrical Engineering University of West Bohemia Univerzitní 2732/8 Pilsen301 00 Czech Republic Department of Electrical and Computer Engineering Faculdade de Ciências e Tecnologia New University of Lisbon Largo da Torre Caparica2825-149 Portugal Research and Innovation Centre for Electrical Engineering Faculty of Electrical Engineering University of West Bohemia Univerzitní 2732/8 Pilsen301 00 Czech Republic Department of Mechanics Institute of Applied Mechanics University of Miskolc Faculty of Mechanical Engineering and Informatics Miskolc-Egyetemváros MiskolcH-3515 Hungary

The paper presents a comparative analysis of different commercial and academic software. The comparison aims to examine how the integrated adaptive grid refinement methodologies can deal with challenging, electromagnetic-field related problems. For this comparison, two bench-mark problems were examined in the paper. The first example is a solution of an L-shape domain like test problem, which has a singularity at a certain point in the geometry. The second problem is an induction heated aluminum rod, which accurate solution needs to solve non-linear, coupled physical fields. The accurate solution of this problem requires applying adaptive mesh generation strategies or applying a very fine mesh in the electromagnetic domain, which can significantly increase the computational complexity. The results show that the fully-hp adaptive meshing strategies, which are integrated into Agros Suite, can significantly reduce the task's computational complexity compared to the automatic h-adaptivity, which is part of the examined, popular commercial solvers. © 2021 Budapest University of Technology and Economics. All rights reserved.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Indoor 3D Visible Light Positioning Analysis with Channel Estimation Errors

Indoor 3D Visible Light Positioning Analysis with Channel Es...

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： Dimitrios Bozanis Nikos G. Evgenidis Vasilis K. Papanikolaou Pavlos S. Bouzinis Sotiris A. Tegos Alexis A. Dowhuszko Panagiotis D. Diamantoulakis George K. Karagiannidis Department of Electrical and Computer Engineering Wireless Communications and Information Processing Group (WCIP) Aristotle University of Thessaloniki Thessaloniki Greece Institute for Digital Communications (IDC) Friedrich-Alexander Universitat Erlangen-Nurnberg (FAU) Germany Department of Applied Informatics University of Macedonia Thessaloniki Greece Department of Communications and Networking Aalto University Espoo Finland Cyber Security Systems and Applied AI Research Center Lebanese American University (LAU) Lebanon

Since radio-frequency signals are affected signifi-cantly by multipath fading, the localization accuracy they offer cannot meet the sixth generations (6G) demanding specifications. On the other hand, visible light positioning (VLP) has emerged as a low cost alternative that takes into account the highly deterministic channel characteristics of visible light communications to provide cm-level accuracy provided that the investigated spaces are adequately covered by LEDs. However, imperfect channel state information and modeling can lead to positioning errors. In this paper, localization accuracy is quantified in terms of channel estimation errors via low complexity lateration algorithm. The channel estimation errors can be caused by a variety of issues and the provided analysis is general so that it can be easily applied to a plethora of applications. Finally, Monte Carlo simulations validate the proposed method and offer valuable insights for the design and performance bounds of VLP systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machine based Multi-Class Classification for Oriented Instance Selection

Support Vector Machine based Multi-Class Classification for ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Sandeep Kumar Davuluri Deepak Srivastava Manisha Aeri Madhur Arora Ismail Keshta Richard Rivera Department of Information Technology University of the Cumberlands Williamsburg Kentucky Department of Computer Science and Engineering Himalayan school of Science and Technology Swami Rama Himalayan University Dehradun India CSE Graphic Era Hill University Dehradun India CSE Graphic Era deemed to be University Dehradun India RGPV University Bhopal Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Department of Informatics and Computer Science Escuela Politécnica Nacional Quito Ecuador

Support vector machine has emerged as one of the most crucial classification techniques in recent years in pattern recognition, machine learning, and data mining. The model training will become more challenging when dealing with multi-classification problems, and its training time will increase considerably as the number of samples increases. A quick training data reduction technique MOIS that works with multiple classification problems is provided to address the issues above. This method takes the cluster centre as the reference point. While removing redundant training samples, selects the decisive boundary samples to significantly reduce the training data and reduce the distribution imbalance between categories. Experimental results show that MOIS can maintain or even improve the classification effect of support vector machines. Moreover, it can significantly improve training efficiency. For example, on the Opt digit data set, the proposed method improves the classification accuracy from 98.94% to 99.05% and, at the same time, shortens the training time to 15%; On the data set composed of the first 100 categories, when the accuracy rate is slightly improved (from 99.29% to 99.30%), the training time is significantly shortened to less than 6% of the original. In addition, MOIS itself has High operating efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial Attention Cooperative-Based Graph Convolutional Model for Person Re-Identification

