检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Jinli Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

High-dimensional and incomplete (HDI) matrix contains many complex interactions between numerous nodes. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm only considers the current learning error to compute the stochastic gradient without considering the historical and future state of the learning error. To address this critical issue, this paper innovatively proposes an ADRC-incorporated SGD (ADS) algorithm by refining the instance learning error by considering the historical and future state by following the principle of an ADRC controller. With it, an ADS-based LFA model is further achieved for fast and accurate latent factor analysis on an HDI matrix. Empirical studies on two HDI datasets demonstrate that the proposed model outperforms the state-of-the-art LFA models in terms of computational efficiency and accuracy for predicting the missing data of an HDI matrix. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5598-5614页

作者： Xue, Jingjing Sun, Sheng Liu, Min Wang, Yuwei Meng, Xuying Wang, Jingyuan Zhang, JunBo Xu, Ke Chinese Academy of Sciences Institute of Computing Technology Beijing100045 China University of Chinese Academy of Sciences Beijing101408 China Zhongguancun Lab Beijing100190 China Beihang University School of Computer Science and Engineering Beijing100191 China Beihang University MIIT Key Laboratory of Data Intelligence and Management Beijing100191 China JD Technology JD iCity JD Intelligent Cities Research Beijing101111 China Tsinghua University Department of Computer Science and Technology Beijing100190 China Zhongguancun Laboratory Beijing100081 China

For distributed network traffic prediction with data localization and privacy protection, Federated Learning (FL) enables collaborative training without raw data exchange across Base Stations (BSs). Nevertheless, traffic across BSs exhibit inherently heterogeneous trend burst and smooth fluctuation properties, but existing FL methods model single-scale series from only one view, which cannot simultaneously capture diverse trend and fluctuation properties, especially distinct burst distributions. In this paper, we propose Personalized Federated Forecasting with Multi-property Self-fusion (P2FMS), which can represent multi-scale traffic properties from different views. With precise multi-property representations, a fusion-level prediction decision is learned for each client in a personalized manner to promptly sense traffic bursts and improve forecasting performance in non-IID settings. Specifically, P2FMS decomposes the traffic series into distinct time scales, based on which, we effectively extract closeness, period, and trend properties from different views. The closeness and period are embedded through global-view representations with spatial correlations, while non-stationary trends are individually fitted from the client-side view. Furthermore, a personalized combiner is designed to accurately quantify the proportion of general fluctuation raws (i.e., closeness and period) and specific trend property in predictions, which enables multi-property self-fusion for each client to accommodate heterogeneous traffic patterns and enhance prediction accuracy. Besides, an alternant training mechanism is introduced to optimize property representation and fusion modules with the convergence guarantee. Extensive experiments on real-world datasets show that P2FMS outperforms status quo methods in both prediction performance and convergence time. © 2002-2012 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Sustainable Learning of Computer Programming Languages Using Mind Mapping

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1687-1697页

作者： Shahla Gul Muhammad Asif Zubair Nawaz Muhammad Haris Aziz Shahzada Khurram Muhammad Qaiser Saleem Elturabi Osman Ahmed Habib Muhammad Shafiq Osama E.Sheta Department of Computer Science National Textile University Faisalabad37610Pakistan Department of Data Science University of the PunjabLahore54590Pakistan Department of Mechanical Engineering University of SargodhaSargodha40100Pakistan Faculty of Computing The Islamia University of BahawalpurBahawalpur63100Pakistan College of Computer Science and Information Technology Al Baha UniversityAl Baha1988Saudi Arabia Department of Information and Communication Engineering Yeungnam UniversityGyeongsan38541Korea College of Science Zagazig UniversityZagazig44511Egypt

In the current era of information technology,students need to learn modern programming languages efﬁ*** art of teaching/learning program-ming requires many logical and conceptual *** it’s a challenging task for the instructors/learners to teach/learn these programming languages effectively and efﬁ*** mapping is a useful visual tool for establishing ideas and connecting them to solve *** research proposed an effective way to teach programming languages through visual *** experimental study uses a mind mapping tool to teach two programming environments:Text-based Programming and Blocks-based *** performed the experiments with one hundred and sixty undergraduate students of two public sector universities in the Asia Paciﬁc *** different instructional approaches,including block-based language(BBL),text-based languages(TBL),mind map with text-based language(MMTBL)and mind mapping with block-based(MMBBL)are used for this *** results show that instructional approaches using a mind mapping tool to help students solve given tasks in their critical thinking are more effective than other instructional techniques.

