Class Of Network Models Research Articles

PID Control for Synchronization of Complex Dynamical Networks With Directed Topologies.

Over the past decades, the synchronization of complex networks with directed topologies has received considerable attention owing to its extensive applications in the realistic world. Design of proportional-integral-derivative (PID) control protocols for achieving synchronization with directed networks is known to be a challenging task. The purpose of this paper is to establish a connection between the PID control protocols and synchronization of complex dynamical networks with directed topologies. Based on the classical complex network model, we investigate global synchronization with PD controller of a balanced strongly connected directed network and global synchronization with PI controller of a strongly connected directed network, and a directed network containing a spanning tree, respectively. Several sets of sufficient conditions are established under which the network reaches global synchronization. The simulation examples are presented to verify the efficiency of the theoretical results.

Analysis of clinical features of large-cell neuroendocrine carcinoma patients guided by chest CT image under deep learning

This work aimed to explore chest computed tomography (CT) image segmentation of patients with large-cell neuroendocrine carcinoma (LCNEC) based on deep learning, as well as the clinical manifestations and imaging and pathological features of LCNEC patients. Clinical data of 40 patients with LCNEC confirmed by pathological examination in the X Hospital from December 2015 to December 2017 were retrospectively selected. CT image data were segmented by TJ-1 model modified full convolutional neural network (FCNN) model. The accuracy and training time of TJ-1 FCNN model and classic deep learning segmentation network model AlexNet model were compared in terms of image segmentation. According to the image segmentation results by TJ-1 FCNN model, chest CT images of LCNEC patients, were reviewed, and the clinical manifestations, as well as the imaging and pathological features of the patients were reviewed, sorted, and summarized. The results showed that the image segmentation accuracy of TJ-1 network model (99.38%) was higher than that of AlexNet model. The iteration training time of TJ-1 network model for 30 times was 45 min, lower than that of AlexNet model (82 min). LCNEC was more likely to be found in elderly male with a long history of smoking. The clinical symptoms were cough, sputum, sputum blood, and chest pain with no significant specificity. CT imaging showed that peripheral mass was the most common manifestation (67.5%), both lungs were visible, the upper lobe was more likely with lesion (60%), the edge of the lesion was clear or smooth (57.5%), which was lobulated (70%). Under the light microscope, tumor cells were characterized by large volume, low nucleocytoplasmic ratio, high mitosis, and large area necrosis. The positive rates of immunohistochemical neuroendocrine markers were CD56 (62.5%), CgA (50%), and Syn (85%), among which Syn was with the highest positive rate. To sum up, LCNEC lacked clinical and radiological specificity manifestations, while chest CT image segmentation based on TJ-1 FCNN model can quickly mark the location of the lesion, providing technical support for the diagnosis and evaluation of LCNEC clinically.

Hd-ANM a Computationally Efficient, Highly Customizable and Comprehensive Elastic Network Model

The global motions of proteins, occurring in microseconds or slower times are a challenge to obtain. The best method to model these motions remains Molecular Dynamics (MD), which can be computationally intensive and prone to the error accumulations that requires multiple replicas. The Elastic Network Models have been used successfully to study proteins’ global motions more efficiently than with MD. However, the classical Elastic Network Model has some limitations. There have been recent improvements to the elastic network models such as curvilinear extrapolation NOLB and, more recently, Elastic Solid Networks. As an alternative we have developed the ‘hinge-domain Anisotropic Network Model’ (hd-ANM), a novel model that aims to be comprehensive, customizable, computationally efficient, and easy to use. This model not only has the capability of fusing classical the ANM, RTB, and NOLB approaches by changing a few parameters but also is a hybrid of these methods, which allows hd-ANM to incorporate the specific predicted hinges from our PACKMAN tool into the model to study the global motions; we know that hinges are the most common type of motion responsible for the global motions of proteins. This feature allows us to build better models while being computationally efficient because of including domain level coarse-graining, without losing agreement with the dynamics evident in multiple similar experimental structures. The demonstrated success of this method in terms of these conformational overlaps and the ability to simulate closed to open transitions in both directions, demonstrates that the that this protein packing based elastic network model is an excellent choice to study the global motions of the proteins more efficiently than MD to learn about protein mechanisms.

