Optimal Graph Research Articles

Graph Convolutional Neural Network Based Malware Detection in IoT-Cloud Environment

Cybersecurity has become the most significant research area in the domain of the Internet of Things (IoT) owing to the ever-increasing number of cyberattacks. The rapid penetration of Android platforms in mobile devices has made the detection of malware attacks a challenging process. Furthermore, Android malware is increasing on a daily basis. So, precise malware detection analytical techniques need a large number of hardware resources that are significantly resource-limited for mobile devices. In this research article, an optimal Graph Convolutional Neural Network-based Malware Detection and classification (OGCNN-MDC) model is introduced for an IoT-cloud environment. The proposed OGCNN-MDC model aims to recognize and categorize malware occurrences in IoT-enabled cloud platforms. The presented OGCNN-MDC model has three stages in total, such as data pre-processing, malware detection and parameter tuning. To detect and classify the malware, the GCNN model is exploited in this work. In order to enhance the overall efficiency of the GCNN model, the Group Mean-based Optimizer (GMBO) algorithm is utilized to appropriately adjust the GCNN parameters, and this phenomenon shows the novelty of the current study. A widespread experimental analysis was conducted to establish the superiority of the proposed OGCNN-MDC model. A comprehensive comparison study was conducted, and the outcomes highlighted the supreme performance of the proposed OGCNN-MDC model over other recent approaches.

IRun: Horizontal and Vertical Shape of a Region-Based Graph Compression.

Graph data are pervasive worldwide, e.g., social networks, citation networks, and web graphs. A real-world graph can be huge and requires heavy computational and storage resources for processing. Various graph compression techniques have been presented to accelerate the processing time and utilize memory efficiently. SOTA approaches decompose a graph into fixed-size submatrices and compress it by applying the existing graph compression algorithm. This approach is promising if the input graph is dense. Otherwise, an optimal graph compression ratio cannot be achieved. Graphs such as those used by social networks exhibit a power-law distribution. Thus, applying compression to the fixed-size block of a matrix could lead to the empty cell processing of that matrix. In this paper, we solve the problem of ordered matrix compression on a deep level, dividing the block into sub-blocks to achieve the best compression ratio. We observe that the ordered matrix compression ratio could be improved by adopting variable-shape regions, considering both horizontal- and vertical-shaped regions. In our empirical evaluation, the proposed approach achieved a 93.8% compression ratio on average, compared with existing SOTA graph compression techniques.

FEATURES SELECTION FOR USE IN PREDICTIVE ANALYTICS MODELS OF REGIONS FOREIGN ECONOMIC ACTIVITY

The work is devoted to the actual problem of designing and selecting features in the tasks of constructing predictive models of indicators of foreign economic activity of regions. The aim of the work is to develop a methodology for the use of graph models and dimensionality reduction methods for the selection of features in the construction of predictive analytics models of foreign economic activity of regions. As an approach to describe the structure of foreign economic relations, graph models were used that implement the possibility of building on the basis of the UMAP dimension reduction algorithm. To build an optimal graph based on the UMAP algorithm, it is necessary to vary the number of nearest neighbors for each vertex and the minimum metric distance to establish a connection between the vertices. It is shown that the clique symmetry coefficient of the graph makes it possible to estimate the local connectivity of points in the constructed graph, forming a generalized idea of the network structure from the position of the presence of clusters in it. The Gini index of the graph allows us to assess the correspondence of the global structure of the graph to real networks. The selection of features is based on the analysis of the graph clicks, which provides maximum mutual information MI with a minimum of features, which maximally reduces distortions in describing the structure of regional foreign economic relations. The application of the described approach made it possible to eliminate the multicollinearity of features, to select indicators, to expand the possibilities of using the existing data set by including new indicators that introduce new useful information about the subject area into the model. The method of feature selection considered in the paper can be rationally used to construct interpreted predictive models of foreign economic activity indicators and as one of the ways to reduce the dimension of the model feature space. The results obtained allow us to conclude about the advantages of the considered approach to the implementation of the selection of features in the construction of predictive models of indicators of foreign economic activity of regions.

