Adjacency Graph Research Articles

Exploring Adaptive Graph Topologies and Temporal Graph Networks for EEG-Based Depression Detection.

In recent years, Graph Neural Networks (GNNs) based on deep learning techniques have achieved promising results in EEG-based depression detection tasks but still have some limitations. Firstly, most existing GNN-based methods use pre-computed graph adjacency matrices, which ignore the differences in brain networks between individuals. Additionally, methods based on graph-structured data do not consider the temporal dependency information of brain networks. To address these issues, we propose a deep learning algorithm that explores adaptive graph topologies and temporal graph networks for EEG-based depression detection. Specifically, we designed an Adaptive Graph Topology Generation (AGTG) module that can adaptively model the real-time connectivity of the brain networks, revealing differences between individuals. In addition, we designed a Graph Convolutional Gated Recurrent Unit (GCGRU) module to capture the temporal dynamical changes of brain networks. To further explore the differential features between depressed and healthy individuals, we adopt Graph Topology-based Max-Pooling (GTMP) module to extract graph representation vectors accurately. We conduct a comparative analysis with several advanced algorithms on both public and our own datasets. The results reveal that our final model achieves the highest Area Under the Receiver Operating Characteristic Curve (AUROC) on both datasets, with values of 83% and 99%, respectively. Furthermore, we perform extensive validation experiments demonstrating our proposed method's effectiveness and advantages. Finally, we present a comprehensive discussion on the differences in brain networks between healthy and depressed individuals based on the outputs of our final model's AGTG and GTMP modules.

Sharp bounds on eigenvalues via spectral embedding based on signless Laplacians

Using spectral embedding based on the probabilistic signless Laplacian, we obtain bounds on the spectrum of transition matrices on graphs. As a consequence, we bound return probabilities and the uniform mixing time of simple random walk on graphs. In addition, spectral embedding is used in this article to bound the spectrum of graph adjacency matrices. Our method is adapted from Lyons and Oveis Gharan [13].

Structure of Poincaré plots revealed by their graph analysis and low pass filtering of the RRI time series

ObjectivesIn order to reveal their structure, Poincaré plots (PP) of electrocardiogram (ECG) RR intervals (RRI) were studied as linear edge planar directed graphs, obtained by connecting all their sequential points. We were also aimed at studying their graph complexity properties. MethodsRRI signals were subjected to a series of different window length (WL) Moving Average Low Pass (MALP) filters. For each filtered graph, four standard PP descriptors: Pearson’s coefficient, SD1, SD2, and SD2/SD1 were calculated, as well as four new graph complexity measures: mean angle between adjacent graph edges; mean number of edge crossings; directional complexity and directional entropy. This approach was applied to signals of twenty young healthy subjects, recorded in four experimental conditions – combination of two body postures (supine and standing) and two breathing regimes (spontaneous and slow 0.1 Hz). ResultsWe found that PP graphs consist of two superimposed components: one originating from Respiratory Sinus Arrhythmia (RSA) oscillations, the other from slow variations (SV) of the RRI time series. This result was further corroborated by observing the transformation of a PP cloud shape occurring in filtered graphs. When applied to subjects, the outcome was that three measures significantly differentiated the two breathing regimes in the RSA region of the WL domain, while four other measures were able to differentiate two body postures in the SV WL region. DiscussionAfter obtaining these results in healthy, we expect to successfully apply this approach to patients suffering from different pathological conditions.

Detection of Massive Oil Spills in Sun Glint Optical Imagery through Super-Pixel Segmentation

Large volumes of crude oil accidentally released into the sea may cause irreversible adverse impacts on marine and coastal environments. Large swath optical imagery, acquired using platforms such as the moderate-resolution imaging spectroradiometer (MODIS), is frequently used for massive oil spill detection, attributing to its large coverage and short global revisit, providing rich data for oil spill monitoring. The aim of this study was to develop a suitable approach for massive oil spill detection in sun glint optical imagery. Specifically, preprocessing procedures were conducted to mitigate the inhomogeneous light field over the spilled area caused by sun glint, enhance the target boundary contrast, and maintain the internal homogeneity within the target. The image was then segmented into super-pixels based on a simple linear clustering method with similar characteristics of color, brightness, and texture. The neighborhood super-pixels were merged into target objects through the region adjacency graph method based on the Euclidean distance of their colors with an adaptive termination threshold. Oil slicks from the generated bright/dark objects were discriminated through a decision tree with parameters based on spectral and spatial characteristics. The proposed approach was applied to oil spill detection in MODIS images acquired during the Montara oil spill in 2009, with an overall extraction precision of 0.8, recall of 0.838, and F1-score of 0.818. Such an approach is expected to provide timely and accurate oil spill detection for disaster emergency response and ecological impact assessment.

