A Method for Predicting Traction Load of Electrified Railways Considering Spatiotemporal Correlation Characteristics

Dynamic Jacobi graph and trend-aware flow attention convolutional network for traffic forecasting

Precisely segmenting the organs at risk (OARs) in computed tomography (CT) plays an important role in radiotherapy’s treatment planning, aiding in the protection of critical tissues during irradiation. Renowned deep convolutional neural networks (DCNNs) and prevailing transformer-based architectures are widely utilized to accomplish the segmentation task, showcasing advantages in capturing local and contextual characteristics. Graph convolutional networks (GCNs) are another specialized model designed for processing the nongrid dataset, e.g., citation relationship. The DCNNs and GCNs are considered as two distinct models applicable to the grid and nongrid datasets, respectively. Motivated by the recently developed dynamic-channel GCN (DCGCN) that attempts to leverage the graph structure to enhance the feature extracted by the DCNNs, this paper proposes a novel architecture termed adaptive sparse GCN (ASGCN) to mitigate the inherent limitations in DCGCN from the aspect of node’s representation and adjacency matrix’s construction. For the node’s representation, the global average pooling used in the DCGCN is replaced by the learning mechanism to accommodate the segmentation task. For the adjacency matrix, an adaptive regularization strategy is leveraged to penalize the coefficient in the adjacency matrix, resulting in a sparse one that can better exploit the relationships between nodes. Rigorous experiments on multiple OARs’ segmentation tasks of the head and neck demonstrate that the proposed ASGCN can effectively improve the segmentation accuracy. Comparison between the proposed method and other prevalent architectures further confirms the superiority of the ASGCN.

Graph Convolutional Neural Network (GCN) is widely used in text classification tasks. Furthermore, it has been effectively used to accomplish tasks that are thought to have a rich relational structure. However, due to the sparse adjacency matrix constructed by GCN, GCN cannot make full use of context-dependent information in text classification, and it is not good at capturing local information. The Bidirectional Encoder Representation from Transformers (BERT) has the ability to capture contextual information in sentences or documents, but it is limited in capturing global (the corpus) information about vocabulary in a language, which is the advantage of GCN. Therefore, this paper proposes an improved model to solve the above problems. The original GCN uses word co-occurrence relationships to build text graphs. Word connections are not abundant enough and cannot capture context dependencies well, so we introduce a semantic dictionary and dependencies. While the model enhances the ability to capture contextual dependencies, it lacks the ability to capture sequences. Therefore, we introduced BERT and Bi-directional Long Short-Term Memory (BiLSTM) Network to perform deeper learning on the features of text, thereby improving the classification effect of the model. The experimental results show that our model is more effective than previous research reports on four text classification datasets.

Abstract. Short-term traffic demand prediction is one of the crucial issues in intelligent transport systems, which has attracted attention from the taxi industry and Mobility-on-Demand systems. Accurate predictions enable operators to dispatch their vehicles in advance, satisfying both drivers and passengers. This study aims to predict traffic demand over the entire city based on the Graph convolutional network (GCNN). Specially, we divide the study area into several non-overlap sub-regions. Each sub-region is treated as a node, and a traffic demand graph is constructed. Then, we build three graph convolution networks based on three different weighted adjacency matrices, which represent three graph structures. Furthermore, a data-driven graph convolutional network (DDGCNN) is developed, which can capture the correlation between pairs of sub-regions automatically. Finally, we compare our models with other prediction methods, including three GCNNs with a normal adjacency matrix, an existing data-driven graph convolutional neural network, historical average, and random forest. Results show that the weighted adjacency matrix can improve the prediction performance compared with a normal adjacency matrix. In addition, we proved that our DDGCNN outperforms other predictors in three aspects, i.e., performance over the test set, performance over the time aspect, and the performance over the spatial aspect.

In recent years, air pollution has become increasingly serious and poses a great threat to human health. Timely and accurate air quality prediction is crucial for air pollution early warning and control. Although data-driven air quality prediction methods are promising, there are still challenges in studying spatial–temporal correlations of air pollutants to design effective predictors. To address this issue, a novel model called adaptive adjacency matrix-based graph convolutional recurrent network (AAMGCRN) is proposed in this study. The model inputs Point of Interest (POI) data and meteorological data into a fully connected neural network to learn the weights of the adjacency matrix thereby constructing the self-ringing adjacency matrix and passes the pollutant data with this matrix as input to the Graph Convolutional Network (GCN) unit. Then, the GCN unit is embedded into LSTM units to learn spatio-temporal dependencies. Furthermore, temporal features are extracted using Long Short-Term Memory network (LSTM). Finally, the outputs of these two components are merged and air quality predictions are generated through a hidden layer. To evaluate the performance of the model, we conducted multi-step predictions for the hourly concentration of PM2.5, PM10 and O3 at Fangshan, Tiantan and Dongsi monitoring stations in Beijing. The experimental results show that our method achieves better predicted effects compared with other baseline models based on deep learning. In general, we designed a novel air quality prediction method and effectively addressed the shortcomings of existing studies in learning the spatio-temporal correlations of air pollutants. This method can provide more accurate air quality predictions and is expected to provide support for public health protection and government environmental decision-making.

