检索结果-内蒙古大学图书馆

ClipArtGAN: An Application of Pix2Pix Generative Adversarial Network for Clip Art Generation

Multimedia Tools and Applications 2025年 1-25页

作者： Elnabawy, Reham H. Abdennadher, Slim Hellwich, Olaf Eldawlatly, Seif Technische Universität Berlin Berlin Germany Computer Science and Engineering Department Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt Computer Science Department Faculty of Informatics and Computer Science German International University New Administrative Capital Egypt Computer and Systems Engineering Department Faculty of Engineering Ain Shams University 1 El-sarayat st. Abbassia Cairo Egypt Computer Science and Engineering Department The American University in Cairo Cairo Egypt School of Information Technology New Giza University Giza Egypt

An image can convey a thousand words. This statement emphasizes the importance of illustrating ideas visually rather than writing them down. Although detailed image representation is typically instructive, there are several contexts where simplification of image representations may be more informative. One way to provide an abstract representation of an object is via clip art, which is a simple graphic illustration of an object that can be included in documents or presentations. Clip art representation can be utilized in graphic design for concepts expression and daily life objects illustration. Furthermore, clip art had shown remarkable advantages when compared to real images in terms of editing and manipulation since clip art geometry can be easily edited in addition to the feasibility of storing it in a resolution-independent manner. However, it can be difficult to automatically create clip arts that resemble any object. Here, we propose a novel deep learning model, named ClipArtGAN, that utilizes Generative Adversarial Networks (GANs) to convert a photo of an object to its corresponding clip art. To our knowledge, this is the first GAN model based on Pix2Pix architecture that is capable of automatically generating clip art for any arbitrary object. Three training datasets were collected to train and compare two GAN models based on Pix2Pix and CycleGAN architectures. Our results demonstrate that the mean accuracy obtained using ClipArtGAN utilizing Pix2Pix outperforms that of CycleGAN by 58% and that of Google Images-based search by 54%. These results indicate the efficacy of ClipArtGAN in generating representative clip art images. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fusing AraBERT and Graph Neural Networks for Enhanced Arabic Text Classification 24

Fusing AraBERT and Graph Neural Networks for Enhanced Arabic...

引用

24th International Arab Conference on information technology, ACIT 2023

作者： Karajeh, Ola Al-Kabi, Mohammed N. Fox, Edward A. Virginia Tech Computer Science Department BlacksburgVA United States Al-Buraimi University College Information Technology Department Al Buraimi Oman

ISBN: (纸本)9798350384307

Text classification is a fundamental task in natural language processing, and has been widely studied for various languages. However, Arabic text classification is challenging due to the complexity of Arabic (i.e., rich morphological structure), high degree of ambiguity, and optional diacritics in the writing system. Large-scale pre-trained contextualized models (e.g., AraBERT) can successfully capture semantics in the local context. On the other hand, graph-based models could capture the global context by incorporating long-distance semantics. A text classification model combining the local and global context can enhance classifier performance for highly complex and ambiguous languages. In this work, we introduce the Arabic BERT Graph Convolutional Network (AraBERT-GCN), that can leverage the advantage of using large-scale pre-trained models alongside graph convolutional networks. Experimental results show that AraBERT-GCN outperforms the state-of-the-art (SOTA) on our Arabic text datasets. © 2023 IEEE.

关键词： AraBERT-GCN Arabic text classification Graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Detection and Recognition with Type Determination Based on Machine Learning

引用

computers, Materials & Continua 2023年第6期75卷 5307-5319页

作者： Khalid M.O.Nahar Mohammad Alauthman Saud Yonbawi Ammar Almomani Computer Science Department Yarmouk UniversityIrbidJordan Department of Information Security Faculty of Information TechnologyUniversity of PetraAmmanJordan Software Engineering Department University of JeddahJeddahKSA Research and Innovation Department Skyline University CollegeP.O.Box 1797SharjahUAE IT Department-Al-Huson University College Al-Balqa Applied UniversityP.O.Box 50IrbidJordan

