检索结果-内蒙古大学图书馆

7th IEEE Information technology and Mechatronics Engineering Conference, ITOEC 2023

作者： Zeng, Tao Tao, Tiwei Fan, Guangjie Wang, Pengfei Ye, Feiye Jiao, Dian Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9798350334197

The study and analysis of complex systems are confronted with significant challenges due to their inherent adaptability and uncertainty. Traditional modeling techniques focused on individual components of the system are insufficient for capturing the whole character of the system, as complex system structures constantly evolve, leading to non-repetitive outcomes. The unreliability of traditional modeling methods is exacerbated by the unpredictability of complex systems. The limitations of graph-based modeling approaches lie in their reduced capacity to analyze the complex interdependencies among nodes, as well as the low-order and high-order associations that exist between them. The hypergraph weight method, by focusing on the relationships between nodes, captures the unique complex connections of complex systems and provides support for modeling. Therefore, this paper proposes a new approach to model complex systems using hypergraph weights to facilitate multi-agent decision-making. This method enhances the accuracy of analyzing high-order relationships between nodes and improves the precision of complex results. The proposed technique presents innovative ideas and strategies for the intelligent theoretical investigation of complex systems. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Research the Optimization Dispatch Method of New Power Systems with Wind-Solar-Hydro Storage 3

Research the Optimization Dispatch Method of New Power Syste...

引用

3rd International Conference on Energy, Power and Electrical Engineering, EPEE 2023

作者： Wang, Zhenbin Wu, Xixiu Fang, Zheng Xia, Lingyu Li, Li School of Automation Wuhan University of Technology Wuhan China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350318180

To address the issues of randomness and volatility caused by the high integration of renewable energy into the grid, and considering that traditional dispatch methods cannot meet the requirements effectively, the paper establishes a joint wind-solar-hydro storage generation model. An improved particle swarm optimization algorithm is employed for dispatch optimization research. The study reveals that energy storage devices not only mitigate the output fluctuations of renewable energy generation but also enhance energy utilization. Moreover, high-capacity energy storage systems can further strengthen the overall system's regulation capacity. © 2023 IEEE.

关键词： Dispatch Optimization The improved PSO Intelligent Algorithm Wind-Solar-Hydro Storage

来源：评论

学校读者我要写书评

暂无评论

Optimizing Data-Driven Federated Learning in UAV Networks 30

Optimizing Data-Driven Federated Learning in UAV Networks

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Li, Datian Xiao, Mingjun Xu, Yin Wu, Jie University of Science and Technology of China School of Computer Science and Technology & Suzhou Institute for Advanced Research China Temple University Department of Computer and Information Sciences United States

ISBN: (纸本)9798331515966

Federated Learning (FL) is an emerging privacy-preserving distributed machine learning paradigm that enables numerous clients to collaboratively train a global model without transmitting private datasets to the FL server. Unlike most existing research, this paper introduces a Data-Driven FL system in Unmanned Aerial Vehicle (UAV) networks, named DDFL, which features an innovative three-layer architecture. In this architecture, UAVs, inherently lacking data, serve as mobile clients and are tasked with periodically collecting desired data from a group of Points of Interest (PoIs) for FL training. Meanwhile, a Base Station (BS) coordinates these UAVs to efficiently train a high-quality global model. Our objective is to determine a data collection strategy for each UAV to minimize the time required to meet the global model's loss requirement within the constraint of energy consumption. Through theoretical analysis, we establish a bound for the convergence speed of DDFL and quantify the impact of collecting data from different PoIs on the global model's loss function. Leveraging these analyses, we formulate the PoI selection problem as a novel two-stage Combinatorial Multi-Armed Bandit (CMAB) problem with multiple constraints. We then propose an Adaptive Two-stage CMAB-based algorithm, named FedATC, to jointly optimize the data collection route and UAV velocity. Extensive simulations demonstrate that FedATC significantly reduces the time required to achieve desired model quality compared to state-of-the-art algorithms. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

DyGGAN: Traffic flow prediction based on generative adversarial network and dynamic graph convolution 5

DyGGAN: Traffic flow prediction based on generative adversar...

