检索结果-内蒙古大学图书馆

An efficient encoder-decoder network for the capacitated vehicle routing problem

EXPERT SYSTEMS WITH APPLICATIONS 2025年 278卷

作者： Luo, Jia Li, Chaofeng Ningbo Univ Technol Sch Econ & Management Ningbo 315211 Zhejiang Peoples R China Shanghai Maritime Univ Inst Logist Sci & Engn Shanghai 200135 Peoples R China

The capacitated vehicle routing problem (CVRP) is of great importance to intelligent transportation systems. In recent, deep reinforcement learning (DRL) approaches have shown great potential in solving the CVRP efficiently. Specifically, encoder-decoder frameworks are trained via reinforcement learning with different schemes to construct solutions incrementally. As the total customer demands and remaining vehicle capacity are dynamic with time steps, it is still a challenge for this kind of methods to obtain optimal solutions. In this work, we develop an efficient encoder-decoder framework, termed the residual graph convolutional encoder and multiple attention-based decoders (RGCMA), which is trained by a reinforcement learning method with an elite baseline. The encoder produces powerful node representations while being dedicated to aggregating neighborhood features by a fitted dense residual edge and node features updating block. Compared to the popular single decoder strategy, our multiple decoders mechanism incrementally constructs a variety of solutions for any CVRP instance, which diversifies solution space, and eventually improves the solution quality. Extensive experiments demonstrate that RGCMA performs competitively with existing methods on variety CVRP datasets. RGCMA narrows the gap to LKH solver on four benchmark tasks, and its run time is less than 1 s. It also exhibits good generalization ability on large-scale tasks, well-known CVRPLIB dataset and real-world Jingdong Logistics distribution task.

关键词： Capacitated vehicle routing problem Deep reinforcement learning Encoder-decoder framework graph convolutional neural network Attention-based mechanism

来源：评论

学校读者我要写书评

暂无评论

VSA-GCNN: Attention Guided graph neural networks for Brain Tumor Segmentation and Classification

引用

BIG DATA AND COGNITIVE COMPUTING 2025年第2期9卷 29-29页

作者： Joshi, Kambham Pratap Gowda, Vishruth Boraiah Divakarachari, Parameshachari Bidare Parameshwarappa, Paramesh Siddappa Patra, Raj Kumar MLR Inst Technol Dept CSE Data Sci Cyber Secur Hyderabad 500043 India Visvesvaraya Technol Univ SJB Inst Technol Dept Informat Sci & Engn Bangalore 560060 India Nitte Meenakshi Inst Technol Dept Elect & Commun Engn Bengaluru 560064 India Cent Univ Karnataka Sch Engn Dept Comp Sci & Engn Kalaburagi 585367 India CMR Tech Campus Comp Sci Engn Hyderabad 501401 India

For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it challenging to progress an accurate and reliable diagnostic tool. In order to effectively segment and classify the tumor region, still several developments are required to make an accurate diagnosis. Thus, the purpose of this research is to accurately segment and classify brain tumor Magnetic Resonance Images (MRI) to enhance diagnosis. Primarily, the images are collected from BraTS 2019, 2020, and 2021 datasets, which are pre-processed using min-max normalization to eliminate noise. Then, the pre-processed images are given into the segmentation stage, where a Variational Spatial Attention with graph convolutional neural network (VSA-GCNN) is applied to handle the variations in tumor shape, size, and location. Then, the segmented outputs are processed into feature extraction, where an AlexNet model is used to reduce the dimensionality. Finally, in the classification stage, a Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to classify the brain tumor regions as gliomas and meningiomas. From the results, it is evident that the proposed VSA-GCNN-BiGRU shows superior results on the BraTS 2019 dataset in terms of accuracy (99.98%), sensitivity (99.92%), and specificity (99.91%) when compared with existing models. By considering the BraTS 2020 dataset, the proposed VSA-GCNN-BiGRU shows superior results in terms of Dice similarity coefficient (0.4), sensitivity (97.7%), accuracy (98.2%), and specificity (97.4%). While evaluating with the BraTS 2021 dataset, the proposed VSA-GCNN-BiGRU achieved specificity of 97.6%, Dice similarity of 98.6%, sensitivity of 99.4%, and accuracy of 99.8%. From the overall observation, the proposed VSA-GCNN-BiGRU supports accurate brain tumo

