Journal articles: 'Network model'

1

HRABCAK, David, and Lubomir DOBOS. "THE CONCEPT OF MULTILAYERED NETWORK MODEL FOR 5G NETWORKS." Acta Electrotechnica et Informatica 19, no. 3 (December 4, 2019): 39–43. http://dx.doi.org/10.15546/aeei-2019-0022.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Koide, Satoshi, Hiroshi Ohno, Ryuta Terashima, Thanomsak Ajjanapanya, and Itti Rittaporn. "Hidden Markov Flow Network Model: A Generative Model for Dynamic Flow on a Network." International Journal of Machine Learning and Computing 4, no. 4 (2014): 319–27. http://dx.doi.org/10.7763/ijmlc.2014.v4.431.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Usui, Shohei, Fujio Toriumi, Masato Matsuo, Takatsugu Hirayama, and Kenji Mase. "Greedy Network Growth Model of Social Network Service." Journal of Advanced Computational Intelligence and Intelligent Informatics 18, no. 4 (July 20, 2014): 590–97. http://dx.doi.org/10.20965/jaciii.2014.p0590.

Full text

Abstract:

As new network communication tools are developed, social network services (SNS) such as Facebook and Twitter are becoming part of a social phenomenon globally impacting on society. Many researchers are therefore studying the structure of relationship networks among users. We propose a greedy network growth model that appropriately increases nodes and links while automatically reproducing the target network. We handle a wide range of networks with high expressive ability. Results of experiments showed that we accurately reproduced 92.4% of 189 target networks from real services. The model also enabled us to reproduce 30 networks built up by existing network models. We thus show that the proposed model represents the expressiveness of many existing network models.

APA, Harvard, Vancouver, ISO, and other styles

4

Murugan, S., and Dr M. Jeyakarthic. "Optimal Deep Neural Network based Classification Model for Intrusion Detection in Mobile Adhoc Networks." Journal of Advanced Research in Dynamical and Control Systems 11, no. 10-SPECIAL ISSUE (October 31, 2019): 1374–87. http://dx.doi.org/10.5373/jardcs/v11sp10/20192983.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Hrabcak, David, Lubomir Dobos, Jan Papaj, and Lubos Ovsenik. "Multilayered Network Model for Mobile Network Infrastructure Disruption." Sensors 20, no. 19 (September 25, 2020): 5491. http://dx.doi.org/10.3390/s20195491.

Full text

Abstract:

In this paper, the novel study of the multilayered network model for the disrupted infrastructure of the 5G mobile network is introduced. The aim of this study is to present the new way of incorporating different types of networks, such as Wireless Sensor Networks (WSN), Mobile Ad-Hoc Networks (MANET), and DRONET Networks into one fully functional multilayered network. The proposed multilayered network model also presents the resilient way to deal with infrastructure disruption due to different reasons, such as disaster scenarios or malicious actions. In the near future, new network technologies of 5G networks and the phenomenon known as the Internet of Things (IoT) will empower the functionality of different types of networks and interconnects them into one complex network. The proposed concept is oriented on resilient, smart city applications such as public safety and health and it is able to provide critical communication when fixed network infrastructure is destroyed by deploying smart sensors and unmanned aerial vehicles. The provided simulations shows that the proposed multilayered network concept is able to perform better than traditional WSN network in term of delivery time, average number of hops and data rate speed, when disruption scenario occurs.

APA, Harvard, Vancouver, ISO, and other styles

6

Pardo, Raúl, and Gerardo Schneider. "Model Checking Social Network Models." Electronic Proceedings in Theoretical Computer Science 256 (September 6, 2017): 238–52. http://dx.doi.org/10.4204/eptcs.256.17.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Scott, Gary M., and W. Harmon Ray. "Neural Network Process Models Based on Linear Model Structures." Neural Computation 6, no. 4 (July 1994): 718–38. http://dx.doi.org/10.1162/neco.1994.6.4.718.

Full text

Abstract:

The KBANN (Knowledge-Based Artificial Neural Networks) approach uses neural networks to refine knowledge that can be written in the form of simple propositional rules. This idea is extended by presenting the MANNIDENT (Multivariable Artificial Neural Network Identification) algorithm by which the mathematical equations of linear dynamic process models determine the topology and initial weights of a network, which is further trained using backpropagation. This method is applied to the task of modeling a nonisothermal chemical reactor in which a first-order exothermic reaction is occurring. This method produces statistically significant gains in accuracy over both a standard neural network approach and a linear model. Furthermore, using the approximate linear model to initialize the weights of the network produces statistically less variation in model fidelity. By structuring the neural network according to the approximate linear model, the model can be readily interpreted.

