检索结果-内蒙古大学图书馆

Computational Intelligence in Remote Sensing Image Registration:A survey

International Journal of Automation and computing 2021年第1期18卷 1-17页

作者： Yue Wu Jun-Wei Liu Chen-Zhuo Zhu Zhuang-Fei Bai Qi-Guang Miao Wen-Ping Ma Mao-Guo Gong Key Laboratory of Big Data and Intelligent Vision School of Computer Science and TechnologyXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic EngineeringXidian UniversityXi′an 710071China

In recent years,computational intelligence has been widely used in many fields and achieved remarkable *** computing and deep learning are important branches of computational *** methods based on evolutionary computation and deep learning have achieved good performance in remote sensing image *** paper introduces the application of computational intelligence in remote sensing image registration from the two directions of evolutionary computing and deep *** the part of remote sensing image registration based on evolutionary calculation,the principles of evolutionary algorithms and swarm intelligence algorithms are elaborated and their application in remote sensing image registration is *** application of deep learning in remote sensing image registration is also *** the same time,the development status and future of remote sensing image registration are summarized and their prospects are examined.

关键词： Computational intelligence evolutionary computation neural network deep learning remote sensing image registration

来源：评论

学校读者我要写书评

暂无评论

St-Kan-Former: A Novel Spatiotemporal Transformer Neural Network for Air Quality Prediction

SSRN

引用

SSRN 2025年

作者： Zhang, Wenyong Xia, Dawen Chang, Guoyan Zheng, Zhiquan Hu, Yang Huo, Yujia Wang, Ziqiang Feng, Fujian Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili556011 China Affiliated Hospital of Guizhou Medical University Guiyang550001 China State Key Laboratory of Public Big Data Guizhou University Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Accurate and timely air quality prediction is important for supporting daily activities and safeguarding respiratory health. However, the complex aerodynamic properties of air pollutants pose significant challenges to accurate air quality prediction. Most existing spatiotemporal prediction models extract spatial features in a coarse-grained manner, which cannot fully utilize the spatial feature data, resulting in poor prediction accuracy. To this end, we propose a novel air quality prediction method based on a Spatiotemporal Transformer with a Kolmogorov-Arnold Network (ST-KAN-Former). Specifically, in the temporal dimension, we use the wavelet transform, KAN, and ProbAttention network to construct the temporal feature extraction model. Based on this, the temporal dimension data are decomposed into high-frequency and low-frequency components, and then feature extraction is performed for fine-grained acquisition of temporal dimension features. Then, in the spatial dimension, we divide the spatial region into four subregions according to the distance parameter between the master site and the slave site and build a spatial feature extraction model for each subregion using KAN and ProbAttention networks. Next, we simulate the attenuation of pollutants during their dispersion to introduce the concept of diffusion coefficients. This approach allows us to apply diffusion processing to data from each subregion, enabling a finer granularity in capturing spatial characteristics. Finally, we employ the KAN and ProbAttention networks to construct a spatiotemporal feature fusion model that integrates temporal and spatial characteristics. Extensive experiments on the Beijing dataset demonstrate that ST-KAN-Former achieves better results compared with the other 11 benchmarks. © 2025, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DRLO: Optimizing edge server placement in dynamic MEC scenarios using deep reinforcement learning

引用

Computer Networks 2025年 268卷

作者： Yingya Guo Cen Chen College of Computer and Data Science Fuzhou University PR China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University PR China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian PR China