关键词： bidirectional gated recurrent unit brain tumor segmentation convolutional architectures graph convolutional neural network histogram equalization variational spatial attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Design of Multimedia Teaching Software Based on Distributed network Architecture

引用

International Journal of High Speed Electronics and Systems 2025年第1期34卷

作者： Meng, Xiao-Ke Wang, Si-Yu Wang, Li-Xin College of Furnishings and Industrial Design Nanjing Forestry University Nanjing210037 China Party School of Jiangsu Provincial Committee of C.P.C Nanjing210000 China

With the leap of network technology and the vigorous development of online teaching, many universities are actively adopting online means to optimize teaching and course management. This paper focuses on building an efficient and comprehensive auxiliary teaching platform that integrates functions such as student learning monitoring, course management, online testing, and teacher–student interaction, aiming to improve the quality of education. Designs based on distributed B/S architecture and web technology to ensure efficient resource allocation and expansion, meet the needs of large-scale concurrent learning, and achieve cross-platform access to enhance user experience. The platform features personalized learning support, enhanced interactive collaboration, and the construction of a multimedia teaching database through data analysis. The innovation lies in using neural network technology to create an intelligent question answering module, utilizing cosine similarity to automatically group teaching resources, and using graph convolution and variational autoencoder techniques to construct a student performance monitoring model. Experimental verification shows that the platform runs stably, effectively reduces the blocking rate, and significantly improves students’ academic performance, pass rate, and learning interest. This design not only successfully completed the teaching task, but also provided valuable experience for the application of online-assisted teaching systems in subject education. © 2025 World Scientific Publishing Company.

关键词： Distributed architecture web network multimedia teaching software graph convolutional neural network variational automatic coding cosine similarity

来源：评论

学校读者我要写书评

暂无评论

graph neural network Based Interference Estimation for Device-to-Device Wireless Communications

Graph Neural Network Based Interference Estimation for Devic...

引用

International Joint Conference on neural networks (IJCNN)

作者： Jiang, He Li, Lusi Wang, Zhenhua He, Haibo Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA

ISBN: (纸本)9780738133669

This paper concerns interference estimation problem for device-to-device (D2D) communication networks. In the considered system, D2D users share common spectrum resources, such that the D2D links have interference with each other. To achieve effective interference management, it is necessary to have an accurate understanding of the interference relationship of the D2D devices, which is difficult since the locations and the number of mobile devices can vary over time. In this paper, we formulate an interference estimation problem for the D2D communication network where the D2D users change over time. Our objective is to get accurate estimations for the interference suffered by a generic D2D link and for the interference a D2D link introduces on other users. We propose a graph convolutional neural network (GCN) based estimation model which can estimate the interference of a D2D link based on the location information of the corresponding D2D pairs. Simulation results show the performance of our method.

关键词： graph convolutional neural network device-to-device communication interference estimation machine learning

来源：评论

学校读者我要写书评

暂无评论

Electricity Theft Detection Using Euclidean and graph convolutional neural networks

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2023年第4期38卷 3514-3527页

作者： Liao, Wenlong Yang, Zhe Liu, Kuangpu Zhang, Bin Chen, Xinxin Song, Runan Aalborg Univ AAU Energy DK-9220 Aalborg Denmark Aalborg Univ Dept Chem & Biosci DK-9220 Aalborg Denmark China Elect Power Res Inst Beijing 100192 Peoples R China

The widespread penetration of advanced metering infrastructure brings an opportunity to detect electricity theft by analyzing the electricity consumption data collected from smart meters. However, existing models have poor performance in electricity theft detection, since most of them fail to capture the time dependence, periodicity, and latent feature from complex electricity consumption data. To address above concerns, a graph convolutional neural network (GCN) and a Euclidean convolutional neural network (CNN) are combined to form a novel model for electricity theft detection in this paper. On one hand, the high-dimensional power load curves are modeled as a graph from a new perspective on graph theory. Then, the GCN depicts the time dependence and periodicity by performing graph convolutional operations. On the other hand, the CNN captures the latent features from the power load curves by carrying out Euclidean convolutional procedures. Numerical simulations show that the proposed model integrates the benefits of GCN and CNN, leading to superiority over the popular benchmarks in electricity theft detection.

