Search

• We propose a model to detect the spatial locus of a listener's auditory attention. • EEG is modeled as a graph with node features based on time-frequency feature fusion. • Graph convolution can take advantage of local brain neuroanatomical connectivity. • Global attention mechanism is adopted to learn global brain effective connectivity. • Right-lateralized frontotemporal activation and connectivity exist in spatial hearing. Auditory spatial attention detection (ASAD) aims to decipher the spatial locus of a listener's selective auditory attention from electroencephalogram (EEG) signals. However, current models may exhibit deficiencies in EEG feature extraction, leading to overfitting on small datasets or a decline in EEG discriminability. Furthermore, they often neglect topological relationships between EEG channels and, consequently, brain connectivities. Although graph-based EEG modeling has been employed in ASAD, effectively incorporating both local and global connectivities remains a great challenge. To address these limitations, we propose a new ASAD model. First, time-frequency feature fusion provides a more precise and discriminative EEG representation. Second, EEG segments are treated as graphs, and the graph convolution and global attention mechanism are leveraged to capture local and global brain connections, respectively. A series of experiments are conducted in a leave-trials-out cross-validation manner. On the MAD-EEG and KUL datasets, the accuracies of the proposed model are more than 9% and 3% higher than those of the corresponding state-of-the-art models, respectively, while the accuracy of the proposed model on the SNHL dataset is roughly comparable to that of the state-of-the-art model. EEG time-frequency feature fusion proves to be indispensable in the proposed model. EEG electrodes over the frontal cortex are most important for ASAD tasks, followed by those over the temporal lobe. Additionally, the proposed model performs well even on small datasets. This study contributes to a deeper understanding of the neural encoding related to human hearing and attention, with potential applications in neuro-steered hearing devices. [ABSTRACT FROM AUTHOR]

Current research often formalizes traffic prediction tasks as spatio-temporal graph modeling problems. Despite some progress, this approach still has the following limitations. First, space can be divided into intrinsic and latent spaces. Static graphs in intrinsic space lack flexibility when facing changing prediction tasks, while dynamic relationships in latent space are influenced by multiple factors. A deep understanding of specific traffic patterns in different spaces is crucial for accurately modeling spatial dependencies. Second, most studies focus on correlations in sequential time periods, neglecting both reverse and global temporal correlations. This oversight leads to incomplete temporal representations in models. In this work, we propose a Space-Specific Graph Convolutional Recurrent Transformer Network (SSGCRTN) to address these limitations simultaneously. For the spatial aspect, we propose a space-specific graph convolution operation to identify patterns unique to each space. For the temporal aspect, we introduce a spatio-temporal interaction module that integrates spatial and temporal domain knowledge of nodes at multiple granularities. This module learns and utilizes parallel spatio-temporal relationships between different time points from both forward and backward perspectives, revealing latent patterns in spatio-temporal associations. Additionally, we use a transformer-based global temporal fusion module to capture global spatio-temporal correlations. We conduct experiments on four real-world traffic flow datasets (PeMS03/04/07/08) and two traffic speed datasets (PeMSD7(M)/(L)), achieving better performance than existing technologies. Notably, on the PeMS08 dataset, our model improves the MAE by 6.41% compared to DGCRN. The code of SSGCRTN is available at https://github.com/OvOYu/SSGCRTN. [ABSTRACT FROM AUTHOR]

Acupuncture therapy, rooted in traditional Chinese medicine (TCM), plays a pivotal role in both disease treatment and preventive health care. A significant challenge within this realm is precise acupoint recommendations tailored to specific symptoms, with consideration of the intricate inherent relationships between the symptoms and acupoints. Traditional recommendation methods encounter another difficulty in grappling with the sparse nature of TCM data. To address these issues, we present a novel approach called the enhanced graph convolutional network with property fusion (PEGCN), which consists of two key components, the property feature graph encoder module and the enhanced graph convolutional network module. The former extracts property knowledge of acupoints to enrich their representations. The latter integrates the GCN structure and an attention mechanism to efficiently capture the underlying relationships between symptoms and acupoints. In this paper, we apply the PEGCN model to a real-world dataset related to acupuncture therapy, and the experimental results demonstrate its superiority over the baseline models in terms of the evaluation metrics, which include Precision@K, Recall@K, and NDCG@K. This finding suggests that our model effectively addresses the challenges associated with acupoint recommendations, offering an improved method for personalized treatments in the TCM context. [ABSTRACT FROM AUTHOR]

With the development and acceleration of urbanization, urban metro traffic is gradually growing up to a large network, and the structure of topology between stations becomes more complex, which makes it increasingly difficult to capture the spatial dependency. The vertical and horizontal interlacing of multiple lines makes the stations distributed topologically, and the traditional graph convolution is implemented on the adjacency matrix generated based on a priori knowledge, which cannot reflect the actual spatial dependence between stations. To address these problems, this paper proposes an adaptive graph convolutional network model (Adapt-GCN), which replaces the fixed adjacency matrix obtained from a priori knowledge in the traditional GCN with a trainable adaptive adjacency matrix. This can not only effectively adjust the weights of correlations between adjacent stations, but also adaptively capture the spatial dependencies between non-adjacent stations. This paper uses the Shanghai Metro dataset to verify the effectiveness of the model in improving prediction accuracy and reducing training time. [ABSTRACT FROM AUTHOR]

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people's needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography. [ABSTRACT FROM AUTHOR]

The article focuses on the Cluster-based Graph Collaborative Filtering (ClusterGCF), a novel recommendation model designed to enhance representation learning by addressing the challenges of high-order neighboring nodes and user interests. Topics include the introduction of a soft node clustering method that groups users and items, the construction of cluster-specific graphs to filter out noise and capture information and ClusterGCF's state-of-the-art performance across multiple datasets.

