Search

Traditional human skeleton action recognition algorithms manually construct topological graphs to model the action sequence contained in multiple video frames and learn each video frame to reflect the data changes,which may lead to the high computational cost,low network generalization performance and catastrophic forgetting.To solve these problems,a human skeleton action recognition algorithm based on dynamic topological graph is proposed,in which the human skeleton topological graph is dynamically constructed based on continuous learning.Specifically,human skeleton sequence data with multi-relationship characte-ristics are recoded into relationship triplets,and feature embedding is learned in a decoupling manner via the long short-term me-mory network.When handling new skeleton relationship triplets,we dynamically construct the human skeleton topological graph by a partial update mechanism,and then send it to the skeleton action recognition algorithm based on spatio-temporal graph convolution network for action recognition.Experimental results demonstrate that the proposed algorithm achieves 40%,85% and 90% recognition accuracy on three benchmark datasets,namely Kinetics-Skeleton,NTU-RGB+D(X-Sub) and NTU-RGB+D(X-View),respectively,which improve the accuracy of human skeleton action recognition.

Health professionals often prescribe patients to perform specific exercises for rehabilitation of several diseases (e.g., stroke, Parkinson, backpain). When patients perform those exercises in the absence of an expert (e.g., physicians/therapists), they cannot assess the correctness of the performance. Automatic assessment of physical rehabilitation exercises aims to assign a quality score given an RGBD video of the body movement as input. Recent deep learning approaches address this problem by extracting CNN features from co-ordinate grids of skeleton data (body-joints) obtained from videos. However, they could not extract rich spatio-temporal features from variable-length inputs. To address this issue, we investigate Graph Convolutional Networks (GCNs) for this task. We adapt spatio-temporal GCN to predict continuous scores(assessment) instead of discrete class labels. Our model can process variable-length inputs so that users can perform any number of repetitions of the prescribed exercise. Moreover, our novel design also provides self-attention of body-joints, indicating their role in predicting assessment scores. It guides the user to achieve a better score in future trials by matching the same attention weights of expert users. Our model successfully outperforms existing exercise assessment methods on KIMORE and UI-PRMD datasets.

3D model classification is an important task. Now, 3D model is usually expressed as point cloud. Disorder of point cloud brings great difficulty into 3D model classification. In order to classify 3D model correctly, a new classification method combining Graph Convolution Network (GCN) and Support Vector Machine (SVM) is proposed in this paper. Point cloud is sampled. K-Nearest Neighbor (KNN) algorithm is used to find K nearest points of sampling point, and adjacency matrix is established for graph convolution operation. Shape features D1, D2, D3 and A3 of sampling point are computed based on its K nearest points. Coordinates and shape features of sampling point are combined as discriminative feature. 2-layer graph convolution is used to aggregate disambiguation information of 1-degree and 2-degree adjacent points of sampling point for describing point cloud comprehensively. At the same time, maximum pooling and average pooling are adopted to retain representative information. Finally, SVM is used to classify point clouds. Experimental results show that compared with GCN based on coordinates, the proposed network improves accuracy of 3D model classification by 1.67%. Global and local information can be extracted adequately when 1024 points are sampled from point cloud. When we select 20 nearest points to compute shape features D1, D2, D3, A3, local information of point can be described better. Shape features D1, D2, D3, A3 are combined with coordinates to describe shape and structure of point cloud better. 2-layer graph convolutions are adopted to aggregate information of 1-degree and 2-degree nodes for extracting effective disambiguation features.

Building a dense correspondence between two images is a fundamental vision problem. Most existing methods use local features, but global features cannot be ignored. Local features are often not enough to disambiguate similar regions without global features. Computing relevant features between images requires structural relationship and the importance of local features. For that, We propose novel multi-scale attention and structural relation graph (MASRG) for local feature matching. The MASRG adopts an overall architecture that first builds coarse-level matches on a coarse feature map and then refines fine matches on a fine-level feature map. We propose a structural relation graph module and a multi-scale attention module. We introduce global context information into the overall architecture. Using global information to separately assist in learning the structural information between local descriptors, the features of different receptive fields, and the importance of modeling single local information, a limited number of possible matches can be obtained with high confidence. Finally, the matching relationship is predicted. In this way, the network significantly improves the matching reliability and localization accuracy. Our proposed method has 5.6%, 6.7%, and 6.3% performance increases over the baseline method(See I) under different conditions in the HPatches. Extensive experiments on three large-scale datasets (i.e., HPatches, InLoc, and Aachen Day-Night v1.1) demonstrate that our proposed MASRG method is superior to state-of-the-art local feature matching approaches.