关键词： Index Terms-Electricity theft detection graph convolutional neural network deep learning machine learning smart grids

来源：评论

学校读者我要写书评

暂无评论

graph learning-based spatial-temporal graph convolutional neural networks for traffic forecasting

引用

CONNECTION SCIENCE 2022年第1期34卷 429-448页

作者： Hu, Na Zhang, Dafang Xie, Kun Liang, Wei Hsieh, Meng-Yen Hunan Univ Coll Comp Sci & Elect Engn Changsha Peoples R China Hunan Univ Sci & Technol Sch Comp Sci & Engn Xiangtan Peoples R China Providence Univ Dept Comp Sci & Informat Engn Taipei Taiwan

Traffic forecasting is highly challenging due to its complex spatial and temporal dependencies in the traffic network. graph convolutional neural network (GCN) has been effectively used for traffic forecasting due to its excellent performance in modelling spatial dependencies. In most existing approaches, GCN models spatial dependencies in the traffic network with a fixed adjacency matrix. However, the spatial dependencies change over time in the actual situation. In this paper, we propose a graph learning-based spatial-temporal graph convolutional neural network (GLSTGCN) for traffic forecasting. To capture the dynamic spatial dependencies, we design a graph learning module to learn the dynamic spatial relationships in the traffic network. To save training time and computation resources, we adopt dilated causal convolution networks with a gating mechanism to capture long-term temporal correlations in traffic data. We conducted extensive experiments using two real-world traffic datasets. Experimental results demonstrate that the proposed GLSTGCN achieves superior performance than all state-of-art baselines.

关键词： graph convolutional neural network dynamic graph learning traffic speed prediction spatial-temporal data

来源：评论

学校读者我要写书评

暂无评论

SOGCN: Prediction of key properties of MR-TADF materials using graph convolutional neural networks

引用

CHEMICAL ENGINEERING JOURNAL 2024年 501卷

作者： Li, Yingfu Zhang, Bohua Ren, Aimin Wang, Dongdong Zhang, Jun Nie, Changming Su, Zhongmin Zou, Luyi Jilin Univ Coll Chem Inst Theoret Chem Changchun 130023 Peoples R China Univ South China Sch Chem & Chem Engn Hengyang 421001 Peoples R China Xi An Jiao Tong Univ Sch Chem Xian 710049 Peoples R China Shenzhen Bay Lab Inst Syst & Phys Biol Shenzhen 518055 Peoples R China

The exploration of the structure and properties of the luminescent materials in OLED devices using Multiple Resonance Thermally Activated Delayed Fluorescence (MR-TADF) is constrained by challenges related to long cycles and high experimental costs, making it a key obstacle in the development of new materials. In response to this challenge, we propose an innovative approach by constructing a graph convolutional neural network model named SOGCN to quickly determine whether an unsynthesized material has the potential to become an MR material, and accurately predict its energy gap and half-peak width, thereby expediting the development process of MR-TADF materials. We constructed the MR220 dataset for training the model based on 220 MR-TADF molecules reported in experiments. To ensure the reliability of the SOGCN model in predicting new samples, we have established a rigorous set of theoretical calculation evaluation standards, providing crucial references for the model. In the prediction of the properties of 37 new samples of MR-TADF molecules, SOGCN successfully predicted the singlet-triplet energy gap (LEST) of some samples, demonstrating a good trend in FWHM prediction as well. Finally, we have synthesized our designed molecule, Design3 (DtCzB-Boz), the organic light-emitting diodes based on DtCzB-Boz exhibit an emission peak at 508 nm, with the FWHM is 27 nm. The result of photophysical characterization is highly consistent with the predicted value of SOGCN. Notably, the mean absolute errors (MAE) between our model predictions and experimental/computational values were as low as 0.037 eV and 10 nm, respectively. This indicates that SOGCN exhibits higher efficiency and accuracy in predicting the properties of MR-TADF materials.