Graph convolutional networks are capable of handling non-Euclidean data with sparse features, and some research has begun to apply them to the field of recommendation systems. Graph convolutional network's aggregation and propagation mechanism can learn features well and improve the embedding quality. However, simply applying GCN to the recommendation domain can only show some of its advantages, and the complex structure makes it difficult for the model to handle the massive amount of data in the industrial domain. Some work has been done to integrate GCN with recommendation systems better. However, most related work pursues the model's simplicity and ignores the large amount of hidden auxiliary information. In this paper, we propose a GCN-SA model, which adds a multi-head self-attention mechanism to the aggregation and propagation process to learn the weights of neighboring nodes and analyze the importance of the relationships between nodes; we also design a new embedding splicing layer for the graph convolutional network, which dynamically adjusts the embedding of different layers to achieve adaptive layer smoothing and mitigate the over-smoothing phenomenon. After experimental results on five benchmark datasets, we show that the GCN-SA model outperforms previous related work, captures a large amount of auxiliary information, and enhances the expressive ability of the model. [ABSTRACT FROM AUTHOR]

Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. Autoregressive models, including recurrent neural networks (RNNs) and their variants, as well as transformer networks, are commonly used for addressing this challenge. However, autoregressive models have several serious drawbacks, such as vanishing or exploding gradients. Other researchers have attempted to solve the communication problem in the spatial dimension by integrating graph convolutional networks (GCNs) and long short-term memory (LSTM) or convolutional neural network (CNN) models. These approaches process temporal and spatial information separately and fuse them to extract features, whereas this sequential processing hampers the model's ability to capture spatiotemporal information and perform feature extraction simultaneously. To address this in human pose forecasting, we propose a novel approach called the multi-graph convolution network (MGCN). By introducing an augmented graph for pose sequences, our model captures spatial and temporal information in one step only using GCN. Multiple frames provide multiple parts, which are joined together in a unified graph instance. Furthermore, our model investigates the impact of natural structure and sequence-aware attention. In the experimental evaluation of the large-scale benchmark datasets (Human3.6M, AMSS, and 3DPW), MGCN outperforms the state-of-the-art methods in human pose prediction. [ABSTRACT FROM AUTHOR]

Temporal knowledge graphs (TKGs) are a form of knowledge representation constructed based on the evolution of events at different time points. It provides an additional perspective by extending the temporal dimension for a range of downstream tasks. Given the evolving nature of events, it is essential for TKGs to reason about non-existent or future events. Most of the existing models divide the graph into multiple time snapshots and predict future events by modeling information within and between snapshots. However, since the knowledge graph inherently suffers from missing data and uneven data distribution, this time-based division leads to a drastic reduction in available data within each snapshot, which makes it difficult to learn high-quality representations of entities and relationships. In addition, the contribution of historical information changes over time, distinguishing its importance to the final results when capturing information that evolves over time. In this paper, we introduce CH-TKG (Contrastive Learning and Historical Information Learning for TKG Reasoning) to addresses issues related to data sparseness and the ambiguity of historical information weights. Firstly, we obtain embedding representations of entities and relationships with evolutionary dependencies by R-GCN and GRU. On this foundation, we introduce a novel contrastive learning method to optimize the representation of entities and relationships within individual snapshots of sparse data. Then we utilize self-attention and copy mechanisms to learn the effects of different historical data on the final inference results. We conduct extensive experiments on four datasets, and the experimental results demonstrate the effectiveness of our proposed model with sparse data. [ABSTRACT FROM AUTHOR]

Traffic flow prediction plays a crucial role in the development of smart cities. However, existing studies face challenges in effectively capturing spatio-temporal contexts, handling hierarchical temporal features, and understanding spatial heterogeneity. To better manage the spatio-temporal correlations inherent in traffic flow, we present a novel model called Dynamic Spatio-Temporal Memory-Augmented Network (DSTMAN). Firstly, we design three spatial–temporal embeddings to capture dynamic spatial–temporal contexts and encode the unique characteristics of time units and spatial states. Secondly, these three spatial–temporal components are integrated to form a multi-scale spatial–temporal block, which effectively extracts hierarchical spatial–temporal dependencies. Finally, we introduce a meta-memory node bank to construct an adaptive neighborhood graph, implicitly representing spatial relationships and enhancing the learning of spatial heterogeneity through a secondary memory mechanism. Evaluation on four public datasets, including METR-LA and PEMS-BAY, demonstrates that the proposed model outperforms benchmark models such as MTGNN, DCRNN, and AGCRN. On the METR-LA dataset, our model reduces the MAE by 4% compared to MTGNN, 6.9% compared to DCRNN, and 5.8% compared to AGCRN, confirming its efficacy in traffic flow prediction. [ABSTRACT FROM AUTHOR]

Accurate and efficient congested link identification is crucial in wireless sensor networks (WSNs). However, in some networks with a centralized management architecture, it is often not feasible to monitor large numbers of internal links directly or even impossible in some heterogeneous networks. Network tomography, the science of inferring the performance characteristics of a network's interior by correlating sets of end-to-end measurements, was put forward to solve this problem. Nevertheless, a network always contains more links than end-to-end paths, making it problematic to find a determined solution. To solve this problem, most of the current methods try to use some additional prerequisites, such as the link congestion probability. However, most existing studies have not considered the congestion caused by node factors and the case of multiple congested links on one path. In this paper, we initially model the issue of link congestion as a Bayesian network model (BNM). Subsequently, we introduce a congestion link identification method based on graph convolutional networks (GCNs), novelly converting the intricate Bayesian network solving problem into a graph node classification task. The simulation results validate the feasibility of our proposed algorithm in identifying congested links and underscore its advantages in scenarios involving node congestion and multiple congested links. [ABSTRACT FROM AUTHOR]

Graph convolutional network (GCN) is a deep learning model for processing graph data. In the classic GCN, the aggregation between nodes does not consider the feature information of similarity between nodes, which affects the model accuracy and training convergence speed for the classification model. This paper proposes a graph convolutional neural network IAW-GCN, via improved aggregation weights. The node aggregation weight function is designed by utilizing the Manhattan distance metric that describes the node similarity, and the GCN model is improved by the node distance metric matrix. The feature matrix can adjust the node aggregation weight according to similarity during the message passing aggregation process in the model. Experimental results show that under the conditions of Cora, Citeseer and Pubmed standard citation data sets, the improved model has better classification accuracy and model performance in semi-supervised classification tasks. Particularly, the training convergence speed is better than the classic GCN model. This paper provids a new method for solving semi-supervised classification problems. [ABSTRACT FROM AUTHOR]