Evolution-Driven Randomized Graph Convolutional Networks

Randomized neural networks (NNs), such as random vector functional link (RVFL) and extreme learning machine (ELM), have been widely applied in various classification problems owing to their computational efficiency and universal approximation capability. However, such approaches are designed for regular Euclidean data and lack the ability to generalize to complex structured data. Moreover, their randomly generated parameters often lead to a suboptimal decision boundary with a growing requirement of hidden neurons. In this article, we first propose a plain framework, termed randomized graph convolutional networks (RGCNs), to generalize the classic randomized NNs to the non-Euclidean domain. Then, a hybrid framework called evolution-driven RGCN (EvoRGCN) is presented by using adaptive differential evolution with novelty search strategy to seek the globally optimal graph embedding for the plain RGCN. Finally, we recast the classic ELM and RVFL under the proposed frameworks, resulting in four novel semi-supervised models, including the plain models [i.e., graph convolutional extreme learning machines (GCELMs) and graph convolutional RVFL (GCRVFL)] and the optimized models (i.e., O-GCELM and O-GCRVFL). We show that our approaches are the natural generalization of the traditional randomized NNs in the non-Euclidean domain. Furthermore, our approaches not only retain the advantages of the classic approaches but also enable them to handle graph data. We compare our approaches against many existing methods across regular datasets and graph benchmarks, demonstrating that the proposed approaches dramatically outperform the compared methods with better generalization ability and robustness. Particularly, we quantitatively show the performance ranking of different randomized NNs, i.e., O-GCRVFL <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&gt; $ </tex-math></inline-formula> O-GCELM <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> GCRVFL <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&gt; $ </tex-math></inline-formula> GCELM <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> RVFL <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&gt; $ </tex-math></inline-formula> ELM.

Unboxing the graph: Towards interpretable graph neural networks for transport prediction through neural relational inference

Predicting the supply and demand of transport systems is vital for efficient traffic management, control, optimization, and planning. For example, predicting where from/to and when people intend to travel by taxi can support fleet managers in distributing resources; better predictions of traffic speeds/congestion allows for pro-active control measures or for users to better choose their paths. Making spatio-temporal predictions is known to be a hard task, but recently Graph Neural Networks (GNNs) have been widely applied on non-Euclidean spatial data. However, most GNN models require a predefined graph, and so far, researchers rely on heuristics to generate this graph for the model to use. In this paper, we use Neural Relational Inference to learn the optimal graph for the model. Our approach has several advantages: 1) a Variational Auto Encoder structure allows for the graph to be dynamically determined by the data, potentially changing through time; 2) the encoder structure allows the use of external data in the generation of the graph; 3) it is possible to place Bayesian priors on the generated graphs to encode domain knowledge. We conduct experiments on two datasets, namely the NYC Yellow Taxi and the PEMS-BAY road traffic datasets. In both datasets, we outperform benchmarks and show performance comparable to state-of-the-art. Furthermore, we do an in-depth analysis of the learned graphs, providing insights on what kinds of connections GNNs use for spatio-temporal predictions in the transport domain and how these connections can help interpretability.

In-season crop type identification using optimal feature knowledge graph

Early or in-season crop type mapping using remote sensing data is important for crop managements to maximize crop yield. Existing remote sensing-based approaches in the literature rely mainly on the timing and temporal frequency of satellite data acquisition during a growing season to obtain optimal identification feature (OIF) to complete crop mapping. At present, the optimal features for mapping crop types are commonly generated by using different feature selection methods, and thereby are not generic in nature. In this paper, a novel approach based on the OIF knowledge graph is proposed for identification of crop types within the crop growing season. The concept of OIF was proposed based on the one-class classification and optimization theory, which relates a specific crop type to its OIF. The OIF knowledge graph can be created to describe the seasonal trend of OIF in a season. Eventually, the OIF knowledge graphs can be incorporated into the moment-preserving segmentation method to automatically identify crop types within the growing season. To evaluate the performance of the new method, crop mapping was conducted using 2019 Sentinel-2 data in Heilongjiang province, China, and Illinois, USA, respectively. Results demonstrate that integrating the OIF knowledge graph and moment-preserving thresholding method is effective in identifying crop types without ground-truth data. The overall accuracy higher than 90 % (Kappa coefficient greater than 0.90), and the producer’s accuracies for corn, soybean, and rice are generally greater than 93 % in Heilongjiang province. The proposed approach has the advantage of simplifying crop identification process while maintaining a satisfactory identification accuracy in shorter time than conventional methods.

