检索结果-内蒙古大学图书馆

3rd International Conference on Video, Signal and Image Processing, VSIP 2021

作者： Deng, Shiping Uchida, Kaoru Yin, Zhengwei School Of Software Engineering University Of Science And Technology Of China China Hosei University Japan Alibaba Group China

ISBN: (纸本)9781450385886

Human face to anime face translation has attracted the attention of many researchers in recent years, and various works have achieved high-quality style transfer on conventional tasks. However, existing works often have fatal shortcomings when the target domain training data is heavily insufficient, which is named as imbalanced setting. Here the imbalanced (low-resource) task, generally means there is no sufficient data on the training dataset compared with the conventional task, e.g. the training data size is less than 100. To solve this problem, we propose a multi-modal translation model for a specific style. Based on the cyclic adversarial network and class activation map, we import semantic modality to enhance data information and attention modules, which help the model focus more on the discriminative areas between source and target domain. The experimental results show that our method has superiority in low-resource settings compared with similar existing work. © 2021 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation of CEP Rules using Data Analysis Techniques and Model-Driven engineering

Automatic Generation of CEP Rules using Data Analysis Techni...

引用

International Conference on Internet of Things and Applications (IoT)

作者： Mohsen Gholami Bahman Zamani Behrouz Shahgholi Ghahfarokhi Department of Software Engineering MDSE Research Group University of Isfahan Isfahan Iran Department of Information Technology Engineering University of Isfahan Isfahan Iran

The widespread use of Internet of Things (IoT) systems results in a large volume of data that needs to be analyzed in real time for efficient usage. Complex Event Processing (CEP) is a technique that enables organizations to analyze data and identify complex and meaningful events. CEP uses patterns written in an Event Pattern Language (EPL) to describe an event. However, producing patterns and rules using EPL remains a significant *** research benefits from data analysis and model-driven engineering to automatically produce CEP rules that allow domain experts to extract and define patterns automatically, even if unfamiliar with data analysis or CEP rule design. At the end of the paper, a case problem is solved, resulting in a coverage coefficient of 60%, an average accuracy of 82.5%, and an average precision of 82%. The results show that this combined approach is beneficial in providing a more appropriate response in less time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Research on KVM-based Cloud Desktop Solution for VDI Converged Architecture

Design and Research on KVM-based Cloud Desktop Solution for ...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Meng, Yixin Qin, Yuan Sun, Ling Zhong, Wenling Zhao, Kaifeng Zhao, Bowen Lenovo Group 696 Songtao Road Pudong New Area Shanghai201203 China College of Foreign Studies Guilin University of Technology Guilin541006 China Sichuan Meiwang Children's Care Charity Foundation Chengdu610095 China School of Software Engineering Chengdu University of Information Technology Chengdu610225 China College of Economic and Management Chang'an University Xi'an710064 China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

Based on the market demand, the company decides to independently develop a desktop cloud system for government, education and small and medium-sized enterprises. The system is designed for low-cost, easy-to-use, easy-to-manage and high-performance experience, aiming to solve the pain points of traditional PCs such as information security loopholes, high maintenance costs, inefficient management, etc., and to provide a cost-effective and easy-to-adopt desktop virtualization solution. The author has participated in the requirement study, technical solution design and R&D work, focusing on the system architecture design and part of the code development. Mainly through the optimization of the virtualization platform, management console, security mechanism and storage database and other modules, so that the desktop cloud system of security, reliability, manageability is better than similar products and easier to be accepted by customers and deployed to meet demands. © 2025 SPIE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Cancelable Face Template Protection based on Deep Neural Network 7

Cancelable Face Template Protection based on Deep Neural Net...

引用

7th International Conference on Signal and Image Processing, ICSIP 2022

作者： Ma, Qianya Li, Bing Liu, Guozhu Li, Yuqi Wang, Yazhou Gu, Minzhang Zheng, Ke Cai, Hongqun School of Microelectronics Southeast University China School of Software Engineering Southeast University China School of Cyber Science and Engineering Southeast University China China Electronics Technology Group Corporation No. 58 Research Institute China

ISBN: (数字)9781665495639

ISBN: (纸本)9781665495639

In recent years, biometrics are increasingly being employed in identity authentication systems, including Internet of Things (IoT), blockchain, cloud computing, and other application fields. Face template is widely used in the field of biometric identification due to its high reliability, uniqueness, and separability. However, once the face template is lost or stolen, it will suffer from the security and privacy threats to individuals. To solve these issues, we propose a cancelable face protection template scheme based on a deep neural network (DNN). On the one hand, a mapping network is used to map a face image to random binary codes, which improves the security and distinguishability of face templates. On the other hand, a hash network is used to obtain high entropy templates that enhances the authentication accuracy and privacy. Moreover, a token-based random projection is applied to realize template revocability without retraining the DNN model. The experiments are conducted on the ORL and the LFW databases, which achieve a better genuine positive rate (GAR) up to 99.6% at a zero false accept rate (FAR). In addition, the revocability and security are further analyzed in our scheme, and the results prove their effectiveness. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Bandwidth-Efficient Video Compression for Web Streaming Using Camera Localization

Bandwidth-Efficient Video Compression for Web Streaming Usin...

