Search

The accurate identification of chemicals with ocular toxicity is of paramount importance in health hazard assessment. In contemporary chemical toxicology, there is a growing emphasis on refining, reducing, and replacing animal testing in safety evaluations. Therefore, the development of robust computational tools is crucial for regulatory applications. The performance of predictive models is heavily reliant on the quality and quantity of data. In this investigation, we amalgamated the most extensive dataset (4901 compounds) sourced from governmental GHS-compliant databases and literature to develop binary classification models of chemical ocular toxicity. We employed 12 molecular representations in conjunction with six machine learning algorithms and two deep learning algorithms to create a series of binary classification models. The findings indicated that the deep learning method GCN outperformed the machine learning models in cross-validation, achieving an impressive AUC of 0.915. However, the top-performing machine learning model (RF-Descriptor) demonstrated excellent performance with an AUC of 0.869 on the test set and was therefore selected as the best model. To enhance model interpretability, we conducted the SHAP method and attention weights analysis. The two approaches offered visual depictions of the relevance of key descriptors and substructures in predicting ocular toxicity of chemicals. Thus, we successfully struck a delicate balance between data quality and model interpretability, rendering our model valuable for predicting and comprehending potential ocular-toxic compounds in the early stages of drug discovery., (© 2024 John Wiley & Sons Ltd.)

The human ether-à-go-go-related gene (hERG) is associated with drug cardiotoxicity. If the hERG channel is blocked, it will lead to prolonged QT interval and cause sudden death in severe cases. Therefore, it is important to evaluate the hERG-blocking property of compounds in early drug discovery. In this study, a dataset containing 4556 compounds with IC 50 values determined by patch clamp techniques on mammalian lineage cells was collected, and hERG blockers and non-blockers were distinguished according to three single thresholds and two binary thresholds. Four machine learning (ML) algorithms combining four molecular fingerprints and molecular descriptors as well as graph convolutional neural networks (GCNs) were used to construct a series of binary classification models. The results showed that the best models varied for different thresholds. The ML models implemented by support vector machine and random forest performed well based on Morgan fingerprints and molecular descriptors, with AUCs ranging from 0.884 to 0.950. GCN showed superior prediction performance with AUCs above 0.952, which might be related to its direct extraction of molecular features from the original input. Meanwhile, the classification of binary threshold was better than that of single threshold, which could provide us with a more accurate prediction of hERG blockers. At last, the applicability domain for the model was defined, and seven structural alerts that might generate hERG blockage were identified by information gain and substructure frequency analysis. Our work would be beneficial for identifying hERG blockers in chemicals., (© 2023 John Wiley & Sons Ltd.)

The combination of memory forensics and deep learning for malware detection has achieved certain progress, but most existing methods convert process dump to images for classification, which is still based on process byte feature classification. After the malware is loaded into memory, the original byte features will change. Compared with byte features, function call features can represent the behaviors of malware more robustly. Therefore, this article proposes the ProcGCN model, a deep learning model based on DGCNN (Deep Graph Convolutional Neural Network), to detect malicious processes in memory images. First, the process dump is extracted from the whole system memory image; then, the Function Call Graph (FCG) of the process is extracted, and feature vectors for the function node in the FCG are generated based on the word bag model; finally, the FCG is input to the ProcGCN model for classification and detection. Using a public dataset for experiments, the ProcGCN model achieved an accuracy of 98.44% and an F1 score of 0.9828. It shows a better result than the existing deep learning methods based on static features, and its detection speed is faster, which demonstrates the effectiveness of the method based on function call features and graph representation learning in memory forensics. [ABSTRACT FROM AUTHOR]

Summary: Real‐time estimation of crowd counting in underground metro systems, constrained by limited space, is crucial for managing heightened pedestrian volumes and responding promptly to emergencies. To address this challenge, we propose a passenger state transition‐based model, called STRmt, designed for the seamless and continuous monitoring of real‐time crowd movement within service areas of stations and trains, leveraging auto fare collection systems (AFC) as a comprehensive sensor network. Our innovation lies in modeling the dynamic movement of passengers within a metro system over time as a state transition process aligned with the train schedule. To achieve this, we introduce a spatio‐temporal deep learning framework, denoted as STnet, designed to dynamically predict these state transitions. The performance of our method is rigorously assessed through extensive experiments conducted spanning 2 years in Shenzhen, China, utilizing AFC data, train schedule data, and weather data. The results demonstrate that the proposed method surpasses baseline methods, achieving an estimation precision of 0.92. [ABSTRACT FROM AUTHOR]

Buildings are responsible for around 30% and 42% of the consumed energy at the global and European levels, respectively. Accurate building power consumption estimation is crucial for resource saving. This research investigates the combination of graph convolutional networks (GCNs) and long short-term memory networks (LSTMs) to analyze power building consumption, thereby focusing on predictive modeling. Specifically, by structuring graphs based on Pearson's correlation and Euclidean distance methods, GCNs are employed to discern intricate spatial dependencies, and LSTM is used for temporal dependencies. The proposed models are applied to data from a multistory, multizone educational building, and they are then compared with baseline machine learning, deep learning, and statistical models. The performance of all models is evaluated using metrics such as the mean absolute error (MAE), mean squared error (MSE), R-squared (R2), and the coefficient of variation of the root mean squared error (CV(RMSE)). Among the proposed computation models, one of the Euclidean-based models consistently achieved the lowest MAE and MSE values, thus indicating superior prediction accuracy. The suggested methods seem promising and highlight the effectiveness of GCNs in improving accuracy and reliability in predicting power consumption. The results could be useful in the planning of building energy policies by engineers, as well as in the evaluation of the energy management of structures. [ABSTRACT FROM AUTHOR]