Prediction of state of health and remaining useful life of lithium-ion battery using graph convolutional network with dual attention mechanisms

Prediction of state-of-health and remaining useful life is crucial to the safety of lithium-ion batteries. Existing state-of-health and remaining useful life prediction methods are not effective in revealing the correlation among features. Establishing the correlation can help identify features with high similarities and aggregate them to improve the accuracy of predictive models. Moreover, existing methods, such as recurrent neural networks and long short-term memory, have limitations in state-of-health and remaining useful life predictions as they are not capable of using the most relevant part of time-series data to make predictions. To address these issues, a two-stage optimization model is introduced to construct an undirected graph with optimal graph entropy. Based on the graph, the graph convolutional networks with different attention mechanisms are developed to predict the state-of-health and remaining useful life of a battery, where the attention mechanisms enable the neural network to use the most relevant part of time series data to make predictions. Experimental results have shown that the proposed method can accurately predict the state-of-health and remaining useful life with a minimum root-mean-squared-error of 0.0104 and 5.80, respectively. The proposed method also outperforms existing data-driven methods, such as gradient-boosting decision trees, long short-term memory, and Gaussian process.

Activity Graph Based Convolutional Neural Network for Human Activity Recognition Using Acceleration and Gyroscope Data

Human activity recognition (HAR) using smartphone sensors have been recently studied in various applications including healthcare, fitness, and smart home. Their recognition accuracy often depends on high-quality feature design and effectiveness of classification algorithms, where existing work mostly replies on laborious hand-crafted design and shallow feature learning architecture. Recent deep learning techniques demonstrate outstanding effectiveness in performing automatic feature learning and outperform traditional models in terms of accuracy. But their performance is limited by the quality and volumes of available labelled data. It is challenging to achieve accurate multisubject HAR with only smartphone sensing data. This article proposes a novel optimal activity graph generation model incorporating a deep learning framework for automatic and accurate HAR with multiple subjects using only acceleration and gyroscope data. The activity graph generation model presents a multisensory integration mechanism with three-steps sorting algorithms for producing optimal activity graphs containing alignments of neighbored signals in their width and height. Then, we propose a deep convolutional neural network to automatically learn distinguishable features from the graphs for HAR. By leveraging superior presentation of correlations between human activities and neighbored signals alignments via optimal activity graphs, the learned features are endowed with more discriminative power. The experimental evaluation was carried out on several benchmark datasets (i.e., UCI, USCHAD, and UTD-MHAD). The results showed that our approach improved the average recognition accuracy by about 5% when compared with other state-of-the-art HAR methods. Particularly towards multisubject HAR cases (UTD-MHAD dataset with 21 subjects), it achieved up to 10% accuracy gain over other methods. These improvements show the advantage and potential of our method dealing with complex HAR problems with multiple subjects using limited sensing data.

Joint Feature Adaptation and Graph Adaptive Label Propagation for Cross-Subject Emotion Recognition From EEG Signals

Though Electroencephalogram (EEG) could objectively reflect emotional states of our human beings, its weak, non-stationary, and low signal-to-noise properties easily cause the individual differences. To enhance the universality of affective brain-computer interface systems, transfer learning has been widely used to alleviate the data distribution discrepancies among subjects. However, most of existing approaches focused mainly on the domain-invariant feature learning, which is not unified together with the recognition process. In this paper, we propose a joint feature adaptation and graph adaptive label propagation model (JAGP) for cross-subject emotion recognition from EEG signals, which seamlessly unifies the three components of domain-invariant feature learning, emotional state estimation and optimal graph learning together into a single objective. We conduct extensive experiments on two benchmark SEED_IV and SEED_V data sets and the results reveal that 1) the recognition performance is greatly improved, indicating the effectiveness of the triple unification mode; 2) the emotion metric of EEG samples are gradually optimized during model training, showing the necessity of optimal graph learning, and 3) the projection matrix-induced feature importance is obtained based on which the critical frequency bands and brain regions corresponding to subject-invariant features can be automatically identified, demonstrating the superiority of the learned shared subspace.

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.

Multi-view clustering with graph regularized optimal transport

For a multi-view learning task, it is crucial to assign appropriate weights to each view in order to learn complementary and consistent information across different views. In the field of multi-view clustering, most existing methods have been able to handle the weights of different views. However, these algorithms face the problem of unacceptable time complexity when dealing with large-scale datasets, and the learned similarity matrix fails to satisfy the graph regularization. In this paper, we propose an auto-weight learning method called multi-view clustering with graph regularized optimal transport. First, an anchor-based method is employed to overcome the problem of heavy time complexity when processing large-scale datasets, and it is able to automatically learn an appropriate weight for each view. Second, by introducing optimal transport we learn a regularized doubly-stochastic similarity matrix applicable to multi-view clustering tasks. Third, the optimal regularized anchor graph can be classified into specific clusters by adding a rank constraint. Finally, an effective optimization method is designed to optimize the formulated problem. Comprehensive experiments on multiple real-world datasets demonstrate that the proposed algorithm achieves superior performance to other state-of-the-arts algorithms.