关键词： Text programming blocks programming novice programmer

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Face Recognition Algorithm: Convolution Neural Network Approach 5

Heterogeneous Face Recognition Algorithm: Convolution Neural...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Sujatha, E. Manickam, M. Ani Minisha, R. Rekha, K.S. Indumathy, T. Department of Computer Science and Engineering Tamil Nadu Chennai India School of Computing Srm Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India Vel Tech Multi Tech Dr. Rr and Dr Sr Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu India Department of Medical Electronics Tamil Nadu Chennai India

ISBN: (纸本)9798350385649

Heterogeneous face recognition, also known as HFR, is an approach to facial recognition that attempts to match facial pictures that have been gathered through a variety of sensory modalities. HFR is primarily used for forensics, network security, and all commercial applications. The heterogeneous face recognition (HFR) algorithm is robust in handling challenges that exist in conventional face recognition. This is since heterogeneous face images display an enormous amount of intra- class variation, and it does not support hybrid modality of face images. This study provides a unique technique to transfer learning as a means of mastering invariant facial feature characteristics in visual (VIS) face pictures. A wrapping procedure combines end to end connections of two components for deep network. A discriminator has the details of fine-grained data for improving the quality of image which depends on wavelets. The system is made up of two different modules: one deals with face recognition, while the other determines a person's gender. It analysis about the characteristics of gender from the image using Convolutional Neural Networks that have been pre-trained. To train CNN in the face recognition module, in particular, the use of the open-source datasets Labelled Faces within the Wild, YouTube Face, and VGGFace2 results in an improvement in accuracy. Deep learning techniques and a substantial number of photographic examples of people's faces are what make it feasible for the proposed recognition to function so admirably. The problem of studying recognition remains challenging due to the limited size of the sample and the information gap between the senses. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning

arXiv

引用

arXiv 2024年

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

Dynamic graphs (DG) describe dynamic interactions between entities in many practical scenarios. Most existing DG representation learning models combine graph convolutional network and sequence neural network, which model spatial-temporal dependencies through two different types of neural networks. However, this hybrid design cannot well capture the spatial-temporal continuity of a DG. In this paper, we propose a tensor graph convolutional network to learn DG representations in one convolution framework based on the tensor product with the following two-fold ideas: a) representing the information of DG by tensor form;b) adopting tensor product to design a tensor graph convolutional network modeling spatial-temporal feature simultaneously. Experiments on real-world DG datasets demonstrate that our model obtains state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Healthcare gamification: science mapping the body of literature 43

Healthcare gamification: Science mapping the body of literat...

引用

43rd International Conference on Information Systems: Digitization for the Next Generation, ICIS 2022

作者： Machado, Franklin Jean Sanchez, Otávio Próspero Department of Technology and Data Science Fundação Getulio Vargas's Sao Paulo School of Business Administration Sao Paulo Brazil

ISBN: (纸本)9781713893615

Healthcare gamification is a research topic being investigated in numerous contexts. As it is an interdisciplinary subject, it is hard for researchers to keep up with the research published in these venues. This paper aims to unveil the intellectual structure of the healthcare gamification research field through a systematic literature review. We apply a science map strategy to a 520-document database. This database was analyzed to build an evolutionary map revealing the most co-cited authors, their publications, and the theories used. Results evidence that referenced research can be classified into six research traditions. Finally, research opportunities are presented. © 2022 International Conference on Information Systems, ICIS 2022: "Digitization for the Next Generation". All Rights Reserved.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH LINEAR FUNCTION APPROXIMATION: SINGLE-AGENT MDP AND MARKOV GAME 11