Social media networks are becoming essential to our daily activities,and many issues are due to this great involvement in our *** is a social media network issue,a global crisis affecting the victims and society as a *** results from a misunderstanding regarding freedom of *** this work,we proposed a methodology for detecting such behaviors(bullying,harassment,and hate-related texts)using supervised machine learning algo-rithms(SVM,Naïve Bayes,Logistic regression,and random forest)and for predicting a topic associated with these text data using unsupervised natural language processing,such as latent Dirichlet *** addition,we used accuracy,precision,recall,and F1 score to assess prior *** show that the use of logistic regression,support vector machine,random forest model,and Naïve Bayes has 95%,94.97%,94.66%,and 93.1%accuracy,respectively.

关键词： Cyberbullying social media naïve bayes support vector machine natural language processing LDA

来源：评论

学校读者我要写书评

暂无评论

Transient Session Key Derivation Protocol for Key Escrow Prevention in Public Key Infrastructure 1st

Transient Session Key Derivation Protocol for Key Escrow Pre...

引用

1st EAI International Conference on Internet of Everything, IoECon 2022

作者： Nyangaresi, Vincent Omollo Abduljabbar, Zaid Ameen Maolood, Ismail Yaqub Sibahee, Mustafa A. Al Ma, Junchao Aldarwish, Abdulla J. Y. Faculty of Biological and Physical Sciences Tom Mboya University Homabay40300 Kenya Department of Computer Science College of Education for Pure Sciences University of Basrah Basrah61004 Iraq Shenzhen Institute Huazhong University of Science and Technology Shenzhen518118 China – System Information Ministry of Higher Education and Scientific Research Erbil Iraq College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China Computer Technology Engineering Department Iraq University College Basrah Iraq

ISBN: (纸本)9783031252211

The Internet of Things (IoT) devices have been deployed to realize smart environments such as smart cities, smart homes, smart health and smart grids. In these domains, the IoT devices collect and forward high volumes of sensitive and private data. It is therefore important that security schemes be developed to protect the exchanged data. In this regard, a myriad of authentication protocols have been developed over the recent past. However, these schemes deploy cryptographic primitives that result in extremely high communication, storage and computation complexities. In addition, some of these protocols still have numerous security and privacy issues that render them unsuitable for deployment in an IoT environment. For instance, untraceability, anonymity, key escrow problems and attack vectors such as de-synchronization and forgery attacks are frequently ignored. In this paper, a transient session key derivation protocol is developed to address some of these security and efficiency challenges. The security analysis executed shows that this protocol offers untraceability, device anonymity and perfect forward key secrecy. In addition, it is robust against de-synchronization, known secret key leakage, eavesdropping and forgery attacks. In terms of operational efficiency, this protocol incurs the lowest computation and communication complexities. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

system Dynamics in Manufacturing Processes Modelling and Analysis 1

引用

3rd International Conference on Innovation in Engineering, ICIE 2024

作者： Litwin, Pawel Szymusik, Anna Department of Computer Science Faculty of Mechanical Engineering and Aeronautics Rzeszow University of Technology Al. Powstanców Warszawy 8 Rzeszów35-959 Poland

ISBN: (数字)9783031615825

ISBN: (纸本)9783031615818

The systems dynamics (SD) method allows analysis of the performance of complex systems over the full simulation period. It allows for prediction of the dynamics of systems containing many interdependent elements. However, due to the complexity of models, SD is most often used to map systems at an aggregate level with a low level of detail. This paper presents solutions to improve the process of detailed modelling and simulation of manufacturing systems. The integration of SD with value stream mapping (VSM) and the use of pattern models help streamline the modeling process and can contribute to increasing the SD application area in manufacturing process analysis. The case study illustrates the methodology for modeling and simulation and shows how SD can be used to improve the manufacturing process. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： system theory

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Coding and Cryptanalysis for the Secure Communications 25th

Physical Layer Coding and Cryptanalysis for the Secure Commu...

