Graphical Features Research Articles

Graphical Features & Perceptions of Reliability

This study examines the impact of graphical features on perceived reliability and user trust in automated systems. Participants viewed 60 static graphs showing system reliability over time, with variables such as maximum reliability, minimum reliability, average reliability, cumulative probability of success/failure, and slope. Each graph was presented with different success or failure rates. Participants rated the system’s reliability, predicted success rates, and willingness to rely on the system. Analysis revealed that perceived reliability was most influenced by minimum reliability when success was depicted and maximum reliability when failure was depicted. These findings suggest that user perceptions of reliability are complex and not solely dependent on the expected features of system performance, indicating a need for further research into the relationship between graphical representations and perceived reliability.

Contrastive Graph Pooling for Explainable Classification of Brain Networks.

Functional magnetic resonance imaging (fMRI) is a commonly used technique to measure neural activation. Its application has been particularly important in identifying underlying neurodegenerative conditions such as Parkinson's, Alzheimer's, and Autism. Recent analysis of fMRI data models the brain as a graph and extracts features by graph neural networks (GNNs). However, the unique characteristics of fMRI data require a special design of GNN. Tailoring GNN to generate effective and domain-explainable features remains challenging. In this paper, we propose a contrastive dual-attention block and a differentiable graph pooling method called ContrastPool to better utilize GNN for brain networks, meeting fMRI-specific requirements. We apply our method to 5 resting-state fMRI brain network datasets of 3 diseases and demonstrate its superiority over state-of-the-art baselines. Our case study confirms that the patterns extracted by our method match the domain knowledge in neuroscience literature, and disclose direct and interesting insights. Our contributions underscore the potential of ContrastPool for advancing the understanding of brain networks and neurodegenerative conditions. The source code is available at https://github.com/AngusMonroe/ContrastPool.

ER-GET: Emotion Recognition Based on Global ECG Trajectory.

In recent years, the recognition of human emotions based on electrocardiogram (ECG) signals has been considered a novel area of study among researchers. Despite the challenge of extracting latent emotion information from ECG signals, existing methods are able to recognize emotions by calculating the heart rate variability (HRV) features. However, such local features have drawbacks, as they do not provide a comprehensive description of ECG signals, leading to suboptimal recognition performance. For the first time, we propose a new strategy to extract hidden emotional information from the global ECG trajectory for emotion recognition. Specifically, a period of ECG signals is decomposed into sub-signals of different frequency bands through ensemble empirical mode decomposition (EEMD), and a series of multi-sequence trajectory graphs is constructed by orthogonally combining these sub-signals to extract latent emotional information. Additionally, to better utilize these graph features, a network has been designed that includes self-supervised graph representation learning and ensemble learning for classification. This approach surpasses recent notable works, achieving outstanding results, with an accuracy of 95.08% in arousal and 95.90% in valence detection. Additionally, this global feature is compared and discussed in relation to HRV features, with the intention of providing inspiration for subsequent research.

Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification.

Convolutional neural networks (CNNs) have been widely applied to hyperspectral image classification (HSIC). However, traditional convolutions can not effectively extract features for objects with irregular distributions. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies, but fixed graph structures and local perceptions limit their performances. To tackle these problems, in this article, different from previous approaches, we perform the superpixel generation on intermediate features during network training to adaptively produce homogeneous regions, obtain graph structures, and further generate spatial descriptors, which are served as graph nodes. Besides spatial objects, we also explore the graph relationships between channels by reasonably aggregating channels to generate spectral descriptors. The adjacent matrices in these graph convolutions are obtained by considering the relationships among all descriptors to realize global perceptions. By combining the extracted spatial and spectral graph features, we finally obtain a spectral-spatial graph reasoning network (SSGRN). The spatial and spectral parts of SSGRN are separately called spatial and spectral graph reasoning subnetworks. Comprehensive experiments on four public datasets demonstrate the competitiveness of the proposed methods compared with other state-of-the-art graph convolution-based approaches.

