检索结果-内蒙古大学图书馆

7th International Conference on Machine Learning and Natural Language Processing, MLNLP 2024

作者： Feng, Bo Yan, Xi Yan, Li Luo, Bing Pei, Zheng School of Science Xihua University Chengdu China School of Computer Science and Software Engineering Xihua University Chengdu China

ISBN: (纸本)9798350354973

The integration of the contrastive learning paradigm into deep clustering has led to enhanced performance in image clustering. However, in existing researches, the samples in the class of the target may be still treated as negative samples, this means that more semantic sample pairs cannot be constructed and the intra-class compactness may be compromised. In this paper, we propose a new contrastive clustering method based on mining latent positive samples (CCLPS), which utilizes the nearest neighbor relationship between samples to mine semantic positive samples in the same class. In more detail, by mining latent positive samples in both the feature and cluster spaces, CCLPS can obtain more cluster-friendly feature representation of samples to enhance clustering performance. Samples mined from the feature space fuel the cluster-level contrastive learning task, while samples mined from the cluster space fuel the instance-level task. Three image datasets CIFAR-10, CIFAR-100 and Tiny-ImageNet are employed to experimentally demonstrate usefulness and effectiveness of the proposed method in image clustering, and transfer learning based on mining latent positive samples is also discussed and comparisons are made with 19 representative clustering methods on the datasets. Experimental results indicate that the proposed method can serve as a pre-training model for transfer learning and exhibits commendable feature modeling capabilities. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Heliostat Field Arrangement Model Based on Geometric Relationship and Particle Swarm Algorithm 4

Optimization of Heliostat Field Arrangement Model Based on G...

引用

4th IEEE International Conference on Power, Electronics and computer Applications, ICPECA 2024

作者： Liu, Zhishuai Wei, Zhengyang Li, Jiangnan School of Mathematics Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350359589

With the continuous progress of photovoltaic (PV) technology and the steady reduction of related costs, solar energy, as an important renewable energy source, shows an increasingly strong competitiveness in energy market competition. In the tower solar thermal power station, the arrangement of the heliostat field directly affects the power generation efficiency of the tower power generation system as well as the working cost. Therefore, this paper presents a model based on geometric relationship and particle swarm algorithm for the optimization of the heliostat field arrangement, mathematical modeling and calculating cosine efficiency, truncation efficiency, etc., and effectively improves the output thermal power as well as the optical efficiency of the heliostat field. Geometric planning is utilized to determine the location of the absorption tower, the coordinates of the heliostat arrangement and other layout parameters to optimize the layout of the tower solar system. Drawing on the idea of clustering, the model analyzes the characteristics of the heliostat mirrors in the same region, uses same or similar parameters to minimize the cost of computation, improving the overall optical efficiency of the mirror field. The particle swarm algorithm is utilized to solve the parameters such as mirror length and mirror width of the heliostat to get the suitable size of the heliostat for the heliostat mirror field. After completing all the calculation and optimization steps, the final solution of the model is carried out in this paper. The layout scheme of the heliostat field optimized by the implementation of the model gets a significant performance improvement. Specifically, the average annual thermal power output of the heliostat field is improved by 33.2309 MW, while the average annual optical efficiency is also improved by 43.2%. These improvements effectively enhance the power generation efficiency of the whole system, confirming the effectiveness of the optimization

关键词： Campo arrangement method Geometric relationship Mirror field optimization arrangement Particle swarm algorithm Spatial transformation

来源：评论

学校读者我要写书评

暂无评论

Security-Oriented Network Intent Placement using Particle Swarm Optimization 7

Security-Oriented Network Intent Placement using Particle Sw...

引用

7th Cyber Security in Networking Conference, CSNet 2023

作者： Landeau, Gabriel Avgeris, Marios Leivadeas, Aris Lambadaris, Ioannis Department of Software and It Engineering Montréal Canada Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350342871

As the network infrastructure grows, its configuration and service provisioning become a tedious process. Accordingly, new paradigms have emerged, such as the Intent-Based Networking (IBN), that envision the automation of the network configuration, while minimizing the human intervention. Specifically, IBN allows users to interact with the network through high-level and declarative requests, called intents, which later can be translated into low-level configurations. IBN can entail different scopes and target network infrastructures, while being domain specific, which can create several challenges in terms of the final activation of the requested intents. To this end, in this paper, we mainly focus on intents that are expressing security and Quality of Service (QoS) network services demands that can be translated into Service Function Chains (SFC) and automatically deployed over a campus network. Our work and depending on the security level expressed in the intent, tries to optimally decide the level of multi-tenancy or complete segregation of the users' services that can be achieved, while satisfying the network provider's objectives. In particular, an artificial intelligence inspired algorithm called Particle Swarm Optimization (PSO) is modeled that automatically tries to find the best placement of the intents, while satisfying the security and QoS requirements of the users issuing the intents. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