引用

5th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2023

作者： Li, Xiaofeng Li, Songjiang Wang, Peng Zhang, Wenxin Changchun University of Science and Technology School of Computer Science and Technology Changchun Jilin130013 China

ISBN: (纸本)9798350359930

Effective traffic management and planning hinge on precise short-term traffic flow forecasting, a challenging task given the non-Euclidean nature of traffic data and the intricate spatiotemporal dynamics within traffic networks. This research introduces DyGGAN, a novel model combining generative adversarial networks (GANs) and graph convolutional networks (GCNs) to overcome limitations of existing traffic flow prediction algorithms. DyGGAN dynamically adapts by utilizing a dynamic adjacency matrix, ensuring comprehensive learning of each node's attributes and capturing nuanced spatiotemporal correlations. The model integrates a dynamic graph convolutional network (DGCN) with a spatial attention mechanism, allowing the generator network to adeptly capture dynamic spatial features. A seamless integration of a gated recurrent unit (GRU) network enables understanding of dynamic changes in traffic flow and capturing local temporal dependencies, while a temporal attention mechanism records global dynamic temporal correlations. The synergy of unsupervised and supervised training in DyGGAN produces accurate traffic forecasts, as validated through experiments on real datasets (PEMS04 and PEMS08), showcasing its state-of-the-art performance in addressing the complexities of short-term traffic flow forecasting. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Empowering Biomedical Named Entity Recognition Through Multi-Tagger Collaboration 27

Empowering Biomedical Named Entity Recognition Through Multi...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zhao, Jin Xie, Jian Zhu, Tinghui Guo, Qian Li, Zhixu Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Department of Computer Science and Engineering East China University of Science and Technology China

ISBN: (纸本)9781643685489

Biomedical Named Entity Recognition (BioNER) plays a crucial role in automatically identifying specific categories of entities from biomedical texts. Currently, region-based methods have shown promising performance in BioNER. However, existing paradigms in the region-based methods suffer from inherent limitations, including the generation of negative samples, and the ignorance of token dependencies. To overcome these limitations, we propose a new paradigm, implemented as Token Cascade Tagger (TCT), which combines span identification and category classification. The TCT utilizes category information to enhance the correlation between the heads and tails of entities, effectively reducing the generation of negative samples. Additionally, we introduce a Token Dependency Tagger (TDT) that captures token dependencies within entity spans by identifying the longest span in a sentence. The TDT filters out incorrect spans and further improves the accuracy of span detection obtained from the TCT. Furthermore, we employ a multi-task learning framework to optimize both the TCT and TDT, leading to superior performance in BioNER. Extensive experiments on publicly available biomedical datasets demonstrate our method outperforms the previous state-of-the-art methods, achieving 92.44%, 92.54%, and 81.26% on NCBI-Disease, BC5CDR, and GENIA, respectively, in terms of F1 score. © 2024 The Authors.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization 33

Fine-grained Analysis of Stability and Generalization for St...

引用

33rd International Joint Conference on Artificial Intelligence, IJCAI 2024

作者： Zhang, Xuelin Chen, Hong Gu, Bin Gong, Tieliang Zheng, Feng College of Informatics Huazhong Agricultural University Wuhan430070 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China School of Artificial Intelligence Jilin University Jilin130012 China School of Computer Science and Technology Xi'an Jiaotong University Xi'an710049 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9781956792041

Stochastic bilevel optimization (SBO) has been integrated into many machine learning paradigms recently including hyperparameter optimization, meta learning, reinforcement learning, etc. Along with the wide range of applications, there have been abundant studies on concerning the computing behaviors of SBO. However, the generalization guarantees of SBO methods are far less understood from the lens of statistical learning theory. In this paper, we provide a systematical generalization analysis of the first-order gradient-based bilevel optimization methods. Firstly, we establish the quantitative connections between the on-average argument stability and the generalization gap of SBO methods. Then, we derive the upper bounds of on-average argument stability for single timescale stochastic gradient descent (SGD) and two timescale SGD, where three settings (nonconvex-nonconvex (NC-NC), convex-convex (C-C) and strongly-convex-strongly-convex (SC-SC)) are considered respectively. Experimental analysis validates our theoretical findings. Compared with the previous algorithmic stability analysis, our results do not require the re-initialization of the inner-level parameters before each iteration and are suited for more general objective functions. © 2024 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational study of laser fragmentation in liquid:Phase explosion,inverse Leidenfrost effect at the nanoscale,and evaporation in a nanobubble

引用

science China(Physics,Mechanics & Astronomy) 2022年第7期65卷 99-114页

作者： Hao Huang Leonid V.Zhigilei School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China Department of Materials Science and Engineering University of VirginiaCharlottesville 22904-4745USA