APA, Harvard, Vancouver, ISO, and other styles

8

Xu, Shuai, and Bai Da Zhang. "Complex Network Model and its Application." Advanced Materials Research 791-793 (September 2013): 1589–92. http://dx.doi.org/10.4028/www.scientific.net/amr.791-793.1589.

Full text

Abstract:

Human life is in a complex network world. In everyday life, the network can be a physical object such as the Internet, power network, road network and neural network; can also abstract not touch, such as interpersonal networks, networks of co-operation in scientific research, product supply chain network, biological populations, networks, etc.. The topology of these networks, the statistical characteristics and the formation mechanism, and so on, has a very important significance for the efficient allocation of resources, provides various functions, as well as the stability of the network, however, due to the complexity of these networks, conventional simplified model and cannot be good solution to the above problems. The complex network and network complexity has become a hot issue in the scientific and engineering concern. This article describes a few common complex network models and its application brief.

APA, Harvard, Vancouver, ISO, and other styles

9

Ouassit, Youssef. "CT Liver Segmentation: A Capsules Network Model." Journal of Advanced Research in Dynamical and Control Systems 12, SP4 (March 31, 2020): 1016–24. http://dx.doi.org/10.5373/jardcs/v12sp4/20201574.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Djellali, Choukri, and Mehdi adda. "An Enhanced Deep Learning Model to Network Attack Detection, by using Parameter Tuning, Hidden Markov Model and Neural Network." Journal of Ubiquitous Systems and Pervasive Networks 15, no. 01 (March 1, 2021): 35–41. http://dx.doi.org/10.5383/juspn.15.01.005.

Full text

Abstract:

In recent years, Deep Learning has become a critical success factor for Machine Learning. In the present study, we introduced a Deep Learning model to network attack detection, by using Hidden Markov Model and Artificial Neural Networks. We used a model aggregation technique to find a single consolidated Deep Learning model for better data fitting. The model selection technique is applied to optimize the bias-variance trade-off of the expected prediction. We demonstrate its ability to reduce the convergence, reach the optimal solution and obtain more cluttered decision boundaries. Experimental studies conducted on attack detection indicate that our proposed model outperformed existing Deep Learning models and gives an enhanced generalization.

APA, Harvard, Vancouver, ISO, and other styles

11

Venkatesh, Raghav, and Raja Muthalagu. "Network security prediction model using neural networks." Journal of Physics: Conference Series 1706 (December 2020): 012167. http://dx.doi.org/10.1088/1742-6596/1706/1/012167.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Christensen, Alexander P., and Hudson Golino. "Factor or Network Model? Predictions From Neural Networks." Journal of Behavioral Data Science 1, no. 1 (May 2021): 85–126. http://dx.doi.org/10.35566/jbds/v1n1/p5.

Full text

Abstract:

The nature of associations between variables is important for constructing theory about psychological phenomena. In the last decade, this topic has received renewed interest with the introduction of psychometric network models. In psychology, network models are often contrasted with latent variable (e.g., factor) models. Recent research has shown that differences between the two tend to be more substantive than statistical. One recently developed algorithm called the Loadings Comparison Test (LCT) was developed to predict whether data were generated from a factor or small-world network model. A significant limitation of the current LCT implementation is that it's based on heuristics that were derived from descriptive statistics. In the present study, we used artificial neural networks to replace these heuristics and develop a more robust and generalizable algorithm. We performed a Monte Carlo simulation study that compared neural networks to the original LCT algorithm as well as logistic regression models that were trained on the same data. We found that the neural networks performed as well as or better than both methods for predicting whether data were generated from a factor, small-world network, or random network model. Although the neural networks were trained on small-world networks, we show that they can reliably predict the data-generating model of random networks, demonstrating generalizability beyond the trained data. We echo the call for more formal theories about the relations between variables and discuss the role of the LCT in this process.

APA, Harvard, Vancouver, ISO, and other styles

13

Yang, Hong Mei, Chun Ying Zhang, Rui Tao Liang, and Fang Tian. "Set Pair Social Network Analysis Model." Applied Mechanics and Materials 50-51 (February 2011): 63–67. http://dx.doi.org/10.4028/www.scientific.net/amm.50-51.63.