As an emerging computing paradigm, Mobile Edge Computing (MEC) significantly enhances user experience and alleviates network congestion by strategically deploying edge servers in close proximity to mobile users. However, the effectiveness of MEC hinges on the precise placement of these edge servers, a critical factor in determining the Quality of Experience (QoE) for mobile users. While existing studies predominantly focus on optimizing edge server placement in static scenarios, they often fall short when faced with user mobility, resulting in a degradation of QoE. To address this challenge, we propose an adaptive edge server placement approach that leverages Deep Reinforcement Learning (DRL) to select the base stations for placing edge servers in a dynamic MEC environment. Our objective is to minimize access delay by optimizing edge server placement for adapting to dynamic environment. To tackle the vast action space associated with edge server placement, we introduce a novel activation function in the actor neural network for efficient exploration. Furthermore, to enhance the adaptability of the derived edge server placement strategy, we meticulously design a new reward function, which takes into account the minimization of total access delay within dynamic MEC scenarios. Finally, to validate the effectiveness of our proposed method, extensive experiments were conducted using the Shanghai Telecom dataset. The results demonstrate that our approach outperforms baseline methods in minimizing access delay for users in dynamic MEC scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Noise-enhanced graph contrastive learning for multimodal recommendation systems

引用

Knowledge-Based Systems 2025年 324卷

作者： Ke Shi Yan Zhang Miao Zhang Kui Xiao Xiaoju Hou Zhifei Li School of Computer Science Hubei University Wuhan 430062 China Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University) Wuhan 430062 China Institute of Vocational Education Guangdong Industry Polytechnic University Guangzhou 510300 China

Multimodal recommendation systems enhance recommendation accuracy through the fusion of different types of information. Graph Contrastive Learning (GCL) has recently been widely applied in recommendation systems. However, the application of GCL mainly focuses on general user–item interactions, and few models apply it to multimodal information learning. This limitation may hinder the full potential of GCL in more complex multimodal scenarios. To address this issue, we propose a N oise- E nhanced G raph C ontrastive L earning for Multimodal Recommendation Systems (NEGCL). As different data augmentation strategies yield distinct outcomes in GCL, we have examined their relative strengths and weaknesses. Introducing innovative contrastive learning into the multimodal information extraction process helps address the limitations of this method in multimodal recommendation, supplemented by an improved transformer for learning in general interactions. A longitudinal comparison of contrastive learning across different methods reveals that noise-based contrastive learning substantially reduces the additional overhead potentially introduced by data augmentation. Furthermore, the introduction of appropriate noise allows contrastive learning to develop more robust nodes. Extensive experiments on three public datasets reveal that NEGCL surpasses previous benchmark models, achieving performance improvements ranging from 8.46% to 11.62% on the Clothing dataset. The source code is publicly available at https://***/HubuKG/NEGCL .

关键词：

来源：评论

学校读者我要写书评

暂无评论

A teaching quality evaluation framework for blended classroom modes with multi-domain heterogeneous data integration

引用

Expert Systems with Applications 2025年 289卷

作者： Yu Zhou Sai Zou Minghui Liwang Yanglong Sun Wei Ni The State Key Laboratory of Public Big Data College of Big Data and Information Engineering Guizhou University Guiyang Guizhou 550000 China Department of Control Science and Engineering the National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai 200433 China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai 200433 China Navigation College Jimei University Xiamen Fujian 361021 China Data61 CSIRO Sydney Australia

The blended teaching model, combining online and traditional classroom education, has become a normalized instructional approach in the artificial intelligence (AI) era. However, effectively integrating diverse educational data, accurately evaluating student learning, and providing personalized teaching recommendations remain key challenges. To address these, this study develops an AI-driven framework for evaluating teaching quality in blended classrooms. The framework aggregates multi-source educational data from both physical and digital learning environments, enabling a comprehensive assessment of student progress. Based on the evaluation outcomes, it leverages AI to generate personalized teaching strategies aligned with each student’s learning profile. Applied on a large scale in Western China, this framework has demonstrated significant improvements in teaching quality and efficiency. By bridging educational theory and AI-driven applications, this study offers a scalable model for enhancing personalized learning experiences in global digital education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Link prediction for attribute and structure learning based on attention mechanism

引用

Applied Soft Computing 2025年 179卷

作者： Renjuan Nie Guoyin Wang Qun Liu Chengxin Peng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing 400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing 400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing 401331 China

