Adjacency Information Research Articles

Adjacency‐based, non‐intrusive reduced‐order modeling for fluid‐structure interactions

AbstractNon‐intrusive model reduction is a promising solution to system dynamics prediction, especially in cases where data are collected from experimental campaigns or proprietary software simulations. In this work, we present a method for non‐intrusive model reduction applied to Fluid‐Structure Interaction (FSI) problems. The approach is based on the a priori known sparsity of the full‐order system operators, which is dictated by grid adjacency information. In order to enforce this type of sparsity, we solve a “local”, regularized least‐squares problem for each degree of freedom on a grid, considering only the training data from adjacent degrees of freedom (DoFs), thus making computation and storage of the inferred full‐order operators feasible. After constructing the non‐intrusive, sparse full‐order model (FOM), Proper Orthogonal Decomposition (POD) is used for its projection to a reduced dimension subspace and thus the construction of a reduced‐order model (ROM). The methodology is applied to the challenging Hron‐Turek benchmark FSI3, for Re = 200. A physics‐informed, non‐intrusive ROM is constructed to predict the two‐way coupled dynamics of a solid with a deformable, slender tail, subject to an incompressible, laminar flow. Results considering the accuracy and predictive capabilities of the inferred reduced models are discussed.

GENII: A graph neural network-based model for citywide litter prediction leveraging crowdsensing data

Plastic litter and its associated environmental hazards have garnered global attention in recent years, highlighting the need for effective management. Improper handling of plastic litter can lead to environmental degradation, making it crucial to address this issue. In this paper, we propose an innovative approach to predict the spatial distribution and quantity of plastic litter at the city level by leveraging crowd-sensing data and designing a graph neural network-based model. Meteorological data is specifically used to enhance temporal correlation, while the spatial distribution of litter is clustered using the K-means method to capture spatial correlation. For each cluster, multiple graphs are constructed based on the points of interest (POIs) and litter distribution within the cluster. Graph attention neural networks and heterogeneous graph attention networks are then utilized to aggregate the adjacency information and overall structural information of these graphs, respectively. Finally, the litter prediction results are obtained through multiple fully connected layers. Real-world experiments convincingly demonstrate the high effectiveness of our proposed model in predicting city-wide litter, surpassing multiple comparative models. All the code and datasets can be accessed from the GitHub repository at https://github.com/ZJUDataIntelligence/Genii.

Spectral domain graph convolutional deep neural network for predicting unsteady and nonlinear flows

Mode decomposition methods, such as proper orthogonal decomposition and dynamic mode decomposition (DMD), have introduced a novel data-driven approach for flow prediction. These methods aim to identify a collection of modes that capture the essential flow features. Subsequently, the flow field data are projected onto these modes to reconstruct and predict the evolution of the flow field. However, due to their inherent linearity, mode decomposition methods are limited in effectively handling unsteady and nonlinear flow exhibiting significant nonlinearities. In this study, we propose a spectral graph convolutional deep neural network (SGC-DNN). It employs the eigenvectors of the Laplacian matrix as modes to fully utilize the adjacency information within the graph structure to solve flow on an unstructured grid better. Additionally, we employ a DNN (deep neural network) to model the temporal evolution of each mode, thereby enhancing the model's adaptability to nonlinear flow fields. To evaluate the performance of our proposed SGC-DNN, we compare its prediction results with those obtained using DMD and DNN for the flow around a cylinder on unstructured grids at various Reynolds numbers (ranging from 1000 to 500 000). We also compared the predictive results of these three models for flow with complex geometries, such as the Da Vinci pipeline flow and intracranial aneurysm blood flow. The comparative analysis demonstrates that SGC-DNN outperformed the other models, yielding lower L2 relative errors and higher R2 values. These outcomes highlight the superiority of SGC-DNN in accurately predicting unsteady and nonlinear flow characterized by graph structures.