Link prediction for knowledge graphs based on extended relational graph attention networks

Limited by the sufficiency and timeliness of information obtained, the connections among entities of knowledge graphs need to be updated continuously. Therefore, how to infer the possibility of linking between two unlinked entities with known information has important significance in real applications. Most existing works implemented the triple-level graph learning, which focused on the learning of graph features among triples but ignore triple-inside information. In this article, an entity-relation-level graph attention network model is proposed to fully learn the information of entities and relationships in the graph. Firstly, for each entity, the information of entities in their surrounding neighborhoods is learnt, and then the obtained information with relations of entities is integrated into the graph attention network for embeddings. Secondly, a novel entity and relation embedding method is implemented to map each element of the triple into the vector space for achieving deep interactions between entities and relations. Thirdly, ConvKB is used as decoder to complete the task of link prediction. Extensive experiments on real datasets show the promising results of the proposed method.

Brain network analysis in Parkinson's disease patients based on graph theory

Development of Parkinson's disease causes functional impairment in the brain network of Parkinson's patients. The aim of this study is to analyze brain networks of people with Parkinson's disease based on higher resolution parcellations and newer graphical features. The topological features of brain networks were investigated in Parkinson's patients (19 individuals) compared to healthy individuals (17 individuals) using graph theory. In addition, four different methods were used in graph formation to detect linear and nonlinear relationships between functional magnetic resonance imaging (fMRI) signals. The functional connectivity between the left precuneus and the left amygdala, as well as between the vermis 1-2 and the left temporal lobe was evaluated for the healthy and the patient groups. The difference between the healthy and patient groups was evaluated by parametric t-test and nonparametric U-test. Based on the results, Parkinson's patients exhibited a noteworthy reduction in centrality criterion compared to healthy subjects. Moreover, alterations in the regional features of the brain network were evident. Applying centrality criteria and correlation coefficients revealed significant distinctions between healthy subjects and Parkinson's patients across various brain areas. The results obtained for topological features indicate changes in the functional brain network of Parkinson's patients. Finally, similar areas obtained by all three methods of graph formation in the evaluation of connectivity between paired regions in the brain network of Parkinson's patients increased the reliability of the results.

Video Multimodal Entity Linking via Multi-Perspective Enhanced Subgraph Contrastive Network

Video Multimodal Entity Linking (VMEL) is a task to link entities mentioned in videos to entities in multimodal knowledge bases. However, current entity linking methods primarily focus on text and image modalities, neglecting the significance of video modality. To address this challenge, we propose a novel framework called the multi-perspective enhanced Subgraph Contrastive Network (SCMEL) and construct a VMEL dataset named SceneMEL, based on tourism domain. We first integrate textual, auditory and visual modal contexts of videos to generate a comprehensive high-recall candidate entity set. Furthermore, a semantic-enhanced video description subgraph generation module is utilized to convert videos into a multimodal feature graph structure and perform subgraph sampling on the domain-specific knowledge graph. Lastly, we conduct contrastive learning on local perspectives (text, audio, visual) within the video subgraphs and the knowledge graph subgraphs, as well as global perspectives, to capture fine-grained semantic information about videos and entities. A series of experimental results on SceneMel demonstrate the effectiveness of the proposed approach.

Self-adaptive selection graph pooling based fault diagnosis method under few samples and noisy environment

Neural network (NN)-based methods are extensively used for intelligent fault diagnosis in industrial systems. Nevertheless, due to the limited availability of faulty samples and the presence of noise interference, most existing NN-based methods perform limited diagnosis performance. In response to these challenges, a self-adaptive selection graph pooling method is proposed. Firstly, graph encoders with sharing parameters are designed to extract local structure-feature information (SFI) of multiple sensor-wise sub-graphs. Then, the temporal continuity of the SFI is maintained through time-by-time concatenation, resulting in a global sensor graph and reducing the dependency on data volume from the perspective of adding prior knowledge. Subsequently, leveraging a self-adaptive node selection mechanism, the noise interference of redundant and noisy sensor-wise nodes in the graph is alleviated, allowing the networks to concentrate on the fault-attention nodes. Finally, the local max pooling and global mean pooling of the node-selection graph are incorporated in the readout module to get the multi-scale graph features, which serve as input to a multi-layer perceptron for fault diagnosis. Two experimental studies involving different mechanical and electrical systems demonstrate that the proposed method not only achieves superior diagnosis performance with limited data, but also maintains strong anti-interference ability in noisy environments. Additionally, it exhibits good interpretability through the proposed self-adaptive node selection mechanism and visualization methods.

