检索结果-内蒙古大学图书馆

SL-GCNN: A graph convolutional neural network for Granular Human Motion Recognition

IEEE ACCESS 2025年 13卷 12373-12387页

作者： Zhang, Jingyu Li, Yang Changchun Normal Univ Coll Phys Educ Changchun 130032 Jilin Peoples R China

Human motion recognition has significantly advanced, with applications in human-computer interaction, virtual reality, intelligent video surveillance, and athletic training. This paper presents SL-GCNN, a novel graph convolutional neural network framework specifically designed for granular skeletal motion recognition. SL-GCNN incorporates Space-Time Feature Harmonization (STFH) and Linkage Isolation (LI) blocks to enhance classification accuracy for similar motion categories. By leveraging contrastive learning, the model refines hidden layer features and isolates output layer features, effectively addressing the challenges posed by subtle differences in granular motions. Experimental results on the two different datasets demonstrate that SL-GCNN outperforms existing state-of-the-art methods, achieving accuracies of 92.73% and 97.47% on the X-Sub and X-View benchmarks of NTU_RGB_plus_D, and 89.19% and 90.56% on the X-Sub and X-View benchmarks of NTU_RGB_plus_D_120, respectively. The findings highlight the model's robust performance in distinguishing complex granular motion categories, validating its efficacy in real-world applications.

关键词： Feature extraction Contrastive learning Couplings Accuracy Training convolutional neural networks Human activity recognition Data models Transformers Prototypes Human motion recognition advanced sports analysis graph convolutional neural network artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Dual channel visible graph convolutional neural network for microleakage monitoring of pipeline weld homalographic cracks

引用

COMPUTERS IN INDUSTRY 2025年 164卷

作者： Huang, Jing Zhang, Zhifen Qin, Rui Yu, Yanlong Li, Yongjie Xu, Quanning Xing, Ji Wen, Guangrui Cheng, Wei Chen, Xuefeng Xi An Jiao Tong Univ Natl Key Lab Aerosp Power Syst & Plasma Technol Xian 710049 Peoples R China China Nucl Power Engn Co Ltd Beijing 100840 Peoples R China

When using a single sensor to monitor early microleakage of nuclear power pressure pipeline leakage, there are problems such as low monitoring accuracy and poor early warning reliability due to the limitations of the monitoring range and weak difference between the leakage signals. To address these challenges, this paper proposes a dual channel visible graph convolutional neural network (DCV-GCN). Firstly, the acoustic emission time-series data of each channel are truncated and divided, and the significant frequency bands are selected based on the envelope spectrum. On this basis, the sequence group is averaged to obtain the graph structure sequence. Then, the limited penetrable visibility (LPV) graph construction algorithm is used to calculate the adjacency matrix, and the important nodes is reserved according to the eigenvector centrality. Furthermore, the inverse ratio of the distance from the sensor in each single channel to the center of the crack is used as the fusion weight, and the adjacency matrices are merged after normalization to transform the construction of the graph structure dataset. Finally, the dataset is input into the graph convolutional neural network, and the effectiveness of the method is verified by carefully designing three homalographic cracks. The results show that the proposed method can effectively extract the distinguishing features with similar frequency components and similar leakage rates, and the recognition accuracy of different leakage states can reach 98.56 %. In addition, through ablation experiments and different parameter strategy settings, the operating mechanism is explained, which can provide a reference for monitoring and analysis by industrial technicians.

关键词： Pipeline weld crack Microleakage Acoustic emission graph convolutional neural network Limited penetrable visible graph

来源：评论

学校读者我要写书评

暂无评论

Freeway optimal control based on emission oriented microscopic graph convolutional neural network

引用

APPLIED INTELLIGENCE 2025年第6期55卷 1-17页

作者： Fang, Jie Lu, Mingwen Fu, Lina Wang, Juanmeizi Xu, Mengyun Fuzhou Univ Coll Civil Engn Fuzhou 350108 Peoples R China Natl Univ Singapore Dept Civil & Environm Engn Singapore 119077 Singapore