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH L...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Xiong, Wei Zhong, Han Shi, Chengshuai Shen, Cong Wang, Liwei Zhang, Tong Department of Mathematics The Hong Kong University of Science and Technology Hong Kong Center for Data Science Peking University China Department of Electrical and Computer Engineering University of Virginia United States National Key Laboratory of General Artificial Intelligence Peking University China School of Intelligence Science and Technology Peking University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the literature of offline RL under linear function approximation. Theoretical analysis demonstrates that our algorithm can match the performance lower bound up to logarithmic factors. We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm. To the best of our knowledge, these are the first computationally efficient and nearly minimax optimal algorithms for offline single-agent MDPs and MGs with linear function approximation. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

WatE: A Wasserstein t-distributed Embedding Method for Information-enriched Graph Visualization 39

WatE: A Wasserstein t-distributed Embedding Method for Infor...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cheng, Minjie Luo, Dixin Xu, Hongteng Gaoling School of Artifcial Intelligence Renmin University of China China School of Computer Science and Technology Beijing Institute of Technology China Beijing Key Laboratory of Big Data Management and Analysis Methods China

ISBN: (纸本)157735897X

As a fundamental problem of graph analysis, graph visualization aims to embed a set of graphs in a low-dimensional (e.g., 2D) space and provide insights into their distribution and clustering structure. Focusing on this problem, we propose a novel Wasserstein t-distributed embedding (WatE) method, leading to an information-enriched graph visualization paradigm. Our method learns a graph neural network to represent each graph as the mean and covariance of its node embedding distribution. Accordingly, our method can visualize each graph as an ellipse (determined by the mean and the covariance) rather than a single point. The positions of different ellipses reveal the relations among different graphs as traditional visualization methods do, while the size and shape of an ellipse preserve the node-level structural information of the corresponding graph. We propose a regularized t-distributed stochastic neighbor embedding (Rt-SNE) framework to learn the visualization model, deriving a Wasserstein distance-based Student’s t-distribution of graph pairs and fitting the distribution to the data distribution under regularization. Both subjective and objective evaluations demonstrate that WatE achieves encouraging performance in various graph visualization and clustering tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Flow visualization

来源：评论

学校读者我要写书评

暂无评论

Cross-domain NER with Generated Task-Oriented Knowledge: An Empirical Study from Information Density Perspective

Cross-domain NER with Generated Task-Oriented Knowledge: An ...

引用

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

作者： Zhang, Zhihao Lee, Sophia Yat Mei Wu, Junshuang Zhang, Dong Li, Shoushan Cambria, Erik Zhou, Guodong School of Computer Science & Technology NLP Lab Soochow University China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University Hong Kong Beijing Jinghang Research Institute of Computing and Communication China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Cross-domain Named Entity Recognition (CDNER) is crucial for Knowledge Graph (KG) construction and natural language processing (NLP), enabling learning from source to target domains with limited data. Previous studies often rely on manually collected entity-relevant sentences from the web or attempt to bridge the gap between tokens and entity labels across domains. These approaches are time-consuming and inefficient, as these data are often weakly correlated with the target task and require extensive pre-training. To address these issues, we propose automatically generating task-oriented knowledge (GTOK) using large language models (LLMs), focusing on the reasoning process of entity extraction. Then, we employ task-oriented pre-training (TOPT) to facilitate domain adaptation. Additionally, current cross-domain NER methods often lack explicit explanations for their effectiveness. Therefore, we introduce the concept of information density to better evaluate the model's effectiveness before performing entity recognition. We conduct systematic experiments and analyses to demonstrate the effectiveness of our proposed approach and the validity of using information density for model evaluation. © 2024 Association for Computational Linguistics.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Personalized Dementia Prediction Using Machine Learning Techniques

Personalized Dementia Prediction Using Machine Learning Tech...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Jayashree S Livedha S T Ragupathi Kumaran Hariharan R. Sanjana Dr Ginni Arora Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai India Manav Rachna International Institute of Research and Studies

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Early-stage dementia detection is a significant challenge in the healthcare field. Many individuals remain unaware of their cognitive decline until the condition progresses. This research aims to develop a personalized approach for predicting dementia. Multiple machine learning algorithms were applied to the dataset. Impressively, Random Forest model achieved a perfect accuracy of 98.75%.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Training data Medical services data models Random forests Dementia Overfitting

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：