检索结果-内蒙古大学图书馆

Predicting travel demand of a bike sharing system using graph convolutional neural networks

PUBLIC TRANSPORT 2025年第1期17卷 281-317页

作者： Behroozi, Ali Edrisi, Ali KN Toosi Univ Technol Fac Civil Engn Tehran Iran

Public transportation systems play a crucial role in daily commutes, business operations, and leisure activities, emphasizing the need for effective management to meet public demands. One approach to achieve this goal is by predicting demand at the station level. Bike-sharing systems, as a form of transit service, contribute to the reduction of air and noise pollution, as well as traffic congestion. This study focuses on predicting travel demand within a bike-sharing system. A novel hybrid deep learning model called the gate graph convolutional neural network is introduced. This model enables prediction of the travel demand at station level. By integrating trajectory data, weather data, access data, and leveraging gate graph convolution networks, the accuracy of travel demand forecasting is significantly improved. The Chicago city bike-sharing system is chosen as the case study. In this investigation, the proposed model is compared to the base models used in previous literature to evaluate their performance, demonstrating that the main model exhibits better performance than the base models. By utilizing this framework, transportation planners can make informed decisions on resource allocation and rebalancing management.

关键词： Demand modeling Machine learning graph convolutional neural network Accessibility Bike-sharing

来源：评论

学校读者我要写书评

暂无评论

Rural Distributed Photovoltaic Spatial Generation Forecasting Based on graph convolutional neural networks with Temporal-Spatial Correlation 13th

Rural Distributed Photovoltaic Spatial Generation Forecastin...

引用

13th International Conference on Clean and Green Energy

作者： Zhou, Milu Wang, Shuai Yang, Xiaoyan Nanning Power Supply Bur Guangxi Power Grid Co Lt Nanning Peoples R China

ISBN: (纸本)9789819618149;9789819618125;9789819618118

Due to the unique geographical location of rural areas, distributed PV systems are more dispersed. This leads to difficulties in mining the spatio-temporal characteristics of their output. To overcome this challenge, a graph-temporal convolutional neural network prediction method based on spatio-temporal correlation is proposed. The distributed PV system is considered a class I cell nodes. Its historical output data serves as the feature information of the node, while the topology of its spatial location is used as an edge to construct a spatio-temporal information graph of the system's output. The adjacency matrix is determined using the spatial correlation of distributed PV systems. The spatio-temporal information graph and the spatial output is input into the graph-temporal convolutional network for training and prediction. This paper uses PV power generation data in a rural area as an example to compare with existing methods and verify the effectiveness of the proposed method.

关键词： Spatiotemporal characteristics Adjacency matrix graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

GShuttle:Optimizing Memory Access Efficiency for graph Convolu-tional neural network Accelerators

引用

Journal of Computer Science & Technology 2023年第1期38卷 115-127页

作者：李家军王可郑皓 Ahmed Louri School of Astronautics Beihang UniversityBeijing 100191China Department of Electrical and Computer Engineering University of North Carolina at CharlotteCharlotteNC 28223 U.S.A. Department of Electrical and Computer Engineering University of Central FloridaOrlandoFL 32816U.S.A. Department of Electrical and Computer Engineering George Washington UniversityWashingtonDC 20052U.S.A.

graph convolutional neural networks(GCNs)have emerged as an effective approach to extending deep learning for graph data analytics,but they are computationally challenging given the irregular graphs and the large num-ber of nodes in a *** involve chain sparse-dense matrix multiplications with six loops,which results in a large de-sign space for GCN *** work on GCN acceleration either employs limited loop optimization techniques,or determines the design variables based on random sampling,which can hardly exploit data reuse efficiently,thus degrading system *** overcome this limitation,this paper proposes GShuttle,a GCN acceleration scheme that maximizes memory access efficiency to achieve high performance and energy *** systematically explores loop opti-mization techniques for GCN acceleration,and quantitatively analyzes the design objectives(e.g.,required DRAM access-es and SRAM accesses)by analytical calculation based on multiple design *** further employs two ap-proaches,pruned search space sweeping and greedy search,to find the optimal design variables under certain design *** demonstrated the efficacy of GShuttle by evaluation on five widely used graph *** experimental simulations show that GShuttle reduces the number of DRAM accesses by a factor of 1.5 and saves energy by a factor of 1.7 compared with the state-of-the-art approaches.