IsoTGAN: Spatial and Geometrical Constraints at GAN and Transformer for 3D Contour Generation 17th

IsoTGAN: Spatial and Geometrical Constraints at GAN and Tr...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Phuong, Thao Nguyen Duy, Vinh Nguyen Sakaino, Hidetomo FPT Consulting Japan FPT Software Minato Japan Department of Computer Science and Communications Engineering Waseda University Shinjuku Japan

ISBN: (纸本)9789819626434

Image generation in 2D and 3D has become an active research topic in Deep Learning. Single or multiple input images with non-orthogonal views are used for another shape and texture with different viewing angles. On the other hand, computer-Aided Design (CAD) relies on handling-based 3D generation, i.e., isometric view images, from three orthographic view line drawings in 2D. However, since unique viewing pairs of such 2D and 3D images are required to train, SOTA models are insufficient to generate desirable images. More spatial and geometrical constraints remain undone due to less corresponding image features between images. This paper proposes IsoTGAN with a GAN-based generator with the Transformer in its generator, where three images of an object’s front, side, and top view are input. The encoder is trained by the spatial and geometrical relation among three view images. A novel Gaussian Enhanced Euclidean attention mechanism and a geometry-constrained loss function are also proposed for further local image feature enhancement. Extensive experiments on the SPARE3D dataset demonstrate that the proposed IsoTGAN outperforms State-of-the-art (SOTA) models, i.e., DINO, regarding local and global image feature accuracy. This helps generate 3D isometric view images in auto-CAD system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D generation attention CAD GAN Isometric view Transformer

来源：评论

学校读者我要写书评

暂无评论

An Efficient Privacy-Preserving Face Authentication Scheme Using Local Sensitive Hashing 24

An Efficient Privacy-Preserving Face Authentication Scheme U...

引用

12th International Conference on Communications and Broadband Networking, ICCBN 2024

作者： Zhu, Hui Xiong, Ling Zhang, XuCheng School of Cyberspace Security School of Cryptology Hainan University China School of Computer and Software Engineering Xihua University China

ISBN: (纸本)9798400717109

In the last few years, face recognition gains a huge development because of the popularity of intelligent devices and the development of computer vision. Security and privacy are essential to ensure the widespread application of face recognition authentication systems. Recently, a series of excellent privacy-preserving face recognition schemes have been proposed. However, existing schemes have computational bottlenecks or security risks, and the demand for security in real life is also continuously increasing. Targeted by these computation and security issues, we propose an efficient privacy-preserving face recognition authentication scheme based on symmetric cryptography and locally sensitive hashing. In the proposed scheme, the server can be semi-trusted and the user can get efficient authentication services from the server while protecting the privacy of user facial images, avoiding computational bottlenecks, where the authentication validity period of each user is controllable. In addition, the comparison with related schemes indicates that the proposed one has fewer computation overhead and communication overhead. © 2024 ACM.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Exploiting Secure Multi-Hop Transmissions with NOMA Networks: Performance Analysis 6

Exploiting Secure Multi-Hop Transmissions with NOMA Networks...

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Pramitarini, Yushintia Yoga Perdana, Ridho Hendra Shim, Kyusung An, Beongku Graduate School Hongik University Dept. of Software and Communications Engineering Korea Republic of School of Computer Engineering and Applied Mathematics Hankyong National University Korea Republic of Hongik University Dept. of Software and Communications Engineering Korea Republic of

ISBN: (纸本)9798350344349

In this paper, we analyze the secrecy performance of secure multi-hop transmission for the NOMA system. More specifically, the multi-hop transmission can extend the coverage of wireless transmission. However, according to the principle of the wireless medium, an eavesdropper can overhear the legitimate users' transmission, which leads to serious security issues. In order to analyze the relationship between network parameters and secrecy outage probability, we derive exact closed-form expressions for the secrecy outage probability (SOP) of cell center and cell edge users, respectively. The numerical results show that the simulation and analysis results are tightly matched. Additionally, we investigate the impact of the number of hops and the distance on the secrecy performance. © 2024 IEEE.

关键词： Transmissions

来源：评论

学校读者我要写书评

暂无评论

A Model for Detection of the Susceptible in Hospital Contact Network Based on Social Network Analysis 14th

A Model for Detection of the Susceptible in Hospital Contact...