Full text

Abstract:

Through the study on social network information, this paper explore that there exists the certain and uncertain phenomena in the process of finding the relationship between individuals by using social networks, and the social networks are constantly changing. In light of there are some uncertainty and dynamic problems for the network, this paper put forward the set pair social network analysis model and set pair social network analysis model and its properties.

APA, Harvard, Vancouver, ISO, and other styles

14

Xiao, Wen Hong, and Xiang Dong Cai. "A Novel Wireless Sensor Network Model Based on Complex Network Theory." Advanced Materials Research 546-547 (July 2012): 1276–82. http://dx.doi.org/10.4028/www.scientific.net/amr.546-547.1276.

Full text

Abstract:

The key issue of wireless sensor networks is to balance the energy costs of the entire network, to enhance the robustness of the entire sensor network. Sensor networks as a special kind of complex network, in particular, environmental constraints, and more from the traditional complex networks, such as Internet networks, ecological networks, social networks, is to introduce a way of wireless sensor networks way of complex networks theory and analytical method, the key lies in, which is a successful model of complex network theory and analysis methods, more suitable for the application of wireless sensor networks, in order to achieve certain characteristics of some wireless sensor networks to optimize the network. Considering multi-hop transmission of sensor network, this paper has proposed a maximum restriction on the communication radius of each sensor node; in order to improve the efficiency of energy consumption and maintain the sparsely of the entire network, this paper has also added a minimum restriction on the communication radius of each sensor node to the improved model; to balance the energy consumption of the entire network, The simulation results show that proposed improvements to the entire network more robust to random failure and energy costs are more balanced and reasonable. This is more applicable to wireless sensor networks.

APA, Harvard, Vancouver, ISO, and other styles

15

Fahd, Syed Muhammed. "Artificial Neural Network Model for Friction Stir Processing." International Journal of Engineering Research 3, no. 6 (June 1, 2014): 396–97. http://dx.doi.org/10.17950/ijer/v3s6/606.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

P., Tymoshchuk. "SIMPLIFIED PARALLEL SORTING DISCRETE-TIME NEURAL NETWORK MODEL." Computer systems and network 2, no. 1 (March 23, 2017): 94–101. http://dx.doi.org/10.23939/csn2020.01.094.

Full text

Abstract:

A model of parallel sorting neural network of discrete-time has been proposed. The model is described by system of difference equations and by step functions. The model is based on simplified neural circuit of discrete-time that identifies maximal/minimal values of input data and is described by difference equation and by step functions. A bound from above on a number of iterations required for reaching convergence of search process to steady state is determined. The model does not need a knowledge of change range of input data. In order to use the model a minimal difference between values of input data should be known. The network can process unknown input data with finite values, located in arbitrary unknown finite range. The network is characterized by moderate computational complexity and complexity of software implementation, any finite resolution of input data, speed,. Computing simulation results illustrating efficiency of the network are given. Keywords — Parallel sorting, neural network, difference equation, computational complexity, hardware implementation.

APA, Harvard, Vancouver, ISO, and other styles

17

Vakulenko, S., and M. Zimin. "An Analytically Tractable Model of Large Network." International Journal of Nanotechnology and Molecular Computation 2, no. 1 (January 2010): 1–12. http://dx.doi.org/10.4018/jnmc.2010010101.

Full text

Abstract:

This paper considers specially organized networks of large size. They can serve as models of computer communication systems, economical systems, neural and genetic networks. The topology of this network is simple and the analysis of the network behaviour is an analytically tractable task, while computer simulations are difficult. The authors show that such networks generate any structurally stable attractors in particular chaotic and periodic. They can simulate all Turing machines, that is, perform any computations. In noisy cases, the reliability of such network is exponentially high as a function of network size and has a maximum for an optimal network size.

APA, Harvard, Vancouver, ISO, and other styles

18

Bede, Zsuzsanna, Tamás Péter, and Ferenc Szauter. "Variable network model." IFAC Proceedings Volumes 46, no. 25 (2013): 173–77. http://dx.doi.org/10.3182/20130916-2-tr-4042.00026.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Moeller, Joe. "Noncommutative network models." Mathematical Structures in Computer Science 30, no. 1 (November 11, 2019): 14–32. http://dx.doi.org/10.1017/s0960129519000161.

