检索结果-内蒙古大学图书馆

arXiv 2022年

作者： MacLaren, Neil G. Kundu, Prosenjit Masuda, Naoki Department of Mathematics State University of New York BuffaloNY14260-2900 United States Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY14260-5030 United States

Successfully anticipating sudden major changes in complex systems is a practical concern. Such complex systems often form a heterogeneous network, which may show multistage transitions in which some nodes experience a regime shift earlier than others as an environment gradually changes. Here we investigate early warning signals for networked systems undergoing a multistage transition. We found that knowledge of both the ongoing multistage transition and network structure enables us to calculate effective early warning signals for multistage transitions. Furthermore, we found that small subsets of nodes could anticipate transitions as well as or even better than using all the nodes. Even if we fix the network and dynamical system, no single best subset of nodes provides good early warning signals, and a good choice of sentinel nodes depends on the tipping direction and the current stage of the dynamics within a multistage transition, which we systematically characterize. © 2022, CC BY.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Gnn-Mgrpool: Enhanced Graph Neural Networks with Multi-Granularity Pooling for Graph Classification

SSRN

引用

SSRN 2023年

作者： Sun, Haichao Wang, Guoyin Liu, Qun Guo, Yike Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology 999077 Hong Kong School of Computer Engineering and Science Shanghai University Shanghai200444 China

Graph neural networks (GNNs) have gained significant attention and have been applied in various domain tasks. Currently, numerous pooling approaches have been proposed to aggregate node features and obtain node embeddings. However, current GNNs are almost black-box models that typically use a flat or single pooling step to aggregate nodes by only considering the similarity between nodes within the cluster. These approaches ignore the influence of relationships within and between clusters. To address this issue, we propose a novel multi-granular pooling method to aggregate nodes by simultaneously considering density and relationships among nodes and clusters. This method allows to obtain multi-granular node embedding clusters. The clusters in the current layer are built upon the previous layer, and these clusters change from fine to coarse as the number of clusters decreases, which is achieved by using multi-granular pooling (MgrPool for short). Additionally, the node representation of each layer is established through the ratio of node distance within clusters to that of between clusters. Finally, we conduct several experiments on node and graph classification tasks by this pooling approach. The results demonstrate that our GNN-MgrPool model outperforms the state-of-the-art similar algorithms and largely improves the interpretability of the learning process. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Non-adaptive and two-stage coding over the Z-channel

arXiv

引用

arXiv 2022年

作者： Lebedev, Alexey Lebedev, Vladimir Vorobyev, Ilya Deppe, Christian Kharkevich Institute for Information Transmission Problems Russian Academy of Sciences Moscow Russia Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow Russia Institute for Communications Engineering Department of Electrical and Computer Engineering Technical University of Munich Munich Germany

In this paper, we developed new coding strategies for the Z-channel. In particular, we look at the case with two-stage encoding. In this case, the encoder uses noiseless feedback once and adjusts the further encoding strategy based on the previous partial output of the channel. Nevertheless, the developed codes improve the known results with full feedback for small length and 1 error. A tool for the two-stage strategy is the development of a new optimality condition for non-adaptive codes. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency Analysis using Machine Learning and Deep Learning

Cryptocurrency Analysis using Machine Learning and Deep Lear...

引用

2021 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2021

作者： Thomas, C. Watson, Z. Kim, M. Baidya, A. Lamsal, M. Chowdhury, M.H. Basnet, M. Poudel, K.N. East Central University Department of Mathematics and Computer Science AdaOK United States Middle Tennessee State University Computational Science Program MurfreesboroTN United States University of Memphis Department of Electrical and Computer Engineering MemphisTN United States Embry-Riddle Aeronautical University Department of Mathematics and Data Science FL United States

来源：评论

学校读者我要写书评

暂无评论

Dimension reduction of dynamical systems on networks with leading and non-leading eigenvectors of adjacency matrices

arXiv

引用

arXiv 2022年

作者： Masuda, Naoki Kundu, Prosenjit Department of Mathematics State University of New York BuffaloNY14260-2900 United States Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY14260-5030 United States

