检索结果-内蒙古大学图书馆

Two-stream graph convolutional neural network fusion for weakly supervised temporal action detection

SIGNAL IMAGE AND VIDEO PROCESSING 2022年第4期16卷 947-954页

作者： Zhao, Mengyao Hu, Zhengping Li, Shufang Bi, Shuai Sun, Zhe Yanshan Univ Sch Informat Sci & Engn Qinhuangdao Hebei Peoples R China Hebei Key Lab Informat Transmiss & Signal Proc Qinhuangdao Hebei Peoples R China

Weakly supervised temporal action detection is an important and challenging task, which is to detect temporal intervals of actions and identify category with only video-level labels. Correctly identifying the transition state between action and background will improve the detection accuracy;therefore, this paper focuses on filtering the transition state and proposes two-stream graph convolutional neural network fusion for weakly supervised temporal action detection. Generally, the transition state changes prominently and lasts for a short time, but it is not the same as the characteristics of the action. The feature difference between two video segments with temporal interactions indicates whether this segment belongs to the transition state. Then, according to the feature similarity and temporal correlation of the segments, the semantic similarity weighted graph and the transition-aware temporal correlation graph are constructed. Finally, the temporal attention sequence of video segments is extracted according to the fused two-stream graph feature. Taking the attention-based feature expression as input for the linear classifier to generate the class activation sequence, and the temporal action detection is performed accordingly. Experimental results on shared datasets show that the proposed method can effectively improve the performance of action detection.

关键词： Temporal action detection graph convolutional neural network Transition-aware Attention

来源：评论

学校读者我要写书评

暂无评论

A graph convolutional neural network for classification of building patterns using spatial vector data

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2019年 150卷 259-273页

作者： Yan, Xiongfeng Ai, Tinghua Yang, Min Yin, Hongmei Wuhan Univ Sch Resource & Environm Sci Wuhan 430079 Hubei Peoples R China Chinese Acad Surveying & Mapping Beijing 100830 Peoples R China

Machine learning methods, specifically, convolutional neural networks (CNNs), have emerged as an integral part of scientific research in many disciplines. However, these powerful methods often fail to perform pattern analysis and knowledge mining with spatial vector data because in most cases, such data are not underlying grid-like or array structures but can only be modeled as graph structures. The present study introduces a novel graph convolution by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem. In addition, the graph convolutional neural network (GCNN) architecture is proposed to analyze graph-structured spatial vector data. The focus of this study is the classical task of building pattern classification, which remains limited by the use of design rules and manually extracted features for specific patterns. The spatial vector data representing grouped buildings are modeled as graphs, and indices for the characteristics of individual buildings are investigated to collect the input variables. The pattern features of these graphs are directly extracted by training labeled data. Experiments confirmed that the GCNN produces satisfactory results in terms of identifying regular and irregular patterns, and thus achieves a significant improvement over existing methods. In summary, the GCNN has considerable potential for the analysis of graph structured spatial vector data as well as scope for further improvement.

关键词： Building pattern classification graph convolutional neural network Machine learning Spatial vector data graph Fourier transform Deep learning

来源：评论

学校读者我要写书评

暂无评论

A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2019年 664卷 1-10页

作者： Qi, Yanlin Li, Qi Karimian, Hamed Liu, Di Peking Univ Inst Remote Sensing & Geog Informat Syst Beijing Peoples R China Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan Hubei Peoples R China

Increasing availability of data related to air quality from ground monitoring stations has provided the chance for data mining researchers to propose sophisticated models for predicting the concentrations of different air pollutants. In this paper, we proposed a hybrid model based on deep learning methods that integrates graph convolutional networks and Long Short-Term Memory networks (GC-LSTM) to model and forecast the spatiotemporal variation of PM2.5 concentrations. Specifically, historical observations on different stations are constructed as spatiotemporal graph series, and historical air quality variables, meteorological factors, spatial terms and temporal attributes are defined as graph signals. To evaluate the performance of the GC-LSTM, we compared our results with several state-of-the-art methods in different time intervals. Based on the results, our GC-LSTM model achieved the best performance for predictions. Moreover, evaluations of recall rate (68.45%), false alarm rate (4.65%) (both of threshold: 115 mu g/m(3)) and correlation coefficient R-2 (0.72) for 72-hour predictions also verify the feasibility of our proposed model. This methodology can be used for concentration forecasting of different air pollutants in future. (C) 2019 Published by Elsevier B.V.