Research on Surface Defect Detection of Solar Pv Panels Based on Pre-Training Network and Feature Fusion

Aiming at the problems of the lack of sample size and the complexity of defect images in defect detection task, based on the idea of transfer learning and hierarchical feature fusion, this paper proposes a deep classification network model of improved vgg19 pre-training network by analyzing the basic principle of feature extraction of convolutional neural network and getting inspiration from feature pyramid network. Then, the model is trained by the small-scale defect images of solar pv panel. Finally, the solar pv panel data set containing four kinds of defects, including cracks, debris, broken gates and black areas, is selected to comprehensively verify the effectiveness of the improved network in the defect detection task. The experimental results show that the proposed method is superior to the classical vgg19 network model in four evaluation indexes, such as accuracy, precision, recall rate and F1 score.

Multi-Information Hybrid Network Spreading Model Based on Competition Consciousness

In fact, information is not transmitted in a single message, but rather multiple messages are transmitted simultaneously and interact with each other as they are transmitted. Based on this phenomenon, a multi-information overlay network model that differs from the traditional network structure is first constructed on the basis of two classical network models, BA scale-free and WS Small World. When multiple messages are transmitted simultaneously, the competitive nature of the message affects the transmission process to some extent, and therefore a sense of competition for the message is introduced into the classical SIS model of infectious disease. Simulation experiments have shown that a sense of competition enhances or inhibits the spread of information to varying degrees, and that information with a high sense of competition has a greater scale of spread, in line with the real-life “Matthew effect”. In addition, the sense of competition also accelerates the spread of information. Therefore, it is possible to inhibit the spread of negative information by controlling the sense of competition, so as to achieve timely warning and control of negative information.

Model and Analyze the Cascading Failure of Scale-Free Network Considering the Selective Forwarding Attack

Many real-world networks have scale-free characteristics and can be abstracted into scale-free networks. Aiming at the problem that scale-free networks have low fault tolerance in the face of malicious attacks, we focus on the selective forwarding attack behavior that exists widely in the networks, and build a selective forwarding attack model based on node importance. Moreover, according to the neighbor node's malicious and non-malicious behavior, a load redistribution strategy for failed node is proposed. Then, the network's damage degree is given to evaluate the comprehensive impact of cascading failure phenomenon on network connectivity and information integrity under selective forwarding attack. Finally, a cascading failure model of scale-free networks considering selective forwarding attack behavior is obtained. Based on this model, the propagation condition without triggering network cascading failure, the selective forwarding attack intensity threshold and the load loss ratio are obtained. By simulation on the classical BA scale-free network model, the results show that multiple nodes' random failure occurs in scale-free networks, selective forwarding attack behavior is helpful to improve the connectivity of the network. Besides, the network exists selective forwarding attack intensity threshold, when attack intensity is greater than the intensity threshold, the malicious nodes will not fail because of the failure of the neighbor nodes. But, selective forwarding attack behavior can destroy the information integrity, and there is a negative correlation between the attack intensity and the information integrity. These results have certain guiding significance for cascade failure analysis and prevention method research and design in real life.

MPGM: Scalable and Accurate Multiple Network Alignment.

Protein-protein interaction (PPI) network alignment is a canonical operation to transfer biological knowledge among species. The alignment of PPI-networks has many applications, such as the prediction of protein function, detection of conserved network motifs, and the reconstruction of species' phylogenetic relationships. A good multiple-network alignment (MNA), by considering the data related to several species, provides a deep understanding of biological networks and system-level cellular processes. With the massive amounts of available PPI data and the increasing number of known PPI networks, the problem of MNA is gaining more attention in the systems-biology studies. In this paper, we introduce a new scalable and accurate algorithm, called MPGM, for aligning multiple networks. The MPGM algorithm has two main steps: (i) SeedGeneration and (ii) MultiplePercolation. In the first step, to generate an initial set of seed tuples, the SeedGeneration algorithm uses only protein sequence similarities. In the second step, to align remaining unmatched nodes, the MultiplePercolation algorithm uses network structures and the seed tuples generated from the first step. We show that, with respect to different evaluation criteria, MPGM outperforms the other state-of-the-art algorithms. In addition, we guarantee the performance of MPGM under certain classes of network models. We introduce a sampling-based stochastic model for generating k correlated networks. We prove that for this model if a sufficient number of seed tuples are available, the MultiplePercolation algorithm correctly aligns almost all the nodes. Our theoretical results are supported by experimental evaluations over synthetic networks.

