检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Fei Gu, Tianhao Huang, Zhicong Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China SZU-AFS Joint Innovation Center for Artificial Intelligence Technology Shenzhen518000 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science The University of Nottingham Ningbo China Zhejiang315100 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA). While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC1) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation. The link to the TADAC dataset is https://***/documents/tadactextannotated-distortion-appearance-and-content Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of a 2D discrete memristive map

引用

Physica Scripta 2025年第7期100卷 075219-075219页

作者： Haiwei Sang Qiao Wang Yuling Chen Xiong Yu Feifei Wu Guizhou Key Laboratory of Artificial Intelligence and Brain-inspired Computing College of Mathematics and Big Data Guizhou Education University Guiyang 550018 People’s Republic of China School of artificial intelligence Guangzhou University 510006 People’s Republic of China State Key Laboratory of Public Big Data Guizhou University Guiyang 550025 People’s Republic of China Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor 43600 Malaysia

This study proposes a novel 2D memristive hyperchaotic map (2DMHM) with hyperbolic tangent and absolute value functions. The 2DMHM exhibits an infinite of fixed points in a set of lines on the y-axis, with stability characteristics partitioned across memristor parameters and initial condition planes. System dynamics are systematically investigated through bifurcation analysis, Lyapunov exponent spectra, and basin of attraction, trajectory plots, revealing remarkable multistability and initial-sensitive chaotic behavior. The map demonstrates superior spectral entropy (SE) complexity across critical parameter ranges, significantly outperforming conventional chaotic systems. A microcontroller-based digital implementation validates the physical realizability of 2DMHM, while the NIST test success rate demonstrates its exceptional performance in pseudorandom number generation. These results establish 2DMHM as a promising candidate for secure communication systems and cryptographic applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FlowX: Towards Explainable Graph Neural Networks via Message Flows

arXiv

引用

arXiv 2022年

作者： Gui, Shurui Yuan, Hao Wang, Jie Lao, Qicheng Li, Kang Ji, Shuiwang The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States The Department of Electronic Engineering and Information Science University of Science and Technology of China Anhui Hefei230026 China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The West China Biomedical Big Data Center West China Hospital Sichuan Chengdu610041 China

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows are more natural for performing explainability. To this end, we propose a novel method here, known as FlowX, to explain GNNs by identifying important message flows. To quantify the importance of flows, we propose to follow the philosophy of Shapley values from cooperative game theory. To tackle the complexity of computing all coalitions’ marginal contributions, we propose a flow sampling scheme to compute Shapley value approximations as initial assessments of further training. We then propose an information-controlled learning algorithm to train flow scores toward diverse explanation targets: necessary or sufficient explanations. Experimental studies on both synthetic and real-world datasets demonstrate that our proposed FlowX and its variants lead to improved explainability of GNNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

(Benefits of Internet of Things (IoT) Applications in Health care - An Overview)

(Benefits of Internet of Things (IoT) Applications in Health...

引用

Computational intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Preeti Chaudhary Satya Prakash Yadav Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Mersin Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Mersin Turkey Research Center for AI and IoT Faculty ofEngineering University of Kyrenia Kyrenia Mersin Turkey Computer Science and Engineering Graphic Era Hill University Dehradun Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) Greater Noida India

In a nutshell, the IoT refers to the idea of integrating high-tech technology in the form of "smart" gadgets and sensors into a single setting to gather data. There are still numerous areas in which machines cannot compete favorably with people, but data collection and analysis are undeniably two of their strongest points. The Internet of Things makes it possible to fully or partially automation data, it involves related activities, which is obviously very important for the healthcare industry. What exactly is the Internet connected medical things, and how exactly might it make a significant impact on the sector? By having to apply the concept of the internet of things (IoT) to the field of medicine, several significant advancements have become possible, including the ability to automatically control the thermostat of containers while transmitting inoculations and antibiotics, the accurate tracking of the ailments of a lot of illnesses without a need for additional meetings with a general practitioner, the correct and most useful use of meds, and a great deal more. All of this is realizable because of the capability of MedTech gadgets to carry out continuous monitoring system. The potential applications of internet of things technology in healthcare are very interesting. Let’s review the ways in which this technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An in-depth examination of cyberbullying detection utilizing machine learning techniques