In the context of a world increasingly reliant on digital technology, Advanced Persistent Threats (APT) pose a significant challenge to global cybersecurity. To address this issue, this paper introduces a novel approach called BiLSTM-Attention-GCN (BiLAG), an advanced model combining Bidirectional Long Short-Term Memory (BiLSTM) networks, Attention mechanisms, and Graph Convolutional Networks (GCN). The goal of BiLAG is to provide an effective and accurate method for detecting APT. BiLSTM is employed to capture temporal features related to event sequences, enabling the detection of anomalies over time. The Attention mechanism focuses on the most critical aspects of the dataset, allowing the model to identify hidden signals that indicate potential attacks. Lastly, GCN is utilized to explore complex relationships among network entities, enhancing APT detection by constructing a detailed and precise relational graph. Experimental results demonstrate that BiLAG achieves an accuracy of 99%, with high recall and significantly reduced false positive rates.

Adaptive dynamic spatial-temporal graph convolutional neural network for traffic flow prediction.

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.

In the field of transportation, accurate and real-time forecasting of traffic information is of great significance. However, Most of the existing traffic flow prediction methods lack the ability to model the dynamic spatial-temporal correlations. In order to obtain the satisfactory prediction results, We propose a new traffic prediction method based on neural network—a graph convolutional network (GCN) model based on the attention mechanism combined with gated recurrent unit (GRU). Specifically, the model uses an attention mechanism to obtain the weight information of each node at the input, and then uses GCN to learn complex topological structures to effectively capture spatial correlation, and finally uses GRU to learn the dynamics of traffic data change to capture time correlation. Applying the model to the experimental network dataset from the Traffic Performance Measurement System (PeMS) shows that our AT-GCN model can obtain spatial-temporal correlations from the traffic data, and has relatively good prediction effect.KeywordsTraffic flow predictionGraph convolutional networkSpatio-temporal correlationsAttention mechanism

Emotion recognition based on electroencephalography (EEG) plays a pivotal role in the field of affective computing, and graph convolutional neural network (GCN) has been proved to be an effective method and made considerable progress. Since the adjacency matrix that can describe the electrode relationships is critical in GCN, it becomes necessary to explore effective electrode relationships for GCN. However, the setting of the adjacency matrix and the corresponding value is empirical and subjective in emotion recognition, and whether it matches the target task remains to be discussed. To solve the problem, we proposed a graph convolutional network with learnable electrode relations (LR-GCN), which learns the adjacency matrix automatically in a goal-driven manner, including using self-attention to forward update the Laplacian matrix and using gradient propagation to backward update the adjacency matrix. Compared with previous works that use simple electrode relationships or only the feature information, LR-GCN achieved higher emotion recognition ability by extracting more reasonable electrode relationships during the training progress. We conducted a subject-dependent experiment on the SEED database and achieved recognition accuracy of 94.72% on the DE feature and 85.24% on the PSD feature. After visualizing the optimized Laplacian matrix, we found that the brain connections related to vision, hearing, and emotion have been enhanced.

Graph Convolutional Network (GCN) is adopted to tackle the problem of convolution operation in non-Euclidean space. Previous works on GCN have made some progress, however, one of their limitations is that the design of Adjacency Matrix (AM) as GCN input requires domain knowledge and such process is cumbersome, tedious and error-prone. In addition, entries of a fixed Adjacency Matrix are generally designed as binary values (i.e., ones and zeros) which can not reflect the real relationship between nodes. Meanwhile, many applications require a weighted and dynamic Adjacency Matrix instead of an unweighted and fixed AM, and there are few works focusing on designing a more flexible Adjacency Matrix. To that end, we propose an end-to-end algorithm to improve the GCN performance by focusing on the Adjacency Matrix. We first provide a calculation method called node information entropy to update the matrix. Then, we perform the search strategy in a continuous space and introduce the Deep Deterministic Policy Gradient (DDPG) method to overcome the drawback of the discrete space search. Finally, we integrate the GCN and reinforcement learning into an end-to-end framework. Our method can automatically define the Adjacency Matrix without prior knowledge. At the same time, the proposed approach can deal with any size of the matrix and provide a better AM for network. Four popular datasets are selected to evaluate the capability of our algorithm. The method in this paper achieves the state-of-the-art performance on Cora and Pubmed datasets, with the accuracy of 84.6% and 81.6% respectively.