引用

25th International computer Symposium on New Trends in computer Technologies and Applications, ICS 2022

作者： Yang, Cheng-Ying Lin, Chuan-Bi Yao, Jenq-Foung J. F. Hwang, Ming-Hsiang Department of Computer Science University of Taipei Taipei Taiwan Development of Information and Communication Technology Chaoyang University of Technology Taichung Taiwan Department of Computer Science Georgia College and State University Milledgeville United States Department of Computer Science and Information Engineering Asia University Taichung Taiwan

ISBN: (纸本)9789811995811

The privacy and security are highly requested in the cooperative communication system. The information is sent to the destination with the help of relays. In the system, there might be the eavesdroppers playing the role of the relay. It suffers the system security. Traditionally, the complex and difficult encryption scheme would be applied to a higher network layer. It is not suitable to apply to the equipment with low computing resources. According to Shannon Theory, positive secrecy capacity could support secure communications. In this work, based on the information theorem, the secrecy capacity analysis in the communication is given. Consider the difference between the amount of information at the source and that at the transmitter, the positive secrecy capacity with memory coding scheme under the lossless communication environment might be obtained. Then, the communication security could be implemented with the physical coding scheme. In this work, the physical layer coding schemes are examined. According to the degree of the freedom of the codeword, the secure communication could be achieved. It could be found the secrecy capacity could increase with coding rate decreasing with the multiple code assignments. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Secure communication

来源：评论

学校读者我要写书评

暂无评论

Previs-Real:Interactive virtual previsualization system for news shooting rehearsal and evaluation

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 527-549页

作者： Che QU Shaocong WANG Chao ZHOU Tongchen ZHAO Rui GUO Cheng Wa WONG Chi DENG Bin JI Yuhui WEN Yuanchun SHI Yong-Jin LIU Department of Film and Television Technology Beijing Film AcademyBeijing 100088China Department of Computer Science and Technology MOE-Key Laboratory of Pervasive ComputingTsinghua UniversityBeijing 100084China School of Social Sciences Tsinghua UniversityBeijing 100084China News Production and Broadcasting First Division China Media GroupBeijing 100038China School of Computer and Information Technology Bejing Jiaotong UniversityBejing 100044China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong UniversityBeijing 100044China

Background In the demanding field of live news broadcasting,the intricate studio production procedures and tight schedules pose significant challenges for physical rehearsals by *** paper explores the design and implementation of a lightweight virtual news previsualization system,leveraging virtual production technology and interaction design methods to address the lack of fidelity in presentations and manipulations,and the quantitative feedback of rehearsal effects in previous virtual *** Our system,Previs-Real,is informed by user investigation with professional cameramen and studio technicians,and adheres to principles of high fidelity,accurate replication of actual hardware operations,and real-time feedback on rehearsal *** system's software and hardware development are implemented based on Unreal Engine and accompanying toolsets,incorporating cutting-edge modeling and camera calibration *** We validated Previs-Real through a user study,demonstrating superior performance in previsualization shooting tasks using the virtual system compared to traditional camera *** findings,supported by both objective performance metrics and subjective responses,underline Previs-Real's effectiveness and potential in transforming news broadcasting *** Previs-Real eliminates the requirement for complex equipment interconnections and team coordination inherent in a physical studio by implementing methodologies complying the above principles,objectively resulting in a lightweight design of applicable version of virtual news previsualization *** offers a novel solution to the challenges in news studio previsualization by focusing on key operational features rather than full environment *** design approach is equally effective in the process of designing lightweight systems in other fields.

关键词： News broadcast Previsualization Human computer interaction design User-centered design Interface evaluation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Procedural Level Generation for 2D Platformer Game

Hybrid Approach for Procedural Level Generation for 2D Platf...