SSRN

引用

SSRN 2023年

作者： Xiong, Mingfu Xiong, Jiefan Wang, Zhongyuan Chen, Jia Hu, Ruimin Ser, Javier Del Muhammad, Khan Xiong, Zixiang School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China School of Cyber Science and Engineering Wuhan University Wuhan430072 China Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of Derio48160 Spain Bilbao48013 Spain The Department of Electrical and Computer Engineering Texas A&M University College StationTX7784 United States

Recently, person re-identification (person Re-ID) equipped with an attention mechanism has gradually emerged as one of the most active areas of study in the field of computer vision and neural processing. Despite the upsurge in related research, existing attention-based methods still face two major challenges when recognizing different persons with similar appearances in unpredictable realistic environments: (1) the adaptability of a single local salient feature to hostile scenes cannot be guaranteed, and (2) most existing methods originating from attention features usually find a simple linear transformation or implement variation strategies, which makes it difficult to discriminate different pedestrians with similar appearance attributes. To address these issues, this paper proposes a spatial attention cooperative-based graph convolutional model (SACGCM) to examine the relevance of local body regions for individuals. The proposed framework encompasses a multi-dimensional attention model (MAM) and spatial adaptive graph convolutional model (SAGCM). In particular, the MAM comprises a dual-attention (local and global) module and feature channel-attention stage, which are used to capture multiple key points for each person. Then, SAGCM is used to construct spatial nonlinear transformation relationships among the various body regions for each person using graph optimization. Extensive experiments were conducted using public person Re-ID datasets (Market-1501, DukeMTMC-reid, and CUHK-03). The results demonstrate that the performance of the proposed approach is superior to that of state-of-the-art methods by between 2 and 10\% at Rank-1 (mAP). © 2023, The Authors. All rights reserved.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Indonesian Language Model for Emotion Classification and Sentiment Analysis

Transformer-Based Indonesian Language Model for Emotion Clas...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Hendri Ahmadian Taufik Fuadi Abidin Hammam Riza Kahlil Muchtar Graduate School of Mathematics and Applied Sciences Universitas Syiah Kuala Banda Aceh Indonesia Department of Informatics Faculty of Mathematics and Natural Sciences Universitas Syiah Kuala Banda Aceh Indonesia Research Center for Artificial Intelligence and Cyber Security National Research and Innovation Agency Jakarta Indonesia Department of Electrical and Computer Engineering Faculty of Engineering Universitas Syiah Kuala Banda Aceh Indonesia

The rapid development of social networks has made much user-generated data accessible for public evaluation. These data can be used for multiple purposes, such as textual analysis of comments and reviews. This article employs a variant of the bidirectional encoder representations from Transformer (BERT) model designed explicitly for Bahasa Indonesia (called IndoBERT model) to enhance the performance of the Indonesian natural language understanding benchmark in tasks, such as sentiment analysis and emotion classification. The two tasks were tested using a hybrid method, combining the IndoBERT model's last hidden layer summation with a neural network model. The performance of the resulting model was assessed using the F1-score metric. The experimental results show that the proposed model attains an accuracy of 0.92 and 0.76 for sentiment analysis and emotion classification, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Advanced Encryption Standard with a Dynamic S-Box Using the RC4 Key Schedule

The Advanced Encryption Standard with a Dynamic S-Box Using ...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Abdelrahman Altigani Muhammad Rukunuddin Ghalib Huwaida T. Elshoush Muawia A. Elsadig Nashat Alrefai Shiraz Naserelden Computer Information Science Higher Colleges of Technology Al Ain UAE School of Engineering & Computing De Monfort University Dubai UAE Computer Science Department Faculty of Mathematical Sciences and Informatics University of Khartoum Khartoum Sudan College of Computer Science and Information Technology Imam Abdulrahman bin Faisal University Dammam KSA Department of Mathematics College of Science Imam Abdulrahman Bin Faisal University Basic and Applied Scientific Research Center Imam Abdulrahman Bin Faisal University Dammam KSA Department of Mathematical Sciences Faculty of Science Universiti Teknologi Malaysia Johor Malaysia

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

Since the inception of secure communication, safeguarding data confidentiality has been paramount. With the increased reliance on technology, the need for robust security mechanisms is more critical than ever. This paper explores confidentiality in cybersecurity, focusing on symmetric encryption algorithms. While symmetric encryption, particularly the Advanced Encryption Standard (AES), is in wide use, concerns arise regarding its static nature. Therefore, the paper introduces a dynamic cipher, augmenting AES security by introducing a key-dependent S-Box. By leveraging the RC4 key schedule, the proposed cipher generates unique S-Boxes for each encryption key, significantly increasing security against non-generic attacks. Theoretical analysis demonstrates the proposed cipher is capable of resisting brute force, linear cryptanalysis, and differential cryptanalysis. Furthermore, its adaptability to existing AES implementations ensures practicality and ease of adoption.