关键词： graph convolutional neural network memory access neural network accelerator

来源：评论

学校读者我要写书评

暂无评论

Rapidly tailor metal-organic frameworks for arsenate removal using graph convolutional neural networks

引用

SEPARATION AND PURIFICATION TECHNOLOGY 2025年第Part7期354卷

作者： Lin, Zuhong Chen, Jiarong Fang, Ying Deng, Shi-hai Li, Haipu Yang, Ying Yao, Jingjing Cent South Univ Coll Chem & Chem Engn Ctr Environm & Water Resources Changsha 410083 Peoples R China Key Lab Hunan Prov Water Environm & Agr Prod Safet Changsha 410083 Peoples R China Yueyang Univ Coll Chem Engn & Mat Sci Yueyang 414000 Peoples R China Xi An Jiao Tong Univ Sch Human Settlements & Civil Engn Xian 710049 Peoples R China

Metal-organic frameworks (MOFs) are effective materials for the removal of highly toxic arsenates (As(V)). However, the intricate structure-activity relationships of MOFs for As(V) removal remain unclear, thus impeding its targeted fabrication. In this work, we used the graph convolutional neural network to integrate MOFs' chemical composition, physical structure, and adsorption environment, thereby developing an end-to-end predictive model for As(V) adsorption by MOFs. The model's high coefficient of determination, low mean absolute error, and experimental verification of MOFs synthesized based on model predictions not previously used in the As (V) adsorption confirmed the precision and general applicability of the model. Our constructed model identified two key features for adsorption, i.e., metal nodes and pore features, and the modular blocks for constructing MOFs. The strategic design for MOFs to absorb As(V) informed by the model, emphasized integrating open single or binuclear metal nets with aromatic di- or tricarboxylic acid linkers within a robust threedimensional topological net. This work highlights the integration of predictive modeling and structural refinement to enhance MOF design for As (V) adsorption, even in more other pollutants.

关键词： graph convolutional neural network Metal-organic frameworks (MOFs) Arsenate (As(V)) absorption Water purification

来源：评论

学校读者我要写书评

暂无评论

An adaptive spatio-temporal graph recurrent network for short-term electric vehicle charging demand prediction

引用

APPLIED ENERGY 2025年 383卷

作者： Wang, Shengyou Li, Yuan Shao, Chunfu Wang, Pinxi Wang, Aixi Zhuge, Chengxiang Peoples Publ Secur Univ China Sch Traff Management Beijing Peoples R China Hong Kong Polytech Univ Shenzhen Res Inst Shenzhen Peoples R China Hong Kong Polytech Univ Dept Land Surveying & Geoinformat Hung Hom Kowloon Hong Kong Peoples R China Xinjiang Univ Xinjiang Key Lab Green Construct & Smart Traff Con Urumqi Peoples R China Beijing Transport Inst 9 Liuliqiao South Lane Beijing 100073 Peoples R China China Univ Petr Coll Chem Engn & Environm Beijing Peoples R China Hong Kong Polytech Univ Res Inst Sustainable Urban Dev Hong Kong Peoples R China Hong Kong Polytech Univ Smart Cities Res Inst Hong Kong Peoples R China Hong Kong Polytech Univ Shenzhen Technol & Innovat Res Inst Futian Shenzhen Peoples R China

Predicting Electric vehicle (EV) charging demand can facilitate the efficient operation and management of the smart power grid and intelligent transportation systems. We propose an adaptive spatial-temporal graph recurrent network (ASTGRN) to predict the EV charging demand in short term at the charging station level. Specifically, we design an adaptive graph learning layer that learns the spatial correlations in a data-driven manner. Additionally, an embedding project layer is integrated to enhance the graph learning layer. Subsequently, a graph recurrent layer consisting graph convolutional kernel and gated recurrent unit is employed to extract spatial-temporal features from the observations. We evaluate the proposed ASTGRN model using a real- world EV GPS trajectory dataset containing charging information of over 76,000 EVs in Beijing. The experiment results suggest that ASTGRN achieves state-of-the-art performance compared to those advanced spatial-temporal prediction models (e.g., Temporal graph convolutional network and graphWave Net). The effectiveness of the proposed model in charging demand prediction indicates that the spatial correlation between different charging stations may not be related to geographical distance in the charging demand prediction task, and the use of prior knowledge of geographical location may undermine model performance.