The logistics demands of industries represented by e-commerce have experienced explosive growth in recent years. Vehicle path-planning plays a crucial role in optimization systems for logistics and distribution. A path-planning scheme suitable for an actual scenario is the key to reducing costs and improving service efficiency in logistics industries. In complex application scenarios, however, it is difficult for conventional heuristic algorithms to ensure the quality of solutions for vehicle routing problems. This study proposes a joint approach based on the genetic algorithm and graph convolutional network for solving the capacitated vehicle routing problem with multiple distribution centers. First, we use the heuristic method to modularize the complex environment and encode each module based on the constraint conditions. Next, the graph convolutional network is adopted for feature embedding for the graph representation of the vehicle routing problem, and multiple decoders are used to increase the diversity of the solution space. Meanwhile, the REINFORCE algorithm with a baseline is employed to train the model, ensuring quick returns of high-quality solutions. Moreover, the fitness function is calculated based on the solution to each module, and the genetic algorithm is employed to seek the optimal solution on a global scale. Finally, the effectiveness of the proposed framework is validated through experiments at different scales and comparisons with other algorithms. The experimental results show that, compared to the single decoder GCN-based solving method, the method proposed in this paper improves the solving success rate to 100% across 15 generated instances. The average path length obtained is only 11% of the optimal solution produced by the GCN-based multi-decoder method. [ABSTRACT FROM AUTHOR]

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalanced number between the target and the background spatially and the high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation-learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and spatial–spectral features to improve its representation ability. Firstly, a Graph Convolutional Network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene's underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing the detection and background suppression capabilities. The performance of the proposed approach is evaluated using the average scores of AU C D , F , AU C F , τ , AU C BS , and AU C SNPR . The corresponding values are 0.99660, 0.00078, 0.99587, and 333.629, respectively. These results demonstrate the accuracy of the model in different evaluation metrics, with AU C D , F achieving the highest score, indicating strong detection performance across varying thresholds. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture. [ABSTRACT FROM AUTHOR]

Skeleton-based human interaction recognition is a formidable challenge that demands the capability to discern spatial, temporal, and interactive features. However, current research still faces some limitations in identifying spatial, temporal, and interaction features. Methods based on graph convolutional networks often prove to be insufficient in capturing interactive features and structural semantic information of skeletons. In order to solve this problem, we construct a Mutual-semantic Adjacency Matrix (MAM) by amalgamating the relative semantic attention of two skeleton sequences. This MAM was then integrated with the convolution of residual graphs to enhance the extraction of spatial and interaction features. We propose a novel interactive semantics neural network (ISNN) for skeleton-based human interaction recognition to hierarchically fuse MAM and structural semantic information. In addition, integrating the bone stream, we propose a two-stream Interactive Semantics Neural Network (2 s-ISNN). Experiments conducted with our models on two interaction datasets, NTU-RGB+D (mutual) and NTU-RGB+D 120 (mutual), demonstrate significantly improved recognition capabilities in comprehending human interactions. The source code is available at: https://github.com/czant1977/ISNN-master//. [ABSTRACT FROM AUTHOR]

Shadow detection is essential for scene understanding and image restoration. Existing paradigms for producing shadow detection training data usually rely on densely labeling each image pixel, which will lead to a bottleneck when scaling up the number of images. To tackle this problem, by labeling shadow images with only a few strokes, this paper designs a learning framework for Weakly supervised Shadow Detection, namely WSD. Firstly, it creates two shadow detection datasets with scribble annotations, namely Scr-SBU and Scr-ISTD. Secondly, it proposes an uncertainty-guided label augmentation scheme based on graph convolutional networks, which can propagate the sparse scribble annotations to more reliable regions, and then avoid the model converging to an undesired local minima as intra-class discontinuity. Finally, it introduces a multi-task learning framework to jointly learn for shadow detection and edge detection, which encourages generated shadow maps to be comprehensive and well aligned with shadow boundaries. Experimental results on benchmark datasets demonstrate that our framework even outperforms existing semi-supervised and fully supervised shadow detectors requiring only 2% pixels to be labeled. [ABSTRACT FROM AUTHOR]

As the era of big data develops rapidly, cross-modal retrieval is a research field that has received widespread attention. Most current methods of cross-modal retrieval just pursue the macro alignment of modal data in a shared space to gain a common representation. However, they cannot achieve the satisfactory performance of cross-modal retrieval since they neglect the deep semantic alignment and the inherent differences between modalities. Being aware of these, this paper presents a dual graph-structured semantics multi-subspace learning (DGMS) method for cross-modal retrieval. Specifically in DGMS, the double semantics graph is established to represent the deep semantics of modal data, and the multiple subspace learning network constructs public and independent subspaces to capture the relevance and dissimilarity of modal data. Finally, a dual learning method based on the generative adversarial network is employed further to catch the joint probability distribution of the different modalities. The superiority of DGMS is demonstrated by experiments on Wikipedia, XMedia, and Pascal Sentence, for it can not only learn deep structural semantics but also explore the consistency and diversity of modalities. [ABSTRACT FROM AUTHOR]

To improve site safety status, the construction safety literature has investigated machine learning (ML) prediction models with a particular emphasis on their prediction accuracy. This study shifts its focus on reliability of a construction safety model beyond their prediction accuracy by increasing its representativeness. A novel dual-edge construction safety network was synthesized that considers the mutual contribution of behaviors (human factors) and the physical environment (workplace factors). A graph convolutional network (GCN) was created to learn the high-level information of the dual-edge network to predict the severity outcome of construction accidents. The dual-edge GCN model was tested on a comprehensive construction safety dataset collected from 73 projects that resulted in an 85.67% prediction accuracy while leveraging shared human and workplace factors in predicting construction accident outcomes. The incorporated dual-edge safety network offers more representative and explainable accident visualization that enables prioritizing related safety interventions and developing tailored prevention strategies based on two different decision objectives. Compared with other ML approaches, the proposed construction safety model emphasizes both human and workplace factors without trading off its prediction accuracy, thereby increasing the reliability of the prediction outcome for integration in relevant safety decisions. The transparency of the input network and its accident visualization enable practitioners to develop tailored prevention strategies while increasing trust in accident prediction outcomes. [ABSTRACT FROM AUTHOR]