引用

AIP Conference Proceedings 2024年第1期3207卷

作者： Ajay B. Gadicha Vijay B. Gadicha Ahmed J. Obaid Zainab Ali Abbood Department of Artificial Intelligence and Data Science P R Pote Patil College of Engineering and Management Amravati Maharashtra India Faculty of Computer Science and Mathematics University of Kufa Najaf Iraq Al-Esraa University Baghdad Iraq

During the era of web 4.0, social media has become a popular trend among internet users. People use social media platforms to share their thoughts and emotions, seeking support from their peers. However, this also exposes them to privacy threats from certain individuals. Cyberbullying is a significant issue in this context, referring to attacks that occur on social media platforms through comments or tweets. The consequences of cyberbullying can be severe, leading to depression, anxiety, and other forms of self-harm. To gain a deeper understanding of this problem, a comprehensive survey was conducted, focusing on the contributions of various authors. This survey primarily examined different machine learning techniques and pre-processing techniques, utilizing data from popular sources between 2015 and 2023. The findings of this survey indicate that the most commonly employed methods in cyberbullying research are tokenization processing and support vector machines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Hypergraph Convolution Group Recommendation with Member Information Enhancement

Multi-Channel Hypergraph Convolution Group Recommendation wi...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Tianhao Chen Qian Gao Jun Fan Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Shandong China China Telecom Digital Intelligence Techonology Co Ltd Jinan Shandong China

Group recommendation involves comprehensively considering various aspects, including members and items, to predict the overall interests of a group and recommend suitable items through a recommendation system. With the rapid evolution of the Internet, online group activities have become increasingly prevalent, making group recommendation a highly discussed topic within the realm of recommendation systems. However, current research in group recommendation still confronts the following challenges. Firstly, a predominant portion of group recommendation research focuses solely on aggregating group-level information, neglecting the valuable contribution of higher-order member-level insights to group recommendation. Moreover, some aggregation strategies overly prioritize fairness, thereby disregarding common real-world patterns. Secondly, previous studies have primarily relied on aggregating individual member interests to establish group preferences, lacking a holistic consideration of group dynamics. To tackle these challenges, this study introduces an innovative approach by implementing multi-channel hypergraph convolution within the member perspective. This approach aims to effectively extract higher-order insights from members by utilizing a member information enhancement module. By establishing group interconnections based on similarity and employing an adaptive fusion network to amalgamate multiple viewpoints, a final representation is derived. Experimental results demonstrate that our proposed model surpasses baseline models by 3% to 4% in terms of hit rate and accuracy, validating the efficacy of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of artificial intelligence in Medical Sectors

Analysis of Artificial Intelligence in Medical Sectors

引用

Augmented intelligence and Sustainable Systems (ICAISS), International Conference on

作者： J Thilagavathi K Lavanya S. Elango M. Santhoshi T. Muthumanickam G. Ramachandran Dept of Artificial intelligence and data science Arjun College of Technology Coimbatore Dept of CSE Madanapalle Institute of Technology & Science Chittoor Andhra Pradesh Department of Electronics and Communication Engineering CVR college of engineering Telangana Department of Electronics and Communication Engineering Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation Deemed to be University Salem India Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation (Deemed to be University) Salem

ISBN: (纸本)9781665489638

Medical engineering research has recently advanced significantly. The ability to accurately record a significant amount of medical data has increased because to advancements in measuring device technology, which has caused medical data to rise rapidly. A significant amount of data has been encountered and it is crucial to use this enormous amount of data sensibly. By using an artificial intelligence (AI) based reasoning engine to scan medical data, it is possible to compile user-generated keywords and instantly suggest relevant content to users. The decision tree algorithm is emphasized as one of the main technologies to implement data mining in this research, and it also explores how data mining technology is used in clinical medical diagnosis mining and analysis.