Deciphering the targets of microRNAs (miRNAs) in plants is crucial for comprehending their function and the variation in phenotype that they cause. As the highly cell-specific nature of miRNA regulation, recent computational approaches usually utilize expression data to identify the most physiologically relevant targets. Although these methods are effective, they typically require a large sample size and high-depth sequencing to detect potential miRNA-target pairs, thereby limiting their applicability in improving plant breeding. In this study, we propose a novel miRNA-target prediction framework named kmerPMTF (k-mer-based prediction framework for plant miRNA-target). Our framework effectively extracts the latent semantic embeddings of sequences by utilizing k-mer splitting and a deep self-supervised neural network. We construct multiple similarity networks based on k-mer embeddings and employ graph convolutional networks to derive deep representations of miRNAs and targets and calculate the probabilities of potential associations. We evaluated the performance of kmerPMTF on four typical plant datasets: Arabidopsis thaliana, Oryza sativa, Solanum lycopersicum, and Prunus persica. The results demonstrate its ability to achieve AUPRC values of 84.9%, 91.0%, 80.1%, and 82.1% in 5-fold cross-validation, respectively. Compared with several state-of-the-art existing methods, our framework achieves better performance on threshold-independent evaluation metrics. Overall, our study provides an efficient and simplified methodology for identifying plant miRNA-target associations, which will contribute to a deeper comprehension of miRNA regulatory mechanisms in plants. [ABSTRACT FROM AUTHOR]

Forecasting air quality plays a crucial role in preventing and controlling air pollution. It is particularly significant for improving preparedness for heavily polluted weather conditions and ensuring the health and safety of the population. In this study, a novel deep learning model for predicting air quality spatio-temporal variations is introduced. The model, named graph long short-term memory with multi-head attention (GLSTMMA), is designed to capture the temporal patterns and spatial relationships within multivariate time series data related to air quality. The GLSTMMA model utilizes a hybrid neural network architecture to effectively learn the complex dependencies and correlations present in the data. The extraction of spatial features related to air quality involves the utilization of a graph convolutional network (GCN) to collect air quality data based on the geographical distribution of monitoring sites. The resulting graph structure is imported into a long short-term memory (LSTM) network to establish a Graph LSTM unit, facilitating the extraction of temporal dependencies in air quality. Leveraging a Graph LSTM unit, an encoder-multiple-attention decoder framework is formulated to enable a more profound and efficient exploration of spatio-temporal correlation features within air quality time series data. The research utilizes the 2019–2021 multi-source air quality dataset of Qinghai Province for experimental assessment. The results indicate that the model effectively leverages the impact of multi-source data, resulting in optimal accuracy in predicting six air pollutants. [ABSTRACT FROM AUTHOR]

The total electron content (TEC) of the ionosphere is one of the key parameters for both scientific study and engineering application. A hybrid deep learning network based on Grapy Convolution Network (GCN) and Long Short Term Memory (LSTM) is proposed to predict the regional ionospheric TEC 24 h in advance across China. The extensive 14-year dataset during 2005–2018 from the CODE TEC measurements, covering a wide variety of solar activity, are used to comprehensively evaluate the performance of the predictive model. The experimental results show that the model predicted TEC is in good agreement with the actual CODE TEC. Over 90% of differences between the actual TEC and the predicted TEC are within ±2 TECU, and the model errors obviously depend on seasons, latitudes and solar activity. Comparison with the previous work indicate that the proposed regional forecast model is competitive. [ABSTRACT FROM AUTHOR]

In recent years, skeleton-based action recognition has made great achievements in Computer Vision. A graph convolutional network (GCN) is effective for action recognition, modelling the human skeleton as a spatiotemporal graph. Most GCNs define the graph topology by physical relations of the human joints. However, this predefined graph ignores the spatial relationship between non-adjacent joint pairs in special actions and the behavior dependence between joint pairs, resulting in a low recognition rate for specific actions with implicit correlation between joint pairs. In addition, existing methods ignore the trend correlation between adjacent frames within an action and context clues, leading to erroneous action recognition with similar poses. Therefore, this study proposes a learnable GCN based on behavior dependence, which considers implicit joint correlation by constructing a dynamic learnable graph with extraction of specific behavior dependence of joint pairs. By using the weight relationship between the joint pairs, an adaptive model is constructed. It also designs a self-attention module to obtain their inter-frame topological relationship for exploring the context of actions. Combining the shared topology and the multi-head self-attention map, the module obtains the context-based clue topology to update the dynamic graph convolution, achieving accurate recognition of different actions with similar poses. Detailed experiments on public datasets demonstrate that the proposed method achieves better results and realizes higher quality representation of actions under various evaluation protocols compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Nowadays, the automatic detection of driver fatigue has become one of the important measures to prevent traffic accidents. For this purpose, a lot of research has been conducted in this field in recent years. However, the diagnosis of fatigue in recent research is binary and has no operational capability. This research presents a multi-class driver fatigue detection system based on electroencephalography (EEG) signals using deep learning networks. In the proposed system, a standard driving simulator has been designed, and a database has been collected based on the recording of EEG signals from 20 participants in five different classes of fatigue. In addition to self-report questionnaires, changes in physiological patterns are used to confirm the various stages of weariness in the suggested model. To pre-process and process the signal, a combination of generative adversarial networks (GAN) and graph convolutional networks (GCN) has been used. The proposed deep model includes five convolutional graph layers, one dense layer, and one fully connected layer. The accuracy obtained for the proposed model is 99%, 97%, 96%, and 91%, respectively, for the four different considered practical cases. The proposed model is compared to one developed through recent methods and research and has a promising performance. [ABSTRACT FROM AUTHOR]