The bipartite Laplacian matrix of a nonsingular tree

Abstract For a bipartite graph, the complete adjacency matrix is not necessary to display its adjacency information. In 1985, Godsil used a smaller size matrix to represent this, known as the bipartite adjacency matrix. Recently, the bipartite distance matrix of a tree with perfect matching was introduced as a concept similar to the bipartite adjacency matrix. It has been observed that these matrices are nonsingular, and a combinatorial formula for their determinants has been derived. In this article, we provide a combinatorial description of the inverse of the bipartite distance matrix and establish identities similar to some well-known identities. The study leads us to an unexpected generalization of the usual Laplacian matrix of a tree. This generalized Laplacian matrix, which we call the bipartite Laplacian matrix, is usually not symmetric, but it shares many properties with the usual Laplacian matrix. In addition, we study some of the fundamental properties of the bipartite Laplacian matrix and compare them with those of the usual Laplacian matrix.

Local Adaptive Image Filtering Based on Recursive Dilation Segmentation.

This paper introduces a simple but effective image filtering method, namely, local adaptive image filtering (LAIF), based on an image segmentation method, i.e., recursive dilation segmentation (RDS). The algorithm is motivated by the observation that for the pixel to be smoothed, only the similar pixels nearby are utilized to obtain the filtering result. Relying on this observation, similar pixels are partitioned by RDS before applying a locally adaptive filter to smooth the image. More specifically, by directly taking the spatial information between adjacent pixels into consideration in a recursive dilation way, RDS is firstly proposed to partition the guided image into several regions, so that the pixels belonging to the same segmentation region share a similar property. Then, guided by the iterative segmented results, the input image can be easily filtered via a local adaptive filtering technique, which smooths each pixel by selectively averaging its local similar pixels. It is worth mentioning that RDS makes full use of multiple integrated information including pixel intensity, hue information, and especially spatial adjacent information, leading to more robust filtering results. In addition, the application of LAIF in the remote sensing field has achieved outstanding results, specifically in areas such as image dehazing, denoising, enhancement, and edge preservation, among others. Experimental results show that the proposed LAIF can be successfully applied to various filtering-based tasks with favorable performance against state-of-the-art methods.

Time series imputation with GAN inversion and decay connection

Time series imputation is essential for real-world applications. Though the emergence of Generative Adversarial Networks (GANs) and Graph Convolution Networks (GCNs) provides more possibilities to improve imputation performance, how to achieve the optimal latent code and precisely model the properties of incomplete time series remain a challenge. In GAN-based methods, an effective latent code of incomplete time series is necessary for precise reconstruction. To acquire the optimal latent code, we introduce GAN inversion to invert the input to the latent space of a pretrained GAN. The inverted latent code contains rich properties of original observations and thus can better reconstruct the target sample. To model the temporal irregularity due to the presence of missing values, the decay connection is exploited to quantify the influence that dependencies between adjacent observations should decrease as the time lags between them increase. We incorporate the quantification into the adjacent matrix of the GCN to better aggregate adjacent information of incomplete time series. With the adoption of decay connection, the resulting latent code through GAN inversion can further produce faithful reconstruction. Quantitative and qualitative experiments conducted on several time series datasets show that our proposal achieves state-of-the-art or competitive imputation performance.

Fully distributed attack-resilient Nash equilibrium seeking for networked games subject to DoS attacks

This paper is concerned with distributed Nash equilibrium seeking problem for networked games that may suffer from denial-of-service (DoS) attacks. A node-based fully distributed resilient strategy for Nash equilibrium seeking is presented, where the control gains of each player can be adaptively tuned based on its local adjacent information. Then, under this strategy, the Nash equilibrium seeking can be achieved without involving any global information, provided that some conditions of DoS attacks duration can be satisfied. Moreover, an edge-based fully distributed resilient Nash equilibrium seeking strategy is presented, where an adaptive control gain is imposed on each communication link between neighbors. Finally, illustrative simulation case studies are conducted to validate the obtained results.