Virtual reality (VR) has been adopted in various fields such as entertainment, education, healthcare, and the military, due to its ability to provide an immersive experience to users. However, 360° images, one of the main components in VR systems, have bulky sizes and thus require effective transmitting and rendering solutions. One of the potential solutions is to use foveated technologies, that take advantage of the foveation feature of the human eyes. Foveated technologies can significantly reduce the data required for transmission and computation complexity in rendering. However, understanding the impact of foveated 360° images on human quality perception is still limited. This paper addresses the above problems by proposing an accurate machine-learning-based quality assessment model for foveated 360° images. The proposed model is proven to outperform the three cutting-edge machine-learning-based models, which apply deep learning techniques and 25 traditional-metric-based models (or analytical-function-based-models), which utilize analytical functions. It is also expected that our model helps to evaluate and improve 360° content streaming and rendering solutions to further reduce data sizes while ensuring user experience. Also, this model could be used as a building block to construct quality assessment methods for 360° videos, that are reserved for our future work. The source code is available at https://github.com/telagment/FoVGCN.

In skeleton-based human action recognition, Transformer, which models the correlations between joint pairs in global topology, has achieved remarkable results. However, compared to many researches on changing graph topology learning in graph convolution network (GCN), Transformer self-attention ignores the topology of the skeleton graph when capturing the dependencies between joints. To address these problems, we propose a novel two-stream spatial Graphormer network (2s-SGR), which uses self-attention incorporating structural encodings to model joint and bone information, and which consists of two networks, the joint stream spatial Graphormer network (Js-SGR) and the bone stream spatial Graphormer network (Bs-SGR). First, in the Js-SGR, while Transformer models joint correlations in the global topology of the space, the topology of the joints and the edge information of the bones are introduced into the self-attention through custom structural encodings. At the same time, joint motion information is modeled in spatial-temporal blocks. The added information on structure and motion can effectively capture the dependencies of nodes between frames and enhance feature representation. Second, for the second-order information of the skeleton, the Bs-SGR adapts to the structure of the bone by adjusting the custom structural encodings. Finally, the global spatial-temporal features of joints and bones in the skeleton are fused and input into the classification network to obtain action recognition results. Extensive experiments on three large-scale datasets, NTU-RGB+D 60, NTU-RGB+D 120, and Kinetics, demonstrate that the performance of the 2s-SGR proposed in this paper is at the state-of-the-art level and is effectively validated by ablation experiments.

Understanding maritime network structure and traffic flow changes is a challenging task that must incorporate economic, energy, geopolitics, maritime transportation, and network sciences. Crude oil is the most imported energy in the world. Investigating the crude oil maritime network status and predicting the crude oil traffic flow changes has great significance for the global trade, especially for key crude oil importing/exporting regions and countries. To address this, a system-based approach using long short-term memory and graph convolution network for the crude oil traffic flow forecasting named LGCOTFF is introduced. The LGCOTFF approach constructs a maritime transportation network firstly, and then calculates and predicts the node traffic flow based on trajectory data and crude oil berth geographical position. Firstly, we construct a maritime crude oil transportation network based on supply-demand relationship, ship trajectory and route information. Then, we design an approach to calculate how many crude oil ships finished up-load/offtake tasks in a single week for each port, and gather this data to countries and regions. Finally, we design a deep learning neural network named long short-term memory and graph convolution network (L-GCN) to extract the temporal and spatial characteristics of crude oil transportation, and predict the node traffic flow. We evaluate the proposed model on China, Russia, Middle East and America respectively and observe consistent improvement of more than 10% over state-of-the-art baselines.