Intelligent medical systems have great potential to play an important role in people's daily lives, as they can provide disease and medicine information immediately for both doctors and patients. Graph-structured data are attracting more and more attention in the artificial intelligence sector. Combining graph-structured data with a medical data set, a tripartite graph convolutional network named TriGCN is proposed. This model is able connect to disease and medicine or patient, disease, and medicine nodes, propagate information from layer to layer, and update node features at the same time. After this, calibrated label ranking is used to give personalized medicine recommendation lists to patients. The TriGCN approach has a great performance, outperforming other machine learning methods. Thus, this model has the potential to be applied in reality and will provide contributions to public health in the future. [ABSTRACT FROM AUTHOR]

Efficient operation of urban metro systems depends on accurate passenger flow predictions, a task complicated by intricate spatiotemporal correlations. This paper introduces a novel spatiotemporal graph neural network (STGNN) designed explicitly for predicting multistep passenger flow within metro stations. In the spatial dimension, previous research primarily focuses on local spatial dependencies, struggling to capture implicit global information. We propose a spatial modeling module that leverages a dynamic global attention network (DGAN) to capture dynamic global information from all-pair interactions, intricately fusing prior knowledge from the input graph with a graph convolutional network. In the temporal dimension, we design a temporal modeling module tailored to navigate the challenges of both long-term and recent-term temporal passenger flow patterns. This module consists of series decomposition blocks and locality-aware sparse attention (LSA) blocks to incorporate multiple local contexts and reduce computational complexities in long sequence modeling. Experiments conducted on both simulated and real-world datasets validate the exceptional predictive performance of our proposed model. [ABSTRACT FROM AUTHOR]

Dynamic gesture recognition based on skeletal data has garnered significant attention with the rise of graph convolutional networks (GCNs). Existing methods typically calculate dependencies between joints and utilize spatio-temporal attention features. However, they often rely on joint topological features of limited spatial extent and short-time features, making it challenging to extract intra-frame spatial features and long-term inter-frame temporal features. To address this, we propose a new GCN architecture for dynamic hand gesture recognition, called a spatio-temporal dynamic attention graph convolutional network (STDA-GCN). This model employs dynamic attention spatial graph convolution, enhancing spatial feature extraction capabilities while reducing computational complexity through improved cross-channel information interaction. Additionally, a salient location channel attention mechanism is integrated between spatio-temporal convolutions to extract useful spatial features and avoid redundancy. Finally, dynamic multi-scale temporal convolution is used to extract richer inter-frame gesture features, effectively capturing information across various time scales. Evaluations on the SHREC'17 Track and DHG-14/28 benchmark datasets show that our model achieves 97.14% and 95.84% accuracy, respectively. These results demonstrate the superior performance of STDA-GCN in dynamic gesture recognition tasks. [ABSTRACT FROM AUTHOR]

Inferring gene regulatory networks through deep learning and causal inference methods is a crucial task in the field of computational biology and bioinformatics. This study presents a novel approach that uses a Graph Convolutional Network (GCN) guided by causal information to infer Gene Regulatory Networks (GRN). The transfer entropy and reconstruction layer are utilized to achieve causal feature reconstruction, mitigating the information loss problem caused by multiple rounds of neighbor aggregation in GCN, resulting in a causal and integrated representation of node features. Separable features are extracted from gene expression data by the Gaussian-kernel Autoencoder to improve computational efficiency. Experimental results on the DREAM5 and the mDC dataset demonstrate that our method exhibits superior performance compared to existing algorithms, as indicated by the higher values of the AUPRC metrics. Furthermore, the incorporation of causal feature reconstruction enhances the inferred GRN, rendering them more reasonable, accurate, and reliable. [ABSTRACT FROM AUTHOR]

The prediction of bike-sharing demand plays a pivotal role in the optimization of intelligent transportation systems, particularly amidst the COVID-19 pandemic, which has significantly altered travel behaviors and demand dynamics. In this study, we examine various spatiotemporal influencing factors associated with bike-sharing and propose the Local-Global Dynamic Multi-Graph Convolutional Network (LGDMGCN) model, driven by multi-source data, for multi-step prediction of station-level bike-sharing demand. In the temporal dimension, we dynamically model temporal dependencies by incorporating multiple sources of time semantic features such as confirmed COVID-19 cases, weather conditions, and holidays. Additionally, we integrate a time attention mechanism to better capture variations over time. In the spatial dimension, we consider factors related to the addition or removal of stations and utilize spatial semantic features, such as urban points of interest and station locations, to construct dynamic multi-graphs. The model utilizes a local-global structure to capture spatial dependencies among individual bike-sharing stations and all stations collectively. Experimental results, obtained through comparisons with baseline models on the same dataset and conducting ablation studies, demonstrate the feasibility and effectiveness of the proposed model in predicting bike-sharing demand. [ABSTRACT FROM AUTHOR]

Turnover numbers (k cat), which indicate an enzyme's catalytic efficiency, have a wide range of applications in fields including protein engineering and synthetic biology. Experimentally measuring the enzymes' k cat is always time-consuming. Recently, the prediction of k cat using deep learning models has mitigated this problem. However, the accuracy and robustness in k cat prediction still needs to be improved significantly, particularly when dealing with enzymes with low sequence similarity compared to those within the training dataset. Herein, we present DeepEnzyme, a cutting-edge deep learning model that combines the most recent Transformer and Graph Convolutional Network (GCN) to capture the information of both the sequence and 3D-structure of a protein. To improve the prediction accuracy, DeepEnzyme was trained by leveraging the integrated features from both sequences and 3D-structures. Consequently, DeepEnzyme exhibits remarkable robustness when processing enzymes with low sequence similarity compared to those in the training dataset by utilizing additional features from high-quality protein 3D-structures. DeepEnzyme also makes it possible to evaluate how point mutations affect the catalytic activity of the enzyme, which helps identify residue sites that are crucial for the catalytic function. In summary, DeepEnzyme represents a pioneering effort in predicting enzymes' k cat values with improved accuracy and robustness compared to previous algorithms. This advancement will significantly contribute to our comprehension of enzyme function and its evolutionary patterns across species. [ABSTRACT FROM AUTHOR]