引用

14th International Conference on computer Science and its Applications, CSA 2022 and the 16th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2022

作者： Yang, Yixuan Park, Doo-Soon Kim, Seok-Hoon Peng, Sony Siet, Sophort Ugli, Sadriddinov Ilkhomjon Rovshan Vilakone, Phonexay Department of Software Convergence Soonchunhyang University Asan Korea Republic of Department of Computer Software Engineering Soonchunhyang University Asan Korea Republic of Department of Computer Engineering and Information Technology National University of Laos Vientiane Laos

ISBN: (纸本)9789819912513

COVID-19 can be modeled as a SEIR disease transmission model, and early detection and prevention of susceptible is a great way to stop the spread of the virus. The purpose of this paper is to conduct community detection on the hospital's contact network (including patients, nurses, doctors, and managers), obtain frequently contacted communities (susceptible communities), and analyze the independent contact networks of different roles to obtain high-influence communities and rank the node influence, if nodes with high influence are included in the susceptible community, we will recommend focusing on observing these nodes to prevent the spread of virus. In this paper, we introduce a model that combines social networks analysis with disease transmission model to analyze hospital contact networks, apply the classic overlapping community detection method CPM to community detection of contact networks, and utilize PageRank algorithm to calculate the node's influence. The experimental results show that the model can effectively solve our problem. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Security and Privacy in Metaverse: A Comprehensive Survey

引用

Big Data Mining and Analytics 2023年第2期6卷 234-247页

作者： Yan Huang Yi(Joy)Li Zhipeng Cai Department of Software Engineering and Game Development Kennesaw State UniversityAtlantaCA 30060USA Department of Computer Science Georgia State UniversityAtlantaCA 30303USA

Metaverse describes a new shape of cyberspace and has become a hot-trending word since *** are many explanations about what Meterverse is and attempts to provide a formal standard or definition of ***,these definitions could hardly reach universal *** than providing a formal definition of the Metaverse,we list four must-have characteristics of the Metaverse:socialization,immersive interaction,real world-building,and *** characteristics not only carve the Metaverse into a novel and fantastic digital world,but also make it suffer from all security/privacy risks,such as personal information leakage,eavesdropping,unauthorized access,phishing,data injection,broken authentication,insecure design,and *** paper first introduces the four characteristics,then the current progress and typical applications of the Metaverse are surveyed and categorized into four economic *** on the four characteristics and the findings of the current progress,the security and privacy issues in the Metaverse are *** then identify and discuss more potential critical security and privacy issues that can be caused by combining the four ***,the paper also raises some other concerns regarding society and humanity.

关键词： Metaverse cybersecurity privacy protection cyber infrastructure extended reality

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in ChatGPT - A Survey 7

Deep Learning in ChatGPT - A Survey

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Hashana, A.M. Jasmine Brundha, P. Ahamed Ayoobkhan, Mohamed Uvaze Fazila, S. Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India Software Engineering New Uzbekistan University Tashkent Uzbekistan

ISBN: (纸本)9798350397284

Abstract-As a subset of machine learning, deep learning makes use of multiple-layer neural networks to learn with available data and make decisions or predictions. A large language model called ChatGPT is based on deep learning, specifically a type of neural network called a transformer. ChatGPT's transformer architecture uses attention mechanisms to focus on the most important parts of the input, allowing it to process and comprehend a large amount of text data. In order for the model to comprehend the context and meaning of natural language text, it is trained on a huge database of text, including articles and books. One of the main importance of using deep learning in ChatGPT is its intelligence to understand relationships and patterns from the input text and generate or predict new text that is homogeneous to the input/training data. Because of this, ChatGPT is able to respond to questions and prompts in a manner that is comparable to that of a human, making it useful for a wide scope of natural language processing missions like translating languages, summarizing texts, and responding to questions. It's worth noting that, while deep learning has been highly effective in ChatGPT, it is not without its limitations. To train, deep learning models can be very complex and require a lot of data and computing power. © 2023 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Experience as Source for Anticipation and Planning: Experiential Policy Learning for Target-driven Recommendation Dialogues

Experience as Source for Anticipation and Planning: Experien...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Dao, Huy Deng, Yang Bui, Khanh-Huyen Le, Dung D. Liao, Lizi Singapore Management University Singapore FPT Software AI Center College of Engineering and Computer Science VinUniversity Viet Nam

ISBN: (纸本)9798891761681

Target-driven recommendation dialogues present unique challenges in dialogue management due to the necessity of anticipating user interactions for successful conversations. Current methods face significant limitations: (I) inadequate capabilities for conversation anticipation, (II) computational inefficiencies due to costly simulations, and (III) neglect of valuable past dialogue experiences. To address these limitations, we propose a new framework, Experiential Policy Learning (EPL), to enhance such dialogues. Specifically, EPL embodies the principle of Learning From Experience, facilitating anticipation with an experiential scoring function that estimates dialogue state potential using similar past interactions stored in long-term memory. Moreover, to demonstrate its flexibility, we introduce Tree-structured EPL (T-EPL) as one possible training-free realization with Large Language Models (LLMs) and Monte-Carlo Tree Search (MCTS). In particular, T-EPL assesses past dialogue states with LLMs while utilizing MCTS to achieve hierarchical and multi-level reasoning. Extensive experiments on two published datasets demonstrate the superiority and efficacy of T-EPL. Code and data are available here. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：