Deciphering the targets of microRNAs (miRNAs) in plants is crucial for comprehending their function and the variation in phenotype that they cause. As the highly cell-specific nature of miRNA regulation, recent computational approaches usually utilize expression data to identify the most physiologically relevant targets. Although these methods are effective, they typically require a large sample size and high-depth sequencing to detect potential miRNA-target pairs, thereby limiting their applicability in improving plant breeding. In this study, we propose a novel miRNA-target prediction framework named kmerPMTF (k-mer-based prediction framework for plant miRNA-target). Our framework effectively extracts the latent semantic embeddings of sequences by utilizing k-mer splitting and a deep self-supervised neural network. We construct multiple similarity networks based on k-mer embeddings and employ graph convolutional networks to derive deep representations of miRNAs and targets and calculate the probabilities of potential associations. We evaluated the performance of kmerPMTF on four typical plant datasets: Arabidopsis thaliana, Oryza sativa, Solanum lycopersicum, and Prunus persica. The results demonstrate its ability to achieve AUPRC values of 84.9%, 91.0%, 80.1%, and 82.1% in 5-fold cross-validation, respectively. Compared with several state-of-the-art existing methods, our framework achieves better performance on threshold-independent evaluation metrics. Overall, our study provides an efficient and simplified methodology for identifying plant miRNA-target associations, which will contribute to a deeper comprehension of miRNA regulatory mechanisms in plants.

High-resolution range profile (HRRP), characterized by its high availability and rich target structural information, has been extensively studied. However, HRRP-based target recognition methods using closed datasets exhibit limitations when it comes to identifying new classes of targets. The scarcity of samples for new classes leads to overfitting during the deep learning process, and the similarity in the scattering structures of different ships, combined with the significant structural differences among samples of the same ship, contribute to a high level of confusion among targets. To address these challenges, this paper proposed Task-Specific Mate-learning (TSML) for few-shot HRRP. Firstly, a Task-Adaptive Mixed Transfer (TAMT) strategy is proposed, which combines basic learning with meta-learning, to reduce the likelihood of overfitting and enhance adaptability for recognizing new classes of ships. Secondly, a Prototype Network is introduced to enable the recognition of new classes of targets with limited samples. Additionally, a Space-Adjusted Meta Embedding (SAME) is proposed based on the Prototype Network. This embedding function, designed for HRRP data, modifies the distances between samples in meta-tasks by increasing the distances between samples from different ships and decreasing the distances between samples from the same ship. The proposed method is evaluated based on an actual measured HRRP dataset and the experimental results prove that the proposed method can more accurately recognize the unknown ship classes with a small number of labels by learning the known classes of ships. In addition, the method has a degree of robustness to the number of training samples and a certain generalization ability, which can produce improved results when applied to other backbones. [ABSTRACT FROM AUTHOR]

Most short-term passenger flow prediction methods only consider absolute errors as the optimization objective, which fails to account for spatial and temporal constraints on the predictions. To overcome these limitations, we propose a deep learning-based spatiotemporal graph generative adversarial network (STG-GAN) to accurately predict network-wide short-term passenger flows of the urban rail transit with higher efficiency and lower memory occupancy. Our model is optimized in an adversarial learning manner and includes (1) a generator network including gated temporal conventional networks (TCN) and weight sharing graph convolution networks (GCN) to capture structural spatiotemporal dependencies and generate predictions with a small computational burden; (2) a discriminator network including a spatial discriminator and a temporal discriminator to enhance spatial and temporal constraints of the predictions. The STG-GAN is evaluated on two datasets from Beijing Subway. Results illustrate its superiority and robustness. [ABSTRACT FROM AUTHOR]

As cloud system architectures evolve continuously, the interactions among distributed components in various roles become increasingly complex. This complexity makes it difficult to detect anomalies in cloud systems. The system status can no longer be determined through individual key performance indicators (KPIs) but through joint judgments based on synergistic relationships among distributed components. Furthermore, anomalies in modern cloud systems are usually not sudden crashes but rather gradual, chronic, localized failures or quality degradations in a weakly available state. Therefore, accurately modeling cloud systems and mining the hidden system state is crucial. To address this challenge, we propose an anomaly detection method with dynamic spatiotemporal learning (AD-DSTL). ADDSTL leverages the spatiotemporal dynamics of the system to train an endto- end deep learning model driven by data from system monitoring to detect underlying anomalous states in complex cloud systems. Unlike previous work that focuses on the KPIs of separate components, AD-DSTL builds a model for the entire system and characterizes its spatiotemporal dynamics based on graph convolutional networks (GCN) and long short-term memory (LSTM). We validated AD-DSTL using four datasets from different backgrounds, and it demonstrated superior robustness compared to other baseline algorithms. Moreover,when raising the target exception level, both the recall and precision of AD-DSTL reached approximately 0.9. Our experimental results demonstrate that AD-DSTL can meet the requirements of anomaly detection for complex cloud systems. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation. With the continuous development of artificial intelligence technology, the use of deep learning methods for interpreting remote-sensing images has matured. Existing neural networks disregard the spatial relationship between two targets in remote sensing images. Semantic segmentation models that combine convolutional neural networks (CNNs) and graph convolutional neural networks (GCNs) cause a lack of feature boundaries, which leads to the unsatisfactory segmentation of various target feature boundaries. In this paper, we propose a new semantic segmentation model for remote sensing images (called DGCN hereinafter), which combines deep semantic segmentation networks (DSSN) and GCNs. In the GCN module, a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships. A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship information in the original feature information. Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images, the DGCN significantly optimizes the segmentation effect of feature boundaries, effectively reduces the noise in the segmentation results and improves the segmentation accuracy, which demonstrates the advancements of our model. [ABSTRACT FROM AUTHOR]

Nowadays, the automatic detection of driver fatigue has become one of the important measures to prevent traffic accidents. For this purpose, a lot of research has been conducted in this field in recent years. However, the diagnosis of fatigue in recent research is binary and has no operational capability. This research presents a multi-class driver fatigue detection system based on electroencephalography (EEG) signals using deep learning networks. In the proposed system, a standard driving simulator has been designed, and a database has been collected based on the recording of EEG signals from 20 participants in five different classes of fatigue. In addition to self-report questionnaires, changes in physiological patterns are used to confirm the various stages of weariness in the suggested model. To pre-process and process the signal, a combination of generative adversarial networks (GAN) and graph convolutional networks (GCN) has been used. The proposed deep model includes five convolutional graph layers, one dense layer, and one fully connected layer. The accuracy obtained for the proposed model is 99%, 97%, 96%, and 91%, respectively, for the four different considered practical cases. The proposed model is compared to one developed through recent methods and research and has a promising performance.