The annotation of enzyme function is a fundamental challenge in industrial biotechnology and pathologies. Numerous computational methods have been proposed to predict enzyme function by annotating enzyme labels with Enzyme Commission number. However, the existing methods face difficulties in modelling the hierarchical structure of enzyme label in a global view. Moreover, they haven't gone entirely to leverage the mutual interactions between different levels of enzyme label. In this paper, we formulate the hierarchy of enzyme label as a directed enzyme graph and propose a hierarchy-GCN (Graph Convolutional Network) encoder to globally model enzyme label dependency on the enzyme graph. Based on the enzyme hierarchy encoder, we develop an end-to-end hierarchical-aware global model named GloEC to predict enzyme function. GloEC learns hierarchical-aware enzyme label embeddings via the hierarchy-GCN encoder and conducts deductive fusion of label-aware enzyme features to predict enzyme labels. Meanwhile, our hierarchy-GCN encoder is designed to bidirectionally compute to investigate the enzyme label correlation information in both bottom-up and top-down manners, which has not been explored in enzyme function prediction. Comparative experiments on three benchmark datasets show that GloEC achieves better predictive performance as compared to the existing methods. The case studies also demonstrate that GloEC is capable of effectively predicting the function of isoenzyme. GloEC is available at: https://github.com/hyr0771/GloEC. [ABSTRACT FROM AUTHOR]

The increasingly widespread use of new power equipment has brought new disturbances to the power system and has placed increasing demands on power quality. In order to make full use of the power quality indicators in the national standards and to make a more comprehensive and integrated evaluation of power quality, this study proposes a power quality evaluation method based on graph convolutional network. A power quality assessment system with graded indicators is proposed according to the current national standards. The correlation between the various power quality assessment indicators is initially determined, and on this basis the indicator relationship diagram is determined, a graph neural network model is built and trained, and the error rate of the test set is 9.02%. A comparison and analysis with other assessment methods using actual measurement data of a power system proves that the proposed method is more effective in assessing power quality over a long time span. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of cyber-attack detection in a discrete event system by proposing a novel model. The model utilizes graph convolutional networks to extract spatial features from event sequences. Subsequently, it employs gated recurrent units to re-extract spatio-temporal features from these spatial features. The obtained spatio-temporal features are then fed into an attention model. This approach enables the model to learn the importance of different event sequences, ensuring that it is sufficiently general for identifying cyber-attacks, obviating the need to specify attack types. Compared with traditional methods that rely on synchronous product computations to synthesize diagnosers, our deep learning-based model circumvents state explosion problems. Our method facilitates real-time and efficient cyber-attack detection, eliminating the necessity to specifically identify system states or distinguish attack types, thereby significantly simplifying the diagnostic process. Additionally, we set an adjustable probability threshold to determine whether an event sequence has been compromised, allowing for customization to meet diverse requirements. Experimental results demonstrate that the proposed method performs well in cyber-attack detection, achieving over 99.9 % accuracy at a 1 % threshold and a weighted F1-score of 0.8126, validating its superior performance. [ABSTRACT FROM AUTHOR]

Rotating machinery is widely used in modern industrial systems, and its health status can directly impact the operation of the entire system. Timely and accurate diagnosis of rotating machinery faults is crucial for ensuring production safety, reducing economic losses, and improving efficiency. Traditional deep learning methods can only extract features from the vertices of the input data, thereby overlooking the information contained in the relationships between vertices. This paper proposes a Legendre graph convolutional network (LGCN) integrated with a self-attention graph pooling method, which is applied to fault diagnosis of rotating machinery. The SA-LGCN model converts vibration signals from Euclidean space into graph signals in non-Euclidean space, employing a fast local spectral filter based on Legendre polynomials and a self-attention graph pooling method, significantly improving the model's stability and computational efficiency. By applying the proposed method to 10 different planetary gearbox fault tasks, we verify that it offers significant advantages in fault diagnosis accuracy and load adaptability under various working conditions. [ABSTRACT FROM AUTHOR]

The task of fraud detection in blockchain requires a thorough exploration of the inherent temporal and spatial characteristics in historical transaction data. Existing fraud detection methods suffer from large prediction errors. To address this issue, this paper proposed a blockchain fraud detection method, named RGCN-SRG, based on reinforced graph convolutional network (RGCN) and spatiotemporal recurrent gate (SRG). Firstly, leveraging Bitcoin's historical transaction data for the construction of the transaction graph, the method used a reinforced graph convolutional network with different kernel sizes to comprehensively extract the graph's topology information and generate feature vectors. Additionally, considering the temporal characteristics of blockchain transactions, the method introduced a spatiotemporal recurrent gate structure that incorporated graph convolutional operations into the traditional gate structure to extract dependency information from multiple spatiotemporal dimensions of the transaction graph. Finally, it obtained the prediction results of money laundering detection through a linear layer and activation function. The proposed fraud detection method was evaluated by the constructed dataset. Compared with GCN, DEDGAT, EGT and GCN + MLP F, by the proposed method improves 18.4, 10.7, 9.2 and 4.9 percentage points, respectively; the precision improves 11.5, 11.2, 7.7 and 3.7 percentage points, respectively. [ABSTRACT FROM AUTHOR]

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM–miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM–miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM–miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs. [ABSTRACT FROM AUTHOR]