Quantitative Assessment of Resting-State Functional Connectivity MRI to Differentiate Amnestic Mild Cognitive Impairment, Late-Onset Alzheimer's Disease From Normal Subjects.

Alzheimer disease (AD) is a neurological disorder with brain network dysfunction. Investigation of the brain network functional connectivity (FC) alterations using resting-state functional MRI (rs-fMRI) can provide valuable information about the brain network pattern in early AD diagnosis. To quantitatively assess FC patterns of resting-state brain networks and graph theory metrics (GTMs) to identify potential features for differentiation of amnestic mild cognitive impairment (aMCI) and late-onset AD from normal. Prospective. A total of 14 normal, 16 aMCI, and 13 late-onset AD. A 3.0 T; rs-fMRI: single-shot 2D-EPI and T1-weighted structure: MPRAGE. By applying bivariate correlation coefficient and Fisher transformation on the time series of predefined ROIs' pairs, correlation coefficient matrixes and ROI-to-ROI connectivity (RRC) were extracted. By thresholding the RRC matrix (with a threshold of 0.15), a graph adjacency matrix was created to compute GTMs. Region of interest (ROI)-based analysis: parametric multivariable statistical analysis (PMSA) with a false discovery rate using (FDR)-corrected P< 0.05 cluster-level threshold together with posthoc uncorrected P< 0.05 connection-level threshold. Graph-theory analysis (GTA): P-FDR-corrected < 0.05. One-way ANOVA and Chi-square tests were used to compare clinical characteristics. PMSA differentiated AD from normal, with a significant decrease in FC of default mode, salience, dorsal attention, frontoparietal, language, visual, and cerebellar networks. Furthermore, significant increase in overall FC of visual and language networks was observed in aMCI compared to normal. GTA revealed a significant decrease in global-efficiency (28.05 < 45), local-efficiency (22.98 < 24.05), and betweenness-centrality (14.60 < 17.39) for AD against normal. Moreover, a significant increase in local-efficiency (33.46 > 24.05) and clustering-coefficient (25 > 20.18) were found in aMCI compared to normal. This study demonstrated resting-state FC potential as an indicator to differentiate AD, aMCI, and normal. GTA revealed brain integration and breakdown by providing concise and comprehensible statistics. 1 TECHNICAL EFFICACY: Stage 2.

MBD-Based Machining Feature Recognition and Process Route Optimization

Machining feature recognition is considered the key connecting technique to the integration of Computer-Aided Design (CAD) and Computer-Aided Process Planning (CAPP), and decision-making of the part processing scheme and the optimization of process route can effectively improve the processing efficiency and reduce the cost of product machining cost. At present, for the recognition of machining features in CAD models, there is a lack of a systematic method to consider process information (such as tolerance and roughness) and an effective process route optimization method to plan part processing procedures. Here we represent a novel model processing feature recognition method, and, on the basis of feature processing plan decision, realize the optimization of the process route. On the basis of a building model Attributed Adjacency Graph (AAG) based on model geometry, topology, and process information, we propose an AAG decomposition and reconstruction method based on Decomposed Base Surface (DBS) and Joint Base Surface (JBS) as well as the recognition of model machining features through Attributed Adjacency Matrix-based (AAM) feature matching. The feature machining scheme decision method based on fuzzy comprehensive evaluation is adopted, and the decision is realized by calculating the comprehensive evaluation index. Finally, the Machining Element Directed Graph (MEDGraph) is established based on the constraint relationship between Machining Elements (MEs). The improved topological sorting algorithm lists the topological sequences of all MEs. The evaluation function is constructed with the processing cost or efficiency as the optimization objective to obtain the optimal process route. Our research provides a new method for model machining feature recognition and process route optimization. Applications of the proposed approach are provided to validate the method by case study.