Research on Buffer Calculation Model of Critical Chain Based on Adjacency Information Entropy

In project network planning, the correlation complexity of the processes is not only related to the immediately preceding and following processes, but also closely related to indirect adjacent processes. In the existing relevant studies, many scholars have considered the influence of direct adjacent processes but ignored the influence of indirect adjacent processes. In addition, the three-point time estimation method and Monte Carlo simulation are mostly used in the current research for the estimation of process duration, while less research exists on the estimation of process optimal duration under multi-objective constraints. Therefore, this paper proposes a buffer calculation model of critical chain based on adjacency information entropy. This methodology provides comprehensive consideration of the relationship between cost, quality, safety, environment and process duration, the influence of process’s resource demand intensity, resource constraints and process duration on the buffer size, the influence of the relay potential of mutual cooperation and cross construction between processes, as well as the influence of adjacent complexity of processes on the project construction schedule. The calculation example analysis shows that this method can improve the accuracy of the calculation of process safety time, reduce the influence of the complexity of process adjacency correlation on the project construction schedule, reasonably control the buffer size, and effectively shorten the planned project duration.

Detection method of absence seizures based on Resnet and bidirectional GRU

BackgroundEpilepsy is a common chronic neurological disease. Its repeated seizure attacks have a great negative impact on patients’ physical and mental health. The diagnosis of epilepsy mainly depends on electroencephalogram (EEG) signals detection and analysis. There are two main EEG signals detection methods for epilepsy. One is the detection based on abnormal waveform, the other is the analysis of EEG signals based on the traditional machine learning. The feature extraction method of the traditional machine learning is difficult to capture the high-dimension information between adjacent sequences.MethodsIn this paper, redundant information was removed from the data by Gaussian filtering, downsampling, and short-time Fourier transform. Convolutional Neural Networks (CNN) was used to extract the high-dimensional features of the preprocessed data, and then Gate Recurrent Unit (GRU) was used to combine the sequence information before and after, to fully integrate the adjacent information EEG signals and improve the accuracy of the model detection.ResultsFour models were designed and compared. The experimental results showed that the prediction model based on deep residual network and bidirectional GRU had the best effect, and the test accuracy of the absence epilepsy test set reached 92%.ConclusionsThe prediction time of the network is only 10 sec when predicting four-hour EEG signals. It can be effectively used in EEG software to provide reference for doctors in EEG analysis and save doctors’ time, which has great practical value.

SimGRL: a simple self-supervised graph representation learning framework via triplets

Recently, graph contrastive learning (GCL) has achieved remarkable performance in graph representation learning. However, existing GCL methods usually follow a dual-channel encoder network (i.e., Siamese networks), which adds to the complexity of the network architecture. Additionally, these methods overly depend on varied data augmentation techniques, corrupting graph information. Furthermore, they are heavily reliant on large quantities of negative nodes for each object node, which requires tremendous memory costs. To address these issues, we propose a novel and simple graph representation learning framework, named SimGRL. Firstly, our proposed network architecture only contains one encoder based on a graph neural network instead of a dual-channel encoder, which simplifies the network architecture. Then we introduce a distributor to generate triplets to obtain the contrastive views between nodes and their neighbors, avoiding the need for data augmentations. Finally, we design a triplet loss based on adjacency information in graphs that utilizes only one negative node for each object node, reducing memory overhead significantly. Extensive experiments demonstrate that SimGRL achieves competitive performance on node classification and graph classification tasks, especially in terms of running time and memory overhead.

A Cluster-Based 3D Reconstruction System for Large-Scale Scenes

The reconstruction of realistic large-scale 3D scene models using aerial images or videos has significant applications in smart cities, surveying and mapping, the military and other fields. In the current state-of-the-art 3D-reconstruction pipeline, the massive scale of the scene and the enormous amount of input data are still considerable obstacles to the rapid reconstruction of large-scale 3D scene models. In this paper, we develop a professional system for large-scale 3D reconstruction. First, in the sparse point-cloud reconstruction stage, the computed matching relationships are used as the initial camera graph and divided into multiple subgraphs by a clustering algorithm. Multiple computational nodes execute the local structure-from-motion (SFM) technique, and local cameras are registered. Global camera alignment is achieved by integrating and optimizing all local camera poses. Second, in the dense point-cloud reconstruction stage, the adjacency information is decoupled from the pixel level by red-and-black checkerboard grid sampling. The optimal depth value is obtained using normalized cross-correlation (NCC). Additionally, during the mesh-reconstruction stage, feature-preserving mesh simplification, Laplace mesh-smoothing and mesh-detail-recovery methods are used to improve the quality of the mesh model. Finally, the above algorithms are integrated into our large-scale 3D-reconstruction system. Experiments show that the system can effectively improve the reconstruction speed of large-scale 3D scenes.