The absence of clinically-validated biomarkers or objective protocols hinders effective major depressive disorder (MDD) diagnosis. Compared to healthy control (HC), MDD exhibits anomalies in plasma protein levels and neuroimaging presentations. Despite extensive machine learning studies in psychiatric diagnosis, a reliable tool integrating multi-modality data is still lacking. In this study, blood samples from 100 MDD and 100 HC were analyzed, along with MRI images from 46 MDD and 49 HC. Here, we devised a novel algorithm, integrating graph neural networks and attention modules, for MDD diagnosis based on inflammatory cytokines, neurotrophic factors, and Orexin A levels in the blood samples. Model performance was assessed via accuracy and F1 value in 3-fold cross-validation, comparing with 9 traditional algorithms. We then applied our algorithm to a dataset containing both the aforementioned protein quantifications and neuroimages, evaluating if integrating neuroimages into the model improves performance. Compared to HC, MDD showed significant alterations in plasma protein levels and gray matter volume revealed by MRI. Our new algorithm exhibited superior performance, achieving an F1 value and accuracy of 0.9436 and 94.08 %, respectively. Integration of neuroimaging data enhanced our novel algorithm's performance, resulting in an improved F1 value and accuracy, reaching 0.9543 and 95.06 %. This single-center study with a small sample size requires future evaluations on a larger test set for improved reliability. In comparison to traditional machine learning models, our newly developed MDD diagnostic model exhibited superior performance and showed promising potential for inclusion in routine clinical diagnosis for MDD. • Significant changes observed in the levels of various plasma proteins and neuroimaging alterations in MDD. • Altered indicators of protein levels and neuroimaging are correlated with clinical features. • Pioneered the development of a novel algorithm integrating graph neural networks and attention modules. [ABSTRACT FROM AUTHOR]

Human motion prediction in various motion capture applications, e.g., optical and inertial, is challenging because of the complexity of human motion sequences. Current studies on this issue have insufficient analysis on the latent motion information in a given motion sequence, such as motion trends, transient changes, and temporal evolution. Meanwhile, methods using simple graph convolution networks suffer from over-smoothing, causing the predicted poses staying invariant in long-term prediction. To address these challenges, we propose a multi-feature-based orthogonal graph convolution network (MFOGCN), where the multi-feature extraction consists of two key modules: (1) hybrid spectral transform, which captures local transient features and global motion trends of motion sequences by discrete wavelet transform while considering temporal smoothing between human joints and (2) mask-aware multiple attention, with sliding time windows to extract motion sequence feature representations from historical multiple subsequences, refining the correlation between adjacent poses while obtaining global dependencies between sequences. In addition, we propose orthogonal graph convolution and orthogonal loss for the prediction network, which help to stabilize the feature transformation of the graph convolution to resolve the over-smoothing issue. An extensive evaluation on the Human 3.6M, AMASS and 3DPW datasets has been conducted, showing reliable effectiveness of the proposed MFOGCN that outperforms other approaches. [ABSTRACT FROM AUTHOR]

Identifying miRNA-disease associations (MDAs) is crucial for improving the diagnosis and treatment of various diseases. However, biological experiments can be time-consuming and expensive. To overcome these challenges, computational approaches have been developed, with Graph Convolutional Network (GCN) showing promising results in MDA prediction. The success of GCN-based methods relies on learning a meaningful spatial operator to extract effective node feature representations. To enhance the inference of MDAs, we propose a novel method called PGCNMDA, which employs graph convolutional networks with a learning graph spatial operator from paths. This approach enables the generation of meaningful spatial convolutions from paths in GCN, leading to improved prediction performance. On HMDD v2.0, PGCNMDA obtains a mean AUC of 0.9229 and an AUPRC of 0.9206 under 5-fold cross-validation (5-CV), and a mean AUC of 0.9235 and an AUPRC of 0.9212 under 10-fold cross-validation (10-CV), respectively. Additionally, the AUC of PGCNMDA also reaches 0.9238 under global leave-one-out cross-validation (GLOOCV). On HMDD v3.2, PGCNMDA obtains a mean AUC of 0.9413 and an AUPRC of 0.9417 under 5-CV, and a mean AUC of 0.9419 and an AUPRC of 0.9425 under 10-CV, respectively. Furthermore, the AUC of PGCNMDA also reaches 0.9415 under GLOOCV. The results show that PGCNMDA is superior to other compared methods. In addition, the case studies on pancreatic neoplasms, thyroid neoplasms and leukemia show that 50, 50 and 48 of the top 50 predicted miRNAs linked to these diseases are confirmed, respectively. It further validates the effectiveness and feasibility of PGCNMDA in practical applications. • PGCNMDA employs GCN with path learning to infer miRNA-disease associations. • PGCNMDA obtains the representations from similarity and association networks, respectively. • PGCNMDA performs well in all comparative experiments and case studies. [ABSTRACT FROM AUTHOR]

Aspect-based sentiment analysis (ABSA) aims to analyze the emotional color contained in sentences or documents in more detail by classifying and evaluating different aspects and emotions in the text. However, the current research methods cannot effectively analyze the relationship between aspect words and context and extract grammatical information about sentences. Additionally, the extracted syntactic information is insufficient, and the combination of syntactic and semantic information is inefficient, leaving the model unable to correctly determine aspects' emotional orientations. This paper proposes an aspect-level sentiment analysis based on Fusion Graph Double Convolutional Neural Networks (FGD-GCN) to address these issues. Firstly, FGD-GCN proposes a multi-feature extraction module. Using BERT and bidirectional long-short-term memory models, this module extracts the hidden context between words. In addition, the positional attention module is used to capture important features in sentences, reducing noise and bias. Then, a semantic enhancement module is proposed, which fuses attention-focused information and feature information extracted from graphs to emphasize aspect words and context, and uses CNN model to classify on feature vectors. According to experiment results on three benchmark datasets, the model outperforms previous GCN methods for context-based aspect-level sentiment analysis. [ABSTRACT FROM AUTHOR]

Stock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn more stable profits. However, these dependencies are not directly observable and need to be analyzed from stock data. In this paper, we propose a model based on Long short-term memory (LSTM) and graph convolutional network to capture these dependencies for stock trend prediction. Specifically, an LSTM is employed to extract the stock features, with all hidden state outputs utilized to construct the graph nodes. Subsequently, Pearson correlation coefficient is used to organize the stock features into a graph structure. Finally, a graph convolutional network is applied to extract the relevant features for accurate stock trend prediction. Experiments based on China A50 stocks demonstrate that our proposed model outperforms baseline methods in terms of prediction performance and trading backtest returns. In trading backtest, we have identified a set of effective trading strategies as part of the trading plan. Based on China A50 stocks, our proposed model shows promising results in generating desirable returns during both upward and downward channels of the stock market. The proposed model has proven beneficial for investors to seeking optimal timing and pricing when dealing with shares. [ABSTRACT FROM AUTHOR]