Self-expressiveness property-induced structured optimal graph for unsupervised feature selection

Self-expressiveness property-induced structured optimal graph for unsupervised feature selection

Automatic Seizure Identification from EEG Signals Based on Brain Connectivity Learning.

Epilepsy is a neurological disorder caused by brain dysfunction, which could cause uncontrolled behavior, loss of consciousness and other hazards. Electroencephalography (EEG) is an indispensable auxiliary tool for clinical diagnosis. Great progress has been made by current seizure identification methods. However, the performance of the methods on different patients varies a lot. In order to deal with this problem, we propose an automatic seizure identification method based on brain connectivity learning. The connectivity of different brain regions is modeled by a graph. Different from the manually defined graph structure, our method can extract the optimal graph structure and EEG features in an end-to-end manner. Combined with the popular graph attention neural network (GAT), this method achieves high performance and stability on different patients from the CHB-MIT dataset. The average values of accuracy, sensitivity, specificity, F1-score and AUC of the proposed model are 98.90%, 98.33%, 98.48%, 97.72% and 98.54%, respectively. The standard deviations of the above five indicators are 0.0049, 0.0125, 0.0116 and 0.0094, respectively. Compared with the existing seizure identification methods, the stability of the proposed model is improved by 78-95%.

Wireless ultraviolet cooperative unmanned aerial vehicle formation communication link maintenance method.

A stable formation communication network can improve the task efficiency of a unmanned aerial vehicle (UAV) cluster. Aiming at the topology construction of the UAV formation communication network, combined with the optimal rigid graph theory, we design a three-dimensional UAV formation communication network generation algorithm based on the optimal rigid graph. We construct a new link weight function by introducing node residual energy and communication path loss to reduce the overall energy consumption of formation. Aiming at the problem that the communication link of the UAV is interrupted when the formation network is moving, a UAV communication beam tracking and holding method based on a multiple-input multiple-output (MIMO) structure and position prediction is designed. Simulation results show that the network topology constructed by the UAV formation communication network generation algorithm has a good average node degree, and effectively improves the network connectivity and communication fault tolerance. Compared with the tracking and holding algorithm based on the received signal strength, the beam tracking and holding algorithm significantly reduces the number of link interruptions, and the communication success holding rate can be basically maintained at about 90%.

Improved Belief Propagation List Decoding for Polar Codes

Polar codes have become the channel coding scheme for control channel of enhanced mobile broadband in the 5G communication systems. Belief propagation (BP) decoding of polar codes has advantages of low decoding latency and high parallelism but achieves worse bit error ratio (BER) performance compared with the successive cancellation list (SCL) decoding scheme. In this paper, an improved BP list (IBPL) decoding algorithm is proposed with comparable BER performance to SCL algoritm. Firstly, the optimal permuted factor graph is analyzed for polar codes, which improves the performance of the BP decoder without path extension. Furthermore, based on the optimal graph, the bit metric and decoding path metric are proposed to extend and prune the decoding path. The proposed IBPL decoder is focused on not only the permutation of polar codes but also the reliabilities of decoded codewords during each iteration of BP decoding, which has a more accurate decoding path list. The simulation results show that the proposed IBPL decoder improves the BER performance compared with the original BP decoder significantly, and can approach the performance of the SCL decoder at low signal to noise ratio regions.

LGLNN: Label Guided Graph Learning-Neural Network for few-shot learning

Graph Neural Networks (GNNs) have been employed for few-shot learning (FSL) tasks. The aim of GNN based FSL is to transform the few-shot learning problem into a graph node classification or edge labeling tasks, which can thus fully explore the relationships among samples in support and query sets. However, existing works generally consider the graph learned by node features which ignore the initial pairwise label constraints and thus are generally not guaranteed to be optimal for FSL tasks. Also, existing works generally learn graph edges independently based on node’s own features which lack of considering the consistent relationships among different edges. To address these issues, we propose a novel Label Guided Graph Learning-Neural network (LGLNN) model for FSL tasks. The aim of LGLNN is to incorporate the label information to learn an optimal metric graph for GNN by employing the pairwise constraint propagation. The main advantage of LGLNN is that it can learn the metrics (both similarity and dissimilarity) for each graph edge by aggregating the metric information from its neighboring edges and thus can conduct metric learning of all edges cooperatively and consistently. Experimental results demonstrate the effectiveness and better performance of the proposed LGLNN method.