MGNDTI: A Drug-Target Interaction Prediction Framework Based on Multimodal Representation Learning and the Gating Mechanism.

Drug-Target Interaction (DTI) prediction facilitates acceleration of drug discovery and promotes drug repositioning. Most existing deep learning-based DTI prediction methods can better extract discriminative features for drugs and proteins, but they rarely consider multimodal features of drugs. Moreover, learning the interaction representations between drugs and targets needs further exploration. Here, we proposed a simple M ulti-modal G ating N etwork for DTI prediction, MGNDTI, based on multimodal representation learning and the gating mechanism. MGNDTI first learns the sequence representations of drugs and targets using different retentive networks. Next, it extracts molecular graph features of drugs through a graph convolutional network. Subsequently, it devises a multimodal gating network to obtain the joint representations of drugs and targets. Finally, it builds a fully connected network for computing the interaction probability. MGNDTI was benchmarked against seven state-of-the-art DTI prediction models (CPI-GNN, TransformerCPI, MolTrans, BACPI, CPGL, GIFDTI, and FOTF-CPI) using four data sets (i.e., Human, C. elegans, BioSNAP, and BindingDB) under four different experimental settings. Through evaluation with AUROC, AUPRC, accuracy, F1 score, and MCC, MGNDTI significantly outperformed the above seven methods. MGNDTI is a powerful tool for DTI prediction, showcasing its superior robustness and generalization ability on diverse data sets and different experimental settings. It is freely available at https://github.com/plhhnu/MGNDTI.

ERT-GFAN: A multimodal drug–target interaction prediction model based on molecular biology and knowledge-enhanced attention mechanism

In drug discovery, precisely identifying drug–target interactions is crucial for finding new drugs and understanding drug mechanisms. Evolving drug/target heterogeneous data presents challenges in obtaining multimodal representation in drug–target prediction(DTI). To deal with this, we propose ‘ERT-GFAN’, a multimodal drug–target interaction prediction model inspired by molecular biology. Firstly, it integrates bio-inspired principles to obtain structure feature of drugs and targets using Extended Connectivity Fingerprints(ECFP). Simultaneously, the knowledge graph embedding model RotatE is employed to discover the interaction feature of drug–target pairs. Subsequently, Transformer is utilized to refine the contextual neighborhood features from the obtained structure feature and interaction features, and multi-modal high-dimensional fusion features of the three-modal information constructed. Finally, the final DTI prediction results are outputted by integrating the multimodal fusion features into a graphical high-dimensional fusion feature attention network (GFAN) using our innovative multimodal high-dimensional fusion feature attention. This multimodal approach offers a comprehensive understanding of drug–target interactions, addressing challenges in complex knowledge graphs. By combining structure feature, interaction feature, and contextual neighborhood features, ‘ERT-GFAN’ excels in predicting DTI. Empirical evaluations on three datasets demonstrate our method’s superior performance, with AUC of 0.9739, 0.9862, and 0.9667, AUPR of 0.9598, 0.9789, and 0.9750, and Mean Reciprocal Rank(MRR) of 0.7386, 0.7035, and 0.7133. Ablation studies show over a 5% improvement in predictive performance compared to baseline unimodal and bimodal models. These results, along with detailed case studies, highlight the efficacy and robustness of our approach.

A bivariate simultaneous pollutant forecasting approach by Unified Spectro-Spatial Graph Neural Network (USSGNN) and its application in prediction of O3 and NO2 for New Delhi, India

