检索结果-内蒙古大学图书馆

2024 international conference on Image processing

作者： Tariq, Razaib Tariq, Shahroz Woo, Simon S. Sungkyunkwan Univ Comp Sci & Engn Dept Seoul South Korea CSIROs Data61 Eveleigh Australia

ISBN: (纸本)9798350349405;9798350349399

Deepfake detection is critical in mitigating the societal threats posed by manipulated videos. While various algorithms have been developed for this purpose, challenges arise when detectors operate externally, such as on smartphones, when users take a photo of deepfake images and upload on the Internet. One significant challenge in such scenarios is the presence of Moire patterns, which degrade image quality and confound conventional classification algorithms, including deep neural networks (DNNs). The impact of Moire patterns remains largely unexplored for deepfake detectors. In this study, we investigate how camera-captured deepfake videos from digital screens affect detector performance. We conducted experiments using two prominent datasets, CelebDF and FF++, comparing the performance of four state-of-the-art detectors on camera-captured deepfake videos with introduced Moire patterns. Our findings reveal a significant decline in detector accuracy, with none achieving above 68% on average. This underscores the critical need to address Moire pattern challenges in real-world deepfake detection scenarios.

关键词： Moire Pattern Deepfakes Detection Video Manipulation Digital Screen Capture Analysis

来源：评论

学校读者我要写书评

暂无评论

Agitating Sustainability using Fog computing for Smart Cities 10

Agitating Sustainability using Fog Computing for Smart Citie...

引用

17th INDIACom;2023 10th international conference on computing for Sustainable Global Development, INDIACom 2023

作者： Siddiqui, Eram Fatima Nayak, Sandeep Kumar Integral University Department of Computer Application Lucknow India

ISBN: (纸本)9789380544472

Internet of Things (IoT) is well known for connecting every digital object to one another and serving as a strong foundation for the construction of future sustainable smart cities. Fog computing (FC) makes IoT more effective in a variety of fields in smart cities and thus makes it sustainable through its decentralized method of data collection and transformation with less time and energy usage. FC aims to make equipments and resources more accessible for better data processing and management. By extending the cloud-like service close to the smart devices, it serves as an improvement infrastructure for Cloud computing (CC) technology. FC significantly reduces the types and quantities of resources required for data computation close to the network edge. In this paper, characteristics of fog computing and the underlying essential technologies have been thoroughly explored. It also describes the different FC variations that can be used in conjunction with other technologies to function for a particular infrastructure. The paper focuses on how FC may be used in many smart city fields to make it sustainable. Finally, problems and difficulties, associated with FC for smart cities, are highlighted which need to be thoroughly researched in order to achieve a sustainable environment, such as security, privacy, heterogeneity, energy consumption, and acceptance. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Classifying the Country of Origin of Traffic Transactions Based on Computer Raw dataset data processing 4

Classifying the Country of Origin of Traffic Transactions Ba...

引用

4th international conference on Computers, Information processing and Advanced Education, CIPAE 2023

作者： Wang, Yichun Tongji University College of Design and Innovation Shanghai China

ISBN: (纸本)9798350342710

Accurate network traffic classification is the key to achieve controllable and manageable Internet. This paper analyzes and compares the application of algorithm in the classification of network traffic source country. The experimental results show that logistic regression is the most efficient. SVM and neural networks take longer, probably because their algorithms are more complex. Optimize the neural network time consumption by setting the appropriate batch size. The time consumption of the three machine learning algorithm models on Precision is about 92%. In terms of Recall and F1 scores, the three machine learning algorithms mainly concentrate between 89% and 90%. There is no significant difference between the algorithm models. SVM was superior in precision (92%), recall (89%) and F1 score (90%). © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Improving Library Document Resource Management and data Sharing Through Semantic Web Technology 3

Improving Library Document Resource Management and Data Shar...