Chinese long text classification plays a vital role in Natural Language Processing. Compared to Chinese short texts, Chinese long texts contain more complex semantic feature information. Furthermore, the distribution of these semantic features is uneven due to the varying lengths of the texts. Current research on Chinese long text classification models primarily focuses on enhancing text semantic features and representing Chinese long texts as graph-structured data. Nonetheless, these methods are still susceptible to noise information and tend to overlook the deep semantic information in long texts. To address the above challenges, this study proposes a novel and effective method called MACFM, which introduces a deep feature information mining method and an adaptive modal feature information fusion strategy to learn the semantic features of Chinese long texts thoroughly. First, we present the DCAM module to capture complex semantic features in Chinese long texts, allowing the model to learn detailed high-level representation features. Then, we explore the relationships between word vectors and text graphs, enabling the model to capture abundant semantic information and text positional information from the graph. Finally, we develop the AMFM module to effectively combine different modal feature representations and eliminate the unrelated noise information. The experimental results on five Chinese long text datasets show that our method significantly improves the accuracy of Chinese long text classification tasks. Furthermore, the generalization experiments on five English datasets and the visualized results demonstrate the effectiveness and interpretability of the MACFM model. [ABSTRACT FROM AUTHOR]

Temporal sentence grounding in videos (TSGV) aims to retrieve video segments from untrimmed videos that semantically matched a given query. Although existing methods have made significant progress in fine-grained intra- and inter-modal representations, they failed to comprehensively consider the redundancy of the entire video relative to the target segment and the fact that interactions could obscure crucial intra-modal information, which leads to the degradation of model performance. In this paper, we proposed a novel Parameterized Multi-Perspective Graph Learning Network for Temporal Sentence Grounding in Videos. Specifically, to effectively handle redundant information in video graphs, the concept of a parameterized network is introduced to dynamically construct new video graphs. Parameterizing the graph structure, making it adaptable to various video scenes while suppressing unnecessary redundant information. Furthermore, we designed a dual-path attention gating module that delves into cross-modal relationships while fully considering intra-modal information. The mechanism simultaneously considers the association between video and query from both inter- and intra-modal perspectives. This method allowed the model to better balance the local and global semantic consistency, further enhancing its representation capability for multimodal data. Extensive experiments on the ActivityNet Captions and Tacos benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The Graph Attention Network (GAT) is a type of graph neural network (GNN) that uses attention mechanisms to weigh the importance of nodes' neighbors, demonstrating flexibility and power in representation learning. However, GAT and its variants still face common challenges in GNNs, such as over-smoothing and over-squashing. To address this, we propose Multi-Head Multi-Order Graph Attention Networks (MHMOGAT) as an enhanced GAT layer. MHMOGAT is built based on multi-head attention and adjacency matrices of different orders, aiming to expand the receptive field of GAT to effectively capture long-distance dependencies. Moreover, Bayesian optimization is employed to determine optimal hyperparameter combinations for different datasets. Experimental results on six prevailing datasets demonstrate that MHMOGAT improves GAT accuracy by approximately 2-5% across various datasets with different label rates, indicating its effectiveness. Additionally, MHMOGAT exhibits potential in handling large and complex graphs with low label rates. [ABSTRACT FROM AUTHOR]

Molecular property prediction is an important step in the drug discovery pipeline. Numerous computational methods have been developed to predict a wide range of molecular properties. While recent approaches have shown promising results, no single architecture can comprehensively address all tasks, making this area persistently challenging and requiring substantial time and effort. Beyond traditional machine learning and deep learning architectures for regular data, several deep learning architectures have been designed for graph-structured data to overcome the limitations of conventional methods. Utilizing graph-structured data in quantitative structure–activity relationship (QSAR) modeling allows models to effectively extract unique features, especially where connectivity information is crucial. In our study, we developed residual graph attention networks (ResGAT), a deep learning architecture for molecular graph-structured data. This architecture is a combination of graph attention networks and shortcut connections to address both regression and classification problems. It is also customizable to adapt to various dataset sizes, enhancing the learning process based on molecular patterns. When tested multiple times with both random and scaffold sampling strategies on nine benchmark molecular datasets, QSAR models developed using ResGAT demonstrated stability and competitive performance compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Despite the considerable advancements made in the field of 3D human pose estimation from single-view images, previous studies have often overlooked the exploration of global and local correlations. Recognizing this limitation, we present MGAPoseNet, a novel network architecture meticulously designed to elevate the accuracy of 3D pose estimation. Our approach is distinguished by its simultaneous extraction of both local and global features, achieved through the parallel integration of Local Graph-based Joint Connection (LGC) and Global Attention-based Body Constraint (GAC) modules. Moreover, the performance of MGAPoseNet is further elevated by the sequential Spatial-Channel Graph MLP-Like Architecture (SC-GraphMLP) module. This module adeptly leverages spatial and channel information to model intricate interactions and dependencies among joint features, thereby refining the accuracy of pose estimation. Experimental evaluation conducted on benchmark datasets, including Human3.6M and MPI-INF-3DHP, unequivocally verifies the state-of-the-art performance of MGAPoseNet. This rigorous validation underscores its superiority in 3D human pose estimation tasks, while enhancing its coherence and clarity. [ABSTRACT FROM AUTHOR]

Spatiotemporal axle temperature forecasting is crucial for real-time failure detection in locomotive control systems, significantly enhancing reliability and facilitating early maintenance. Motivated by the need for more accurate and reliable prediction models, this paper proposes a novel ensemble graph convolutional recurrent unit network. This innovative approach aims to develop a highly reliable and accurate spatiotemporal axle temperature forecasting model, thereby increasing locomotive safety and operational efficiency. The modeling structure involves three key steps: (1) the GCN module extracts and aggregates spatiotemporal temperature data and deep feature information from the raw data of different axles; (2) these features are fed into GRU and BiLSTM networks for modeling and forecasting; (3) the ICA algorithm optimizes the fusion weight coefficients to combine the forecasting results from GRU and BiLSTM, achieving superior outcomes. Comparative experiments demonstrate that the proposed model achieves RMSE values of 0.2517 °C, 0.2011 °C, and 0.2079 °C across three temperature series, respectively, indicating superior prediction accuracy and reduced errors compared to benchmark models in all experimental scenarios. The Wilcoxon signed-rank test further confirms the statistical significance of the result improvements with high confidence. [ABSTRACT FROM AUTHOR]