A significant aspect of today’s digital information is attributed networks, which combine multiple node attributes with the basic network topology to extract knowledge. Anomaly Detection on attributed networks has recently drawn significant attention from researchers and is widely used in several high-impact areas. Most current approaches focus on shallow learning methods such as community analysis, ego network or selection of subspace method. These approaches have network sparsity and data nonlinearity problems, and they do not even capture the intricate relationships between various information sources. Deep learning approaches like graph autoencoders are utilized to perform anomaly detection through obtaining node embeddings while dealing with the network nonlinearity and sparsity issues. However, they suffer from the problem of ignoring the latent codes’ embedding distribution, which results in poor representation in many instances. In this paper, we propose a new framework called DVAEGMM to detect anomalies on attributed networks. First, our framework utilizes a dual variational autoencoder for capturing the complex cross-modality relationships between node attributes and network structure, like vanilla autoencoders, but it also considers the potential data distribution and makes use of a generative adversarial network (GAN) for an adversarial regularization approach. An adversarial mechanism makes the encoder make more accurate estimates of how potential features might be distributed. As a result, decoders can make graphs that are more like the original graph. Each input data point is represented by a low-dimensional representation and a probability of reconstruction by the algorithm. Lastly, the Gaussian Mixture Model, a distinct estimation network, is used to approximate the latent vector density, resulting in the detection of anomalies from measuring sample energy. They are trained jointly as an end-to-end framework. DVAEGMM helps in the simultaneous optimization of the mixture model, generative adversarial network, and variational autoencoder parameters. The joint optimization balances the reconstruction probability, the latent representation density approximation, and regularization. Extensive experiments on attributed networks prove that DVAEGMM significantly beats the existing methods, proving the efficiency of the presented approach. The AUC scores of our proposed framework for the BlogCatalog, Flickr, Enron, and Amazon datasets are 0.89380, 0.87130, 0.72480, and 0.75102, respectively.

Ancient Chinese architecture(ACA), especially like roof ridge decoration, vividly exhibits Chinese civilization and the typical, accurate image semantics can well reflect the historical style of ACA at that time. However, the current research on the 2D image annotation method of ACA lacks the annotation of historical and cultural information(such as dynasties, regions, etc.). In addition, with the enrichment of ACA labels, the number of irrelevant labels will increase. To solve these problems, we propose an ACA image annotation method based on visual attention mechanism and graph convolutional network (GCN). Firstly, according to the uniqueness of the roof ridge decoration of ACA, we introduce the visual attention mechanism into the convolution neural network (CNN) to focus on the roof ridge decoration area and the corresponding image features are extracted. Secondly, to avoid the output of irrelevant labels, we construct a correlation matrix in the GCN to transfer the correlation between the labels of ACA and then obtain the label-related classifier. Finally, the classifier is applied to the extracted image features for multi-label loss training. Experiments on six types of ACA datasets demonstrate that the proposed method can effectively improve the annotation accuracy and enrich the semantic information of ACA. [ABSTRACT FROM AUTHOR]

Structural deep clustering involves the use of neural networks for fusing semantic and structural representations for clustering tasks, and it has been receiving increasing attention. In some pioneering works, auto-encoder (AE)-specific representations were integrated with a graph convolutional network (GCN)-specific representation by delivering semantic information to the GCN module layer-by-layer. Although promising performance has been achieved in various applications, we observed that a vital aspect was overlooked in these works: the structural information may vanish in the learning process because of the over-smoothing problem of the GCN module, leading to non-representative features and, thus, deteriorating clustering performance. In this study, we address this issue by proposing a structure enhanced deep clustering network. The GCN-specific structural data representation is enhanced and supervised by its structural information. Specifically, the GCN-specific structural data representation is strengthened during the learning process by combining it with a structure enhanced semantic (SES) representation. A novel structure enhanced AE, named the weighted neighbourhood AE (wNAE), is employed to learn the SES representation for each data sample. Finally, we design a joint supervision strategy to uniformly guide the simultaneous learning of the wNAE and GCN modules and the clustering assignment. Experimental results for different datasets empirically validate the importance of semantic and neighbour-wise structure learning. [ABSTRACT FROM AUTHOR]

