Community Detection Framework Based on Dynamic Graph Convolutional Networks and Model Transfer

With the development of precision sensing instruments and data storage devices, the fusion of multi-sensor data in gearbox fault diagnosis has attracted much attention. However, existing methods have difficulty in capturing the local temporal dependencies of multi-sensor monitoring information, and the inescapable noise severely decreases the accuracy of multi-sensor information fusion diagnosis. To address these issues, this paper proposes a fault diagnosis method based on dynamic graph convolutional neural networks and hard threshold denoising. Firstly, considering that the relationships between monitoring data from different sensors change over time, a dynamic graph structure is adopted to model the temporal dependencies of multi-sensor data, and, further, a graph convolutional neural network is constructed to achieve the interaction and feature extraction of temporal information from multi-sensor data. Secondly, to avoid the influence of noise in practical engineering, a hard threshold denoising strategy is designed, and a learnable hard threshold denoising layer is embedded into the graph neural network. Experimental fault datasets from two typical gearbox fault test benches under environmental noise are used to verify the effectiveness of the proposed method in gearbox fault diagnosis. The experimental results show that the proposed DDGCN method achieves an average diagnostic accuracy of up to 99.7% under different levels of environmental noise, demonstrating good noise resistance.

In a wide range of social unrest events prediction, the dynamic graph convolutional network (DGCN) have been successfully leveraged to achieve reliable performance. The innovation of dynamic graph convolutional networks mainly focuses on capturing the temporal features of unrest events. Inspired by the dynamic graph convolutional network, we propose a new graph convolutional network model called Contextual Gated Graph Convolutional Network (CGGCN). We apply CGGCN to predict and analyze social unrest events. The CGGCN uses the contextual gated layer, which improves the layer-wise propagation rules of graph convolutional networks. The contextual gated layer can re-learn the keyword representation to capture the contextual semantic features of unrest events by using squeeze & excitation module. The principle of the squeeze & excitation module is to increase the weight of meaningful words for event prediction and suppress weaker ones. In this paper, we obtain historical texts including published news and short tweets related to social unrest events. Based on these historical texts data, the CGGCN can predict the occurrence of social unrest events. In addition, we propose a method for establishing the evolution graph of unrest events. In this way, we can use several core words to summarize the evolution of the event. Finally, we design experiments on the specific unrest events data sets. The experimental results show that the CGGCN leads by about 5% - 7% in the performance of prediction compared with other popular methods.

Fake news has become a significant societal problem, and the need for automatic fake news detection techniques is growing. In recent years, graph-based methods focusing on the structure of news propagation have been proposed and significantly improved detection accuracy. Although some methods consider the temporal evolution of the propagation structure using dynamic graphs, they typically use a two-step approach, where structural features are first extracted independently of the temporal information and are then combined with temporal features in a separate step. In this study, we propose a novel fake news detection method based on a dynamic graph convolutional network that directly incorporates time series information during structural feature extraction. By introducing time series-aware structural feature extraction, our method more effectively captures the temporal evolution of the news propagation structure, improving fake news detection performance. We evaluated the effectiveness of the proposed method through experiments on two real-world datasets, FakeNewsNet and FibVID.

Traffic congestion is a major challenge in urban life, and traffic flow prediction, as a critical task in intelligent transportation management, can effectively alleviate congestion and enhance traffic control efficiency. Although deep learning models have achieved significant progress in traffic flow prediction, most existing studies focus on capturing dynamic spatiotemporal features, with insufficient attention to the pivotal role of historical data's periodic characteristics in forecasting. To address this, we proposed a Transformer‐based Dynamic Graph Convolutional Network (T‐DGCN), which significantly improves prediction accuracy by integrating historical periodic features and real‐time dynamic variations. T‐DGCN employs the self‐attention mechanism of Transformer to capture temporal dependencies and combines dynamic graph convolutional networks to extract spatial features, thereby comprehensively modelling spatiotemporal dynamics. Experiments on the real highway datasets from California (PeMSD4 and PeMSD8) show that T‐DGCN outperforms state‐of‐the‐art models across multiple time horizons. On the PeMSD4 dataset, it reduces the MAE and RMSE by an average of 12.9% and 5.2% across the 15 min, 30 min, and 60 min prediction horizons, respectively. On the PeMSD8 dataset, it reduces the MAE and RMSE results by approximately 8.8% and 5.7% on average, respectively.

Dynamic graph convolutional network for multi-video summarization

Many real-world systems can be expressed in temporal networks with nodes playing different roles in structure and function, and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread of public opinions or epidemics, predict leading figures in academia, conduct advertisements for various commodities and so on. However, it is rather difficult to identify critical nodes, because the network structure changes over time in temporal networks. In this paper, considering the sequence topological information of temporal networks, a novel and effective learning framework based on the combination of special graph convolutional and long short-term memory network (LSTM) is proposed to identify nodes with the best spreading ability. The special graph convolutional network can embed nodes in each sequential weighted snapshot and LSTM is used to predict the future importance of timing-embedded features. The effectiveness of the approach is evaluated by a weighted Susceptible-Infected-Recovered model. Experimental results on four real-world temporal networks demonstrate that the proposed method outperforms both traditional and deep learning benchmark methods in terms of the Kendall τ coefficient and top k hit rate.