Declining urban air quality affects socioeconomic stability, public health, and ecosystems and is demanding attention of the administration to address environmental sustainability goals. Given the effects of ozone, a greenhouse gas, on local climate and health, this study introduces a Unified Spectro-Spatial Graph Neural Network (USS-GNN) designed for simultaneous 24-hour forecasting of ozone and its precursor, nitrogen-dioxide, while addressing their chemical interactions and spatiotemporal dynamics. This model exploits the graph structure of atmospheric dynamics and mines high-level spatial, spectral, and physical features from atmospheric data through a Dot Product Edge Attention mechanism and a location-aware graph feature rewiring technique. The proposed model is developed for Indian capital city New Delhi, utilizes hourly observations for the years 2021 and 2022 and achieved R2 values of 0.650 and 0.618, RMSE of 13.950 and 16.120 μg/m3, MAE of 10.730 and 12.930 μg/m3 for ozone and nitrogen-dioxide respectively, outperforming state-of-the-art models. The model’s forecast analysis identified error-prone areas, effects of local meteorology, and pollutant interdependencies. An ablation study further detailed the impacts of graph operations on forecasts. Moreover, this study promotes the utility of bivariate modeling frameworks in improving urban pollution monitoring and supporting sustainable city management through data-driven policy implementations.

AdpSTGCN: Adaptive spatial–temporal graph convolutional network for traffic forecasting

Traffic flow forecasting plays a crucial role in applications such as intelligent transportation systems. Despite significant research in this field, the current methods have limitations that hinder the realization of highly accurate predictions. Existing GCN-based approaches typically rely on a definite graph structure derived from a physical topology or learned from node features, which is insufficient for building intricate spatial relationships among nodes. To address this challenge, we propose an adaptive spatial–temporal graph convolutional network for traffic forecasting. Our approach exploits a multi-head attention mechanism to construct multi-view feature graphs. We then introduce an adaptive graph convolution method to dynamically aggregate and propagate information from both the topology graph and multi-view feature graphs, which are capable of capturing complex spatial correlations across diverse proximity ranges. Furthermore, we designed a cascaded structural framework that combines temporal information with node features using gated dilated causal convolution to ensure the integrated modeling of spatial–temporal dynamics in traffic flow. Experiments on real-world datasets demonstrate that our proposed method outperforms the current mainstream methods, achieving better performance in traffic flow forecasting. The code is available at https://github.com/dhxdla/AdpSTGCN.git.

A lightweight security defense algorithm for multimodal attack blocking in industrial control networks based on momentum enhanced feature graphs

AbstractAs the infrastructure of modern industry, the safe and stable operation of lightweight industrial control network is crucial for industrial production. Multi‐mode attack is a kind of highly customized and low resource consumption network attack method, which can target the specific vulnerabilities and configuration weaknesses of lightweight industrial control network. In order to improve the defense capability of industrial control network against multimodal attacks, a lightweight security defense algorithm based on momentum‐enhanced feature graph is proposed. The lightweight industrial control network operation mode is determined by abstract relationship, and the ontology structure of industrial control network multi‐mode attack is established; with reference to the ontology structure, the multi‐mode attack map of industrial control network is defined; the normal behavior and lightweight attack behavior are divided, and the convolutional network is used to enhance the characteristics of lightweight attack; and the momentum‐enhanced feature map technology is used to correspond to the enhancement process, and to block and defend against the multi‐mode attack of industrial control network. The results show that the studied algorithm can realize accurate prediction of attack behaviors with different attack behaviors as test objects, and ensure accurate blocking of all kinds of attack behaviors with better security defense effect.

Connectivity study on resting-state EEG between motor imagery BCI-literate and BCI-illiterate groups.

Although Motor Imagery-based Brain-Computer Interface (MI-BCI) holds significant potential, its practical application faces challenges such as BCI-illiteracy. To mitigate this issue, researchers have attempted to predict BCI-illiteracy by using the resting state, as this was found to be associated with BCI performance. As connectivity's significance in neuroscience has grown, BCI researchers have applied connectivity to it. However, the issues of connectivity have not been considered fully. First, although various connectivity metrics exist, only some have been used to predict BCI-illiteracy. This is problematic because each metric has a distinct hypothesis and perspective to estimate connectivity, resulting in different outcomes according to the metric. Second, the frequency range affects the connectivity estimation. In addition, it is still unknown whether each metric has its own optimal frequency range. Third, the way that estimating connectivity may vary depending upon the dataset has not been investigated. Meanwhile, we still do not know a great deal about how the resting state EEG network differs between BCI-literacy and -illiteracy. To address the issues above, we analysed three large public EEG datasets using three functional connectivity (FC) and three effective connectivity (EC) metrics by employing diverse graph theory measures. Our analysis revealed that the appropriate frequency range to predict BCI-illiteracy varies depending upon the metric. The alpha range was found to be suitable for the metrics of the frequency domain, while alpha + theta were found to be appropriate for Multivariate Granger Causality (MVGC). The difference in network efficiency between BCI-literate and -illiterate groups was constant regardless of the metrics and datasets used. Although we observed that BCI-literacy had stronger connectivity, no other significant constructional differences were found. Based upon our findings, we predicted MI-BCI performance for the entire dataset. We discovered that combining several graph features could improve the prediction's accuracy.