3D reconstruction based on single view aims to reconstruct the entire 3D shape of an object from one perspective. When existing methods reconstruct the mesh surface of complex objects, the surface details are difficult to predict and the reconstruction visual effect is poor because the mesh representation is not easily integrated into the deep learning framework; the 3D topology is easily limited by predefined templates and inflexible, and unnecessary mesh self-intersections and connections will be generated when reconstructing complex topology, thus destroying the surface details; the training of the reconstruction network is limited by the large amount of information attached to the mesh vertices, and the training time of the reconstructed network is too long. In this paper, we propose a method for fast mesh reconstruction from single view based on Graph Convolutional Network (GCN) and topology modification. We use GCN to ensure the generation of high-quality mesh surfaces and use topology modification to improve the flexibility of the topology. Meanwhile, a feature fusion method is proposed to make full use of the features of each stage of the image hierarchically. We use 3D open dataset ShapeNet to train our network and add a new weight parameter to speed up the training process. Extensive experiments demonstrate that our method can not only reconstruct object meshes on complex topological surfaces, but also has better qualitative and quantitative results. [ABSTRACT FROM AUTHOR]

Urban online ride-hailing demand forecasting is an important component of smart city transportation systems. An accurate online ride-hailing demand prediction model can help cities allocate online ride-hailing resources reasonably, reduce energy waste, and reduce traffic congestion. With the massive popularity of online ride-hailing, we can collect a large amount of order data, and how to use deep learning models for improving order prediction accuracy has become a hot research topic. Most of the urban online taxi demand forecasting methods do not sufficiently consider the influencing factors and cannot model the complex nonlinear spatio-temporal relationships. Therefore, we propose a multi-view deep spatio-temporal network framework (MVDSTN) architecture to obtain the spatio-temporal relationships for online ride-hailing demand prediction. Our proposed model includes five views,up-passenger order view, down-passenger order view, POI view, spatial GCN view, POI view and weather view, applies LSTM with attention mechanism to achieve demand prediction for urban online taxi bodies. Experiments Haikou Didi Taxi datasets and Wuhan Taxi datasets prove that our model has good robustness and the prediction method outperforms current methods. [ABSTRACT FROM AUTHOR]

In most Internet of Things (IoT) scenes, data missing can be unavoidable when huge number of smart devices are collecting data uninterruptedly. Therefore, data imputation can be an integral part of pre-processing before data mining. It is widely known that IoT time series show strong dependencies in both spatial and temporal dimension, and the spatial relation among the devices is in non-euclidean space. However, most machine-learning-based and deep-learning-based approaches either only take temporal features into account or only catch spatial features in euclidean space. In this paper, we propose a novel network as ST-VAE (Spatio-Temporal Variational Auto-Encoder) to address the problem above. Our architecture is mainly based on Variational Auto-Encoder (VAE). Specifically, two kinds of VAE are utilized. One is for calculating the adjacent matrix of device network which is the essential input of GCN, and the other is for data imputation task based on the spatial and temporal dependencies. Experiments conducted on different real-world and public datasets demonstrate that our ST-VAE can not only populate the missing spatio-temporal data accurately but also outperforms other state-of-art approaches from the whole. [ABSTRACT FROM AUTHOR]

Multiple station passenger flow prediction is crucial but challenging for intelligent transportation systems. Recently, deep learning models have been widely applied in multi-station passenger flow prediction. However, flows at the same station in different periods, or different stations in the same period, always present different characteristics. These indicate that globally extracting spatio-temporal features for multi-station passenger flow prediction may only be powerful enough to achieve the excepted performance for some stations. Therefore, a novel two-step multi-station passenger flow prediction model is proposed. First, an unsupervised clustering method for station classification using pure passenger flow is proposed based on the Transformer encoder and K-Means. Two novel evaluation metrics are introduced to verify the effectiveness of the classification results. Then, based on the classification results, a passenger flow prediction model is proposed for every type of station. Residual network (ResNet) and graph convolution network (GCN) are applied for spatial feature extraction, and attention long short-term memory network (AttLSTM) is used for temporal feature extraction. Integrating results for every type of station creates a prediction model for all stations in the network. Experiments are conducted on two real-world ridership datasets. The proposed model performs better than unclassified results in multi-station passenger flow prediction. [ABSTRACT FROM AUTHOR]

Graph Convolutional Network (GCN) is a powerful emerging deep learning technique for learning graph data. However, there are still some challenges for GCN. For example, the model is shallow; the performance is poor when labelled nodes are severely scarce. In this paper, we propose a Multi-Semantic Aligned Graph Convolutional Network (MSAGCN), which contains two fundamental operations: multi-angle aggregation and semantic alignment, to resolve two challenges simultaneously. The core of MSAGCN is the aggregation of nodes that belong to the same class from three perspectives: nodes, features, and graph structure, and expects the obtained node features to be mapped nearby. Specifically, multi-angle aggregation is applied to extract features from three angles of the labelled nodes, and semantic alignment is utilised to align the semantics in the extracted features to enhance the similar content from different angles. In this way, the problem of over-smoothing and over-fitting for GCN can be alleviated. We perform the node clustering task on three citation datasets, and the experimental results demonstrate that our method outperforms the state-of-the-art (SOTA) baselines. [ABSTRACT FROM AUTHOR]