Spatial and temporal prediction of ozone concentration in the Pearl River Delta region based on a dynamic graph convolutional network

Recently, graph convolutional network (GCN) has drawn increasing attention in hyperspectral image (HSI) classification, as it can process arbitrary non-Euclidean data. However, dynamic GCN that refines the graph heavily relies on the graph embedding in the previous layer, which will result in performance degradation when the embedding contains noise. In this letter, we propose a novel dual residual graph convolutional network (DRGCN) for HSI classification that integrates two adjacency matrices of dual GCN. In detail, one GCN applies a soft adjacency matrix to extract spatial features, the other utilizes the dynamic adjacency matrix to extract global context-aware features. Subsequently, the features extracted by dual GCN are fused to make full use of the complementary and correlated information among two graph representations. Moreover, we introduce residual learning to optimize graph convolutional layers during the training process, to alleviate the over-smoothing problem. The advantage of dual GCN is that it can extract robust and discriminative features from HSI. Extensive experiments on four HSI data sets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the effectiveness and superiority of our proposed DRGCN, even with small-sized training data.

We introduced a novel methodology Multivariate Degree Distribution to Dynamic Graph (MDD2DG) with Inter-channel Relevance Attention (IRA) mechanism to analyze multi-channel Electrocardiogram (ECG) signals and explore signal connections across different channels. Our methodology comprises three main steps. First, multi-channel cardiac signals are transformed into multi-channel visual graphs to extract crucial degree distribution features. Then, degree distributions are mapped into dynamic graphs using a neural network with an IRA mechanism. After that, critical features are extracted within dynamic graphs utilizing a Graph Convolutional Neural Networks (GCNNs), and classification is subsequently performed using a multilayer perceptron. In this model, a method of multi-scale position embedding was introduced, which significantly enhanced the processing efficiency of the model by providing a simpler yet sufficiently effective feature representation. Compared to traditional complex network methods, our approach replaces fixed formula-calculated features with dynamic graph models, resulting in improved recognition accuracy. In the experiments, we achieved an impressive 99.94% classification accuracy for distinguishing ECG signals from the five distinct locations (AMI, ASMI, ALMI, IMI and ILMI) with myocardial infarction (MI) as well as those of the healthy controls (HC). This work contributes to the analysis of complex physiological signals in the field of multi-channel ECG sequence, and provides a robust approach with promising implications for improving clinical medicine and the early detection of cardiac diseases.

Optimising dynamic graphical models for video content analysis

Multi-Camera Multiple Object Tracking (MC-MOT) is a significant computer vision problem due to its emerging applicability in several real-world applications. Despite a large number of existing works, solving the data association problem in any MC-MOT pipeline is arguably one of the most challenging tasks. Developing a robust MC-MOT system, however, is still highly challenging due to many practical issues such as inconsistent lighting conditions, varying object movement patterns, or the trajectory occlusions of the objects between the cameras. To address these problems, this work, therefore, proposes a new Dynamic Graph Model with Link Prediction (DyGLIP) approach <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> to solve the data association task. Compared to existing methods, our new model offers several advantages, including better feature representations and the ability to recover from lost tracks during camera transitions. Moreover, our model works gracefully regardless of the overlapping ratios between the cameras. Experimental results show that we out-perform existing MC-MOT algorithms by a large margin on several practical datasets. Notably, our model works favor-ably on online settings but can be extended to an incremental approach for large-scale datasets.

Dynamic networks require effective methods of monitoring and surveillance in order to respond promptly to unusual disturbances. In many applications, it is of interest to identify anomalous behavior within a dynamic interacting system. Such anomalous interactions are reflected by structural changes in the network representation of the system. In this paper, a dynamic random graph model is proposed that takes into account the past activities of the individuals in the social network and also represents temporal dependency of the network. The model parameters are appearance and disappearance probabilities of an edge which are estimated using a maximum likelihood approach. A generalization of a single path‐dependent likelihood ratio test is employed to detect changes in the parameters of the proposed model. Through monitoring the estimated parameters, one can effectively detect structural changes in a temporal‐dependent network. The proposed model is employed to describe the behavior of a real network, and its parameters are monitored via dependent likelihood ratio test and multivariate exponentially weighted moving average control chart. Results indicate that the proposed dynamic random graph model is a reliable mean to modeling and detecting changes in temporally dependent networks.

TANGO: A temporal spatial dynamic graph model for event prediction

Dynamic graphical models aim to describe the time-varying dependency structure of multiple time-series. In this article we review research focusing on the formulation and estimation of such models. The bulk of work in graphical structurelearning problems has focused in the stationary i.i.d setting, we present a brief overview of this work before introducing some dynamic extensions. In particular we focuson two classes of dynamic graphical model; continuous (smooth) models which are estimated via localised kernels, and piecewise models utilising regularisation based estimation. We give an overview of theoretical and empirical results regarding these models, before demonstrating their qualitative difference in the context of a real-world financial time-series dataset. We conclude with a discussion of the state of the field and future research directions.

Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph modeling methods have achieved satisfactory results, they still suffer from three key limitations, hindering their scalability and further applicability. i) Indiscriminate updating. For incoming edges, existing methods would indiscriminately deal with them, which may lead to more time consumption and unexpected noisy information. ii) Ineffective node-wise long-term modeling. They heavily rely on recurrent neural networks (RNNs) as a backbone, which has been demonstrated to be incapable of fully capturing node-wise long-term dependencies in event sequences. iii) Neglect of re-occurrence patterns. Dynamic graphs involve the repeated occurrence of neighbors that indicates their importance, which is disappointedly neglected by existing methods.