The data-driven intelligent health state diagnosis strategy has been successfully applied in modern industrial equipments. However, many of existing research works suffer from two major deficiencies: First, the sample independence assumption is widely adopted, so the influences of the relationship between samples on the overall performances are not explored. Second, most of the abovementioned application objects are typical key functional components (such as bearings, gearboxes, etc.), and research works on the intelligent health state diagnosis of planar parallel manipulator are rarely reported. To address these issues, a novel intelligent health state diagnosis method, termed multiscale graph-guided convolutional network with node attention (MSGCN-NA), is proposed for a 3-PRR (P and R represent prismatic and revolute pairs, respectively) planar parallel manipulator. Specifically, the developed MSGCN-NA model mainly contains the following two parts: first, the one is an unsupervised convolutional autoencoder, which is employed for the extraction of deep representation features, and then combined with Pearson metric to establish the adjacency matrix. Second, The other part is the constructed multiscale graph convolutional network, in which the node attention mechanism is adopted to achieve cross-scale fusion of different neighborhood information. The effectiveness of the proposed MSGCN-NA method is fully verified based on the simulation and experimental scenarios, the results show that MSGCN-NA can achieve superior diagnosis performances. [ABSTRACT FROM AUTHOR]

With the rapid development of the online shopping, the pursuit of outfit compatibility has become a basic requirement for an increasing number of customers. The existing work on outfit compatibility prediction largely focuses on modeling pairwise item compatibility without considering modeling the whole outfit directly. To address the problem, in this paper, we propose a novel hypergraph-based compatibility modeling scheme named OCPHN, which is able to better model complex relationships among outfits. In OCPHN, we represent the outfit as a hypergraph, where each hypernode represents a category and each hyperedge represents the interactions between multiple categories (i.e., they appear in the same outfit). To better predict outfit compatibility, the hypergraph is transformed into a simple graph, and the message propagation mechanism in the graph convolution network is used to aggregate the neighbours' information on the node and update the node representations. Furthermore, with learned node representations, an attention mechanism is introduced to compute the outfit compatibility score. Using a benchmark dataset, the experimental results show that the proposed method is an improvement over the strangest baselines in terms of accuracy by about 3% and 1% in the fill-in-the-blank and compatibility prediction tasks, respectively. [ABSTRACT FROM AUTHOR]

3D scene graph generation (SGG) aims to predict the class of objects and predicates simultaneously in one 3D point cloud scene with instance segmentation. Since the underlying semantic of 3D point clouds is spatial information, recent ideas of the 3D SGG task usually face difficulties in understanding global contextual semantic relationships and neglect the intrinsic 3D visual structures. To build the global scope of semantic relationships, we first propose two types of Semantic Clue (SC) from entity level and path level, respectively. SC can be extracted from the training set and modeled as the co‐occurrence probability between entities. Then a novel Semantic Clue aware Graph Convolution Network (SC‐GCN) is designed to explicitly model each SC of which the message is passed in their specific neighbor pattern. For constructing the interactions between the 3D visual and semantic modalities, a visual‐language transformer (VLT) module is proposed to jointly learn the correlation between 3D visual features and class label embeddings. Systematic experiments on the 3D semantic scene graph (3DSSG) dataset show that our full method achieves state‐of‐the‐art performance. [ABSTRACT FROM AUTHOR]