引用

3rd international conference on Pervasive computing and Social Networking, ICPCSN 2023

作者： Muruganantham, A. Velmurugan, R. Kumar, R. Bengaluru India

ISBN: (纸本)9798350322842

This research focuses on the limitations of the original association rule and presents a method for addressing these limitations by dividing the dataset into event sequences. The original association rule has a limited ability to identify references related to a keyword, only focusing on the closest ones, which can lead to incomplete and inaccurate results. The proposed method overcomes this limitation by categorizing different types of references based on the research subject, which enables the identification of relevant references that are not immediately adjacent. The reliability of different categories is calculated based on the event table, and candidate records undergo procedures such as aggregation and screening to eliminate less reliable records. The feasibility of this method is evaluated by comparing it with numerous association rule processes in the marketplace. The results show that the proposed method has a significant advantage over other algorithms, with a data correlation rate that remains stable at 80%. Moreover, this study emphasizes the importance of Linked data technology in publishing and sharing data online. Linked data provides a lightweight and incremental data transfer model, which makes it an ideal way to integrate resources into the information flow continuously. Libraries can use this technology to become part of the internet's information resources, thereby facilitating the addition and interoperability of further web resources. The development of Semantic Web technologies allows for easier communication between humans and computers, sharing information perception specifications that greatly facilitate communication between the two parties. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Graph Relation Extraction for Chinese Business datasets

Knowledge-Graph Relation Extraction for Chinese Business Dat...

引用

2023 international conference on algorithms, High Performance computing, and Artificial Intelligence, AHPCAI 2023

作者： Qiu, Yuqi Liu, Haotian Lin, Yucong Hu, Silan Wei, Wei Wang, Xiaoning School of data science and Media Intelligence Communication University of China Beijing100024 China Liu Haotian Beijing Institute of Technology Beijing China School of Medical Technology Beijing Institute of Technology Beijing China Macau University of Science and Technology China Peking University HSBC Business School Shenzhen China

ISBN: (纸本)9781510671881

This article presents the construction of a large-scale, high-quality Chinese Business dataset (CBD) for knowledge graph construction in the Chinese business field. We consider the characteristics of the Chinese language and verify the effectiveness and reliability of the dataset through a series of experiments. The article discusses the process of extracting issues, entity links, and manual evaluation of the dataset. The authors conducted experiments using different relationship extraction algorithms based on the published dataset for training. The results suggest that Context-Aware is highly effective for relation classification in this task, while Bi-LSTM Attention may be insufficient. The use of knowledge graphs has enabled the organization of large amounts of structured and unstructured data, providing a more comprehensive understanding of business entities and their relationships. However, there are still challenges that need to be addressed in this field. Nevertheless, with the continuous advancement of technology and the increasing availability of data, further progress can be expected in this field. © 2023 SPIE. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

data processing System Based on Network Security

Data Processing System Based on Network Security

引用

2023 international conference on Applied Physics and computing, ICAPC 2023

作者： Wu, Aiping School of Economics and Management Guangdong Polytechnic College Zhaoqing526100 China

ISBN: (纸本)9798350359244

This paper studies a data processing method, system, device and computer readable storage medium. The method includes: user terminal sends query request to data storage blockchain;the data storage blockchain querying the target information corresponding to the request based on the smart contract;the user terminal displaying the target information and sending the transaction request to the corresponding merchant terminal based on the smart contract. The merchant terminal executes the transaction operation corresponding to the transaction request. And when the transaction operation is completed, it executes the point issuance operation for the account information corresponding to the transaction request based on incentive points. This paper can realize the transaction operation in the e-commerce platform system through the blockchain technology, and store commodity data (target information) through the data storage blockchain. It also ensures the security of various data in the e-commerce platform system, avoid the leakage of private data in the e-commerce platform system, and improve the data credibility and data security of the e-commerce platform system. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

The Design of Reflectance Spectra data processing Program Based on Python 5

The Design of Reflectance Spectra Data Processing Program Ba...

引用

5th international conference on Optoelectronic Science and Materials, ICOSM 2023

作者： Li, Xin Cui, Mengying Jiang, Shuo Cui, Qiannan Meng, Yingying Li, Bingshao Beijing Institute of Computer and Electronics Application Beijing100089 China China Research and Development Academy of Machinery Equipment Beijing100089 China

ISBN: (纸本)9781510674547

The reflectance spectra data obtained from spectrometer was of great necessity to be processed and analyzed so that the data could be converted to color parameters. Since the Lab color space was characterized by not limited to specific devices, wide color gamut, and high-speed computing process, a data processing program based on python has been developed in this work. Based on the program, Lab color parameters could be calculated from the wavelength and reflectivity obtained from raw data, the relative spectral power distribution of illumination source, and spectral tristimulus values under standard chromaticity observation, which could be visualized in the 3D color space. In comparison with manual data screening and calculation, the efficiency and reliability of color analysis were markedly elevated based on the developed program, by which the color parameters could be quickly and accurately calculated from the reflectance spectra and intuitively displayed in 3D color space. © 2024 SPIE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Explore deep reinforcement learning for efficient task processing based on federated optimization in big data