关键词： Electric Vehicles Charging Demand Prediction Spatial-Temporal graph Recurrent network graph convolutional neural network Gated Recurrent Unit

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Thermal Performance for the Electric Drive Assembly Based on Mechanism and Data-Driven Modeling

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第1期11卷 3169-3181页

作者： Tang, Peng Zhao, Zhiguo Li, Haodi Tongji Univ Sch Automobile Engn Shanghai 201804 Peoples R China

Accurate prediction of transient temperature field (TTF) dynamic variation for electric drive assembly (EDA) can effectively monitor its future abnormal temperature, thereby ensuring the safe operation of vehicles. In this study, a spatio-temporal fusion relational graph convolutional neural network combined with ordinary least-squares method (OLS-FRGCN) is introduced. First, the lumped parameter thermal network (LPTN) is used to establish EDA's thermal network model. An adaptive coverage matrix is used to dynamically optimize each thermal path weight. Second, node embedding is used to learn nodes' spatial dependence and dynamically generate the adjacency matrix. Finally, a weighted fusion both of static and dynamic graph features is carried out to improve the TTF's prediction accuracy. The comparison results indicate that OLS-FRGCN has better integrated prediction accuracy than the other four algorithms on two measured real datasets. When the prediction time is 10 s, the peak root mean squared error (RMSE) does not exceed 1.24 degrees C, which reduces 5.99%-27.98% and 8.3%-46.56% than the four algorithms. Meanwhile, the online prediction results are also very close to the real measured values, and the global prediction errors and RMSE are 4.14 degrees C and 1.055 degrees C, respectively.

关键词： Temperature sensors Estimation Motors Temperature measurement Temperature distribution Rotors Predictive models Dynamic thermal network electric drive gearbox fusion graph convolution structure graph convolutional neural network transient temperature field (TTF)

来源：评论

学校读者我要写书评

暂无评论

Cross-modal retrieval of chest X-ray images and diagnostic reports based on report entity graph and dual attention

引用

MULTIMEDIA SYSTEMS 2025年第1期31卷 1-16页

作者： Ou, Weihua Chen, Yingjie Liang, Linqing Gou, Jianping Xiong, Jiahao Zhang, Jiacheng Lai, Lingge Zhang, Lei Guizhou Normal Univ Sch Big Data & Comp Sci Guiyang Peoples R China Guizhou Normal Univ Sch Math Sci Guiyang Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing Peoples R China Guizhou Univ State Key Lab Publ Big Data Guiyang Peoples R China

Cross-modal retrieval for chest X-ray images and diagnostic reports is the automated process of fetching reports or related images from an extensive medical records database using specific queries. Current methods for cross-modal retrieval of chest X-ray images and diagnostic reports often struggle with the fine-grained semantic representation alignment between chest X-ray images and text reports. However, these methods do not use the structured information in reports well, making it hard to interpret and align the image and text representation effectively, leading to poor retrieval performance. In this paper, we propose a novel framework for cross-modal retrieval of chest X-ray images and diagnostic reports based on a report entity graph and dual attention mechanisms. Specifically, we first employ the X-ray image encoder to extract fine-grained visual semantic representations of the X-ray images, and we use the report encoder to extract text features and anatomical entity features from the diagnostic reports. Moreover, a graph convolutional neural network (GCN) is utilized to effectively capture the semantic relationships among the report entities. To simulate the different levels of attention radiologists pay when reading chest X-ray images and reports, we designed a dual attention: intra-attention and inter-attention. The intra-attention mechanism is proposed to fuse global features with local representations that contain fine-grained structures and rich details in images and reports, respectively. The inter-modal attention mechanism is designed to establish accurate connections between the medical report entities and the fine-grained representations of the chest radiograph images. Our method achieves approximately 6.2%, 3.9%, and 4.9% improvements in report retrieval tasks and 7.4%, 4.0%, and 5.5% improvements in X-ray image retrieval tasks over the latest HSR method on three commonly used chest radiograph datasets.