Full text

Abstract:

AbstractNetwork models, which abstractly are given by lax symmetric monoidal functors, are used to construct operads for modeling and designing complex networks. Many common types of networks can be modeled with simple graphs with edges weighted by a monoid. A feature of the ordinary construction of network models is that it imposes commutativity relations between all edge components. Because of this, it cannot be used to model networks with bounded degree. In this paper, we construct the free network model on a given monoid, which can model networks with bounded degree. To do this, we generalize Green’s graph products of groups to pointed categories which are finitely complete and cocomplete.

APA, Harvard, Vancouver, ISO, and other styles

20

Yan, Yu-Wei, Yuan Jiang, Song-Qing Yang, Rong-Bin Yu, and Cheng Hong. "Network failure model based on time series." Acta Physica Sinica 71, no. 8 (2022): 088901. http://dx.doi.org/10.7498/aps.71.20212106.

Full text

Abstract:

With the development of network science, the static network has been unable to clearly characterize the dynamic process of the network. In real networks, the interaction between individuals evolves rapidly over time. This network model closely links time to interaction process. Compared with static networks, dynamic networks can clearly describe the interaction time of nodes, which has more practical significance. Therefore, how to better describe the behavior changes of networks after being attacked based on time series is an important problem in the existing cascade failure research. In order to better answer this question, a failure model based on time series is proposed in this paper. The model is constructed according to time, activation ratio, number of edges and connection probability. By randomly attacking nodes at a certain time, the effects of four parameters on sequential networks are analyzed. In order to validate the validity and scientificity of this failure model, we use small social networks in the United States. The experimental results show that the model is feasible. The model takes into account the time as well as the spreading dynamics and provides a reference for explaining the dynamic networks in reality.

APA, Harvard, Vancouver, ISO, and other styles

21

Liu, Fengqing, and Weiguang He. "Hose-model network virtualization in flexgrid optical networks." Journal of Optical Communications and Networking 12, no. 3 (January 27, 2020): 13. http://dx.doi.org/10.1364/jocn.374220.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Singh, Samayveer, Satish Chand, and Bijendra Kumar. "Multilevel heterogeneous network model for wireless sensor networks." Telecommunication Systems 64, no. 2 (May 25, 2016): 259–77. http://dx.doi.org/10.1007/s11235-016-0174-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Kabzeva, Aneta, Joachim Götze, and Paul Müller. "Model-Based Relationship Management for Service Networks." International Journal of Systems and Service-Oriented Engineering 5, no. 4 (October 2015): 104–32. http://dx.doi.org/10.4018/ijssoe.2015100105.

Full text

Abstract:

With the broad adoption of service-orientation for the realization of business applications and their provisioning and usage over cloud infrastructures, the topology of the resulting service networks is becoming extremely complex. Due to the composition of services for value-added business capabilities and the reusability of a service in multiple compositions, the execution of one service often depends on other services and changes in its provisioning can affect the health of large parts of the service network. The lack of insight on the relationships between the network components makes the management of the service network's health hard and error prone tasks. This article introduces a service network modeling approach for capturing the topology of a service network at design time. The approach considers the complete modeling process from representation, through collection, to analysis of the relationship information. The major contributions are a generic and adaptable modeling structure, a classification of service network entities and relationships, and a modular management framework automating the modeling process.

APA, Harvard, Vancouver, ISO, and other styles

24

Rak, Rafał, and Ewa Rak. "The Fractional Preferential Attachment Scale-Free Network Model." Entropy 22, no. 5 (April 29, 2020): 509. http://dx.doi.org/10.3390/e22050509.

Full text

Abstract:

Many networks generated by nature have two generic properties: they are formed in the process of preferential attachment and they are scale-free. Considering these features, by interfering with mechanism of the preferential attachment, we propose a generalisation of the Barabási–Albert model—the ’Fractional Preferential Attachment’ (FPA) scale-free network model—that generates networks with time-independent degree distributions p ( k ) ∼ k − γ with degree exponent 2 < γ ≤ 3 (where γ = 3 corresponds to the typical value of the BA model). In the FPA model, the element controlling the network properties is the f parameter, where f ∈ ( 0 , 1 ⟩ . Depending on the different values of f parameter, we study the statistical properties of the numerically generated networks. We investigate the topological properties of FPA networks such as degree distribution, degree correlation (network assortativity), clustering coefficient, average node degree, network diameter, average shortest path length and features of fractality. We compare the obtained values with the results for various synthetic and real-world networks. It is found that, depending on f, the FPA model generates networks with parameters similar to the real-world networks. Furthermore, it is shown that f parameter has a significant impact on, among others, degree distribution and degree correlation of generated networks. Therefore, the FPA scale-free network model can be an interesting alternative to existing network models. In addition, it turns out that, regardless of the value of f, FPA networks are not fractal.