关键词： Air pollution forecasting Spatiotemporal data modelling graph convolutional neural network Long short-term memory Deep learning

来源：评论

学校读者我要写书评

暂无评论

EEG-based emotion recognition using graph convolutional neural network with dual attention mechanism

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2024年 18卷 1416494页

作者： Chen, Wei Liao, Yuan Dai, Rui Dong, Yuanlin Huang, Liya Nanjing Univ Posts & Telecommun Coll Elect & Opt Engn Nanjing Peoples R China Nanjing Univ Posts & Telecommun Coll Flexible Elect Future Technol Nanjing Peoples R China

EEG-based emotion recognition is becoming crucial in brain-computer interfaces (BCI). Currently, most researches focus on improving accuracy, while neglecting further research on the interpretability of models, we are committed to analyzing the impact of different brain regions and signal frequency bands on emotion generation based on graph structure. Therefore, this paper proposes a method named Dual Attention Mechanism graph convolutional neural network (DAMGCN). Specifically, we utilize graph convolutional neural networks to model the brain network as a graph to extract representative spatial features. Furthermore, we employ the self-attention mechanism of the Transformer model which allocates more electrode channel weights and signal frequency band weights to important brain regions and frequency bands. The visualization of attention mechanism clearly demonstrates the weight allocation learned by DAMGCN. During the performance evaluation of our model on the DEAP, SEED, and SEED-IV datasets, we achieved the best results on the SEED dataset, showing subject-dependent experiments' accuracy of 99.42% and subject-independent experiments' accuracy of 73.21%. The results are demonstrably superior to the accuracies of most existing models in the realm of EEG-based emotion recognition.

关键词： attention mechanism EEG electrode channels emotion recognition frequency bands graph convolutional neural network transformer

来源：评论

学校读者我要写书评

暂无评论

Data Privacy Protection Model Based on graph convolutional neural network

引用

MOBILE networkS & APPLICATIONS 2024年第5期29卷 1433-1440页

作者： Gu, Tao Yang, Lin Wang, Hua Southwestern Univ Finance & Econ Fac Business Adm Sch Business Adm Chengdu Peoples R China Southwestern Univ Finance & Econ Inst Chinese Financial Studies Chengdu Peoples R China Guangdong Univ Finance & Econ Sch Finance Guangzhou Peoples R China

In order to solve the problem of leakage of user data privacy in social network scenarios, the author proposes a data privacy protection model based on graph convolutional neural network. This method analyzes in detail the privacy threat to user data caused by the graph convolutional neural network prediction model in the social network scenario, according to the homogeneity principle of social networks, using the attribute features and social relationships disclosed by social users, a graph convolutional neural network classification model is constructed through a semi-supervised learning method, the hidden private attribute categories of target users are inferred, and the accuracy and robustness of the method are finally evaluated on real social network datasets. Experimental results show that: The prediction accuracy rate continues to increase steadily, all in the range of 60%, which is very close to the real prediction accuracy rate, and the data utility is high. Conclusion: The data privacy protection model based on the graph convolutional neural network can better realize the privacy protection, and at the same time ensure the data has high data utility.

关键词： graph convolutional neural network Differential privacy Privacy inference Privacy protection Social network

来源：评论

学校读者我要写书评

暂无评论

TARGCN: temporal attention recurrent graph convolutional neural network for traffic prediction

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第6期10卷 8179-8196页

作者： Yang, He Jiang, Cong Song, Yun Fan, Wendong Deng, Zelin Bai, Xinke Changsha Univ Sci & Technol Sch Int Coll Engn Changsha 410114 Peoples R China Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Peoples R China Hubei Wujing Freeway Dev Co Wuhan 430020 Peoples R China