Dimension reduction techniques for dynamical systems on networks are considered to promote our understanding of the original high-dimensional dynamics. One strategy of dimension reduction is to derive a low-dimensional dynamical system whose behavior approximates the observables of the original dynamical system that are weighted linear summations of the state variables at the different nodes. Recently proposed methods use the leading eigenvector of the adjacency matrix of the network as the mixture weights to obtain such observables. In the present study, we explore performances of this type of one-dimensional reductions of dynamical systems on networks when we use non-leading eigenvectors of the adjacency matrix as the mixture weights. Our theory predicts that non-leading eigenvectors can be more efficient than the leading eigenvector and enables us to select the eigenvector minimizing the error. We numerically verify that the optimal non-leading eigenvector outperforms the leading eigenvector for some dynamical systems and networks. We also argue that, despite our theory, it is practically better to use the leading eigenvector as the mixture weights to avoid misplacing the bifurcation point too distantly and to be resistant against dynamical noise. © 2022, CC BY.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A method for clustering scientific publications based on natural language for the purpose of strategic planning of partnerships in interdisciplinary research

A method for clustering scientific publications based on nat...

引用

Smart Information Systems and Technologies (SIST), IEEE International Conference on

作者： Malika Shamgunova Andrii Biloshchytskyi Oleksandr Kuchanskyi Faizullin Adil Computer Science and Engineering Astana IT University Kazakhstan Technical Sciences Professor Vice-Rector for Science and Innovation Astana IT University Kazakhstan Department of Information Technologies Kyiv National University of Construction and Architecture Ukraine Department of Computational and Data Science Astana IT University Kazakhstan Department of Information Control Systems and Technologies Uzhhorod National University Ukraine Strategy and Corporate Governance Department Astana IT University Kazakhstan

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

The current research aims at examining the Kazakhstani scholars’ publications in order to reveal the topdiscussed topics and possible cooperation topics. By employing natural language processing, the research abstracts are grouped thematically to demonstrate the various clusters of themes present. The results reveal specific themes of the Kazakhstani research to provide the recommendations for the future academic development of the country and the cooperation between various fields. Thus, the approach illustrated the benefit of using thematic clustering for analysis and categorization of a vast amount of scholarly production.

关键词： Productivity Workability data analysis Collaboration Strategic planning Natural language processing Information systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of Influenza in Henan Province Based on SARIMAX-LSTM Hybrid Model

Prediction of Influenza in Henan Province Based on SARIMAX-L...

引用

IEEE International Conference on Cloud Computing and Big data Analysis (ICCCBDA)

作者： Tianyu Xie Zisheng Liu Xu Yang Ping Wang Yilin Min Henan University of Economics and Law School of Data Science and ECommerce Zhengzhou China Henan University of Economics and Law School of Computational Economics Zhengzhou China Henan University of Economics and Law School of Statistics Zhengzhou China Henan University of Economics and Law School of Computer and Information Engineering Zhengzhou China

ISBN: (数字)9798331530808

ISBN: (纸本)9798331530815

In this paper, the relevant data of influenza-like case rate, resident consumer index, number of vaccinated and weather in Henan province in the past decade were selected, and the missing value and Pearson correlation analysis were processed through Lagrange interpolation to ensure the integrity and stability of the data. In this paper, first using the SARIMA model to analyze the data, Can effectively capture the seasonal variation in the data, However, it shows some limitations when dealing with nonlinear characteristics and external influence factors; Secondly, the SARIMAX model was introduced, Adding the significant variable temperature as an external factor, However, there is still room for optimization for complex nonlinear dynamics; Finally, by further introducing the LSTM model, Form a SARIMAXLSTM hybrid model, The empirical results show that, When the mixed model predicts the changing trend in the data, Showed higher accuracy and adaptability than the single model and decreased seasonal influenza activity during the summer, Gradually increasing in autumn and winter. The research results provide a scientific basis for public health prevention and control, and reflect the importance of data analysis in the social process.