AFS-BERT: Information entropy-based adaptive fusion sampling and Bert embedding model for link prediction

Link prediction is an important problem in complex network analysis, which can discover missing or possible future edges in the network. In recent years, link prediction methods based on network representation learning have made progress. But there are two problems with these methods. One is that neighborhood-based node sampling methods cannot handle the situation between two nodes that do not have any common neighbors. The other is the Skip-Gram-based embedding model that represents nodes as static vectors, which cannot reflect the various meanings of nodes. To overcome these two limitations, this paper proposes a method called AFS-BERT (Information entropy based Adaptive Fusion Sampling and BERT embedding model). First, this method defines a centrality score based on adjacency information entropy, which reflects the global and local importance of nodes. Second, we propose a sampling method that adaptively fuses two different strategies using the centrality score. Finally, the BERT-based embedding model is used to realize the low-dimensional dynamic vector representation of nodes. Experimental result on six real-world network datasets shows that AFS-BERT has better performance. Compared with methods of the same type, AFS-BERT achieves upto 6.7% improvement.

Gait Transition to Spinning Gait and Fewer-Legged Walking for Hexapod Robot Based on FCP Gait Control

This paper proposes gait transition methods for hexapod robots based on Follow-the-Contact-Point (FCP) gait control. In the original FCP gait control, each leg contacts on the same position where the foreleg contacts. As the result, propagating the contact points from front to back, a robot walks forward. In this paper, we propose algorithms to change the direction of contact point propagation and the number of legs used for walking to switch the gait in FCP gait control. The propagation direction is governed by the adjacent information that determine legs with which exchange the contact point. Usage types of the legs manage the number of legs used for walking. By regulating the adjacent information and usage types of the legs, the robot can change its gait between forward and spinning gaits, and among four, five, and six-legged gaits. In addition, multiple local controls are installed in each leg to adjust the leg motion. Results of experiments show that the proposed method enables a hexapod robot to change its gait on rough terrain.

A Lightweight Segmented Attention Network for Sleep Staging by Fusing Local Characteristics and Adjacent Information.

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs.

DSCPL: A Deep Cloud Manufacturing Service Clustering Method Using Pseudo-Labels

Research on service clustering for manufacturing network by deep learning is an effective method for service discovery and service management in manufacturing industries. Manufacturing service clustering can be used to solve the problem of service selection and composition in cloud manufacturing. After clustering characteristics of graph data, this paper analyzes and studies the manufacturing network structure, and finds the network characteristics formed by clustering. A deep manufacturing cloud service clustering model using pseudo-labels (DSCPL) is proposed, which combines graph topology and node features to cluster nodes with similar attributes. The specific contributions of the paper are as follows: 1) Defining a parametric nonlinear map embedded the graph space containing graph structure (adjacency information) and node information (features) into a low-dimensional feature space. 2)Building an auxiliary target distribution to realize the self-learning mechanism in order to adapt to the clustering task, and 3) Realizing the unsupervised clustering method. Comprehensive experiments show that the clustering effect of this method is better than the current advanced deep clustering methods on public datasets and simulated datasets.

Rainfall pattern analysis in 24 East Asian megacities using a complex network

Abstract. Concurrent floods in multiple locations pose systemic risks to the interconnected economy in East Asia via supply chain disruptions. Despite these significant economic impacts, understanding of the interconnection between rainfall patterns in the region is still currently limited. Here, we analyzed the spatial dependence of the rainfall patterns of 24 megacities in the region using complex analysis theory and discussed the technique's applicability. Each city and rainfall similarity were represented by a node and a link, respectively. Vital-node identification and clustering analysis were conducted using adjacency information entropy and multiresolution community detection. The results of vital-node identification analysis show that high-ranking nodes are cities that are located near main vapor providers in East Asia. Using multiresolution community detection, the groups were clustered to reflect the spatial characteristics of the climate. In addition, the climate links between each group were identified using cross-mutual information considering the delay time for each group. We found a strong bond between Northeast China and the southern Indochinese Peninsula and verified that the links between each group originated from the summer climate characteristics of East Asia. The results of the study show that complex network analysis could be a valuable method for analyzing the spatial relationships between climate factors.