Traffic prediction is crucial to the intelligent transportation system. However, accurate traffic prediction still faces challenges. It is difficult to extract dynamic spatial-temporal correlations of traffic flow and capture the specific traffic pattern for each sub-region. In this paper, a temporal attention recurrent graph convolutional neural network (TARGCN) is proposed to address these issues. The proposed TARGCN model fuses a node-embedded graph convolutional (Emb-GCN) layer, a gated recurrent unit (GRU) layer, and a temporal attention (TA) layer into a framework to exploit both dynamic spatial correlations between traffic nodes and temporal dependencies between time slices. In the Emb-GCN layer, node embedding matrix and node parameter learning techniques are employed to extract spatial correlations between traffic nodes at a fine-grained level and learn the specific traffic pattern for each node. Following this, a series of gated recurrent units are stacked as a GRU layer to capture spatial and temporal features from the traffic flow of adjacent nodes in the past few time slices simultaneously. Furthermore, an attention layer is applied in the temporal dimension to extend the receptive field of GRU. The combination of the Emb-GCN, GRU, and the TA layer facilitates the proposed framework exploiting not only the spatial-temporal dependencies but also the degree of interconnectedness between traffic nodes, which benefits the prediction a lot. Experiments on public traffic datasets PEMSD4 and PEMSD8 demonstrate the effectiveness of the proposed method. Compared with state-of-the-art baselines, it achieves 4.62% and 5.78% on PEMS03, 3.08% and 0.37% on PEMSD4, and 5.08% and 0.28% on PEMSD8 superiority on average. Especially for long-term prediction, prediction results for the 60-min interval show the proposed method presents a more notable advantage over compared benchmarks. The implementation on Pytorch is publicly available at https://***/csust-sonie/TAR

关键词： Intelligent transportation Traffic prediction Deep learning graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Prediction of the Health Effects of Food Peptides and Elucidation of the Mode-of-action Using Multi-task graph convolutional neural network

引用

MOLECULAR INFORMATICS 2020年第1-2期39卷 e1900134-e1900134页

作者： Fukunaga, Itsuki Sawada, Ryusuke Shibata, Tomokazu Kaitoh, Kazuma Sakai, Yukie Yamanishi, Yoshihiro Kyushu Inst Technol Fac Comp Sci & Syst Engn Dept Biosci & Bioinformat 680-4 Kawazu Iizuka Fukuoka 8208502 Japan

Food proteins work not only as nutrients but also modulators for the physiological functions of the human body. The physiological functions of food proteins are basically regulated by peptides encrypted in food protein sequences (food peptides). In this study, we propose a novel deep learning-based method to predict the health effects of food peptides and elucidate the mode-of-action. In the algorithm, we estimate potential target proteins of food peptides using a multi-task graph convolutional neural network, and predict its health effects using information about therapeutic targets for diseases. We constructed predictive models based on 21,103 peptide-protein interactions involving 10,950 peptides and 2,533 proteins, and applied the models to food peptides (e. g., lactotripeptide, isoleucyltyrosine and sardine peptide) defined in food for specified health use. The models suggested potential effects such as blood-pressure lowering effects, blood glucose level lowering effects, and anti-cancer effects for several food peptides. The interactions of food peptides with target proteins were confirmed by docking simulations.

关键词： foods peptides health effects peptide-protein interaction graph convolutional neural network deep learning

来源：评论

学校读者我要写书评

暂无评论

Athlete facial micro-expression recognition method based on graph convolutional neural network

引用

INTERNATIONAL JOURNAL OF BIOMETRICS 2024年第5期16卷 478-496页

作者： Xu, Haochen Zhu, Zhiqiang Krirk Univ Int Coll Bangkok 10220 Thailand

The recognition accuracy of athlete facial micro-expression is low due to insufficient consideration, failure to remove invalid data from the recognition data, and inaccurate extraction of micro-expression features. To this end, a new method for athlete facial micro-expression recognition based on image convolutional neural networks was studied. Firstly, the athlete's face data is preprocessed using facial alignment, unified frame, and optical flow extraction algorithms;Then, the graph convolutional neural network is used to extract athlete facial micro-expression features;Finally, to improve the performance of micro expression recognition tasks, a classification layer was added before the output layer of the network, and support vector machine algorithm was introduced to optimise and improve the graph convolutional neural network to adjust the discriminative boundaries between categories, achieving more accurate and effective micro expression recognition. The experimental results show that the proposed method can accurately extract micro-expression features, with a recognition accuracy of 97.0% and high convergence, effectively improving the recognition effect.