The recognition of English texts in teaching scenes is a practical research direction. English text recognition can be widely used in English teaching scenes, such as assisting teachers to recognise students' English homework, text positioning before text translation, developing outdoor classrooms, assisting junior students in scene understanding and so on. To identify English information in different scenes as accurately as possible, identifying the corresponding text content is the key. Based on a deep neural network, this paper proposes GCN-Attention English recognition algorithm. The experiment adopts the deep learning framework Tensorflow, which combines 104 × 104 size GCN with an attention mechanism for training. The output of GCN is used to train the cyclic neural network to continuously predict the next most likely letter in the sequence. The goal of training is to match the output words with the expected words as much as possible. The test results show that the model can have a good recognition accuracy for the scene image data set used in teaching. [ABSTRACT FROM AUTHOR]

Graph neural network is a deep learning approach widely applied on structural and non-structural scenarios due to its substantial performance and interpretability recently. In a non-structural scenario, textual and visual research topics like visual question answering (VQA) are important, which need graph reasoning models. VQA aims to build a system that can answer related questions about given images as well as understand the underlying semantic meaning behind the image. The critical issues in VQA are to effectively extract the visual and textual features and subject both features into a common space. These issues have a great impact in handling goal-driven, reasoning, and scene classification subtasks. In the same vein, it is difficult to compare models' performance because most existing datasets do not group instances into meaningful categories. With the recent advances in graph-based models, lots of efforts have been devoted to solving the problems mentioned above. This study focuses on graph convolutional networks (GCN) studies and recent datasets for visual question answering tasks. Specifically, we reviewed current related studies on GCN for the VQA task. Also, 18 common and recent datasets for VQA are well studied, though not all of them are discussed at the same level of detail. A critical review of GCN, datasets and VQA challenges is further highlighted. Finally, this study will help researchers to choose a suitable dataset for a particular VQA subtask, identify VQA challenges, the pros and cons of its approaches, and improve more on GCN for the VQA. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of the Internet and information technology, video websites, shopping websites, and other portals have grown rapidly. However, malicious webpages can disguise themselves as benign websites and steal users' private information, which seriously threatens network security. Current detection methods for malicious webpages do not fully utilize the syntactic and semantic information in the web source code. In this paper, we propose a GCN-based malicious webpage detection method (GMWD), which constructs a text graph to describe and then a GCN model to learn the syntactic and semantic correlations within and between webpage source codes. We replace word nodes in the text graph with phrase nodes to better maintain the syntactic and semantic integrity of the webpage source code. In addition, we use the URL links appearing in the source code as auxiliary detection information to further improve the detection accuracy. The experiments showed that the proposed method can achieve 99.86% accuracy and a 0.137% false negative rate, achieving a better performance than other related malicious webpage detection methods. [ABSTRACT FROM AUTHOR]

In the context of heightened safety concerns and the intricate nature of geological structures in coal mining, accurately localizing microseismic events is a critical challenge. This paper introduces the LGF SeismoLocator, a novel deep learning model tailored to enhance the precision of seismic source detection within coal mines. By innovatively combining long short-term memory networks (LSTM), graph convolutional networks (GCN), and fully convolutional networks (FCN), and utilizing 3D Gaussian distributions as labels, this model demonstrates remarkable capabilities in processing complex seismic data. When tested with microseismic events from the Dongtan Coal Mine, the LGF SeismoLocator exhibited superior accuracy in event localization and computational efficiency. Its effectiveness was further validated through controlled blasting experiments. This study not only highlights the potential of deep learning to improve microseismic monitoring but also provides a practical solution for mitigating risks associated with rockbursts and other mining-related hazards. [ABSTRACT FROM AUTHOR]

Previous video action recognition mainly focuses on extracting spatial and temporal features from videos or capturing physical dependencies among joints. The relation between joints is often ignored. Modeling the relation between joints is important for action recognition. Aiming at learning discriminative relation between joints, this paper proposes a joint spatial-temporal reasoning (JSTR) framework to recognize action from videos. For the spatial representation, a joints spatial relation graph is built to capture position relations between joints. For the temporal representation, temporal information of body joints is modeled by the intra-joint temporal relation graph. The spatial reasoning feature and the temporal reasoning feature are fused to recognize action from videos. The effectiveness of our method is demonstrated in three real-world video action recognition datasets. The experiment results display good performance across all of these datasets.

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHES-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable. [ABSTRACT FROM AUTHOR]

Mobile Laser Scanning (MLS) system can provide high-density and accurate 3D point clouds that enable rapid pavement crack detection for road maintenance tasks. Supervised learning-based algorithms have been proved pretty effective for handling such a large amount of inhomogeneous and unstructured point clouds. However, these algorithms often rely on a lot of annotated data, which is labor-intensive and time-consuming. This paper presents a semi-supervised point-level approach to overcome this challenge. We propose a graph-widen module to construct a reasonable graph structure for point clouds, increasing the detection performance of graph convolutional networks (GCN). The constructed graph characterizes the local features from a small amount of annotated data, avoiding information loss and dramatically reduces the dependence on annotated data. The MLS point clouds acquired by a commercial RIEGL VMX-450 system are used in this study. The experimental results demonstrate that our method outperforms the state-of-the-art point-level methods in terms of recall, F1 score, and efficiency while achieving comparable accuracy. [ABSTRACT FROM AUTHOR]