• A center-connected graph convolutional network enhanced with salient image features (SIFE-CGCN) was proposed by integrating the image semantics to improve the recognition performance of similar actions. • A center-connected skeleton topology was developed to enhance the learning capability of the GCN on the potential cooperative dependencies of all joints. • The DTW-based metric was developed to measure the action similarity and build the similar action dataset. The proposed model achieves state-of-the-art performance on three large-scale datasets. Skeleton-based human action recognition has drawn more and more attention due to its easy implementation and stable application in intelligent human-robot interaction. However, most existing studies only used the skeleton data but completely ignored other image semantic information to build action recognition models, which would confuse the recognition of similar actions because of the ambiguity between skeleton data. Here, a center-connected graph convolutional network enhanced with salient image features (SIFE-CGCN) is proposed to address the problem of similar action recognition. First, a center-connected network (CGCN) is constructed to capture the small differences between similar actions through exploring the possible collaboration between all joints. Subsequently, a metric of movement changes is employed to optimally select the salient image from an action video, and then the EfficientNet is used to achieve the action semantic classification of the salient images. Finally, the recognition results of CGCN are strengthened with the classification results of salient images to further improve the recognition accuracy for similar actions. Additionally, a metric is proposed to measure the action similarity with the skeleton data, and then a similar action dataset is built. Extensive experiments on the datasets of similar action and NTU RGB + D 60/120 were conducted to verify the performance of the proposed methods. Experimental results validated the effectiveness of salient image feature enhancement and showed that the proposed SIFE-CGCN achieved the state-of-the-art performance on the similar action and NTU RGB + D 60/120 datasets. [ABSTRACT FROM AUTHOR]

Entity alignment is used to determine whether entities from different sources refer to the same object in the real world. It is one of the key technologies for constructing large-scale knowledge graphs and is widely used in the fields of knowledge graphs and knowledge complementation. Because of the lack of semantic connection between the visual modality face attribute of the person entity and the text modality attribute and relationship information, it is difficult to model the visual and text modality into the same semantic space, and, as a result, that the traditional multimodal entity alignment method cannot be applied. In view of the scarcity of multimodal person relation graphs datasets and the difficulty of the multimodal semantic modeling of person entities, this paper analyzes and crawls open-source semi-structured data from different sources to build a multimodal person entity alignment dataset and focuses on using the facial and semantic information of multimodal person entities to improve the similarity of entity structural features which are modeled using the graph convolution layer and the dynamic graph attention layer to calculate the similarity. Through verification on the self-made multimodal person entity alignment dataset, the method proposed in this paper is compared with other entity alignment models which have a similar structure. Compared with AliNet, the probability that the first item in the candidate pre-aligned entity set is correct is increased by 12.4% and average ranking of correctly aligned entities in the candidate pre-aligned entity set decreased by 32.8, which proves the positive effect of integrating multimodal facial information, applying dynamic graph attention and a layer-wise gated network to improve the alignment effect of person entities. [ABSTRACT FROM AUTHOR]

Point clouds are fundamental in the representation of 3D objects. However, they can also be highly unstructured and irregular. This makes it difficult to directly extend 2D generative models to three-dimensional space. In this article, we cast the problem of point cloud generation as a topological representation learning problem. In order to capture the representative features of 3D shapes in the latent space, we propose a hierarchical mixture model that integrates self-attention with an inference tree structure for constructing a point cloud generator. Based on this, we design a novel Generative Adversarial Network (GAN) architecture that is capable of generating recognizable point clouds in an unsupervised manner. The proposed adversarial framework (SG-GAN) relies on self-attention mechanism and Graph Convolution Network (GCN) to hierarchically infer the latent topology of 3D shapes. Embedding and transferring the global topology information in a tree framework allows our model to capture and enhance the structural connectivity. Furthermore, the proposed architecture endows our model with partially generating 3D structures. Finally, we propose two gradient penalty methods to stabilize the training of SG-GAN and overcome the possible mode collapse of GAN networks. To demonstrate the performance of our model, we present both quantitative and qualitative evaluations and show that SG-GAN is more efficient in training and it exceeds the state-of-the-art in 3D point cloud generation. [ABSTRACT FROM AUTHOR]

Single-cell RNA sequencing (scRNA-seq) technology has been a significant direction for single-cell research due to its high accuracy and specificity, as it enables unbiased high-throughput studies with minimal sample sizes. The continuous improvement of scRNA-seq technology has promoted parallel research on single-cell multi-omics. Instead of sequencing bulk cells, analyzing single cells inspires greater discovery power for detecting novel genes without prior knowledge of sequence information and with greater sensitivity when quantifying rare variants and transcripts. However, current analyses of scRNA-seq data are usually carried out with unsupervised methods, which cannot take advantage of the prior distribution and structural features of the data. To solve this problem, we propose the SCAFG (Classifying Single Cell Types Based on an Adaptive Threshold Fusion Graph Convolution Network), a semi-supervised single-cell classification model that adaptively fuses cell-to-cell correlation matrices under various thresholds according to the distribution of cells. We tested the performance of the SCAFG in identifying cell types on diverse real scRNA-seq data; then, we compared the SCAFG with other commonly used semi-supervised algorithms, and it was shown that the SCAFG can classify single-cell data with a higher accuracy. [ABSTRACT FROM AUTHOR]