Adaptive graph convolutional clustering network with optimal probabilistic graph

The graph convolutional network (GCN)-based clustering approaches have achieved the impressive performance due to strong ability of exploiting the topological structure. The adjacency graph seriously affects the clustering performance, especially for non-graph data. Existing approaches usually conduct two independent steps, i.e., constructing a fixed graph structure and then graph embedding representation learning by GCN. However, the constructed graph structure may be unreliable one due to noisy data, resulting in sub-optimal graph embedding representation. In this paper, we propose an adaptive graph convolutional clustering network (AGCCN) to alternatively learn the similarity graph structure and node embedding representation in a unified framework. Our AGCCN learns the weighted adjacency graph adaptively from the node representations by solving the optimization problem of graph learning, in which adaptive and optimal neighbors for each sample are assigned with probabilistic way according to local connectivity. Then, the attribute feature extracted by parallel Auto-Encoder (AE) module is fused into the input of adaptive graph convolution module layer-by-layer to learn the comprehensive node embedding representation and strengthen its representation ability. This also skillfully alleviates the over-smoothing problem of GCN. To further improve the discriminant ability of node representation, a dual self-supervised clustering mechanism is designed to guide model optimization with pseudo-labels information. Extensive experimental results on various real-world datasets consistently show the superiority and effectiveness of the proposed deep graph clustering method.

GUBS: Graph-Based Unsupervised Brain Segmentation in MRI Images.

Brain segmentation in magnetic resonance imaging (MRI) images is the process of isolating the brain from non-brain tissues to simplify the further analysis, such as detecting pathology or calculating volumes. This paper proposes a Graph-based Unsupervised Brain Segmentation (GUBS) that processes 3D MRI images and segments them into brain, non-brain tissues, and backgrounds. GUBS first constructs an adjacency graph from a preprocessed MRI image, weights it by the difference between voxel intensities, and computes its minimum spanning tree (MST). It then uses domain knowledge about the different regions of MRIs to sample representative points from the brain, non-brain, and background regions of the MRI image. The adjacency graph nodes corresponding to sampled points in each region are identified and used as the terminal nodes for paths connecting the regions in the MST. GUBS then computes a subgraph of the MST by first removing the longest edge of the path connecting the terminal nodes in the brain and other regions, followed by removing the longest edge of the path connecting non-brain and background regions. This process results in three labeled, connected components, whose labels are used to segment the brain, non-brain tissues, and the background. GUBS was tested by segmenting 3D T1 weighted MRI images from three publicly available data sets. GUBS shows comparable results to the state-of-the-art methods in terms of performance. However, many competing methods rely on having labeled data available for training. Labeling is a time-intensive and costly process, and a big advantage of GUBS is that it does not require labels.

Sentiment interaction and multi-graph perception with graph convolutional networks for aspect-based sentiment analysis

Graph convolutional networks have been successfully applied to aspect-based sentiment analysis, due to their ability to flexibly capture syntactic information and word dependencies. However, most existing graph network-based models only consider the syntactic dependencies between specific aspects and contexts. These cannot capture the internal semantic correlations within aspect-specific phrases and ignore the sentiment interaction relations between different aspects of a sentence. In this paper, we propose a novel graph convolutional network with sentiment interaction and multi-graph perception for aspect-based sentiment analysis. The proposed model considers the complementarity of semantic dependencies and sentiment interactions simultaneously. Specifically, we generate four types of adjacency graphs by integrating the internal semantic correlations between aspect phrases and linking the sentiment interaction relations among different aspects. Adjacency graphs are used to construct graph convolutional neural networks to enrich aspect-centric dependencies and enhance the capability of context-awareness. In addition, we construct a multi-graph perception mechanism to capture the specific dependency information that cannot be captured between different graphs and hence reduce the amount of overlapping information. Experimental results on five publicly-available datasets demonstrate that our proposed model outperforms state-of-the-art methods and achieves the best performance in terms of accuracy and macro-F1 score.