Classification of Malware Families Based on Efficient-Net and 1D-CNN Fusion

A malware family classification method based on Efficient-Net and 1D-CNN fusion is proposed. Given the problem that some local information of malware itself as one-dimensional data will be lost when the malware is imaged, the malware is converted into an image and one-dimensional vector and then input into two neural networks. The network of two-dimensional convolution architecture is used to extract the texture features of malware, and the one-dimensional convolution is used to extract the features of local adjacent information, the deep characteristics of different networks are fused, and the two networks are modified at the same time during backpropagation. This method not only extracts the texture features of malware but also saves the features of the malware itself as one-dimensional data, which shows better performance for multiple datasets.

Recommendation of Knowledge Graph Convolutional Networks Based on Multilayer BiLSTM and Self-Attention

To solve the problems of cold start, sparse data, and poor recommendation performance in collaborative filtering recommendation, an end-to-end framework algorithm based on BiLSTM and BAGCN was proposed. In order to discover the higher-order structural information in the knowledge graph, stacked BiLSTM is used to extract the features of embedded entities and relationships, respectively, and the depth dependence features of user-item interaction matrix are mined. The neighborhood representation of each entity is then calculated by sampling adjacent entities of a fixed size. Then, the self-attention mechanism is used to learn the semantic association between entities and neighboring entities to obtain the final neighborhood information. Aggregators are used to combine neighborhood information and bias information when computing node representations. By extending the sampling of adjacent entities to multihop simulation of higher-order adjacent information, users’ potential long-distance interests can be captured. Compared with the baseline model, the superiority of this method is verified.

Htex

We introduce per-halfedge texturing (Htex) a GPU-friendly method for texturing arbitrary polygon-meshes without an explicit parameterization. Htex builds upon the insight that halfedges encode an intrinsic triangulation for polygon meshes, where each halfedge spans a unique triangle with direct adjacency information. Rather than storing a separate texture per face of the input mesh as is done by previous parameterization-free texturing methods, Htex stores a square texture for each halfedge and its twin. We show that this simple change from face to halfedge induces two important properties for high performance parameterization-free texturing. First, Htex natively supports arbitrary polygons without requiring dedicated code for, e.g, non-quad faces. Second, Htex leads to a straightforward and efficient GPU implementation that uses only three texture-fetches per halfedge to produce continuous texturing across the entire mesh. We demonstrate the effectiveness of Htex by rendering production assets in real time.

Design of Travel Route Identification and Scheduling System Based on Artificial Intelligence-Aided Image Segmentation.

This study designs a travel recognition and scheduling system using artificial intelligence and image segmentation techniques. To address the problem of low division quality of current point division algorithms, this study proposes a streaming graph division model based on a sliding window (GraphWin), which dynamically adjusts the amount of information (vertex degree information and adjacency information) referenced at each division according to the current division quality and division time by introducing a sliding window mechanism, to achieve the highest possible division while allowing loss of certain division efficiency. The goal is to improve the division quality as much as possible while allowing a certain loss of division efficiency. To meet the user's need to travel through multiple destinations with the shortest route, this thesis proposes a deep reinforcement learning actor-critic (AC)-based multiobjective point path planning algorithm. The algorithm builds a strategy network and an evaluation network based on actor-critic's multiobjective point path planning, updates the strategy network and evaluation network parameters using AC optimization training, reduces the reliance of the algorithm model on a large amount of high-quality label data, and speeds up the convergence speed of the deep reinforcement learning algorithm by pretraining, finally completing the multiobjective point access sequential path planning task. Finally, the personalized travel recommendation system is designed and implemented, and the system performance analysis is conducted to clarify the system requirements in terms of functional and nonfunctional aspects: the system architecture, system functional modules, and database tables are designed to conduct use case testing of the main functional modules of the system, and the usability of the attraction recommendation algorithm is verified through the concrete implementation of the functional modules such as attraction recommendation in the system.