Laser fragmentation in liquid is an effective and environment-friendly processing technique capable of yielding colloidal nanoparticles and atomic clusters with a narrow size distribution. The advancement of this technique can be facilitated by an improved understanding of processes that control the sizes, shapes, and structures of the produced nanoparticles. In this work, the dependence of the fragmentation mechanisms on the energy density deposited by the laser pulse is investigated in atomistic simulations performed for 20 nm Au nanoparticles irradiated in water by 10 ps laser pulses. The simulations reveal that the decrease in the absorbed laser energy leads to sequential transitions from the regime of “strong” phase explosion, when all products of an explosive phase decomposition of the irradiated nanoparticle are promptly injected into the water surrounding a nanobubble formed around the nanoparticle, to two distinct regimes of nanoparticle fragmentation leading to the formation of a large central nanoparticle surrounded by smaller satellite fragments. First, in the regime of “mild” phase explosion, the central nanoparticle is produced by the reflection of some of the hot metal droplets generated by the explosive decomposition of the nanoparticle from the boundary of the nanobubble. This reflection is attributed to the inverse Leidenfrost effect acting at the nanoscale. The reflected droplets converge in the center of the nanobubble and coalesce into a single droplet that solidifies shortly after the collapse of the nanobubble. Further decrease in the absorbed laser energy brings the irradiation conditions below the threshold for the phase explosion and results in the formation of a core-satellite structure of the fragmentation products through an interplay of the intense evaporation from the surface of the irradiated nanoparticle, evolution of the nanobubble, and condensation of the metal vapor into clusters and small satellite nanoparticles. The computationa

关键词： laser fragmentation in liquid molecular dynamics simulations phase explosion inverse Leidenfrost effect nanobubble nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Data for Predicting Crop Growth 19th

Remote Sensing Data for Predicting Crop Growth

引用

19th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2024

作者： Li, Yunan Dhelim, Sahraoui Chen, Liming Kechadi, M-Tahar Belfield Dublin 4 Dublin Ireland School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9783031815416

This paper introduces an efficient approach, the dynamic coefficient polynomial model, which emulates crop growth dynamics using NDVI. This model, a significant improvement over traditional models like the NDVI mean and static polynomial models, is designed to be adaptable over time and incorporates spatial variables to account for the diverse growth conditions experienced in different regions. Consequently, the model’s responses and adaptations are influenced by the specific crop growth dynamics observed within these spatial dimensions, adding a new dimension to crop growth forecasting. Our results show that the proposed model achieves a higher accuracy than the other machine learning models, which is about 90.3%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A BLG1 neural model implements the unique looming selectivity to diving target

引用

Optoelectronics Letters 2023年第2期19卷 112-116页

作者： LUAN Hao HUA Mu ZHANG Yicheng YUE Shigang FU Qinbing School of Computer Science and Engineering Tianjin University of TechnologyTianjin 300384China School of Computer Science University of LincolnLincoln LN67TSUK School of Automation Guangdong University of Petrochemical TechnologyMaoming 525000China School of Mathematics and Information Science Guangzhou UniversityGuangzhou 510006China

The bistratified lobula giant type 1(BLG1) neuron is an identified looming-sensitive neuron in crab's visual brain that demonstrates special sensitivity to diving targets, or descending approaching motions. In this paper, a novel neural model is proposed to shape such unique selectivity through incorporating a bio-plausible feedforward contrast inhibition synapse and a radially extending spatial enhancement distribution. Herein the synaptic connections and neuronal functions of this model are placed within a framework for matching and describing underlying biological findings. The systematic and comparative experiments have validated the proposed computational model that reconciles with the characteristics of BLG1 neurons in crab.

关键词： A BLG1 neural model diving target BLG

来源：评论

学校读者我要写书评

暂无评论

A Single Image Derain Method Based on Residue Channel Decomposition in Edge Computing

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1469-1482页

作者： Yong Cheng Zexuan Yang Wenjie Zhang Ling Yang Jun Wang Tingzhao Guan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Automation Nanjing University of Information Science and TechnologyNanjing210044China School of Geographical Sciences Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing100101China School of Applied Technology Nanjing University of Information Science and TechnologyNanjing210044China

The numerous photos captured by low-price Internet of Things(IoT)sensors are frequently affected by meteorological factors,especially *** causes varying sizes of white streaks on the image,destroying the image texture and ruining the performance of the outdoor computer vision *** methods utilise training with pairs of images,which is difficult to cover all scenes and leads to domain *** addition,the network structures adopt deep learning to map rain images to rain-free images,failing to use prior knowledge *** solve these problems,we introduce a single image derain model in edge computing that combines prior knowledge of rain patterns with the learning capability of the neural ***,the algorithm first uses Residue Channel Prior to filter out the rainfall textural features then it uses the Feature Fusion Module to fuse the original image with the background feature *** results in a pre-processed image which is fed into Half Instance Net(HINet)to recover a high-quality rain-free image with a clear and accurate structure,and the model does not rely on any rainfall *** results on synthetic and real-world datasets show that the average peak signal-to-noise ratio of the model decreases by 0.37 dB on the synthetic dataset and increases by 0.43 dB on the real-world dataset,demonstrating that a combined model reduces the gap between synthetic data and natural rain scenes,improves the generalization ability of the derain network,and alleviates the overfitting problem.

关键词： Single image derain method edge computing residue channel prior feature fusion module

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：