Pruning graph neural networks by evaluating edge properties

The emergence of larger and deeper graph neural networks (GNNs) makes their training and inference increasingly expensive. Existing GNN pruning methods simultaneously prune the graph adjacency matrix and the model weights on a pretrained neural network by directly leveraging the lottery-ticket hypothesis, but the benefits of such methods are mainly via weight pruning, and methods based on saliency metrics struggle to outperform random pruning when pruning only the graph adjacency matrix. This motivates us to use different scoring standards for graph edges and network weights during GNN pruning. Thus, rather than measuring the importance of graph edges based on saliency metrics, we formulate the performance of GNNs mathematically with respect to the properties of their edges, elucidating how the performance drop can be avoided by pruning negative edges and nonbridges. This leads to our simple but effective two-step method for GNN pruning, leveraging the saliency metrics for the network pruning while sparsifying the graph with preservation of the loss performance. Experimental results show the effectiveness and efficiency of the proposed method on both small-scale graph datasets (Cora, Citeseer, and PubMed) and a large-scale dataset (Ogbn-ArXiv), where our method saves up to 98% of floating-point operations per second (FLOPs) on the small graphs and 94% of FLOPs on the large one, with no significant drop in accuracy.

China's oases have expanded by nearly 40% over the past 20 years

AbstractOases are supporters of biological, social, and economic activities in arid regions, which guides their prosperity or decay. Given that China has the largest oases area in the world, determining their evolution is of substantial importance for sustainable development and the ecological protection of these systems. Accordingly, the spatiotemporal evolution of China's oases between 2000 and 2020 was analyzed. This was based on the normalized difference vegetation index derived from moderate imaging spectroradiometer data, combined with superpixel image segmentation, the region adjacency graph merging method, and the genetic algorithm. The results were as follows. Between 2000 and 2020: (1) the oases in China expanded significantly from 207,812 to 289,751 km2; with a total increase of 39.43%; and the number of oases decreased from 135 to 93, which mainly occurred in micro and small oases; (2) the areas of oases in stable, expanding, and shrinking states accounted for 96.77%, 42.65%, and respectively 3.23% of the total oasis area in 2000. Oases have become more concentrated and continuously expanded; (3) the increase in glacial meltwater and precipitation caused by rising temperatures increased the availability of water resources in oases, which provides the substantial basis for expansion; and (4) the primary anthropogenic drivers of oasis expansion and stabilization regions were cultivation and construction, respectively.

On valency based topological properties of the starphene St[n,m,l] and fenestrene F[n,m]

In theoretical chemistry the quantitative parameters which are used to describe the atomic topology of graphs are termed as topological indices. Through these topological indices many physical and chemical characteristics such as melting point, entropy, energy generation and vaporisation enthalpy of chemical compounds can be predicted. The theory of graphs has a significant use in measuring the relationship of certain associated graphs with various topological indices. In this paper, we compute novel topological indices based on eV- and ve-degrees for starphene St [ n , m , l ] and fenestrene F [ n , m ] . A Maple-based algorithm is proposed for the calculation of ve and eV-degree based topological indices from the graph adjacency matrix.

Graph Construction for Traffic Prediction: A Data-Driven Approach

Graph learning-based algorithms are becoming the prevalent traffic prediction solutions due to their capability of exploiting non-Euclidean spatial-temporal traffic data correlation. However, current predictors primarily employ heuristically constructed static traffic graphs in forecasting, which may not describe the latent traffic dynamics well. Existing attempts on dynamically generated traffic graphs also face challenges like prolonged model training time and undermined model expressibility. In this paper, a novel data-driven graph construction scheme based on graph adjacency learning is proposed for graph learning-based traffic predictors. The proposed scheme explores inter-time-series dependency with the graph attention mechanism to embed the sensor correlation in a latent attention space, which determines the correlation of any possible sensor pairs for traffic graph construction. Comprehensive case studies on three real-world traffic datasets reveal that the proposed scheme outperforms state-of-the-art static and dynamic graph construction baselines. Additionally, time-varying and sparse graph construction schemes are devised and assessed to boost the efficacy, and a hyper-parameter test develops guidelines for parameter and model architecture selection.