引用

Informatics International Conference (BTS-I2C), Beyond technology Summit on

作者： Jos Timanta Tarigan Erick Yudha Pratama Sukku Sri Melvani Hardi Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research proposes a hybrid approach for a procedural level generation for our 2D platformer game. The method integrates manual level creation and procedural algorithm to generate a complete level for 2D rouge-like platformer game including the overall structure of the level, corridors, enemies, obstacles, and items. The proposed method also allowed user-input parameters that define requirement for the level such as difficulty, room numbers, enemy and item spawn probability. We developed the proposed method and implemented the system in our game, Lost Labyrinth Rouge's Odyssey. We implemented the system specifically to fit the mechanic and rules of our game. To test the performance of the system to develop a level, we performed a usability test by inviting users to play the game multiple times. The result and feedback from the respondents show that most the system was able to generate a good playability for a 2D platformer dungeon game.

关键词： Human computer interaction Procedural generation Navigation Games Manuals Hybrid power systems Generators Usability Informatics

来源：评论

学校读者我要写书评

暂无评论

Handling The Common Method Variance/Bias (CMV/CMB) in Cross-Sectional Research: A systematic Literature Review and Bibliometric Analysis

Handling The Common Method Variance/Bias (CMV/CMB) in Cross-...

引用

International Conference on Informatics, Multimedia, Cyber and information system (ICIMCIS)

作者： Artika Arista Liyana Shuib Maizatul Akmar Ismail Information Systems Faculty of Computer Science Universitas Pembangunan Nasional Veteran Jakarta Jakarta Indonesia Department of Information Systems Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (数字)9798331533243

ISBN: (纸本)9798331533250

Concerns over the validity of survey research have grown among editors, reviewers, and authors in recent years. Common method variance (CMV) is one of the main problems. Common method variance (CMV), which measures the amount of misleading covariance shared between variables as a result of the common data collecting method, is one of the main problems. Because CMV has not been extensively studied by IS researchers. Thus, IS experts are still uncertain about this. The current study intends to address the following research issues and add to the ongoing discussion about how common method variance/bias (CMV/CMB) in cross-sectional research is handled. Eight related research studies were analyzed and assessed using the Preferred Reporting Items for systematic Reviews and Meta-Analyses (PRISMA) approach and VOSviewer's Bibliometric Analysis feature. The findings show that over time, one paper has consistently been published year. This is perhaps because managing common method variance/bias (CMV/CMB) in cross-sectional research is not a topic that most researchers and academics are particularly interested in. As suggested by a number of the above suggestions, common method variance/bias (CMV/CMB) in cross-sectional research can be addressed by (1) employing a large number of respondents; (2) obtaining multiple forms of data (i.e., triangulation approach); and (3) gathering data over multiple periods of time (i.e., longitudinal data).

关键词： Surveys Soft sensors Current measurement Bibliometrics Organizations Multimedia databases Machinery Informatics systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enriched Graph Convolution Network for Hybrid Explainable Recommendation from Review Texts and Reasoning Path 7

Knowledge-Enriched Graph Convolution Network for Hybrid Expl...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Bastola, Rama Shakya, Subarna Nepal Open University Faculty of Science Health And Technology Lalitpur Nepal Tribhuvan University Pulchowk Campus Institute of Engineering Department of Electronics And Computer Engineering Lalitpur Nepal

ISBN: (纸本)9798350359299

In the digital era, organizations leverage technology to handle vast datasets, yet deriving meaningful insights remains a challenge. Recommender systems address this by using deep learning advancements to provide users with relevant content. However, ensuring transparency in recommendations, known as explainable recommendations, is difficult due to complex deep learning algorithms. Clarifying recommendations to both users and system designers to enhance comprehension and decision-making represents a significant research challenge in the field of explainable recommendation systems. Review-based explanations in human-like languages are intuitive to the general users while Reasoning-path based explanations are more informative to the system designers. The existing models focus on one of the above explanation approaches. This research proposes a hybrid explainable recommender model integrating review-based and reasoning path-based interpretation. The model utilizes external knowledge bases and review documents to create contextualized knowledge-enriched embeddings for users, items, and interactions. Path encoding with LSTM and attention mechanism is utilized for both rating prediction and reasoning path explanation. A Gated Recurrent Unit with a Copy Mechanism generates human-like recommendation explanations. The model yields both types of recommendation explanations and rating predictions comparable to state-of-the-art technologies. © 2024 IEEE.

关键词： Convolution

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：