关键词： Organic light-emitting diode Multiple resonance thermal activation delayed fluorescence graph convolutional neural network Density functional theory Coupled cluster

来源：评论

学校读者我要写书评

暂无评论

Promoting Financial Market Development-Financial Stock Classification Using graph convolutional neural networks

引用

IEEE ACCESS 2023年 11卷 49289-49299页

作者： Xu, Huize Zhang, Yuhang Xu, Yaoqun Harbin Univ Commerce Sch Comp & Informat Engn Harbin 150028 Peoples R China Harbin Univ Commerce Inst Syst Engn Harbin 150028 Peoples R China

According to surveys, one in seven people in China are involved in stock trading, and the role of stocks in the global economy is growing. In terms of the entire stock market, the Chinese market alone has over 4000 stocks. Faced with a chaotic and diverse assortment of stocks, it is necessary to categorize them. On the one hand, it can facilitate stock market research, and on the other, it can make it easier for stockholders to purchase shares. The graph convolutional neural network-based SK-GCN model developed in this paper delivers excellent results in the categorization of stock classes. This model employs two layers of convolutional layers and activation functions to effectively categorize stocks by incorporating external nodes to expand stock features and drawing inspiration from short text classification. This strategy is highly innovative and produces promising outcomes. In this paper, we constructed the dataset by crawling the information of all stocks listed on the GEM of Oriental Fortune website. We achieved an accuracy of 83.04% and a macro-F1 value of 0.8303 under the assumption of small sample training, and its classification effect is significantly superior to other classification models.

关键词： convolutional neural networks Training Computational modeling Deep learning Industries Text categorization Stock markets graph neural network financial field graph convolutional neural network node classification

来源：评论

学校读者我要写书评

暂无评论

BCN-GCN: A Novel Brain Connectivity network Classification Method via graph Convolution neural network for Alzheimer's Disease 28th

BCN-GCN: A Novel Brain Connectivity Network Classification M...

引用

28th International Conference on neural Information Processing

作者： Gu, Peiyi Xu, Xiaowen Luo, Ye Wang, Peijun Lu, Jianwei Tongji Univ Shanghai Peoples R China Tongji Univ Sch Med Shanghai Peoples R China

ISBN: (纸本)9783030921842;9783030921859

Brain connectivity network (BCN) is a non-directed graph which represents the relationship between brain regions. Traditional feature extractor methods has been applied to identify diseases related to brains such as Alzheimer's disease (AD) with BCN. However, the feature extraction capabilities of these methods are insufficient to collect various topological properties of non-directed graphs. They can only take into consider the local topological properties or frequent sub-graph topological properties. To explicitly exploit these properties, this paper proposes a BCN based fully-supervised graph Convolution network (GCN) to select features and classify disease automatically, skipping the step of manual feature selection and keeping all information in the brain connectivity network. Extensive experiments show that we outperform other method in classifying different stages of AD. Furthermore, our method can find the most relevant brain regions to classify different stages of AD, showing better interpretation ability compared to traditional methods.

关键词： Brain connectivity network graph convolutional neural network Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Affinity Prediction Based on Self-attention graph Pooling and Mutual Interaction neural network 1

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Wang, Xizi Hu, Jing Zhang, Xiaolong Wuhan Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430065 Hubei Peoples R China Hubei Prov Key Lab Intelligent Informat Proc & Re Wuhan Hubei Peoples R China Wuhan Univ Sci & Technol Inst Big Data Sci & Engn Wuhan Hubei Peoples R China

ISBN: (数字)9789819947492

ISBN: (纸本)9789819947485;9789819947492

Predicting drug-target affinity is an important step in drug screening and discovery. This paper proposes a novel prediction model SAIG-DTA, which is built on SAGPool and MINN and can predict the binding affinity value between drugs and their protein targets. Unlike most prior prediction models, this model converts target and drug molecule into a protein contact map and a drug molecule map respectively and then employs the self-attention method on the maps to generate an effective representation of medicines and targets. Before being aggregated into a molecular representation, the characteristics of each atomic node in graph are weighted using an attention score. The techniques used to score self-attention were compared in this study. Furthermore, while the attention mechanism has been widely used to capture the one-way influence between the drug and the target, the interaction between the drug and the target has been underexplored, so the MINN module is added to the model, and the MINN will combine Interacting-Transformer (Interformer) with the improved Communicative Message Passing neural network (CMPNN) (Inter-CMPNN) to better capture the bidirectional effects between drugs and targets and improve the model. The Davis, KIBA (Kinase Inhibitor Bioactivity), and Metz datasets were used to train our suggested model. The comparative experimental findings on regression and tasks reveal that the SAIG-DTA technique outperforms earlier sequence-based or other graph-based methods and has a high degree of generalization.

关键词： Drug-target affinity prediction graph convolutional neural network Attention mechanism Multi-channel graph convolutional 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：