Simplex closing probabilities in directed graphs

Recent work in mathematical neuroscience has calculated the directed graph homology of the directed simplicial complex given by the brain's sparse adjacency graph, the so called connectome. These biological connectomes show an abundance of both high-dimensional directed simplices and Betti-numbers in all viable dimensions – in contrast to Erdős–Rényi-graphs of comparable size and density. An analysis of synthetically trained connectomes reveals similar findings, raising questions about the graphs comparability and the nature of origin of the simplices.We present a new method capable of delivering insight into the emergence of simplices and thus simplicial abundance. Our approach allows to easily distinguish simplex-rich connectomes of different origin. The method relies on the novel concept of an almost-d-simplex, that is, a simplex missing exactly one edge, and consequently the almost-d-simplex closing probability by dimension. We also describe a fast algorithm to identify almost-d-simplices in a given graph. Applying this method to biological and artificial data allows us to identify a mechanism responsible for simplex emergence, and suggests this mechanism is responsible for the simplex signature of the excitatory subnetwork of a statistical reconstruction of the mouse primary visual cortex. Our highly optimized code for this new method is publicly available.

Learning latent local manifold embeddings for hyperspectral feature extraction

Hyperspectral images with an immense number of spectral bands provide abundant discriminant information for accurate land-cover classification in the remote sensing field. However, these narrow and adjacent bands contain a large amount of redundant information. Analyzing these images always requires a huge storage space with expensive computational costs. Furthermore, their high correlation coefficient would lead to the Hughes phenomenon, hindering the improvement of classification performance. We propose a linear semi-supervised hyperspectral feature extraction method L3ME to learn latent local manifold embeddings. Although labeled samples are beneficial to construct learning models, their number is always limited in real-world tasks. The motivation of this paper is to jointly enhance the contributions of labeled and unlabeled samples for learning local manifold structures of hyperspectral images. Features in labeled samples are extracted by two procedures, the adaptive patch alignment framework and integrated intraclass-interclass relationships, from different perspectives. The former aims to solve the problem of the uneven distribution of classes by introducing spectral angle based adaptive parameters. The latter aims to solve the problem of the uneven distribution of samples by constructing several adjacency graphs. The locality preserving projection is capable of preserving the local neighborhood structure of samples. A penalty for sparse regularization is cleverly integrated into the proposed linear discriminant objective function, which is optimized using a novel updating strategy. The convergence of L3ME is proved in detail and analyzed in this paper. Experiments on three typical hyperspectral datasets illustrate the effectiveness of the proposed method over some state-of-the-art techniques. The implementation of L3ME is available at https://github.com/biowby/L3ME.

CMSuG: Competitive mechanism-based superpixel generation method for image segmentation

During the last years, object-based image segmentation (OBIA) has seen a considerable increase in the image segmentation. OBIA is generally based on superpixel methods, in which the clustering-based method plays an increasingly important role. Most clustering methods for generating superpixels suffer from inaccurate classification points with inappropriate cluster centers. To solve the problem, we propose a competitive mechanism-based superpixel generation (CMSuG) method, which both accelerates convergence and promotes robustness for noise sensitivity. Then, image segmentation results will be obtained by a region adjacent graph (RAG)-based merging algorithm after constructing an RAG. However, high segmentation accuracy is customarily accompanied by expensive time-consuming costs. To improve computational efficiency, we address a parallel CMSuG algorithm, the time of which is much less than the CMSuG method. In addition, we present a parallel RAG method to decrease the expensive time-consuming cost in serial RAG construction. By leveraging parallel techniques, the running time of the whole image segmentation method decline with the time complexity from O (N) + O (K2) to O (N/K) or O (K2), in which N is the size of an input image and K is the given number of the superpixel. In the experiments, both nature image and remote sensing image segmentation results demonstrate that our CMSuG method outperforms the state-of-the-art superpixel generation methods, and then performs well for image segmentation in turn. Compared with the serial segmentation method, our parallel techniques gain more than four times acceleration in both remote sensing image dataset and nature image dataset.

Spatial-Spectral Constrained Adaptive Graph for Hyperspectral Image Clustering.