Boosting the performance of molecular property prediction via graph–text alignment and multi-granularity representation enhancement

Deep learning is playing an increasingly important role in accurate prediction of molecular properties. Prior to being processed by a deep learning model, a molecule is typically represented in the form of a text or a graph. While some methods attempt to integrate these two forms of molecular representations, the misalignment of graph and text embeddings presents a significant challenge to fuse two modalities. To solve this problem, we propose a method that aligns and fuses graph and text features in the embedding space by using contrastive loss and cross attentions. Additionally, we enhance the molecular representation by incorporating multi-granularity information of molecules on the levels of atoms, functional groups, and molecules. Extensive experiments show that our model outperforms state-of-the-art models in downstream tasks of molecular property prediction, achieving superior performance with less pretraining data. The source codes and data are available at https://github.com/zzr624663649/multimodal_molecular_property.

Effective Emotion Recognition by Learning Discriminative Graph Topologies in EEG Brain Networks.

Multichannel electroencephalogram (EEG) is an array signal that represents brain neural networks and can be applied to characterize information propagation patterns for different emotional states. To reveal these inherent spatial graph features and increase the stability of emotion recognition, we propose an effective emotion recognition model that performs multicategory emotion recognition with multiple emotion-related spatial network topology patterns (MESNPs) by learning discriminative graph topologies in EEG brain networks. To evaluate the performance of our proposed MESNP model, we conducted single-subject and multisubject four-class classification experiments on two public datasets, MAHNOB-HCI and DEAP. Compared with existing feature extraction methods, the MESNP model significantly enhances the multiclass emotional classification performance in the single-subject and multisubject conditions. To evaluate the online version of the proposed MESNP model, we designed an online emotion monitoring system. We recruited 14 participants to conduct the online emotion decoding experiments. The average online experimental accuracy of the 14 participants was 84.56%, indicating that our model can be applied in affective brain-computer interface (aBCI) systems. The offline and online experimental results demonstrate that the proposed MESNP model effectively captures discriminative graph topology patterns and significantly improves emotion classification performance. Moreover, the proposed MESNP model provides a new scheme for extracting features from strongly coupled array signals.

DRML-Ensemble: drug repurposing method based on feature construction of multi-layer ensemble.

Computational drug repurposing methods have been continuously developed in recent years to alleviate the high costs associated with drug development. As drug targets or the products of disease-related genes, proteins play an important role in drug repurposing. Although the potential has been demonstrated, heterogeneous graphs with proteins as independent nodes have yet to be studied, where extracting high-quality protein features from heterogeneous graphs poses a significant challenge. A novel drug repurposing model based on the feature construction of multi-layer ensemble (DRML-Ensemble) is proposed in this study. The performance of DRML-Ensemble, as evaluated on publicly available datasets, achieves an AUPR value of 0.93 and an AUROC value of 0.92, surpassing those of existing state-of-the-art methods. Additionally, DRML-Ensemble demonstrates its notable ability for drug repurposing in Alzheimer's disease. DRML-Ensemble is primarily composed of multiple layers of heterogeneous graph feature construction (HGFC). Each HGFC can extract protein features by leveraging the relationships between drugs, diseases, and proteins. These protein features are then utilized in subsequent layers to build drug and disease features, facilitating drug repurposing. By stacking multiple layers, optimal protein features can be obtained from the heterogeneous graph, consequently improving the accuracy of drug repurposing. However, an excessive· stacking of layers usually affect the model's training process, for example, causing problems such as overfitting; a multi-layer ensemble prediction module is designed to further improve the model's performance.

A knowledge graph algorithm enabled deep recommendation system.