Earthquakes threaten people, homes, and infrastructure. Early warning systems provide prior warning of oncoming significant shaking to decrease seismic risk by providing location, magnitude, and depth information of the event. Their usefulness depends on how soon a strong shake begins after the warning. In this article, the authors implement a deep learning model for predicting earthquakes. This model is based on a graph convolutional neural network with batch normalization and attention mechanism techniques that can successfully predict the depth and magnitude of an earthquake event at any number of seismic stations in any number of locations. After preprocessing the waveform data, CNN extracts the feature map. Attention mechanism is used to focus on important features. The batch normalization technique takes place in batches for stable and faster training of the model by adding an extra layer. GNN with extracted features and event location information predicts the event information accurately. We test the proposed model on two datasets from Japan and Alaska, which have different seismic dynamics. The proposed model achieves 2.8 and 4.0 RMSE values in Alaska and Japan for magnitude prediction, and 2.87 and 2.66 RMSE values for depth prediction. Low RMSE values show that the proposed model significantly outperforms the three baseline models on both datasets to provide an accurate estimation of the depth and magnitude of small, medium, and large-magnitude events. [ABSTRACT FROM AUTHOR]

Circular RNA (circRNA) is closely involved in physiological and pathological processes of many diseases. Discovering the associations between circRNAs and diseases is of great significance. Due to the high-cost to verify the circRNA-disease associations by wet-lab experiments, computational approaches for predicting the associations become a promising research direction. In this paper, we propose a method, MDGF-MCEC, based on multi-view dual attention graph convolution network (GCN) with cooperative ensemble learning to predict circRNA-disease associations. First, MDGF-MCEC constructs two disease relation graphs and two circRNA relation graphs based on different similarities. Then, the relation graphs are fed into a multi-view GCN for representation learning. In order to learn high discriminative features, a dual-attention mechanism is introduced to adjust the contribution weights, at both channel level and spatial level, of different features. Based on the learned embedding features of diseases and circRNAs, nine different feature combinations between diseases and circRNAs are treated as new multi-view data. Finally, we construct a multi-view cooperative ensemble classifier to predict the associations between circRNAs and diseases. Experiments conducted on the CircR2Disease database demonstrate that the proposed MDGF-MCEC model achieves a high area under curve of 0.9744 and outperforms the state-of-the-art methods. Promising results are also obtained from experiments on the circ2Disease and circRNADisease databases. Furthermore, the predicted associated circRNAs for hepatocellular carcinoma and gastric cancer are supported by the literature. The code and dataset of this study are available at https://github.com/ABard0/MDGF-MCEC. [ABSTRACT FROM AUTHOR]

Simple Summary: With the development of circRNA–miRNA-mediated models, circRNAs have been shown to play a prominent role in the development and treatment of diseases such as cancer, and unearthing potential miRNA-associated circRNAs may provide new insights and ideas for the diagnosis and treatment of complex diseases such as cancer. Large-scale prediction using computer technology can provide an a priori guide to biological experiments and save costs. This paper presents the third computational method in this field with the highest accuracy to date, and we also collected and integrated high-quality datasets from the current database, which we believe will allow future computational innovations to develop. Computational prediction of miRNAs, diseases, and genes associated with circRNAs has important implications for circRNA research, as well as provides a reference for wet experiments to save costs and time. In this study, SGCNCMI, a computational model combining multimodal information and graph convolutional neural networks, combines node similarity to form node information and then predicts associated nodes using GCN with a distributive contribution mechanism. The model can be used not only to predict the molecular level of circRNA–miRNA interactions but also to predict circRNA–cancer and circRNA–gene associations. The AUCs of circRNA—miRNA, circRNA–disease, and circRNA–gene associations in the five-fold cross-validation experiment of SGCNCMI is 89.42%, 84.18%, and 82.44%, respectively. SGCNCMI is one of the few models in this field and achieved the best results. In addition, in our case study, six of the top ten relationship pairs with the highest prediction scores were verified in PubMed. [ABSTRACT FROM AUTHOR]