Hyperspectral image (HSI) clustering is a challenging task, whose purpose is to assign each pixel to a corresponding cluster. The high-dimensionality and noise corruption are two main problems that limit the performance of HSI clustering. To address those problems, this paper proposes a projected clustering with a spatial–spectral constrained adaptive graph (PCSSCAG) method for HSI clustering. PCSSCAG first constructs an adaptive adjacency graph to capture the accurate local geometric structure of HSI data adaptively. Then, a spatial–spectral constraint is employed to simultaneously explore the spatial and spectral information for reducing the negative influence on graph construction caused by noise. Finally, projection learning is integrated into the spatial–spectral constrained adaptive graph construction for reducing the redundancy and alleviating the computational cost. In addition, an alternating iteration algorithm is designed to solve the proposed model, and its computational complexity is theoretically analyzed. Experiments on two different scales of HSI datasets are conducted to evaluate the performance of PCSSCAG. The associated experimental results demonstrate the superiority of the proposed method for HSI clustering.

A novel graph neural networks approach for 3D product model retrieval

ABSTRACT With the quick development of intelligent manufacturing technology, increasing of 3D product models data resource raises the need for product models retrieval method that can fully exploit model information, whereas the existing methods only concern geometric information with little or no manufacturing information. Model-Based Definition (MBD) 3D engineering has gained wide popularity in recent times which enables smart manufacturing by attaching product manufacturing information. Its tip orientation to the effective reuse of MBD for reducing development time and creating an efficient digital thread. In this paper, we proposed the MBD-based attribute adjacency graph neural networks (MAAGNN) with attention mechanism. Firstly, the MBD-based attribute adjacency graph (MAAG) is established to fully express the product semantic information, which includes geometric and non-geometric information of the MBD model. Then graph neural network (GNN) is employed to embed the MAAG into continuous vector spaces, and attention mechanism is introduced to adaptively recognize more important features information, which can solve the ambiguity problem caused by blend features such as chamfer. Finally, the model is trained to achieve fast and accurate retrieval of the MBD models. Experiments demonstrate its potential advantages to meet the requirements of engineering applications.

Dual collaborative representation based discriminant projection for face recognition

Collaborative representation based techniques have shown promising results for face recognition; however, most of them code the samples by taking the overall samples as a dictionary, which may contain much noise information. To tackle this problem, a new face recognition algorithm, namely dual collaborative representation based discriminant projection (DCRDP), is proposed in this paper. In DCRDP, each training sample is reconstructed via dual collaborative representation to enhance the robustness to noise information: the first collaborative representation is used to choose an appropriate dictionary with respect to the training sample, while the second collaborative representation is used to find collaborative representation relationships between samples. After dual collaborative representation, DCRDP constructs two adjacency graphs to model the similarity and dissimilarity between samples, and then finds the optimal projection matrix for dimension reduction. Experiments on ExtYaleB, AR and CMU PIE face datasets verify the superiority of DCRDP to some other state-of-the-art approaches.

A novel reinforced dynamic graph convolutional network model with data imputation for network-wide traffic flow prediction

Traffic data missing issues due to unpredictable equipment failure, extreme weather, and other reasons have brought great challenges to traffic flow prediction modeling. In this paper, a novel reinforced dynamic graph convolutional network model is proposed to simultaneously conduct data imputation and network-wide traffic flow prediction. First, a multi-graph convolutional fusion network is proposed for data imputation by using the graph convolutional network to analyze the propagation law of traffic states between traffic flow detection stations in both time and space dimensions. Second, to enhance the robustness of network-wide traffic flow prediction, a dynamic graph learning method based on deep reinforcement learning is proposed to adaptively generate the graph adjacency matrix to represent the dynamic spatiotemporal dependencies between the stations. Finally, experimental results on two real-world traffic datasets show that the proposed method outperforms other baseline methods and can effectively extract the data missing features and spatiotemporal dependence features between the stations. The visualization results of the graph adjacency matrix indicate that the proposed method can effectively identify the influential traffic stations in the process of traffic flow prediction, and the extracted dependencies between the stations are interpretable. The proposed model has strong generalization in tackling network-wide traffic flow prediction tasks with different data missing rates and missing patterns, and can be extended to assist decision-makers in enhancing traffic management and mitigating traffic congestion.