Network comparison and the within-ensemble graph distance

Quantifying the differences between networks is a challenging and ever-present problem in network science. In recent years, a multitude of diverse, ad hoc solutions to this problem have been introduced. Here, we propose that simple and well-understood ensembles of random networks—such as Erdős–Rényi graphs, random geometric graphs, Watts–Strogatz graphs, the configuration model and preferential attachment networks—are natural benchmarks for network comparison methods. Moreover, we show that the expected distance between two networks independently sampled from a generative model is a useful property that encapsulates many key features of that model. To illustrate our results, we calculate this within-ensemble graph distance and related quantities for classic network models (and several parameterizations thereof) using 20 distance measures commonly used to compare graphs. The within-ensemble graph distance provides a new framework for developers of graph distances to better understand their creations and for practitioners to better choose an appropriate tool for their particular task.

Automatic segmentation of prostate magnetic resonance imaging using generative adversarial networks

BackgroundAutomatic and detailed segmentation of the prostate using magnetic resonance imaging (MRI) plays an essential role in prostate imaging diagnosis. Traditionally, prostate gland was manually delineated by the clinician in a time-consuming process that requires professional experience of the observer. Thus, we proposed an automatic prostate segmentation method, called SegDGAN, which is based on a classic generative adversarial network model. Material and methodsThe proposed method comprises a fully convolutional generation network of densely con- nected blocks and a critic network with multi-scale feature extraction. In these computations, the objective function is optimized using mean absolute error and the Dice coefficient, leading to improved accuracy of segmentation results and correspondence with the ground truth. The common and similar medical image segmentation networks U-Net, FCN, and SegAN were selected for qualitative and quantitative comparisons with SegDGAN using a 220-patient dataset and the public datasets. The commonly used segmentation evaluation metrics DSC, VOE, ASD, and HD were used to compare the accuracy of segmentation between these methods. ResultsSegDGAN achieved the highest DSC value of 91.66%, the lowest VOE value of 15.28%, the lowest ASD values of 0.51 mm and the lowest HD value of 11.58 mm with the clinical dataset. In addition, the highest DSC value, and the lowest VOE, ASD and HD values obtained with the public data set PROMISE12 were 86.24%, 23.60%, 1.02 mm and 7.57 mm, respectively. ConclusionsOur experimental results show that the SegDGAN model have the potential to improve the accuracy of MRI-based prostate gland segmentation.Code has been made available at: https://github.com/w3user/SegDGAN

Data Augmentation Method for Switchgear Defect Samples Based on Wasserstein Generative Adversarial Network

The problem of sample imbalance will lead to poor generalization ability of the deep learning model algorithm, and the phenomenon of overfitting during network training, which limits the accuracy of intelligent fault diagnosis of switchgear equipment. In view of this, this paper proposes a data augmentation method for switchgear defect samples based on Wasserstein generative adversarial network with the partial discharge live detection data of the substation and the real-time switchgear partial discharge simulation experimental data. This method can improve the imbalanced distribution of data, and solve the problems such as the disappearance of gradients and model collapses in the classic generative adversarial network model, and greatly improve the stability of training. Verification through examples and comparison with traditional data augmentation methods. The results show that the data augmentation method mentioned in this paper can more effectively reduce the data imbalance, improve the performance of data-driven technology, and provide data support for subsequent fault diagnosis of switchgear equipment.

Effectiveness of the Strategies Implemented in Sri Lanka for Controlling the COVID-19 Outbreak

In order to bring the new coronavirus pandemic in the country under control, the government of Sri Lanka implemented a set of control strategies including social distancing, quarantine, lockdowns, travel restrictions, and isolation of villages. The aim of this study is to investigate the effectiveness of the overall control process with the aid of classical compartment models and network models. Our results indicate that the prevailing control strategies are effective with at least 50% contact rate reduction or with at least 40% isolation of the contact history of infected population.

Reliability analysis and optimization of computer communication network based on genetic algorithm

SummaryIn this paper, the design of reliable communication network is solved by genetic algorithm. In order to solve this problem, we must first provide the lowest acceptable network reliability. There are many methods to satisfy the network reliability constraints. The penalty function may produce an invalid solution, so it is not suitable to solve the problem. In order to overcome these difficulties, this paper proposes a heuristic repair method, which is based on the number of spanning trees in the graph. Compared with the heuristic maintenance method with lower cost, this method can generate a better solution with less computation. When the population size is 25, the hybridization rate is 0.96, and the mutation rate is 0.07, the best results can be obtained. This paper analyzes the node fault, grasps the influence rule of the fault on the network, and improves the network reliability. This paper summarizes and classifies the failure modes of communication network nodes. Combined with the classic BA network model in the complex network theory, through the simulation design of MATLAB and OPNET, the influence of node function failure and performance failure on network reliability is studied.