In recent years, traffic forecasting has gradually attracted attention in data mining because of the increasing availability of large-scale traffic data. However, it faces substantial challenges of complex temporal-spatial correlations in traffic. Recent studies mainly focus on modeling the local spatial correlations by utilizing graph neural networks and neglect the influence of long-distance spatial correlations. Besides, most existing works utilize recurrent neural networksbased encoder-decoder architecture to forecast multistep traffic volume and suffer from accumulative errors in recurrent neural networks. To deal with these issues, we propose the memory attention (MA) enhanced graph convolution long short-term memory network (MAEGCLSTM), a novel deep learning model for traffic forecasting. Specifically, MAEGCLSTM combines the MA and the vanilla graph convolution long short-term memory to capture global and local spatio-temporal dependencies, respectively. Then MAEGCLSTM utilizes a simplified GCLSTM to effectively fuse the global and local information. Moreover, we integrate the MAEGCLSTM into an encoder-decoder architecture to forecast multistep traffic volume. Besides MAEGCLSTM, we add the convolution neural network and encoder-decoder attention into the decoder to ease accumulative errors caused by iterative prediction and gain whole historical information from the encoder. Experiments on four realworld traffic data sets show that our model significantly outperforms by up to 6.07% improvement in L1 measure over 14 baselines. [ABSTRACT FROM AUTHOR]

Essential tremor with resting tremor (rET) and tremor-dominant Parkinson's disease (tPD) share many similar clinical symptoms, leading to frequent misdiagnoses. Functional connectivity (FC) matrix analysis derived from resting-state functional MRI (Rs-fMRI) offers a promising approach for early diagnosis and for exploring FC network pathogenesis in rET and tPD. However, methods relying solely on a single connection pattern may overlook the complementary roles of different connectivity patterns, resulting in reduced diagnostic differentiation. Therefore, we propose a multi-pattern connection Graph Convolutional Network (MCGCN) method to integrate information from various connection modes, distinguishing between rET and healthy controls (HC), tPD and HC, and rET and tPD. We constructed FC matrices using three different connectivity modes for each subject and used these as inputs to the MCGCN model for disease classification. The classification performance of the model was evaluated for each connectivity mode. Subsequently, gradient-weighted class activation mapping (Grad-CAM) was used to identify the most discriminative brain regions. The important brain regions identified were primarily distributed within cerebellar-motor and non-motor cortical networks. Compared with single-pattern GCN, our proposed MCGCN model demonstrated superior classification accuracy, underscoring the advantages of integrating multiple connectivity modes. Specifically, the model achieved an average accuracy of 88.0% for distinguishing rET from HC, 88.8% for rET from tPD, and 89.6% for tPD from HC. Our findings indicate that combining graph convolutional networks with multi-connection patterns can not only effectively discriminate between tPD, rET, and HC but also enhance our understanding of the functional network mechanisms underlying rET and tPD., (Copyright © 2024 International Brain Research Organization (IBRO). Published by Elsevier Inc. All rights reserved.)

In the information age, the amount of data is growing exponentially.However, different data sources are heterogeneous, which makes it inconvenient to share and multiplex data.With the rapid development of semantic network, ontology mapping is an effective method to solve this problem.The core of ontology mapping is ontology similarity calculation.Therefore, a calculation method based on graph convolution network was proposed.Firstly, ontologiesare modeled as a heterogeneous graph network, then the graph convolution network was used to learn the text embedding rules, which made ontologies were definedin global unified representation.Lastly, multisource data fusion was completed.The experimental results show that the accuracy of the proposed method is higher than other methods, and the accuracy of multi-source data fusion was effectively improved.