Traffic flow prediction and control in the active traffic control system is considered as one of the most critical issues in Intelligent Transportation Systems (ITS). Among the proposed AI-based approaches, Deep Learning (DL) has been largely applied while showing better performances. This research improves macroscopic traffic flow model METANET by establishing a graph convolution neural network (GCN) to explicitly and more precisely incorporate microscopic traffic flow dynamics. The microscopic emission model utilizes the feature extraction function of GCN to reduce the complexity of measuring the environmental profits for the whole traffic network. By introducing the GCN model to facilitate the aggregation of vehicle information, the proposed framework reduces the computational burden and obtains better optimization performance. The designed algorithms are tested on a microscopic simulation platform based on field data. The results demonstrate that the proposed control method produce a more robust and smooth traffic flow environment, which leads to improved traffic efficiency and overall carbon emissions of the road network.

关键词： Freeway traffic control graph convolutional neural network Emissions mitigation Data-driven approach

来源：评论

学校读者我要写书评

暂无评论

Combined improved tuna swarm optimization with graph convolutional neural network for remaining useful life of engine

引用

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL 2025年第1期41卷 174-191页

作者： Yuan, Yongliang Yang, Qingkang Wang, Guohu Ren, Jianji Wang, Zhenxi Qiu, Feng Li, Kunpeng Liu, Haiqing Henan Polytech Univ Sch Mech & Power Engn Jiaozuo Peoples R China Zhengzhou Univ Ind Technol Sch Mech & Elect Engn Zhengzhou Peoples R China Henan Polytech Univ Sch Software Jiaozuo Peoples R China Jilin Univ Sch Commun Engn Changchun 130012 Peoples R China China South Ind Grp Corp Automat Res Inst Co Ltd Beijing Peoples R China Nanyang Technol Univ Sch Phys & Math Sci Singapore Singapore Fluorine Based New Mat Technol Co Ltd Jiaozuo Henan Peoples R China

Accurate prediction of the engine's remaining useful life (RUL) is essential to ensure the safe operation of the aircraft because. However, traditional deep-learning based methods for RUL prediction has been limited by interpretability and adjustment for hyperparameters in practical applications due to the intricate potential relations during the degradation process. To address these dilemmas, an improved multi-strategy tuna swarm optimization-assisted graph convolutional neural network (IMTSO-GCN) is developed to achieve RUL prediction in this work. Specifically, mutual information is used to describe potential relationships among measured parameters so that they could be utilized in building edges for these parameters. Besides, considering that not all relational nodes will positively affect the RUL prediction and the inherent hyperparameters of the GCN are high-dimensional. Inspired by "No Free Lunch (NFL)", IMTSO is proposed to reduce the optimization cost of hyperparameters, in which cycle chaotic mapping is employed to achieve initialization of the population for improving the uniformity of the initial population distribution. Besides, a novel adaptive approach is proposed to enhance the exploration and exploitation of tuna swarm optimization (TSO). The CMAPSS dataset was used to validate the effectiveness and advancedness of IMTSO-GCN, and the experimental results show that the R2 of the IMTSO-GCN is greater than 0.99, RMSE is less than 3, the Score error is within 1.

关键词： aero-engine graph convolutional neural network mutual information remaining useful life Tuna swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A graph convolutional neural network model based on fused multi-subgraph as input and fused feature information as output

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 139卷

作者： Lu, Junwen Chen, Zeji Deng, Xiaolong Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China Beijing Univ Posts & Telecommun Sch Cyber Secur Beijing Peoples R China

The graph convolution neural network (GCN)-based node classification model tackles the challenge of classifying nodes in graph data through learned feature representations. However, most existing graph neural networks primarily focus on the same type of edges, which might not accurately reflect the intricate real-world graph structure. This paper introduces a novel graph neural network model, MF-GCN, which integrates subgraphs with various edge types as input and combines feature information from each graph convolutional neural network layer to produce the final output. This model learns node feature representations by separately feeding subgraphs with different edge types into the graph convolutional layer. It then computes the weight vectors for fusing various edge type subgraphs based on the learned node features. Additionally, to efficiently extract feature information, the outputs of each graph convolution layer, without an activation function, are weighted and summed to obtain the final node features. This approach resolves the challenges of determining fusion weights and effectively extracting feature information during subgraph fusion. Experimental results show that the proposed model significantly improves performance on all three datasets, highlighting its effectiveness in node representation learning tasks.