Graph Convolutional Network (GCN) is adopted to tackle the problem of convolution operation in non-Euclidean space. Previous works on GCN have made some progress, however, one of their limitations is that the design of Adjacency Matrix (AM) as GCN input requires domain knowledge and such process is cumbersome, tedious and error-prone. In addition, entries of a fixed Adjacency Matrix are generally designed as binary values (i.e., ones and zeros) which can not reflect the real relationship between nodes. Meanwhile, many applications require a weighted and dynamic Adjacency Matrix instead of an unweighted and fixed AM, and there are few works focusing on designing a more flexible Adjacency Matrix. To that end, we propose an end-to-end algorithm to improve the GCN performance by focusing on the Adjacency Matrix. We first provide a calculation method called node information entropy to update the matrix. Then, we perform the search strategy in a continuous space and introduce the Deep Deterministic Policy Gradient (DDPG) method to overcome the drawback of the discrete space search. Finally, we integrate the GCN and reinforcement learning into an end-to-end framework. Our method can automatically define the Adjacency Matrix without prior knowledge. At the same time, the proposed approach can deal with any size of the matrix and provide a better AM for network. Four popular datasets are selected to evaluate the capability of our algorithm. The method in this paper achieves the state-of-the-art performance on Cora and Pubmed datasets, with the accuracy of 84.6% and 81.6% respectively.

April-GCN: Adjacency Position-velocity Relationship Interaction Learning GCN for Human motion prediction

Different from other computer vision tasks, action recognition needs to process larger-scale video data. How to extract and analyze the effective parts from a huge amount of video information is the main difficulty of action recognition technology. In recent years, due to the outstanding performance of Graph Convolutional Networks (GCN) in many fields, a new solution to the action recognition algorithm has emerged. However, in current GCN models, the constant physical adjacency matrix makes it difficult to mine synergistic relationships between key points that are not directly connected in physical space. Additionally, a simple time connection of skeleton data from different frames makes each frame in the video contribute equally to the recognition results, which increases the difficulty of distinguishing action stages. In this paper, the information extraction ability of the model has been optimized in the space domain and time domain, respectively. In the space domain, an Adjacency Matrix Generation (AMG) module, which can pre-analyze node sets and generate an adaptive adjacency matrix, has been proposed. The adaptive adjacency matrix can help the graph convolution model to extract the synergistic information between the key points that are crucial for recognition. In the time domain, the Time Domain Attention (TDA) mechanism has been designed to calculate the time-domain weight vector through double pooling channels and complete the weights of key point sequences. Furthermore, performance of the improved TDA-AMG-GCN modules has been verified on the NTU-RGB+D dataset. Its detection accuracy at the CS and CV divisions reached 84.5% and 89.8%, respectively, with an average level higher than other commonly used detection methods at present.

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art deep learning model for representation learning on graphs. However, it remains notoriously challenging to train and inference GCNs over large graph datasets, limiting their application to large real-world graphs and hindering the exploration of deeper and more sophisticated GCN graphs. This is because as the graph size grows, the sheer number of node features and the large adjacency matrix can easily explode the required memory and data movements. To tackle the aforementioned challenges, we explore the possibility of drawing lottery tickets when sparsifying GCN graphs, i.e., subgraphs that largely shrink the adjacency matrix yet are capable of achieving accuracy comparable to or even better than their full graphs. Specifically, we for the first time discover the existence of graph early-bird (GEB) tickets that emerge at the very early stage when sparsifying GCN graphs, and propose a simple yet effective detector to automatically identify the emergence of such GEB tickets. Furthermore, we advocate graph-model co-optimization and develop a generic efficient GCN early-bird training framework dubbed GEBT that can significantly boost the efficiency of GCN training by (1) drawing joint early-bird tickets between the GCN graphs and models and (2) enabling simultaneously sparsification of both the GCN graphs and models. Experiments on various GCN models and datasets consistently validate our GEB finding and the effectiveness of our GEBT, e.g., our GEBT achieves up to 80.2% ~ 85.6% and 84.6% ~ 87.5% savings of GCN training and inference costs while offering a comparable or even better accuracy as compared to state-of-the-art methods. Our source code and supplementary appendix are available at https://github.com/RICE-EIC/Early-Bird-GCN.