关键词： Analytical models Adaptation models Temperature distribution Correlation computational modeling Time series analysis Influenza Predictive models data models Thermal stability

来源：评论

学校读者我要写书评

暂无评论

DeepCare: Deep Learning-Based Smart Healthcare Framework using 5G Assisted Network Slicing

DeepCare: Deep Learning-Based Smart Healthcare Framework usi...

引用

2022 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2022

作者： Basu, Deborsi Krishnakumar, Vikram Ghosh, Uttam Datta, Raja Indian Institute of Technology G. S. Sanyal School of Telecommunications Kharagpur India SASTRA Deemed Univ. Dept. of Electronics and Communication Engineering Tamil Nadu Thanjavur India School of Applied Computational Sciences MMC Dept. of Data Science and Computer Science United States Indian Institute of Technology Dept. of Electronics and Electrical Comm. Engg. Kharagpur India

ISBN: (纸本)9781665473408

5G and beyond communication networks require satisfying very low latency standards, high reliability, high-speed user connectivity, more security, improved capacity and better service demands. Augmenting such a wide range of KPIs (Key Performance Indicators) needs a smart, intelligent and programmable solution for TSPs (Telecommunication Service Providers). Resource availability and quality sustainability are challenging parameters in a heterogeneous 5G environment. Programmable Dynamic Network Slicing (PDNS) is a key technology enabling parameter that can allow multiple tenants to bring their versatile applications simultaneously over shared physical infrastructure. Latest emerging technologies like virtualized Software-Defined Networks (vSDN) and Artificial Intelligence (AI) play a pivotal supporting role in solving the above-mentioned constraints. Using the PDNS framework, we have proposed a novel slice backup algorithm leveraging Deep Learning (DL) neural network to orchestrate network latency and load efficiently. Our model has been trained using the available KPIs and incoming traffic is analyzed. The proposed solution performs stable load balancing between shared slices even if certain extreme conditions (slice unavailability) through intelligent resource allocation. The framework withstands service outage and always select the most suitable slice as a backup. Our results show latency-aware resource distribution for better network stability. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Explaining Agent Behavior in Agent-Based Modeling Using Subgroup Discovery

SSRN

引用

SSRN 2023年

作者： Romero, Elena Carmona del Jesús, Cristóbal José Cordón, Oscar del Jesus, María José Damas, Sergio Chica, Manuel Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Dept. of Computer Science and Artificial Intelligence DECSAI University of Granada Granada18071 Spain Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Jaen Jaen23071 Spain Leicester School of Pharmacy De Montfort University LeicesterLEI 9BH United Kingdom Dept. of Computer Science University of Jaen Jaen23071 Spain Dept. of Software Engineering University of Granada Granada18071 Spain School of Electrical Engineering and Computing The University of Newcastle CallaghanNSW2308 Australia

Agent-based modeling (ABM) is a popular tool for simulating complex systems. In addition to the key performance indicators ABM provides as main outputs of the modeling process, it also generates valuable information about the agents' roadmap, but the large volume of generated data is difficult to analyze and understand. Explainable Artificial Intelligence (XAI) techniques can improve the transparency and interpretability of these models. Subgroup Discovery (SD) is a useful tool for XAI that can facilitate the analysis of the data with respect to a variable of interest. In this contribution, we propose a methodology for applying SD to ABM for extracting useful knowledge of agents behavior from the model output. We compare the performance of different SD algorithms and show the effectiveness of our methodology through a case study in the marketing area. We analyze the obtained set of rules from the point of view of a marketing expert. The results show that our methodology can provide a deeper understanding of consumer behavior and market dynamics, providing potential areas of opportunity for marketers. © 2023, The Authors. All rights reserved.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

Deep and handcrafted feature supported diabetic retinopathy ...

引用

2022 International Conference on Machine Learning and data engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes;(i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database. © 2022 Elsevier B.V.. All rights reserved.

关键词： Deep learning

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：