In the information age, the amount of data is growing exponentially. However, different data sources are heterogeneous, which makes it inconvenient to share and multiplex data. With the rapid development of semantic network, ontology mapping is an effective method to solve this problem. The core of ontology mapping is ontology similarity calculation. Therefore, a calculation method based on graph convolution network was proposed. Firstly, ontologiesare modeled as a heterogeneous graph network, then the graph convolution network was used to learn the text embedding rules, which made ontologies were definedin global unified representation. Lastly, multisource data fusion was completed. The experimental results show that the accuracy of the proposed method is higher than other methods, and the accuracy of multi-source data fusion was effectively improved.

Automatic modulation classification (AMC) of underwater acoustic communication signals is of great significance in national defense and marine military. Accurate modulation classification methods can make great contributions to accurately grasping the parameters and characteristics of enemy communication systems. While a poor underwater acoustic channel makes it difficult to classify the modulation types correctly. Feature extraction and deep learning methods have proven to be effective methods for the modulation classification of underwater acoustic communication signals, but their performance is still limited by the complex underwater communication environment. Graph convolution networks (GCN) can learn the graph structured information of the data, making it an effective method for processing structured data. To improve the stability and robustness of AMC in underwater channels, we combined the feature extraction and deep learning methods by fusing the multi-domain features and deep features using GCN. The proposed method takes the relationships among the different multi-domain features and deep features into account. Firstly, a feature graph was built using the properties of the features. Secondly, multi-domain features were extracted from the received signals and deep features were extracted from the signals using a deep neural network. Thirdly, we constructed the input of GCN using these features and the graph. Then, the multi-domain features and deep features were fused by the GCN. Finally, we classified the modulation types using the output of GCN by way of a softmax layer. We conducted the experiments on a simulated dataset and a real-world dataset, respectively. The results show that the AMC based on GCN can achieve a significant improvement in performance compared to the current state-of-the-art methods. Our approach is robust in underwater acoustic channels.

Traffic forecasting has always been an important part of intelligent transportation systems. At present, spatiotemporal graph neural networks are widely used to capture spatiotemporal dependencies. However, most spatiotemporal graph neural networks use a single predefined matrix or a single self-generated matrix. It is difficult to obtain deeper spatial information by only relying on a single adjacency matrix. In this paper, we present a progressive multi-graph convolutional network (PMGCN), which includes spatiotemporal attention, multi-graph convolution, and multi-scale convolution modules. Specifically, we use a new spatiotemporal attention multi-graph convolution that can extract extensive and comprehensive dynamic spatial dependence between nodes, in which multiple graph convolutions adopt progressive connections and spatiotemporal attention dynamically adjusts each item of the Chebyshev polynomial in graph convolutions. In addition, multi-scale time convolution was added to obtain an extensive and comprehensive dynamic time dependence from multiple receptive field features. We used real datasets to predict traffic speed and traffic flow, and the results were compared with a variety of typical prediction models. PMGCN has the smallest Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) results under different horizons (H = 15 min, 30 min, 60 min), which shows the superiority of the proposed model.

The core of large-scale drug virtual screening is to select the binders accurately and efficiently with high affinity from large libraries of small molecules in which non-binders are usually dominant. The binding affinity is significantly influenced by the protein pocket, ligand spatial information, and residue types/atom types. Here, we used the pocket residues or ligand atoms as the nodes and constructed edges with the neighboring information to comprehensively represent the protein pocket or ligand information. Moreover, the model with pre-trained molecular vectors performed better than the one-hot representation. The main advantage of DeepBindGCN is that it is independent of docking conformation, and concisely keeps the spatial information and physical–chemical features. Using TIPE3 and PD-L1 dimer as proof-of-concept examples, we proposed a screening pipeline integrating DeepBindGCN and other methods to identify strong-binding-affinity compounds. It is the first time a non-complex-dependent model has achieved a root mean square error (RMSE) value of 1.4190 and Pearson r value of 0.7584 in the PDBbind v.2016 core set, respectively, thereby showing a comparable prediction power with the state-of-the-art affinity prediction models that rely upon the 3D complex. DeepBindGCN provides a powerful tool to predict the protein–ligand interaction and can be used in many important large-scale virtual screening application scenarios.