Long- and Short-Term Comparative Analysis of Renewable Energy Sources

Network working conditions are influenced noticeably by the connection of renewable energy sources to distribution networks. This becomes more and more important due to the increase in renewable energy source penetration over the last few years. This in turn can lead to a mass effect. As a result, the classical open network model with simple unidirectional direction of energy flow has been replaced with an active model that includes many local energy sources. This paper deals with the analysis of long- and short-term changes in power and energy generated by three types of renewable energy sources with similar rated power and which operate in the same region (i.e., located no more than tens of kilometers away). The obtained results can be a starting point for a broader evaluation of the influence of renewable energy sources on power quality in power systems, which can be both positive (supply reliability) and negative (voltage fluctuations and higher harmonics in current and voltage waveforms). It is important not only to correctly place but also to assure the diversity of such sources as it has been confirmed by the source variability coefficient. The long-term analysis allows us also to estimate the annual repeatability of energy production and, furthermore, the profitability of investment in renewable sources in a given region.

A Joint Convolutional Neural Network for Simultaneous Despeckling and Classification of SAR Targets

Deep learning (DL) techniques recently have attracted much attention in the synthetic aperture radar (SAR) automatic target recognition (ATR). Due to the coherent imaging pattern, SAR images inherently suffer from the speckle noise. To mitigate its influence, this letter proposes a joint convolutional neural network (J-CNN) for simultaneous despeckling and classification of SAR targets. It integrates a two-step process in the CNN framework but without the pooling operation during the despeckling phase. Then, a new loss function is introduced, and its partial derivatives with respect to weights are given for the training of J-CNN. Finally, comparative experiments with some classical network models are carried out based on synthetic SAR target images. The results demonstrate that the proposed method not only significantly outperforms other models under strong speckle noise condition but also has an efficient architecture with fewer weight parameters.

Asymptotic Degree Distributions in Large (Homogeneous) Random Networks: A Little Theory and a Counterexample

In random graph models, the degree distribution of an individual node should be distinguished from the (empirical) degree distribution of the graph that records the fractions of nodes with given degree. We introduce a general framework to explore when these two degree distributions coincide asymptotically in a sequence of homogeneous random networks of increasingly large size. The discussion is carried under three basic statistical assumptions on the degree sequence: (i) a weak form of distributional homogeneity; (ii) the existence of an asymptotic (nodal) degree distribution; and (iii) a weak form of asymptotic uncorrelatedness. It follows from the discussion that under (i)-(ii) the asymptotic equality of the two degree distributions occurs if and only if (iii) holds. We use this observation to show that the asymptotic equality may fail in some homogeneous random networks. The counterexample is found in the class of random threshold graphs with exponentially distributed fitness for which (i) and (ii) hold but where (iii) does not. An implication of this finding is that these random threshold graphs cannot be used as a substitute to the Barabási-Albert model for scale-free network modeling, as was proposed by some authors. Results can also be formulated for non-homogeneous models with the help of a random sampling procedure over the nodes. This approach is applicable to many classes of network models, including preferential attachment models and locally weak convergent sequence of random graphs.

Revisiting the power of reinsertion for optimal targets of network attack

Understanding and improving the robustness of networks has significant applications in various areas, such as bioinformatics, transportation, critical infrastructures, and social networks. Recently, there has been a large amount of work on network dismantling, which focuses on removing an optimal set of nodes to break the network into small components with sub-extensive sizes. However, in our experiments, we found these state-of-the-art methods, although seemingly different, utilize the same refinement technique, namely reinsertion, to improve the performance. Despite being mentioned with understatement, the technique essentially plays the key role in the final performance. Without reinsertion, the current best method would deteriorate worse than the simplest heuristic ones; while with reinsertion, even the random removal strategy achieves on par with the best results. As a consequence, we, for the first time, systematically revisit the power of reinsertion in network dismantling problems. We re-implemented and compared 10 heuristic and approximate competing methods on both synthetic networks generated by four classical network models, and 18 real-world networks which cover seven different domains with varying scales. The comprehensive ablation results show that: i) HBA (High Betweenness Adaption, no reinsertion) is the most effective network dismantling strategy, however, it can only be applicable in small scale networks; ii) HDA (High Degree Adaption, with reinsertion) achieves the best balance between effectiveness and efficiency; iii) The reinsertion techniques help improve the performance for most current methods; iv) The one, which adds back the node based on that it joins the clusters minimizing the multiply of both numbers and sizes, is the most effective reinsertion strategy for most methods. Our results can be a survey reference to help further understand the current methods and thereafter design the better ones.