关键词： graph convolutional neural network Node classification Multi-type edges Subgraph fusion Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Schizophrenia recognition based on three-dimensional adaptive graph convolutional neural network

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-11页

作者： Yin, Guimei Yuan, Jie Chen, Yanjun Guo, Guangxing Shi, Dongli Wang, Lin Zhao, Zilong Zhao, Yanli Zhang, Manjie Dong, Yuan Wang, Bin Tan, Shuping Taiyuan Normal Univ Sch Comp Sci & Technol Jinzhong 030619 Peoples R China Shanxi Prov Peoples Hosp Dept Radiol Taiyuan 030012 Peoples R China Taiyuan Normal Univ Inst Big Data Technol Anal & Applicat Jinzhong 030619 Peoples R China Sun Yat sen Univ Sch Chem Engn & Technol Zhuhai 519000 Peoples R China Beijing Huilongguan Hosp Psychiat Res Ctr Beijing 100096 Peoples R China Taiyuan Univ Technol Coll Comp Sci & Technol Jinzhong 030600 Peoples R China

Previous deep learning-based brain network research has made significant progress in understanding the pathophysiology of schizophrenia. However, it ignores the three-dimensional spatial characteristics of EEG signals and cannot dynamically learn the interactions between nodes. To address this issue, a schizophrenia classification model based on a three-dimensional adaptive graph convolutional neural network (3D-AGCN) is proposed. Each subject's EEG data is divided into various segment lengths and frequency bands for the experiment. The attention mechanism is then used to integrate the node features in the spatial, feature, and frequency band dimensions. The resulting adaptive brain functional network features are then constructed and fed into the GAT + GCN model. This adaptive approach eliminates the human-specified criteria for feature selection and brain network construction. The trial results demonstrated that, when using a 6-second segment length and time-domain and frequency-domain features, patients with first-episode schizophrenia achieved the highest classification accuracy of 87.64% This method outperforms other feature selection and brain network modeling approaches, providing new insights and directions for the early diagnosis and recognition of schizophrenia.

关键词： Schizophrenia 3D spaces Attention mechanisms Adaptive brain networks graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Enhancing Recommender Systems through Imputation and Social-Aware graph convolutional neural network

引用

neural networkS 2025年 184卷 107071页

作者： Faroughi, Azadeh Moradi, Parham Jalili, Mahdi Univ Kurdistan Dept Comp Engn Sanandaj Iran RMIT Univ Sch Engn Melbourne Australia

Recommendation systems are vital tools for helping users discover content that suits their interests. Collaborative filtering methods are one of the techniques employed for analyzing interactions between users and items, which are typically stored in a sparse matrix. This inherent sparsity poses a challenge because it necessitates accurately and effectively filling in these gaps to provide users with meaningful and personalized recommendations. Our solution addresses sparsity in recommendations by incorporating diverse data sources, including trust statements and an imputation graph. The trust graph captures user relationships and trust levels, working in conjunction with an imputation graph, which is constructed by estimating the missing rates of each user based on the user-item matrix using the average rates of the most similar users. Combined with the user-item rating graph, an attention mechanism fine tunes the influence of these graphs, resulting in more personalized and effective recommendations. Our method consistently outperforms state-of-the-art recommenders in real-world dataset evaluations, underscoring its potential to strengthen recommendation systems and mitigate sparsity challenges.

关键词： Recommender systems Sparsity graph convolutional neural network Imputation graph Social relations Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Exploration of novel boron nitride polymorphs: High-throughput screening combined with multi-task orbital crystal graph convolutional neural network (MT-OCGCN)

引用

VACUUM 2025年 231卷

作者： Wei, Wenxu Min, Gege Fan, Qingyang Liang, Dong Ye, Ming Yun, Sining Xian Univ Architecture & Technol Coll Informat & Control Engn Xian 710055 Peoples R China Xian Univ Architecture & Technol Sch Mat Sci & Engn Funct Mat Lab FML Xian 710055 Peoples R China