APA, Harvard, Vancouver, ISO, and other styles

25

Gilles, Robert, Tabitha James, Reza Barkhi, and Dimitrios Diamantaras. "Simulating Social Network Formation." International Journal of Virtual Communities and Social Networking 1, no. 4 (October 2009): 1–20. http://dx.doi.org/10.4018/jvcsn.2009092201.

Full text

Abstract:

Social networks depict complex systems as graph theoretic models. The study of the formation of such systems (or networks) and the subsequent analysis of the network structures are of great interest. For information systems research and its impact on business practice, the ability to model and simulate a system of individuals interacting to achieve a certain socio-economic goal holds much promise for proper design and use of cyber networks. We use case-based decision theory to formulate a customizable model of information gathering in a social network. In this model, the agents in the network have limited awareness of the social network in which they operate and of the fixed, underlying payoff structure. Agents collect payoff information from neighbors within the prevailing social network, and they base their networking decisions on this information. Along with the introduction of the decision theoretic model, we developed software to simulate the formation of such networks in a customizable context to examine how the network structure can be influenced by the parameters that define social relationships. We present computational experiments that illustrate the growth and stability of the simulated social networks ensuing from the proposed model. The model and simulation illustrates how network structure influences agent behavior in a social network and how network structures, agent behavior, and agent decisions influence each other.

APA, Harvard, Vancouver, ISO, and other styles

26

Alaeddine, Hmidi, and Malek Jihene. "Deep Residual Network in Network." Computational Intelligence and Neuroscience 2021 (February 23, 2021): 1–9. http://dx.doi.org/10.1155/2021/6659083.

Full text

Abstract:

Deep network in network (DNIN) model is an efficient instance and an important extension of the convolutional neural network (CNN) consisting of alternating convolutional layers and pooling layers. In this model, a multilayer perceptron (MLP), a nonlinear function, is exploited to replace the linear filter for convolution. Increasing the depth of DNIN can also help improve classification accuracy while its formation becomes more difficult, learning time gets slower, and accuracy becomes saturated and then degrades. This paper presents a new deep residual network in network (DrNIN) model that represents a deeper model of DNIN. This model represents an interesting architecture for on-chip implementations on FPGAs. In fact, it can be applied to a variety of image recognition applications. This model has a homogeneous and multilength architecture with the hyperparameter “L” (“L” defines the model length). In this paper, we will apply the residual learning framework to DNIN and we will explicitly reformulate convolutional layers as residual learning functions to solve the vanishing gradient problem and facilitate and speed up the learning process. We will provide a comprehensive study showing that DrNIN models can gain accuracy from a significantly increased depth. On the CIFAR-10 dataset, we evaluate the proposed models with a depth of up to L = 5 DrMLPconv layers, 1.66x deeper than DNIN. The experimental results demonstrate the efficiency of the proposed method and its role in providing the model with a greater capacity to represent features and thus leading to better recognition performance.

APA, Harvard, Vancouver, ISO, and other styles

27

Zendehdel, Nadia. "A novel model for smart grid as a network of networks with hybrid composite cross layer description." Tehnicki vjesnik - Technical Gazette 22, no. 1 (2015): 133–43. http://dx.doi.org/10.17559/tv-20140228191043.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Dan Tian, Dan Tian, Yong-Jie Xu Dan Tian, Tong-Lei Qu Yong-Jie Xu, Rong-Guang Jia Tong-Lei Qu, Hao Zhang Rong-Guang Jia, and Wen-Jie Song Hao Zhang. "A Bayesian Network Model for Rough Estimations of Casualties by Strong Earthquakes in Emergency Mode." 電腦學刊 33, no. 6 (December 2022): 083–90. http://dx.doi.org/10.53106/199115992022123306007.