关键词： Ciphers Schedules Heuristic algorithms Dynamics Force Dynamic scheduling Encryption computer security Time complexity Standards

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Human Verification using HandCAPTCHA and Anti-Spoofed Finger Biometrics with Feature Selection

arXiv

引用

arXiv 2024年

作者： Bera, Asish Bhattacharjee, Debotosh Shum, Hubert P.H. Department of Computer Science Edge Hill University St. Helens Road Lancashire OrmskirkL39 4QP United Kingdom Department of Computer Science and Engineering Jadavpur University 188 Raja S.C. Mallick Rd West Bengal 700032 India Center for Basic and Applied Science Faculty of informatics and management University of Hradec Kralove Rokitanskeho 62 Hradec Kralove500 03 Czech Republic Department of Computer Science Durham University Stockton Road DurhamDH1 3LE United Kingdom

This paper presents a human verification scheme in two independent stages to overcome the vulnerabilities of attacks and to enhance security. At the first stage, a hand image-based CAPTCHA (HandCAPTCHA) is tested to avert automated bot-attacks on the subsequent biometric stage. In the next stage, finger biometric verification of a legitimate user is performed with presentation attack detection (PAD) using the real hand images of the person who has passed a random HandCAPTCHA challenge. The electronic screen-based PAD is tested using image quality metrics. After this spoofing detection, geometric features are extracted from the four fingers (excluding the thumb) of real users. A modified forward-backward (M-FoBa) algorithm is devised to select relevant features for biometric authentication. The experiments are performed on the Boğaziçi University (BU) and the IIT-Delhi (IITD) hand databases using the k-nearest neighbor and random forest classifiers. The average accuracy of the correct HandCAPTCHA solution is 98.5%, and the false accept rate of a bot is 1.23%. The PAD is tested on 255 subjects of BU, and the best average error is 0%. The finger biometric identification accuracy of 98% and an equal error rate (EER) of 6.5% have been achieved for 500 subjects of the BU. For 200 subjects of the IITD, 99.5% identification accuracy, and 5.18% EER are obtained. © 2024, CC BY.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Generative Federated Learning with Small and Large Models In Consumer Electronics for Privacy preserving Data Fusion in Healthcare Internet of Things

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ghazal, Taher M. Islam, Shayla Hasan, Mohammad Kamrul Abu-Shareha, Ahmad A. Mokhtar, Umi A. Khan, M. Attique Baili, Jamel Saeed, Ali Q. Bhattt, Mohammed Wasim Ahmad, Munir Department of Networks and Cybersecurity Hourani Center for Applied Scientific Research Amman Jordan UCSI University Institute of Computer Science and Digital Innovation Kuala Lumpur56000 Malaysia Center for Cyber Security Faculty of Information Science and Technology Malaysia Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Department of Data Science and Artificial Intelligence Amman Jordan Prince Mohammad bin Fahd University Saudi Arabia King Khalid University College of Computer Science Department of Computer Engineering Abha61413 Saudi Arabia Northern Technical University Computer Center Ninevah Iraq Korea University College of Informatics Seoul02841 Korea Republic of

Healthcare Internet of Things (HIoT) requires large-scale privacy features to ensure maximum security in sharing sensitive physiological data in consumer electronics. Recent approaches utilize the fusion concept to provide maximum privacy in health data sharing. Embedded signing data fusion with the health observed data ensures privacy preserved sharing across heterogeneous medical consumer devices for diagnosis. This article proposes a Dependency-correlated Data Fusion Scheme (DcDFS) to maximize the privacy of the health data-sharing process. The proposed scheme prepares separate key signing procedures using triple-DES (data encryption standard) to embed with the accumulated health data. The fusion process is carried out by defining key headers and integrity footers for authentication and verification. Therefore, the fusion generates a combined sequence of linear authentication and validation procedures enclosing the health data. In this scheme, the role of federated learning is to prevent permuted sequences for the same health data. This research integrates Small Language Model (SLM) and Large Language Model (LLM) into the federated learning module to support secure, scalable, and intelligent healthcare data sharing. Their collaboration enhances context-aware training while preserving privacy across decentralized, encrypted environments. A similar sequence mapped between the header and footer is responsible for discarding unauthorized data handling. The learning process verifies the permutation for many-to-one header to footer and vice versa. Therefore, the proposed fusion scheme generates a linear dependency between the actual and security-related data for maximum privacy. The proposed scheme achieves the following: the computation time is confined by 12.424%, the privacy leakage by 12.923%, and the computation efficiency is improved by 11.46%, as observed under the maximum sequences. © 1975-2011 IEEE.

关键词： Sensitive data

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：