In response to the limitations of traditional material property prediction methods, we have developed a Multitask Orbital Crystal graph convolutional neural network (MT-OCGCN). This innovative model allows for sharing parameters and computational resources, significantly improving prediction efficiency and accuracy. Experimental comparisons show that the model can achieve multi-task prediction with high accuracy for both strong and weak correlation properties, this offers an efficient approach for computational materials screening and design. Combined with high-throughput screening has resulted in the discovery of 13 new boron nitride polymorphs in the P21/c phase, among which 7 are characterized as wide direct band gap semiconductors. Furthermore, we have comprehensively analyzed the mechanical, thermal, and electronic properties of these new boron nitride polymorphs. It can be asserted that MT-OCGCN has the capability to precisely forecast the physical properties of novel structures that are absent from current databases.

关键词： Deep learning graph convolutional neural network Multi-task learning Boron nitride polymorphs High-throughput screening

来源：评论

学校读者我要写书评

暂无评论

Estimating travel time in transport network with a combined multi-attributed graph convolutional neural network and multilayer perceptron model

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 142卷

作者： Betkier, Igor Mil Univ Technol Fac Secur Logist & Management gen Sylwestra Kaliskiego St 2 PL-00908 Warsaw Poland

In this article, an advanced model for forecasting travel time in road networks is presented, employing a graph convolutional neural network (GCN) integrated with a Multilayer Perceptron (MLP), focusing on the travel time ratio (TTR). Utilizing data from Poland's Mazovia region, the model analyzes spatial and temporal dependencies in road infrastructure, incorporating road conditions, weather, and time for accurate traffic prediction. The research involved detailed analysis of neuron configurations and learning rates in the GCN-MLP model, focusing on their impact on mean squared error (MSE) and other key performance metrics. The optimized model configurations achieved a Mean Absolute Percentage Error (MAPE) of approximately 8%, outperforming many models in existing literature. The study found that hours, days, weather conditions, and technical road features significantly influence the model's outcomes. Efforts to optimize the model included excluding attributes with minimal impact on MSE, leading to notable improvements in efficiency. A comparison between the GCN-MLP model and traditional MLP models demonstrated the former's superior effectiveness, particularly in achieving lower MSE values and better predictive accuracy. These results highlight the potential and challenges of applying advanced machine learning techniques in traffic management, indicating a significant step forward in this field.

关键词： Traffic Traffic Speed Traffic Estimation Artificial neural networks graph neural networks graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Combining multi-level feature extraction algorithm with residual graph convolutional neural network for partial discharge detection

引用

MEASUREMENT 2025年 242卷

作者： Zhang, Chungfeng Fulnecek, Jan Yang, Lin Zhang, Yongjun Zheng, Jiehui South China Univ Technol Sch Elect Power Guangzhou 510665 Peoples R China VSB Tech Univ Ostrava Dept Elect Power Engn Ostrava 70800 Czech Republic

Partial discharge (PD) identification is critical for the insulation diagnosis of cable conductors;however, there is still scope for enhancement in the existing adaptive extraction capabilities and feature utilization for PD signals. In this context, this paper introduces a method that integrates a one-dimensional convolutional neural network (1D-CNN) with a residual graph convolutional neural network (ResGCN) to recognize PD signals. Noise analysis is performed using various combinations of mother wavelets, and Bayesian optimization is employed to mitigate background noise. Key features of PD signals are progressively abstracted through a 1D-CNN-based multilevel automatic feature learning method, while signal timing attributes are maintained to minimize manual intervention. The graph data is constructed using the signal feature matrix and the signal timing feature similarity matrix. This is followed by the development of a ResGCN utilizing a graph attention mechanism to integrate node feature information and the topology of the PD graph data. This approach aims to fully exploit the correlation between local regions of the feature space and the temporal numerical properties of the signals. Additionally, it jointly optimizes feature extraction and model classification to facilitate adaptive diagnosis. The method is validated with extensive real experimental data obtained from medium voltage overhead power lines. It demonstrates exceptional performance and practicality, achieving an accuracy rate of 97.3% and a recognition rate of 96.1% for PD samples, thus offering reliable theoretical support for effective PD detection.

关键词： Partial discharge convolutional neural network graph data graph attention mechanism graph convolutional neural 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：