A Generic Work Zone Evaluation Tool Driven by Macroscopic Traffic Simulation Model

This study proposed a generic work zone evaluation tool driven by a dynamic macroscopic traffic model. The tool can investigate the effects of a work zone on freeway conditions. The classical freeway traffic network model METANET was extended to better capture typical work zone characteristics in terms of speed and capacity reductions through modifying its speed-density relationship functions. The tool can present profiles of traffic state variables, system-level performance indices, and annotated traffic conditions maps. It was used to develop a prototype computer-aided decision support system and applied in two simulation-based case studies. Case studies show that it is effective and useful for understanding complicated work zone impacts and can aid in better design and assessment of work zone plans. It can be integrated in a dynamic transportation management system for better communication between road operator and travellers.

Evolutionary public goods game on the birandom geometric graph.

To investigate the evolution of cooperation in spatial public goods games, this paper establishes a birandom geometric graph, in which two types of nodes, representing players and public goods respectively, are placed at random locations in the unit square. Each public good has a limit influence range and the individuals that fall into the same range engage in a public good game. In contrast to the classical network models consisting of only one type of nodes, the birandom geometric graph provides a natural way to describe the scenarios where individuals and public resources are independent of each other. Numerical simulations reveal that cooperation can be significantly promoted when the group size and the average number of groups that each player participates in are relatively small, which is at odds with the results on the square lattice, but is consistent with a body of empirical evidence reported by Ostrom and Olson etal. Analysis of the evolutionary process suggests that the facilitation of cooperation is due primarily to the formation of the cooperative clusters, which can effectively resist the invasion of the defectors.

Channel Compression Optimization Oriented Bus Passenger Object Detection

Bus passenger flow information can facilitate scientific dispatching plans, which is essential to decision making and operation performance evaluation. Real-time acquisition of bus passenger flow information is an indispensable part for bus intellectualization. The method of passenger flow statistics in bus video monitoring scene based on deep convolution neural network can provide rich information for passenger flow statistics. In order to adapt to the real scenario of mobile and embedded devices on buses, and to consider the bandwidth limitation, this paper uses a lightweight network model M7, which is suitable for the vehicle system. Based on the classic network model tiny YOLO, the model is optimized by a depthwise separable convolution method. The optimized network model M7 reduces the number of parameters and improves the detection speed, while maintaining a low loss in detection accuracy. As such, the network model M7 is compressed and further optimized by removing redundant channels. The experimental results show that the detection speed of the network model target recognition after channel compression is 40%, which is faster than the precious channel compression on the premise of ensuring detection.

Ancient Mural Classification Method Based on Improved AlexNet Network

ABSTRACT As an important part of art and culture, ancient murals depict a variety of different artistic images, and these individual images have important research value. For research purposes, it is often important to first determine the type of objects represented in a painting. However, the mural painting environment makes datasets difficult to collect, and long-term exposure leads to underlying features that are not distinct, which makes this task challenging. This study proposes a convolutional neural network model based on the classic AlexNet network model and combines it with feature fusion to automatically classify ancient mural images. Due to the lack of large-scale mural datasets, the model first expands the dataset by applying image enhancement algorithms such as scaling, brightness conversion, noise addition, and flipping; then, it extracts the underlying features (such as fresco edges) shared by the first stage of a dual channel structure. Subsequently, a second-stage deep abstraction is conducted on the features extracted by the first stage using a two-channel network, each of which has a different structure. The obtained characteristics from both channels are merged, and a loss function is constructed to obtain the classification result. This approach improves the model's robustness and feature expression ability. The model achieves an accuracy of 84.24%, a recall rate of 84.15%, and an F1-measure of 84.13% when applied to a constructed mural image dataset. Compared with the AlexNet model and other improved convolutional neural network models, the proposed model improves each evaluation index by approximately 5%, verifying the rationality and effectiveness of the model for automatic mural image classification. The mural classification model proposed in this paper comprehensively considers the influences of network width and depth and can extract rich details from mural images from multiple local channels. An effective classification method could help researchers manage and protect mural images in an orderly fashion and quickly and effectively search for target images in a digital mural library based on a specified image category, aiding mural condition monitoring and restoration efforts as well as archaeological and art historical research.