The link prediction problem within complex network analysis focus on accurately inferring future relationships between unconnected node pairs in networks. In real-world scenarios, many relationships can find effective expression through network representation learning, making link prediction pivotal in solving various practical problems. However, existing link prediction methods often exhibit an over-reliance on network structure information or struggle to effectively integrate network structure with node attribute information. Moreover, the current limitations of GPU memory pose challenges for deploying graph neural network (GNN) methods at scale. To address these challenges, this paper introduces attribute and structure learning based on attention mechanism(ASLAM), a novel link prediction framework that amalgamates graph neural networks with attention mechanisms. ASLAM adeptly extracts and integrates both node attribute and structural information, constructing semantic and structural node representations through attention mechanisms and facilitating predictions via adaptive merging. Additionally, to mitigate GPU memory consumption, ASLAM innovatively incorporates the subgraph history embedding method, ensuring stable performance with either constant or linear increases in memory consumption. Experimental results show ASLAM’s superiority over baseline methods across nine real datasets in link prediction tasks. The AUC and AP metrics witness enhancements ranging from 0.11% to 3.03% and 0.15% to 3.32%, respectively, underscoring its promise and applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Temporal Structural Pattern in Scientific Collaborative Behavior from the Perspective of Complex Network 23rd

The Temporal Structural Pattern in Scientific Collaborative...

引用

23rd International Symposium on Knowledge and Systems Sciences, KSS 2024

作者： Zholdoshbaeva, Elina Zhang, Shuang Liu, Feifan Xia, Haoxiang Institute of Systems Engineering Dalian University of Technology No. 2 Linggong Road Liaoning Dalian116024 China Center for Big Data and Intelligent Decision-Making Dalian University of Technology Linggong Road Liaoning Dalian116024 China School of Business East China University of Science and Technology 130 Meilong Road Xuhui District Shanghai200237 China Institute for Advanced Intelligence Dalian University of Technology Linggong Road Liaoning Dalian116024 China Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education of China Linggong Road Liaoning Dalian116024 China

ISBN: (纸本)9789819601776

The rapid advancement of science has underscored the importance of collaboration among scientists. While many studies have explored the structure of collaboration networks, there is a lack of comprehensive quantitative research on the temporal patterns of these collaborations. This study addresses this gap by analyzing temporal scientific collaboration networks in physics, spanning from 1960 to 2021, using complex network theories and methods. By constructing five-year temporal collaborative networks and employing metrics such as network diameter, shortest path, and clustering coefficient, this research reveals an increase in connectivity and small-world characteristics over time. Additionally, community detection highlights a shift towards specialized collaboration patterns and increased cross-community interactions. The study also uncovers growing centrality and social stratification within the research system, with the "rich club" phenomenon indicating strong and dynamic collaborations among highly connected scientists. Temporal analysis shows that while ultra-high connectivity scientists engage in fluctuating relationships, medium-high connectivity scientists maintain more stable collaborations. These findings provide insights into the evolution of collaborative behaviors and inform science policy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arXiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation 30

Step Feasibility-Aware and Error-Correctable Entailment Tree...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Song, Junyue Wu, Xin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

An entailment tree is a structured reasoning path that clearly demonstrates the process of deriving hypotheses through multiple steps of inference from known premises. It enhances the interpretability of QA systems. Existing methods for generating entailment trees typically employ iterative frameworks to ensure reasoning faithfulness. However, they often suffer from the issue of false feasible steps, where selected steps appear feasible but actually lead to incorrect intermediate conclusions. Moreover, the existing iterative frameworks do not consider error-prone search branches, resulting in error propagation. In this work, we propose SPEH: an iterative entailment tree generation framework with Step fesibility Perception and state Error Handling mechanisms. Step Feasibility Perception enables the model to learn how to choose steps that are not false feasible. State Error Handling includes error detection and backtracking, allowing the model to correct errors when entering incorrect search branches. Experimental results demonstrate the effectiveness of our approach in improving the generation of entailment trees. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Iterative methods

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：