Truck cranes, which are crucial construction equipment, need to maintain good operational performance to ensure safe use. However, the complex and ever-changing working conditions they face often make it challenging to test their performance effectively. To address this issue, a multi-input and multi-output soft sensor technology model is suggested, utilizing a graph convolutional network and random forest to predict key performance indicators of crane operations such as luffing, telescoping, winching, and slewing under varying conditions. This method aims to streamline the process of testing and debugging truck cranes, ultimately reducing time and costs. Initially, the graph convolutional network model is employed to extract relevant feature information linked to the target variable. Subsequently, using this feature information and the RF model, multiple decision trees are constructed for regression prediction of the target variables. An operational dataset reflecting the crane's actual working conditions is then generated to assess the graph convolutional network and random forest model. The effectiveness of this approach is further confirmed through comparisons with other methods like gradient boosting trees, support vector regression, and multi-layer perceptron. [ABSTRACT FROM AUTHOR]

Despite great progress in enhancing the efficiency of public transport, one still cannot seamlessly incorporate structural characteristics into existing algorithms. Moreover, comprehensively exploring the structure of urban bus networks through a single-view modelling approach is limited. In this research, a multi-view graph learning algorithm (MvGL) is proposed to aggregate community information from multiple views of urban bus system. First, by developing a single-view graph encoder module, latent community relationships can be captured during learning node embeddings. Second, inspired by attention mechanism, a multi-view graph encoder module is designed to fuse node embeddings in different views, aims to perceive more community information of urban bus network comprehensively. Then, the community assignment can be updated by using a differentiable clustering layer. Finally, a well-defined objective function, which integrates node level, community level and graph level, can help improve the quality of community detection. Experimental results demonstrated that MvGL can effectively aggregate community information from different views and further improve the quality of community detection. This research contributes to the understanding the structural characteristics of public transport networks and facilitates their operational efficiency. [ABSTRACT FROM AUTHOR]

Multi-label image classification (MLIC) is a fundamental and highly challenging task in the field of computer vision. Most methods usually only focus on the inter-label association or the way to extract image semantics, ignoring the relevance of labels at multiple semantic levels. To this end, we propose a new approach for multi-label image classification. Our method consists of a class activation mapping (CAM) module for multi-level semantic extraction of images and a graph convolutional network (GCN) module for label relevance construction. The CAM module follows the sequence of human visual perception of objects and segments the global image into multiple local images with target objects. Afterward, the segmented images are fused into the global stream to obtain global to local semantic information. The GCN module combines the label word embedding matrix and the co-occurrence matrix to map a matrix with label dependencies. Finally, the image features and the classifier are combined to obtain the final classification result. Extensive experiments on two benchmark datasets, i.e., VOC2007 and MS-COCO, show that our approach achieves better results on several generic evaluation indicators compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Accurately predicting the molecular subtype of cancer patients is of great significance for personalized diagnosis and treatment of cancer. The progress of a large amount of multi-omics data and data-driven methods is expected to promote the molecular subtyping of cancer. Existing methods are limited by their ability to deal with high-dimensional data and the influence of misleading and unrelated factors, resulting in ambiguous and overlapping subtypes. This article proposes a method called Multi-Omics Subtypes of Digestive System Tumors (MSDST), which is used for subtype identification of digestive system tumors. The method learns a new representation of the relationship between samples from multi-omics data, and uses a self-encoding model composed of omics-specific graph convolutional networks to learn the high-level representation of each omics data feature while considering the prognosis prediction results. Finally, k-means algorithm is used to cluster samples for analysis. Compared with other state-of-the-art methods, our proposed method performs better in identifying digestive system tumor subtypes. Subsequent clinical data analysis and functional enrichment analysis further confirm the specific biological characteristics and functional differences of the identified subtypes. This research provides new ideas and methods for precision medicine, and is expected to promote personalized treatment and improve the prognosis of digestive system tumors. [ABSTRACT FROM AUTHOR]

The goal of aspect-based sentiment analysis is to recognize the aspect information in the text and the corresponding sentiment polarity. A variety of robust methods, including attention mechanisms and convolutional neural networks, have been extensively utilized to tackle this complex task. Better experimental results are obtained by using graph convolutional networks (GCN) based on semantic dependency trees in previous studies. Therefore, abundant methods begin to use sentence structure information to complete this task. However, only the loose connection between aspect words and contexts is realized in some practices due to sentences may contain complex relations. To solve this problem, Twain-Syntax graph convolutional network model is proposed, which can utilize multiple syntactic structure information simultaneously. Guided by the constituent tree and dependency tree, rich syntactic information is fully used in the model to build the sentiment-aware context for each aspect. In special, the multilayer attention mechanism and GCN are employed for learning to capture the correlation between words. By integrating syntactic information, this approach significantly refines the model's technical performance. Extensive testing on four benchmark datasets shows that the model delineated in this paper exhibits high levels of efficiency, comparable to several cutting-edge models. [ABSTRACT FROM AUTHOR]

In order to implement the "precision supervision" policy, tobacco companies need to increase the hit rate of tobacco-related cases. Past approaches had lacked research on high-risk parties in tobacco-related cases, which had hindered the improvement of case hit rates. Based on the large amount of historical data stored in tobacco companies, mining accurate warning lists is an effective way to improve case hit rates. After conducting the analysis of high-risk parties features, a gated variable relationship graph convolutional network was proposed to obtain an accurate high-risk parties warning list. Firstly, the gated variable relation graph convolutional network used variable relation graph convolutional network to capture the relationship and key features of the parties. Then, the gated layer was applied to further learn the features. Finally, the learned features were inputted to the Softmax layer to get the classification results, and then an alert list is obtained. Through comparison experiments, the constructed model is proved to be more effective. After a municipal monopoly bureau applied the results of this project, its case hit rate improved from about 0.01% to about 0.5%, which proves that the early warning model can meet the needs of real regulation.