In recent years, various deep learning architectures have been proposed to solve complex challenges (e.g. spatial dependency, temporal dependency) in traffic domain, which have achieved satisfactory performance. These architectures are composed of multiple deep learning techniques in order to tackle various challenges in traffic tasks. Traditionally, convolution neural networks (CNNs) are utilized to model spatial dependency by decomposing the traffic network as grids. However, many traffic networks are graph-structured in nature. In order to utilize such spatial information fully, it’s more appropriate to formulate traffic networks as graphs mathematically. Recently, various novel deep learning techniques have been developed to process graph data, called graph neural networks (GNNs). More and more works combine GNNs with other deep learning techniques to construct an architecture dealing with various challenges in a complex traffic task, where GNNs are responsible for extracting spatial correlations in traffic network. These graph-based architectures have achieved state-of-the-art performance. To provide a comprehensive and clear picture of such emerging trend, this survey carefully examines various graph-based deep learning architectures in many traffic applications. We first give guidelines to formulate a traffic problem based on graph and construct graphs from various kinds of traffic datasets. Then we decompose these graph-based architectures to discuss their shared deep learning techniques, clarifying the utilization of each technique in traffic tasks. What’s more, we summarize some common traffic challenges and the corresponding graph-based deep learning solutions to each challenge. Finally, we provide benchmark datasets, open source codes and future research directions in this rapidly growing field. [ABSTRACT FROM AUTHOR]

Online ride-hailing order forecasting is a very important part of the intelligent traffic dispatch system. Accurate order forecasting can reduce the flow of invalid vehicles and improve the user experience of online ride-hailing. We propose a multi-view deep long short-term memory (LSTM) network architecture (MultiView deep LSTM framework), which uses convolutional neural network and graph convolutional network to extract the temporal and spatial characteristics of online ride-hailing orders, obtains the correlation information between regional orders through the order view, regional speed view, and weather factor view, and then uses LSTM unit and attention unit to predict the order volume in real time. We use Didi Haikou, China's online ride-hailing dataset for training, compare it with the prediction algorithms of other articles, and experiment with different choices of the contrast framework. The experimental results show that our deep learning framework can effectively capture comprehensive spatio-temporal correlation and obtain better results. The model maintained good performance at 15 min, 30 min, and 1 h. Experiments conducted on the actual demand data onto ride-hailing from Didi Haikou data prove that our method is better than the latest method. [ABSTRACT FROM AUTHOR]

Event Detection (ED) is a pivotal sub-task of Event Extraction(EE). It aims to locate triggers and categorize them into specific event types. Recent researches on ED have shown that graph convolutional neural networks with syntactic information can achieve advanced performance. However, these methods ignore the implicit importance score of tokens. This will weaken their ability of identifying trigger words. In addition, due to the long-tailed distribution in the corpus, previous methods perform poorly on sparsely labeled trigger words and are prone to overfitting on densely labeled ones. In this paper, we propose a Syntax-Enhanced GCN framework with a Decoupled Classification Rebalance mechanism (SEGCN-DCR) to address the above issues. Specifically, we exploit a tree-structured module based on dependency structure to reduce the noise by capturing global hierarchical syntactic information, and DCR mechanism to rescale the classifier weights, which makes classifier decision boundaries more reasonable. Experiments on benchmark ACE2005 show that the proposed method acquires state-of-the-art performance. [ABSTRACT FROM AUTHOR]

With the rapid development of computer vision, human action recognition has shown its wide application prospects and research value in many fields such as video surveillance, video retrieval, and human-computer interaction. Human action recognition involves the understanding of image content, and the progress of practical applications is slow due to the complexity and diversity of human postures and the occlusion factors of the background. This paper comprehensively reviewed the development of human action recognition, and deeply explored the research methods in this field, including traditional manual feature extraction methods and deep learning-based methods, as well as the recently popular graph convolutional network（GCN）-based method. And this paper systematically summarized these methods according to the data types they used. In addition, for different data types, it introduced some popular action recognition datasets, compared and analyzed the performance of various methods on these datasets. Finally, this paper summarized the review, and prospected the future research direction of human action recognition. [ABSTRACT FROM AUTHOR]

Event detection (ED) is considered as an important task in natural language processing (NLP) which effectively supports to specify instances of multi event types which are mentioned in text. Recent models adopt advanced neural network architectures, such as long short-term memory (LSTM), graph convolutional network (GCN), etc. to capture the sequential and syntactical representations of texts for leveraging the performance of ED. However, recent neural network-based models neglect to sufficiently perverse both sequential comprehensive meanings as well as syntactical co-referencing relationships between words in the sentences. In this paper, we proposed a novel integration of GCN-based textual syntactical encoder and pre-trained BERT sequential embedding with event-aware masked language mechanism, called SynSeq4ED. In our SynSeq4ED model, we formally present a joint text embedding framework which enable to effectively learn the deep semantic representations of event triggers and arguments by introducing a combination of integrated pre-trained BERT with event-aware masked language strategy and GCN-based syntactical co-referencing text encoding mechanism. The achieved text representations by SynSeq4ED model are then used to improve the performance of multiple tasks in ED, including multiple event detection (MED), few-shot learning event detection (FSLED). Extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed SynSeq4ED model in comparing with recent state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of the Internet and information technology, video websites, shopping websites, and other portals have grown rapidly. However, malicious webpages can disguise themselves as benign websites and steal users’ private information, which seriously threatens network security. Current detection methods for malicious webpages do not fully utilize the syntactic and semantic information in the web source code. In this paper, we propose a GCN-based malicious webpage detection method (GMWD), which constructs a text graph to describe and then a GCN model to learn the syntactic and semantic correlations within and between webpage source codes. We replace word nodes in the text graph with phrase nodes to better maintain the syntactic and semantic integrity of the webpage source code. In addition, we use the URL links appearing in the source code as auxiliary detection information to further improve the detection accuracy. The experiments showed that the proposed method can achieve 99.86% accuracy and a 0.137% false negative rate, achieving a better performance than other related malicious webpage detection methods.