引用

International Conference on Web Research (ICWR)

作者： Parisa Tavakkoli Heravi Zahra Tavanaei Sereshki Head of Software & Artificial Intelligence Group Sun-Air Research Institute Mashhad Iran PhD in Electrical Engineering - Control Amir Kabir University of Technology Tehran Iran

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

Majority of today's web traffic consists of highresolution videos for streaming, conferencing, and surveillance. Transmitting raw video over the web demands high bandwidth, creating a pressing need for effective compression. In this paper, we focus on compressing videos captured by moving agentssuch as drones or vehicles-used in IoT-based surveillance systems. Our method exploits 3D scene geometry and camera poses to reduce redundancy while preserving quality. Unlike approaches that rely on Structure-from-Motion, we employ an efficient Simultaneous Localization & Mapping (SLAM) technique for camera localization that can run on typical IoT devices with limited computational power. We analyze the application of SLAM for video compression and tackle the practical challenges inherent to SLAM systems. Simulation results demonstrate significant compression gains and a notable reduction in computational complexity compared to stare-of-the-art SfM methods. This makes the proposed approach highly suitable for video streaming in modern web communications and IoT applications.

关键词： Location awareness Simultaneous localization and mapping Web services Surveillance Simulation Video compression Streaming media Cameras Internet of Things Videos

来源：评论

学校读者我要写书评

暂无评论

Architecting Digital Twins for Intelligent Transportation Systems

arXiv

引用

arXiv 2025年

作者： Bhatt, Hiya Sahil Vaidhyanathan, Karthik Biju, Rahul Gangadharan, Deepak Trestian, Ramona Shah, Purav Software Engineering Research Centre IIIT Hyderabad India Computer Systems Group IIIT Hyderabad India Faculty of Science and Technology Middlesex University London United Kingdom

Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing these challenges requires intelligent solutions capable of real-time monitoring, predictive analytics, and adaptive control. This paper proposes an architecture for DigIT, a Digital Twin (DT) platform for Intelligent Transportation Systems (ITS), designed to overcome the limitations of existing frameworks by offering a modular and scalable solution for traffic management. Built on a Domain Concept Model (DCM), the architecture systematically models key ITS components enabling seamless integration of predictive modeling and simulations. The architecture leverages machine learning models to forecast traffic patterns based on historical and real-time data. To adapt to evolving traffic patterns, the architecture incorporates adaptive Machine Learning Operations (MLOps), automating the deployment and lifecycle management of predictive models. Evaluation results highlight the effectiveness of the architecture in delivering accurate predictions and computational efficiency. © 2025, CC BY.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

In-Depth Analysis of OLAP Query Performance on Heterogeneous Hardware

引用

Datenbank-Spektrum 2021年第2期21卷 133-143页

作者： Broneske, David Drewes, Anna Gurumurthy, Bala Hajjar, Imad Pionteck, Thilo Saake, Gunter Databases and Software Engineering Group Otto von Guericke University Magdeburg Germany Institute for Information Technology and Communications Otto von Guericke University Magdeburg Germany

Classical database systems are now facing the challenge of processing high-volume data feeds at unprecedented rates as efficiently as possible while also minimizing power consumption. Since CPU-only machines hit their limits, co-processors like GPUs and FPGAs are investigated by database system designers for their distinct capabilities. As a result, database systems over heterogeneous processing architectures are on the rise. In order to better understand their potentials and limitations, in-depth performance analyses are vital. This paper provides interesting performance data by benchmarking a portable operator set for column-based systems on CPU, GPU, and FPGA – all available processing devices within the same system. We consider TPC‑H query Q6 and additionally a hash join to profile the execution across the systems. We show that system memory access and/or buffer management remains the main bottleneck for device integration, and that architecture-specific execution engines and operators offer significantly higher performance. © 2021, The Author(s).

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A High Peak-efficiency Cross-coupled Charge Pump with Low Input Voltage for Energy Harvesting System 2

A High Peak-efficiency Cross-coupled Charge Pump with Low In...