关键词： graph convolutional neural network facial micro-expression support vector machine optical flow extraction algorithm unified frame

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning of graph convolutional neural network for Resilient Production Control of Mass Individualized Prototyping Toward Industry 5.0

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2024年第11期54卷 7092-7105页

作者： Leng, Jiewu Ruan, Guolei Xu, Caiyu Zhou, Xueliang Xu, Kailin Qiao, Yan Liu, Zhihong Liu, Qiang Guangdong Univ Technol State Key Lab Precis Elect Mfg Technol & Equipmen Guangzhou 510006 Peoples R China Hubei Univ Automot Technol Dept Elect & Informat Engn Shiyan 442002 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China China South Ind Grp Co Ltd Inst Automat Mianyang 510704 Sichuan Peoples R China

Mass individualized prototyping (MIP) is a kind of advanced and high-value-added manufacturing service. In the MIP context, the service providers usually receive massive individualized prototyping orders, and they should keep a stable state in the presence of continuous significant stresses or disruptions to maximize profit. This article proposed a graph convolutional neural network-based deep reinforcement learning (GCNN-DRL) method to achieve the resilient production control of MIP (RPC-MIP). The proposed method combines the excellent feature extraction ability of graph convolutional neural networks with the autonomous decision-making ability of deep reinforcement learning. First, a three-dimensional disjunctive graph is defined to model the RPC-MIP, and two dimensionality-reduction rules are proposed to reduce the dimensionality of the disjunctive graph. By extracting the features of the reduced-dimensional disjunctive graph through a graph isomorphic network, the convergence of the model is improved. Second, a two-stage control decision strategy is proposed in the DRL process to avoid poor solution quality in the large-scale searching space of the RPC-MIP. As a result, the high generalization capability and efficiency of the proposed GCNN-DRL method are obtained, which is verified by experiments. It could withstand system performance in the presence of continuous significant stresses of workpiece replenishment and also make fast rearrangement of dispatching decisions to achieve rapid recovery after disruptions happen in different production scenarios and system scales, thereby improving the system's resilience.

关键词： Feature extraction Production Stress Resilience Production control Manufacturing Intelligent agents Deep reinforcement learning graph convolutional neural network Industry 5 0 mass individualized prototyping (MIP) resilient production control (RPC)

来源：评论

学校读者我要写书评

暂无评论

Root Cause Analysis of Anomalies Based on graph convolutional neural network

引用

INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING 2022年第8期32卷 1155-1177页

作者： Li, Zhongliang Tu, Yaofeng Ma, Zongmin Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China ZTE Corp Nanjing 210012 Peoples R China

With the gradual increase of network complexity and network scale in the cloud environment, Root Cause Analysis (RCA) of node failures has become a systematic problem of great research significance. This paper proposes graph-Attention-Sage (GASage) algorithm, which is a fault RCA algorithm and scheme. The algorithm solves the RCA by incorporating TOPK sampling and Attention-Aggregation with graphSage algorithm in large-scale and complex microservice network environment. The GASage algorithm is based on graph convolutional neural network and graph attention mechanism, which profoundly combines the characteristics of network fault RCA problems. TOPK sampling mechanism is applied in GASage to select the neighboring nodes with the top K highest correlation as the objectives to be aggregated. GASage adopts an attention mechanism when aggregated, which aggregates the features of the central node according to the weights of the adjacent nodes and the central node. The weight aggregation method can greatly improve the node representation effect in the RCA scenario. The empirical results of our experiments have demonstrated that the model learned with GASage can outperform other model with the same learning framework and achieves more than 10% improvement in precision.

关键词： AIOps: root cause analysis graph convolutional neural network graph attention

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：