This research proposes a novel deep learning approach named causal-temporal graphic convolutional network (CT-GCN) which aims to provide accurate predictions on tunnel boring machine's (TBM) load parameters. The causal associations among the key TBM operational parameters are detected and quantified with causal effects through the Peter and Clark momentary conditional independence plus (PCMCI+) method. The discovered causality can be further integrated with a deep learning model that consists of graph convolutional network (GCN) and long short-term memory (LSTM) layers for accurate prediction of TBM's torque and thrust. Data collected from a realistic tunnel project in Singapore is utilized to demonstrate the effectiveness of the proposed approach. The load parameters are predicted with their historical values and another 7 key operational parameters. The results indicate that (1) The proposed CT-GCN approach can achieve a low mean absolute error (MAE) and root mean squared error (RMSE) of 40.90 k N ∙ m and 64.53 k N ∙ m for thrust force (y 1) and that of 635.76 k N and 1168.59 k N for cutterhead torque (y 2), respectively. (2) The proposed CT-GCN method achieves 12.86 % and 24.38 % average improvements in the coefficient of determination ( R 2) for y 1 and y 2 , respectively when compared with the long-short term memory (LSTM) method and that of 5.62 % and 8.60 % improvements when compared with the GCN-LSTM method. (3) Compared with correlation-based GCN models, the proposed approach exerts an average improvement of 43.10 %, 41.97 %, and 22.72 % in terms of MAE, RMSE, and R 2 for torque and much better performance for thrust estimation. This study contributes to improving the understanding of TBM operation by quantifying the causality among the key operational parameters. It also contributes to developing a novel deep-learning method that estimates TBM's load parameters with high accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, prediction for medical treatment migration has become one of the interesting issues in the field of health informatics. This is because the medical treatment migration behavior is closely related to the evaluation of regional medical level, the rational use of medical resources, and the distribution of medical insurance. Therefore, a prediction model for medical treatment migration based on medical insurance data is introduced in this paper. First, a medical treatment graph is constructed based on medical insurance data. The medical treatment graph is a heterogeneous graph, which contains entities such as patients, diseases, hospitals, medicines, hospitalization events, and the relations between these entities. However, existing graph neural networks are unable to capture the time-series relationships between event-type entities. To this end, a prediction model based on Graph Convolutional Network (GCN) is proposed in this paper, namely, Event-involved GCN (EGCN). The proposed model aggregates conventional entities based on attention mechanism, and aggregates event-type entities based on a gating mechanism similar to LSTM. In addition, jumping connection is deployed to obtain the final node representation. In order to obtain embedded representations of medicines based on external information (medicine descriptions), an automatic encoder capable of embedding medicine descriptions is deployed in the proposed model. Finally, extensive experiments are conducted on a real medical insurance data set. Experimental results show that our model's predictive ability is better than the best models available. [ABSTRACT FROM AUTHOR]

This paper investigates the prediction of geological conditions ahead of tunnel boring machines (TBM) using a hybrid deep learning approach. By integrating graph convolutional network (GCN) and long short-term memory (LSTM) networks, the spatial and temporal features from TBM parameters and geological information are extracted for accurate prediction. The results from the case study indicate that (1) The proposed approach provides estimation with a high accuracy of 0.9986; (2) The past geological information has a significant contribution to the model; (3) The proposed approach outperforms several state-of-the-art methods including support vector machine (SVM), extreme gradient boosting (XGBoost) and LSTM method. The proposed hybrid deep learning approach can be a useful tool that provides reliable estimation of the advanced geological conditions in real-time. • A novel deep learning approach is proposed for advance geological perception. • The dependencies among the TBM parameters and geological information are considered. • A deep-learning framework that incorporates GCN and LSTM is established. • A realistic tunnel project in Singapore is used to demonstrate as a case study. • A high prediction accuracy can be achieved with average accuracy of 0.9986. [ABSTRACT FROM AUTHOR]

Deep learning techniques and attention schemes are used by many researchers for classifying the sentiments. Retrieval of semantic relationship between the aspects with words of context will improve the classification accuracy. This was done by Aspect-Specific Graph Convolutional Networks (ASGCN) which utilises aspect-specific relationships and attention scheme by researchers. Long-range dependencies and sensitive-important words are missing in these methods. This work proposes two novel approaches for improving the effectiveness of sentiment classification. First, we propose a method, Adaptive Aspect-Specific GCN (AASGCN) for enhancing ASGCN by incorporating adaptive weights into ASGCN to better capturing of the semantic meaning of the opinion target. Second, we introduce an Emotional Intensive Sentiment Reasoning (EISR) that incorporates emotional intensive information into the mechanism. We experiment our proposed work along with many existing work's datasets such as LAP14 (Pontiki et al., 2014), TWITTER (Dong et al., 2014), REST14 (Pontiki et al., 2014), REST15 (Pontiki et al., 2015), and REST16 (Pontiki et al., 2016). The results prove that AASGCN performs well than the range of state-of-the-art models and can be substantially improved by incorporating the two approaches. • Deep learning techniques and attention schemes are used for sentiment classification. • Adaptive weights is incorporated in Aspect-Specific Graph Convolutional Networks. • AASGCN enhanced the aspect-based work by adding sentiment polarity along with aspect-level. • Emotional intensive information was incorporated by using EIAASG. • Proposed models have comparable effectiveness to the state-of-art models. [ABSTRACT FROM AUTHOR]