关键词： Medical chest X-ray image Cross-modal retrieval graph convolutional neural network Attention mechanism Entity extraction

来源：评论

学校读者我要写书评

暂无评论

GCATRL: Using deep reinforcement learning to optimize knowledge graph completion

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2025年第3期19卷 790-810页

作者： Zhang, Liping Xu, Minming Li, Song Harbin Univ Sci & Technol Sch Comp Sci & Technol Harbin 150080 Peoples R China

Knowledge graph Completion (KGC) holds significance across various applications, such as Q&A systems, search engines, and recommendation systems. However, employing deep reinforcement learning for this task encounters specific challenges, impacting completion accuracy and stability. These challenges include sparse rewards, intricate multi-step reasoning, absence of domain-specific rules, overestimation problems, and coupling issues of value and policy. In response, this paper presents GCATRL, a reinforcement learning model integrating the Dual-Delay Deep Deterministic Policy Gradient based on Correlation and Attention Mechanisms (CATD3) with Generative Adversarial networks (GANs). Initially, we adopt graph convolutional neural network (GCN) for preprocessing to represent the relationships and entities in the knowledge graph as continuous vectors. Subsequently, we combined Wasserstein-GAN (WGAN) with the designed gated recurrent unit (HOGRU), introduced an attention mechanism to record the path trajectory sequence formed during the knowledge graph traversal process, and dynamically generated new subgraph at the appropriate time to ensure that the traversal process of the knowledge graph continues. Finally, CATD3 is used to optimize rewards and mitigate adversarial losses. We demonstrate through experimental results that the proposed model outperforms traditional algorithms on multiple tasks performed on multiple datasets.

关键词： graph convolutional neural network Knowledge graph Completion Generative Adversarial networks Markov Process Dual-Delay Deep Deterministic Policy Gradient based on Correlation and Attention Mechanisms

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Resource-Coherented graph Learning for Website Fingerprinting Attacks

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 693-708页

作者： Gao, Bo Liu, Weiwei Liu, Guangjie Nie, Fengyuan Huang, Jianan Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing 210044 Peoples R China Minist Educ Key Lab Intelligent Support Technol Complex Enviro Nanjing 210044 Peoples R China

Deep learning-based website fingerprinting (WF) attacks dominate website traffic classification. In the real world, the main challenges limiting their effectiveness are, on the one hand, the difficulty in countering the effect of content updates on the basis of accurate descriptions of page features in traffic representations. On the other hand, the model's accuracy relies on training numerous samples, requiring constant manual labeling. The key to solving the problem is to find a website traffic representation that can stably and accurately display page features, as well as to perform self-supervised learning that is not reliant on manual labeling. This study introduces the multi-level resource-coherented graph convolutional neural network (MRCGCN), a self-supervised learning-based WF attack. It analyzes website traffic using resources as the basic unit, which are coarser than packets, ensuring the page's unique resource layout while improving the robustness of the representations. Then, we utilized an echelon-ordered graph kernel function to extract the graph topology as the label for website traffic. Finally, a two-channel graph convolutional neural network is designed for constructing a self-supervised learning-based traffic classifier. We evaluated the WF attacks using real data in both closed- and open-world scenarios. The results demonstrate that the proposed WF attack has superior and more comprehensive performance compared to state-of-the-art methods.

关键词： Vectors Feature extraction convolutional neural networks HTTP Uniform resource locators Accuracy Random forests Fingerprint recognition Support vector machines Servers network traffic analysis website fingerprinting attacks graph learning representation learning self-supervised learning graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-object tracking based on graph neural networks

引用

MULTIMEDIA SYSTEMS 2025年第1期31卷 1-16页

作者： Zhang, Yubo Zheng, Liying Huang, Qingming Harbin Engn Univ Sch Comp Sci & Technol Harbin 150001 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100019 Peoples R China

Multi-Object Tracking (MOT), an essential task in computer vision, underperforms when existing occlusions or motion blurs, which will cause changes in the object's appearances. We develop three modules based on graph neural networks (GNNs) to handle such appearance changes. The appearance enhancement module boosts appearance features by applying self-attention and graph convolutional neural network (GCNN) to the local features. The temporal feature updating module automatically updates a tracklet appearance template using GCNNs with different Laplacian operations. The spatial feature updating module encodes interactive spatial features by combining a graph attention network and a GCNN. After processing input video frames with these three modules, our tracker stores all extracted features in a memory bank and then forwards them to a matching algorithm to complete tracking. Using popular benchmark datasets MOT16, MOT17, and MOT20, we show that introducing GNNs to MOT benefits tracking, and the proposed tracker surpasses the state-of-the-art trackers, including StrongSORT, ByteTrack, and BoT-SORT. Specifically, we can achieve 81.1% (77.9%) in MOTA, 80.3% (77.3%) in IDF1, and 65.1% (63.2%) in HOTA on the challenging MOT17 (or the newest MOT20) datasets.

关键词： Multi-object tracking Appearance changes graph convolutional neural network graph attention network

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：