Full text

Abstract:

Rough estimations in emergency mode are now playing an important role in making key decisions for managing disasters including search and rescue. Most of the studies only paid attention to the earthquakes and ignored the presence of disaster chains and the hazard interactions in earthquakes. Bayesian Networks are ideal tools to explore the causal relationships between events, combine prior knowledge and observed data, and are integrated to solve uncertain problems. In such situations, we present improvements based on a Bayesian Network Model in approaches to estimations of casualties in earthquakes. According to the development of the earthquake disaster chain in literature, the proposed model extracts the key events of earthquakes, considers the hazard interactions, and constructs the Bayesian Networks based on a scenario-based method, to deal with the events in the earthquakes. In the model, lifeline system damages, fires, landslides, and debris flow have been integrated into the networks. The conditional probability tables are encoded by using the collected cases. Validations in the Netica allow the simulation of expected shaking intensity and estimation of the expected casualties by strong earthquakes in emergency mode. Compared to the literature, the method is closer to the fact in the rough estimations, providing important information for our response to earthquakes. Further, rough estimations are started when only seismic intensity or fewer earthquake source parameters are available.

APA, Harvard, Vancouver, ISO, and other styles

29

Novokhrestov, Aleksey, Anton Konev, and Alexander Shelupanov. "Model of Threats to Computer Network Software." Symmetry 11, no. 12 (December 11, 2019): 1506. http://dx.doi.org/10.3390/sym11121506.

Full text

Abstract:

This article highlights the issue of identifying information security threats to computer networks. The aim of the study is to increase the number of identified threats. Firstly, it was carried out the analysis of computer network models used to identify threats, as well as in approaches to building computer network threat models. The shortcomings that need to be corrected are highlighted. On the basis of the mathematical apparatus of attributive metagraphs, a computer network model is developed that allows to describe the software components of computer networks and all possible connections between them. On the basis of elementary operations on metagraphs, a model of threats to the security of computer network software is developed, which allows compiling lists of threats to the integrity and confidentiality of computer network software. These lists include more threats in comparison with the considered analogues.

APA, Harvard, Vancouver, ISO, and other styles

30

Jurenoks, Aleksejs, and Leonids Novickis. "Wireless sensor networks lifetime assessment model development." Environment. Technology. Resources. Proceedings of the International Scientific and Practical Conference 3 (June 16, 2015): 121. http://dx.doi.org/10.17770/etr2015vol3.508.

Full text

Abstract:

In the recent years low power computing systems have gained popularity. Networks, which use low power computer systems and transmitted data by using wireless connection are called wireless sensor networks, which main task is to get the information from sensors and transmission network. Nowadays, the most topical researches pertaining to wireless sensor networks are grounded on the new optimization of structure of network transmission protocol, the routing optimization in transmission network, optimization of network structure, as a result of which the life circle of wireless network sensors is possible to increase. In the present article the methodology for determining the life circle of network is discussed. The approaches in detection of life circle pertaining to the important network nodes are described.

APA, Harvard, Vancouver, ISO, and other styles

31

Jin, Xue-Guang, Guo-Chu Shou, Yi-Hong Hu, and Zhi-Gang Guo. "Service entity network virtualization architecture and model." Modern Physics Letters B 31, no. 19-21 (July 27, 2017): 1740095. http://dx.doi.org/10.1142/s0217984917400954.

Full text

Abstract:

Communication network can be treated as a complex network carrying a variety of services and service can be treated as a network composed of functional entities. There are growing interests in multiplex service entities where individual entity and link can be used for different services simultaneously. Entities and their relationships constitute a service entity network. In this paper, we introduced a service entity network virtualization architecture including service entity network hierarchical model, service entity network model, service implementation and deployment of service entity networks. Service entity network oriented multiplex planning model were also studied and many of these multiplex models were characterized by a significant multiplex of the links or entities in different service entity network. Service entity networks were mapped onto shared physical resources by dynamic resource allocation controller. The efficiency of the proposed architecture was illustrated in a simulation environment that allows for comparative performance evaluation. The results show that, compared to traditional networking architecture, this architecture has a better performance.

APA, Harvard, Vancouver, ISO, and other styles

32

Zhang, Hu, Jingjing Zhou, Ru Li, and Yue Fan. "Network representation learning method embedding linear and nonlinear network structures." Semantic Web 13, no. 3 (April 6, 2022): 511–26. http://dx.doi.org/10.3233/sw-212968.

Full text

Abstract:

With the rapid development of neural networks, much attention has been focused on network embedding for complex network data, which aims to learn low-dimensional embedding of nodes in the network and how to effectively apply learned network representations to various graph-based analytical tasks. Two typical models exist namely the shallow random walk network representation method and deep learning models such as graph convolution networks (GCNs). The former one can be used to capture the linear structure of the network using depth-first search (DFS) and width-first search (BFS), whereas Hierarchical GCN (HGCN) is an unsupervised graph embedding that can be used to describe the global nonlinear structure of the network via aggregating node information. However, the two existing kinds of models cannot simultaneously capture the nonlinear and linear structure information of nodes. Thus, the nodal characteristics of nonlinear and linear structures are explored in this paper, and an unsupervised representation method based on HGCN that joins learning of shallow and deep models is proposed. Experiments on node classification and dimension reduction visualization are carried out on citation, language, and traffic networks. The results show that, compared with the existing shallow network representation model and deep network model, the proposed model achieves better performances in terms of micro-F1, macro-F1 and accuracy scores.