Ship speed information plays an important role in the maritime intelligent transportation system, and ship speed prediction has attracted extensive attention in maritime community. Previous studies suggest that ship speed is mainly affected by her previous movement status, regardless the interferences from neighboring locations. To address the issue, a novel deep learning framework is proposed to predict ship speed via the support of k-hop graph convolutional network (k-GCN) and long–short term memory (LSTM). Firstly, a ship network model is established with a graph network. The nodes in the proposed networks demonstrate ship trajectory segments, whilst the segments are connected to obtain edges. Secondly, the GCN is used to capture the spatial correlation between the nodes, and the LSTM is used to exploit spatial–temporal correlation among the nodes. Finally, the proposed k-GCN-LSTM model is used to predict ship speed, which are further verified on different real-world ship trajectory data against with other models. Results suggest that the proposed model obtains satisfied prediction performance in terms of typical error measurement indicators. The research findings help maritime traffic participants better avoid potential collisions and enhance maritime traffic safety. • GCN and LSTM are introduced to consider the spatiotemporal correlation of ships. • High-hop neighborhood of nodes is considered to extract more spatial features. • A cell state gate is added in the LSTM cell to consider neighboring cell states. • Three experiments are conducted to verify the performance of the proposed model. [ABSTRACT FROM AUTHOR]

The importance of considering related stocks data for the prediction of stock price movement has been shown in many studies; however, advanced graphical techniques for modeling, embedding and analyzing the behavior of inter-related stocks have not been widely exploited for the prediction of stocks price movements yet. The main challenges in this domain are to find a way for modeling the existing relations among an arbitrary set of stocks and to exploit such a model for improving the prediction performance for those stocks. The most of existing methods in this domain rely on basic graph-analysis techniques, with limited prediction power, and suffer from a lack of generality and flexibility. In this paper, we introduce a novel framework, called GCNET that models the relations among an arbitrary set of stocks as a graph structure called influence network and uses a set of history-based prediction models to infer plausible initial labels for a subset of the stock nodes in the graph. Finally, GCNET uses the Graph Convolutional Network algorithm to analyze this partially labeled graph and predicts the next price direction of movement for each stock in the graph. GCNET is a general prediction framework that can be applied for the prediction of the price fluctuations of interacting stocks based on their historical data. Our experiments and evaluations on a set of stocks from the NASDAQ index demonstrate that GCNET improves the performance of the state-of-the-art algorithms in terms of Accuracy and Matthew's Correlation Coefficient by at least 1.5% and 2%, respectively. • GCNET is a novel graph-based framework for prediction of stock price fluctuations. • GCNET introduce a novel approach for modeling stocks relations as a network. • GCNET applies the novel PLD mechanism to predict reliable initial labels for nodes in a network of stocks. [ABSTRACT FROM AUTHOR]

Human activity recognition is one of the most studied topics in the field of computer vision. In recent years, with the availability of RGB-D sensors and powerful deep learning techniques, research on human activity recognition has gained momentum. From simple human atomic actions, the research has advanced towards recognizing more complex human activities using RGB-D data. This paper presents a comprehensive survey of the advanced deep learning based recognition methods and categorizes them in human atomic action, human–human interaction, human–object interaction. The reviewed methods are further classified based on the individual modality used for recognition i.e. RGB based, depth based, skeleton based, and hybrid. We also review and categorize recent challenging RGB-D datasets for the same. In addition, the paper also briefly reviews RGB-D datasets and methods for online activity recognition. The paper concludes with a discussion on limitations, challenges, and recent trends for promising future directions. • A comprehensive categorical survey of RGB-D human action/interaction recognition. • Categorized RGB-D datasets, methods into human actions, human–object interactions. • In-depth analysis of well-known deep learning methods for actions and interactions. • Examined distinct characteristics of RGB-D modalities for actions/interactions. • Discussed limitations, challenges, and promising future directions in the domain. [ABSTRACT FROM AUTHOR]

With increasingly cyber-attacks and intrusion techniques, the threat of network security has become more and more serious. However, existing solutions are no longer sufficient in terms of accuracy as attacks continue to grow in quantity and complexity. Prior methods mainly focused on the application of deep learning techniques to analyze data changes in traffic flow. The cunning Cyber-attacks cannot be detected because some advanced attack techniques can conceal attacks and make them might seem innocuous in statistics. At the same time, traditional models only concentrate on the statistics of traffic sent by individual hosts, so the potential relationships of communication patterns in network traffic might be ignored. It makes these solutions are not competent for dealing with the various uncertainty in network traffic. In this paper, we propose an efficient anomaly detection approach, called AnoGLA, which considering the complex communication patterns between network structure and node properties. To mine the hidden relationship between network traffic, we built graph structured data in network traffic and exploits graph convolution network (GCN) for modeling. And we also combine long short-term memory network (LSTM) with Attention mechanism to extract the change information of the graph at different times. The effectiveness and robustness of proposed method are evaluated on two real-world datasets. The experiment results indicate that our scheme can effectively detect anomaly flow and outperforms the previous ones in network anomaly detection tasks. [ABSTRACT FROM AUTHOR]

Traffic prediction plays an essential role in the intelligent transportation systems and has broad applications in transportation management and planning. And the key to this field is to explore the spatiotemporal information of traffic data, synchronously. Recently, various deep learning methods, such as Convolution Neural Network (CNN) and Graph Convolutional Network (GCN), have shown promising performance in traffic prediction. However, these methods cannot automatically model spatial dependencies and dynamic spatiotemporal States, and there are no constraints on the distribution of outputs. To solve the above problems, in this paper, a method of automatically obtaining spatiotemporal dependence in data, which can automatically obtain the spatiotemporal state and spatiotemporal dependency using Multi-graph Adversarial Neural Network (GAN) and is named AST-MAGCN, is proposed. The new method AST-MAGCN combines GAN and GCN, extracts spatiotemporal state of the data in real-time, and outputs the traffic forecast by GAN constraint. Lastly, the proposed method is evaluated on two real-world traffic datasets, and the experimental results show that the proposed method outperforms baseline traffic prediction methods. [ABSTRACT FROM AUTHOR]