Personalized learning resource recommendations may help resolve the difficulties of online education that include learning mazes and information overload. However, existing personalized learning resource recommendation algorithms have shortcomings such as low accuracy and low efficiency. This study proposes a deep recommendation system algorithm based on a knowledge graph (D-KGR) that includes four data processing units. These units are the recommendation unit (RS unit), the knowledge graph feature representation unit (KGE unit), the cross compression unit (CC unit), and the feature extraction unit (FE unit). This model integrates technologies including the knowledge graph, deep learning, neural network, and data mining. It introduces cross compression in the feature learning process of the knowledge graph and predicts user attributes. Multimodal technology is used to optimize the process of project attribute processing; text type attributes, multivalued type attributes, and other type attributes are processed separately to reconstruct the knowledge graph. A convolutional neural network algorithm is introduced in the reconstruction process to optimize the data feature qualities. Experimental analysis was conducted from two aspects of algorithm efficiency and accuracy, and the particle swarm optimization, neural network, and knowledge graph algorithms were compared. Several tests showed that the deep recommendation system algorithm had obvious advantages when the number of learning resources and users exceeded 1,000. It has the ability to integrate systems such as the particle swarm optimization iterative classification, neural network intelligent simulation, and low resource consumption. It can quickly process massive amounts of information data, reduce algorithm complexity and requires less time and had lower costs. Our algorithm also has better efficiency and accuracy.

Generation of Graphic Design Color Schemes Based on CMYK Color Model and Corrosion Algorithms

Graphic design colour schemes play a fundamental role in shaping the visual identity and impact of a design. This paper proposed an efficient Feature Extraction Madhami Fuzzy Clustering Probabilistic Corrosion (FEMFcPC) for the graphic design. The proposed FEMFcPC model comprises the CMYK color scheme for the estimation of the features in the images. With the estimation of the FEMFcPC model corrosion algorithm is implemented for the computation of the graphic design features. Once the features are estimated the related features for the graphic design are designed with the mamdhami fuzzy clustering model. The estimated features are clustered with the CMYK color schemes. The proposed FEMFcPC model estimates the patterns and relationships among graphic designs to provide valuable insights for design categorization and recommendation systems. A dataset comprising various graphic design examples with their corresponding CMYK color schemes is utilized for analysis. Through the application of the FEMFcPC algorithm, clustering results are obtained, revealing distinct grouping patterns and similarities among the designs. The simulation results stated that the proposed FEMFcPC model achieves a significant color scheme for the graphic design. Through the clustering process, the proposed FEMFcPC model with the values of the probabilistic features for the graphic design. The Key findings include the identification of dominant clusters, even distribution of designs across multiple clusters, detection of outliers, and assessment of cluster density. These insights offer significant implications for design categorization, recommendation systems, and targeted marketing strategies within the graphic design domain. The study contributes to advancing our understanding of graphic design analysis and provides a foundation for future research in this field.

Global-local manifold embedding broad graph convolutional network for hyperspectral image classification

Graph convolutional neural networks (GCNs) with domain-specific feature aggregation capabilities have unique advantages in hyperspectral image (HSI) classification. However, current GCN-based approaches frequently encounter the issue of node characteristics being over-smoothed while aggregating in higher-order domains. Furthermore, GCN linear classifiers focus solely on sample separability and ignore the potential manifold information of graph features, resulting in a failure to fully investigate extracted features. To address these problems, we propose a global-local manifold embedding broad graph convolutional network (GLMBG) for HSI classification. In GLMBG, we designed two modules from feature extraction and classification perspectives: The graph convolutional edge feature fusion extractor (GEFF) and the broad classifier of global-local manifold embedding (BGLME). GEFF is designed to learn graph node and local edge features from HSI through GCN and recursive filtering, combining them in a weighted manner to construct fused graph features. BGLME is designed to replace traditional linear classifiers with broad learning classifiers through manifold regularized embedding, fully utilizing the global and local manifold discriminant information of graph node features. The combination of GEFF and BGLME effectively reduces over-smoothing of graph node features while maximizing the utilization of manifold discriminant information, hence improving model feature discriminative ability. Experimental evaluations of three commonly used hyperspectral datasets show that our method surpasses state-of-the-art methods.