关键词： Industries Systematics Search engines Stability analysis data mining Medical diagnosis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach

arXiv

引用

arXiv 2023年

作者： Xiao, Yong Xia, Rong Li, Yingyu Shi, Guangming Nguyen, Diep N. Hoang, Dinh Thai Niyato, Dusit Krunz, Marwan The School of Electronic Information and Communications The Huazhong University of Science and Technology Wuhan430074 China The Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Guangzhou510555 China The School of Mech. Eng. and Elect. Inform. The China University of Geosciences Wuhan430074 China The School of Artificial Intelligence The Xidian University Shanxi Xi'An710071 China The School of Electrical and Data Engineering University of Technology Sydney Australia The School of Computer Science and Engineering Nanyang Technological University Singapore The Department of Electrical and Computer Engineering The University of Arizona TucsonAZ United States

With the rising demand for wireless services and increased awareness of the need for data protection, existing network traffic analysis and management architectures are facing unprecedented challenges in classifying and synthesizing the increasingly diverse services and applications. This paper proposes FS-GAN, a federated self-supervised learning framework to support automatic traffic analysis and synthesis over a large number of heterogeneous datasets. FS-GAN is composed of multiple distributed Generative Adversarial Networks (GANs), with a set of generators, each being designed to generate synthesized data samples following the distribution of an individual service traffic, and each discriminator being trained to differentiate the synthesized data samples and the real data samples of a local dataset. A federated learning-based framework is adopted to coordinate local model training processes of different GANs across different datasets. FS-GAN can classify data of unknown types of service and create synthetic samples that capture the traffic distribution of the unknown types. We prove that FS-GAN can minimize the Jensen-Shannon Divergence (JSD) between the distribution of real data across all the datasets and that of the synthesized data samples. FS-GAN also maximizes the JSD among the distributions of data samples created by different generators, resulting in each generator producing synthetic data samples that follow the same distribution as one particular service type. Extensive simulation results show that the classification accuracy of FS-GAN achieves over 20% improvement in average compared to the state-of-the-art clustering-based traffic analysis algorithms. FS-GAN also has the capability to synthesize highly complex mixtures of traffic types without requiring any human-labeled data samples. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An improved entropy function for the intuitionistic fuzzy sets with application to cloud vendor selection

引用

Decision Analytics Journal 2023年 7卷

作者： Krishankumar, Raghunathan Ravichandran, K.S. Aggarwal, Manish Pamucar, Dragan Information Technology Systems and Analytics Area Indian Institute of Management Bodh Gaya Bihar Bodh Gaya 824234 India Department of Mathematics Amrita School of Physical Sciences Coimbatore Amrita Vishwa Vidyapeetham India School of Artificial Intelligence and Data Science IIT Jodhpur Jodhpur India Digital Humanties IIT Jodhpur Jodhpur India Faculty of Organizational Sciences University of Belgrade Serbia College of Engineering Yuan Ze University Taiwan

This study proposes a novel entropy function for the intuitionistic fuzzy sets to improve the existing fuzzy entropy measure. We introduce an attitude-based entropy measure by methodically calculating the experts’ attitude values through variance approach. We discuss several important properties and present an example to demonstrate the applicability and efficacy of the proposed method. An illustrative example exhibits the effectiveness of the proposed intuitionistic fuzzy entropy functions and measures. We further show the superiority of the proposed intuitionistic fuzzy entropy measures over the existing measures. © 2023 The Author(s)

关键词： Aggarwal entropy Cloud vendor selection Decision-making Intuitionistic fuzzy sets Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Stability of partially unstable discrete-time switched positive nonlinear systems with delays

引用

Applied Mathematics and Computation 2025年 507卷

作者： Jinyuan Ni Yin Sheng Qiang Xiao Zhigang Zeng Tingwen Huang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China the Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

This paper addresses the stability issue of discrete-time switched positive nonlinear systems (SPNSs) characterized by partial unstable subsystems and constant delays. Firstly, we use a parameter to constrain the ratio of active durations of the stable and unstable modes, and derive the exponential stability conditions for SPNSs based on a key function. Then we analyze the relationship between convergence speed and the constant delay. Additionally, we obtain a stability criterion of SPNSs under a particular sequence of switching signals. Finally, we validate the results through a numerical example.

关键词： Exponential stability Switched positive nonlinear systems Time delay Unstable subsystems

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：