Experience of planning and support of 3D seismic exploration on the example of a deposit in the South Torgay basin

The modern development of seismic fieldwork technologies and data processing and interpretation techniques make it possible to obtain high-quality material not only for studying structural features, but also for in-depth analysis of rock anisotropy: a detailed understanding of the spatial heterogeneity of lithological and petrophysical properties, predicting the nature of fluid saturation, analyzing finely disjunctive tectonics, fracture density and propagation geometry.&#x0D; Quality control at all stages of the field seismic survey and processing is also important. It is necessary to understand that quality control consists in direct participation in the work process from the beginning of seismic survey planning to obtaining the final result and interpretation.&#x0D; This article discusses the importance of full technical support for seismic exploration from planning and design of field work for solving the geological problems, to choosing the optimal processing graph, the results of which have a significant effect on structural and dynamic interpretation. On the example of the South Torgay Basin field, the detailed design of seismic surveys, the use of the latest fieldwork and data processing technologies made it possible to obtain more complete geological and geophysical information. As a result of the work carried out, in 2021, all wells drilled on the basis of the new seismic survey obtained an industrial inflow of hydrocarbons.

OHGCNet: Optimal feature selection-based hybrid graph convolutional network model for joint DR-DME classification

Diabetic retinopathy (DR) is the crucial eye disease, which effects the blood vessels of the patient suffering with diabetes. The Diabetic macular edema (DME) is another crucial disease, that arises when DR reaches and damages the macula, resulting in fluid buildup in the retina. Individual, and joint screening methods of these DME, and DR require experts to manually analyze color eye fundus images. However, developing an efficient screening-oriented therapy is a time-consuming and costly endeavor because of the difficult nature of the screening approach and a scarcity of qualified human resources. In addition, automated systems are attempting to deal with these issues, and standard machine learning and deep learning processes have failed to fulfil the required criterion of performance and accuracy. Thus, this article focuses on the implementation of graph learning-based graph convolutional network (GCN) for the classification of joint DR-DME with enhanced accuracy. Initially, hybrid GCN (HGCN) with relation aware channel-spatial attention (RACSA) model is developed for extracting the deep features of individual DME, DR, and joint DR-DME. Further, a novel bio-optimization approach named modified deer hunting optimization algorithm (MDHOA) is employed as an optimal feature selection technique for the extraction of salient features. Finally, HGCN is utilized as a classifier for the classification of individual DME, DR, and joint DR-DME diseases. The extensive simulations conducted on IDRiD dataset shows that proposed OHGCNet performed superior as compared to the conventional methods with the improvement in classification accuracy as 5.11%, 3.88%, and 5.47% for DME, DR, and joint DR-DME. Furthermore, the performance of proposed OHGCNet also compared with the ISBI-sub challenge 2 and resulted in superior position as compared with leadership contenders.

Complex carotid artery segmentation in multi-contrast MR sequences by improved optimal surface graph cuts based on flow line learning.

Carotid atherosclerosis is one of the leading causes of cardiovascular disease with high mortality. Multi-contrast MRI can identify atherosclerotic plaque components with high sensitivity and specificity. Accurate segmentation of the diseased carotid artery from MR images is very essential to quantitatively evaluate the state of atherosclerosis. However, due to the complex morphology of atherosclerosis plaques and the lack of well-annotated data, the segmentation of lumen and wall is very challenging. Different from popular deep learning methods, in this paper, we propose an integration segmentation framework by introducing a lightweight prediction model and improved optimal surface graph cuts (OSG), which adopts a simplified flow line sampling and post-reconstructing method to reduce the cost of graph construction. Moreover, a flexibly adaptive smoothing penalty is presented for maintaining the shape of diseased carotid surface. For the experiments, we have collected an MR image dataset from patients with carotid atherosclerosis and evaluated our method by cross-validation. It can reach 89.68%/80.29% of dice coefficients and 0.2480 mm/0.3396 mm of average surface distances on the lumen/wall segmentation, respectively. The experimental results show that our method can generate precise and reliable segmentation of both lumen and wall of diseased carotid artery with a quite small training cost.

Secure Online Fountain Codes With Low Complexity

In this letter, a scheme that achieves strong security using online fountain codes is proposed. By combining coset precoding, we minimize the number of leaked symbols of fountain codes to achieve strong security. We analyze the security performance of fountain codes using uni-partite graphs, and propose an optimal graph structure that achieves the smallest number of leaked symbols. Based on the optimal graph structure, we proposed a coding scheme called “Chain Buildup” and analyzed its expected number of leaked symbols. Simulation results show that our proposed scheme could achieve smaller number of leaked symbols compared to other security fountain codes. The proposed scheme also has smaller decoding overhead and lower complexity compared to conventional online fountain codes.