APA, Harvard, Vancouver, ISO, and other styles

33

SERA, TAKAFUMI, and AKIRA TAKURA. "TASK GENERATION FOR DISTRIBUTED FUNCTIONAL MODEL." International Journal on Artificial Intelligence Tools 05, no. 03 (September 1996): 277–90. http://dx.doi.org/10.1142/s0218213096000183.

Full text

Abstract:

A new method is proposed to automatically generate the network control specifications necessary for executing services in a network from communications service specifications by using a knowledge of virtual resource that expresses logical functions in a network. Because these communication service specifications are described by observable terminal behaviors, the communication service specifications can be described without detailed knowledge of the network. The conventional stepwise description for network control specifications is manually performed for each network architecture. Then an expert, who has thorough knowledge of networks, must make a detailed design to comply with the requests of network architecture. Then an expert, who has thorough knowledge of internal networks, must make a detailed design to comply with the requests of network architecture. An expert can define in advance the relationship between a service state and a virtual resource and the relationship between a state transition of a virtual resource and task components and can store this knowledge in a database. Communications service specifications can be described without detailed knowledge of the network, and the network control specifications of the network can be derived from the communication service specifications.

APA, Harvard, Vancouver, ISO, and other styles

34

Zijlstra, Bonne J. H., Marijtje A. J. van Duijn, and Tom A. B. Snijders. "The Multilevel p2 Model." Methodology 2, no. 1 (January 2006): 42–47. http://dx.doi.org/10.1027/1614-2241.2.1.42.

Full text

Abstract:

The p 2 model is a random effects model with covariates for the analysis of binary directed social network data coming from a single observation of a social network. Here, a multilevel variant of the p 2 model is proposed for the case of multiple observations of social networks, for example, in a sample of schools. The multilevel p 2 model defines an identical p 2 model for each independent observation of the social network, where parameters are allowed to vary across the multiple networks. The multilevel p 2 model is estimated with a Bayesian Markov Chain Monte Carlo (MCMC) algorithm that was implemented in free software for the statistical analysis of complete social network data, called StOCNET. The new model is illustrated with a study on the received practical support by Dutch high school pupils of different ethnic backgrounds.

APA, Harvard, Vancouver, ISO, and other styles

35

B.Palpandi, B. Palpandi, Dr G. Geetharamani Dr. G.Geetharamani, and J. Arun Pandian. "Performance Enhancement in OSI Network Model using Fuzzy Queue." Indian Journal of Applied Research 4, no. 4 (October 1, 2011): 377–86. http://dx.doi.org/10.15373/2249555x/apr2014/116.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Bhatia, Varsha. "Applications of Hidden Markov Model in Wireless Sensor Network." International Journal of Psychosocial Rehabilitation 24, no. 4 (April 30, 2020): 6549–57. http://dx.doi.org/10.37200/ijpr/v24i4/pr2020465.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Bongulwar, Deepali M., and S. N. Talbar. "Robust Convolutional Neural Network Model For Recognition of Fruits." Indian Journal of Science and Technology 14, no. 45 (December 5, 2021): 3318–34. http://dx.doi.org/10.17485/ijst/v14i45.1493.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Zhang, Zhi-hua, En-ke Hou, and Xiao xia Luo. "Integration Method of Three-dimensional Complex Tunnel Network Model." International Journal of Engineering and Technology 3, no. 5 (2011): 533–39. http://dx.doi.org/10.7763/ijet.2011.v3.281.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Li, Ning, Qian Huang, Xiaoyu Ge, Miao He, Shuqin Cui, Penglin Huang, Shuairan Li, and Sai-Fu Fung. "A Review of the Research Progress of Social Network Structure." Complexity 2021 (January 7, 2021): 1–14. http://dx.doi.org/10.1155/2021/6692210.