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE international JOURNAL OF ESCIENCE 2023年 149卷 150-161页

作者： Xiao, Shan Wu, Chunyi Chongqing Coll Elect Engn Big Data & Optimizat Res Inst Chongqing 401331 Peoples R China

In recent years, along with the extensive application of consumer electronics, the task execution with cloud computing for big data has become one of the research focuses. Nevertheless, the traditional theories and algorithms are still employed by existing research work to explore the feasible solutions, which takes a beating from low generalization performance, system load imbalance, more response delay, etc. To solve the matter, a task execution method called DROP (Deep Reinforcement network aided Optimization method aiming at task processing) has been put forward, which is capable of completing task request allocation through virtual network embedding. The prominence of this method is explained by its effect in reducing load balancing degree, minimizing bandwidth resource overhead, and preserving electric energy as well as meeting customer demands. It makes use of Deep Deterministic Policy Gradient (DDPG) instead of depending on tons of iterations for better path selection schemes in previous methods, through continuous environment interaction and trial-anderror evaluation to get better strategy selection for virtual link embedding. To realize the virtual node embedding in the federated optimization based system architecture, the intentional deep feature learning network is applied. Compared with the cutting edge approaches, the performance benefits of DROP can be verified by the experimental results in terms of bringing down the extra cost on resources and energy of the substrate network during the task execution for big data.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Big data Consumer electronics Deep reinforcement learning Federated optimization Virtual network embedding

来源：评论

学校读者我要写书评

暂无评论

Client-Level Monitoring Approach to Secure data in a Cloud Environment 6

Client-Level Monitoring Approach to Secure Data in a Cloud E...

引用

6th international conference on Contemporary computing and Informatics, IC3I 2023

作者： Rajakumar, P. Partheeban, N. Indervati, Ms. Kumar, Himanshu Mlawa, Pius Gautam, Utkarsh School of Computing Science & Engineering Galgotias University Greater Noida Uttar Pradesh India

ISBN: (纸本)9798350304480

Cloud computing imparts huge storage at low cost, because the internet is so widely used around the world, massive amounts of data are stored on local devices and integrated and stored on a common platform for easy access, sharing, and, high availability. The cloud environment provides a convenient way for normal users and enterprises to migrate their apps, data, and storage to the cloud-based server for storage due to the high availability of its services and the flexibility of computing processes. Securing information is the primary challenge in cloud computing. Securing the data from unauthorized modification and access is one of the key challenges of the cloud environment. In order to secure user data, different security algorithms were adapted. This paper provides a client-level monitoring approach to secure data in a cloud environment. The monitoring approach consists of the user or client system, monitor, and cloud storage. The user uploads the encrypted form of documents onto the cloud storage and the cloud storage stores the encrypted form of user documents, and the monitor periodically monitors or the user directs the monitor to check the integrity of user data. © 2023 IEEE.

关键词： authentication cloud Security cloud storage data integrity monitor

来源：评论

学校读者我要写书评

暂无评论

Characteristics of Machining data and Machine Learning Models- A Case Study

Characteristics of Machining Data and Machine Learning Model...

引用

2023 international conference on Green Energy, computing and Intelligent Technology, GEn-CITy 2023

作者： Natarajan, Elango Fiorna, Vxynette Al-Talib, Ammar Abdulaziz Elango, Sangeetha Gnanamuthu, Ezra Morris Abraham Saruchi, Sarah Atifah Binti Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur Malaysia Sungai Long Malaysia Universiti Malaysia Pahang Malaysia

ISBN: (纸本)9781839539596

Advancement of technologies in computing such as internet of things, cloud computing, and artificial intelligence drive manufacturing industries to adopt and implement automation in production. One of the key technologies or preferable methods to increase the productivity is implementing prediction models or machine learning (ML) algorithms in production. This article is aimed to show a comprehensive review on AI implementation in machining of materials, and to present methodology in prediction model development. The characteristic of experimental data and the key attributes in the model development are presented and discussed with a case study. © The Institution of Engineering & Technology 2023.

关键词： Digital storage

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：