引用

2023 2nd International Conference on Electronics and Integrated Circuit technology, EICT 2023

作者： Li, Xinghe Wang, Yanyan Wu, Zhiqiang Xie, Zushuai No.58 Research Institute China Electronics Technology Group Corporation Wuxi214035 China College of Integrated Circuit Science and Engineering Nanjing University of Posts and Telecommunications Nanjing210023 China Rockchip No.89 Software Boulevard Tongpan Rd 350003 China

A high-efficient, low-voltage cross-coupled charge pump is presented in this paper. To decrease the conduction loss, a cross-coupled charge pump is proposed based on two auxiliary dynamic inverters to increase the clock swing. Meanwhile, a clocking scheme is designed to eliminate the reversion power losses. Based on proposed scheme, a higher output voltage is achieved by a three-stage topology by cascading the single stage. The proposed architectures of both single and three-stage charge pump are implemented under a standard 180nm CMOS technology. The post-layout simulation exhibits a peak power efficiency of 86.89% and 78.6%, respectively. And Monte Carlo (MC) simulation results indicate the proposed scheme features strong robustness to process variation. © Published under licence by IOP Publishing Ltd.

关键词： Clocks

来源：评论

学校读者我要写书评

暂无评论

Research and Applications of Large Language Models for Converting Unstructured Data into Structured Data

Research and Applications of Large Language Models for Conve...

引用

Cloud Computing, Big Data Applications and software engineering (CBASE), International Conference on

作者： Xiangfeng Liu Jianting Sun Aidi Lei Junzhi Zhu Chengdu Aircraft Industrial (Group) Co. Ltd Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (数字)9798331506582

ISBN: (纸本)9798331506599

The rapid growth of data has led to a significant increase in unstructured data, such as text, audio, and images, which dominate modern information processing. However, the complexity of unstructured data presents challenges for automated analysis and processing. Converting unstructured data into structured formats is crucial for tasks like data mining, information extraction, and knowledge graph construction. Traditional methods that rely on manual rules or statistical models struggle with complex, context-dependent data. Recently, large language models (LLMs), such as GPT-4 and BERT, have demonstrated great potential in unstructured data processing due to their powerful natural language understanding and generation capabilities. This study explores the application of large language models in transforming unstructured data into structured formats. It begins by reviewing the limitations of traditional approaches and then presents a framework for unstructured data processing using LLMs, covering data preprocessing, information extraction, and structured representation. The study's experiments demonstrate the superior performance of LLMs in handling various types of unstructured data, particularly in tasks like named entity recognition, relation extraction, and contextual understanding. The results show that LLMs achieve higher accuracy and generalization while reducing reliance on manual rules. The paper discusses the strengths and limitations of this method, proposing future improvements, such as combining domain-specific knowledge for model optimization and expanding applications to multimodal data processing. The research highlights the promising role of large language models in converting unstructured data into structured formats.

关键词： Adaptation models Accuracy Data conversion Large language models Computational modeling Manuals Information retrieval Data models Data mining software engineering

来源：评论

学校读者我要写书评

暂无评论

MAEON: An Efficient Weather-Aware Ocean Network Routing Scheme based on Multi-Agent Reinforcement Learning

MAEON: An Efficient Weather-Aware Ocean Network Routing Sche...

引用

International Workshop on Quality of Service

作者： Shu Yang Yaofeng Liu Laizhong Cui Runsu Zhu College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Smart City Technology Development Group Co. Ltd Shenzhen China

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

Ocean network communication is more and more important nowadays. However, it faces significant challenges due to its heterogeneity, low reliability, and narrow bandwidth. Compared with traditional networks, the problem worsens under severe weather conditions because communication channels, e.g., microwave links, may degrade badly due to weather changes. While many ocean applications put higher QoS (Quality of Service) requirements on communications, it is difficult to meet them due to fluctuating weather changes. Thus, it is more challenging to model and operate the ocean network as more factors may influence the ***, artificial intelligence opens up new possibilities to meet the challenges because it can adapt to the dynamic changes of the network. In this paper, we formulate the problem by establishing a model between network performance and weather conditions. We try to optimize network utility given the traffic matrix and important weather factors, such as rain, atmospheric absorption, and clouds. To solve the problem, we propose a two-stage and multi-agent optimization algorithm named MAEON (Multi-Agent Efficient Ocean Network). We conduct a comprehensive simulation using generated network topology traffic and real-world weather datasets. We also carry out a case study with datasets from a real-world scenario. The results show that MAEON can improve performance by 21.5% compared with traditional algorithms.

关键词： Adaptation models Network topology Oceans Atmospheric modeling Quality of service Bandwidth Routing

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：