Full text

Abstract:

Social network theory is an important paradigm of social structure research, which has been widely used in various fields of research. This paper reviews the development process and the latest progress of social network theory research and analyzes the research application of social network. In order to reveal the deep social structure, this paper analyzes the structure of social networks from three levels: microlevel, mesolevel, and macrolevel and reveals the origin, development, perfection, and latest achievements of complex network models. The regular graph model, P1 model, P2 model, exponential random graph model, small-world network model, and scale-free network model are introduced. In the end, the research on the social network structure is reviewed, and social support network and social discussion network are introduced, which are two important contents of social network research. At present, the research on social networks has been widely used in coauthor networks, citation networks, mobile social networks, enterprise knowledge management, and individual happiness, but there are few research studies on multilevel structure, dynamic research, complex network research, whole network research, and discussion network research. This provides space for future research on social networks.

APA, Harvard, Vancouver, ISO, and other styles

40

Li, Ning, Qian Huang, Xiaoyu Ge, Miao He, Shuqin Cui, Penglin Huang, Shuairan Li, and Sai-Fu Fung. "A Review of the Research Progress of Social Network Structure." Complexity 2021 (January 7, 2021): 1–14. http://dx.doi.org/10.1155/2021/6692210.

Full text

Abstract:

Social network theory is an important paradigm of social structure research, which has been widely used in various fields of research. This paper reviews the development process and the latest progress of social network theory research and analyzes the research application of social network. In order to reveal the deep social structure, this paper analyzes the structure of social networks from three levels: microlevel, mesolevel, and macrolevel and reveals the origin, development, perfection, and latest achievements of complex network models. The regular graph model, P1 model, P2 model, exponential random graph model, small-world network model, and scale-free network model are introduced. In the end, the research on the social network structure is reviewed, and social support network and social discussion network are introduced, which are two important contents of social network research. At present, the research on social networks has been widely used in coauthor networks, citation networks, mobile social networks, enterprise knowledge management, and individual happiness, but there are few research studies on multilevel structure, dynamic research, complex network research, whole network research, and discussion network research. This provides space for future research on social networks.

APA, Harvard, Vancouver, ISO, and other styles

41

Henrique, Humberto M., Enrique L. Lima, and Dale E. Seborg. "Model structure determination in neural network models." Chemical Engineering Science 55, no. 22 (November 2000): 5457–69. http://dx.doi.org/10.1016/s0009-2509(00)00170-6.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Wen, Hui, Tao Yan, Zhiqiang Liu, and Deli Chen. "Integrated neural network model with pre-RBF kernels." Science Progress 104, no. 3 (July 2021): 003685042110261. http://dx.doi.org/10.1177/00368504211026111.

Full text

Abstract:

To improve the network performance of radial basis function (RBF) and back-propagation (BP) networks on complex nonlinear problems, an integrated neural network model with pre-RBF kernels is proposed. The proposed method is based on the framework of a single optimized BP network and an RBF network. By integrating and connecting the RBF kernel mapping layer and BP neural network, the local features of a sample set can be effectively extracted to improve separability; subsequently, the connected BP network can be used to perform learning and classification in the kernel space. Experiments on an artificial dataset and three benchmark datasets show that the proposed model combines the advantages of RBF and BP networks, as well as improves the performances of the two networks. Finally, the effectiveness of the proposed method is verified.

APA, Harvard, Vancouver, ISO, and other styles

43

Kumari, Seema, and Dr M. U. Kharat. "Delay analysis of multihop wireless ad hoc network using queuing network model." INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY 10, no. 4 (August 15, 2013): 1503–9. http://dx.doi.org/10.24297/ijct.v10i4.3250.

Full text

Abstract:

Ad hoc wireless network is a self configurable infrastructure less network. The lack of infrastructure support in ad hoc networks makes them useful in various applications such as at the disaster site, highway, vast forest, battle field, oceans, etc. Since there is no centralized control in ad hoc network, each node can act as a source, a destination or a router. Ad hoc wireless networks therefore, experience congestion more than the wired networks, leading to jitter and high end to end delays even for moderate traffic which may lead to performance degradation. So it is crucial to analyze the factors which affect the capacity and end-to-end delay in wireless ad-hoc networks. In this paper a G/G/1queuing network model is proposed togain insights into the end-to-end delay in a multi hop wireless ad hoc networks. Queuing network model is unique as it providesclosed form expressions for average end-to-end delay in multihop wireless ad hoc networks. NS2 simulation is conducted in order to verifyÂ and compare the theoretical results.

APA, Harvard, Vancouver, ISO, and other styles

44

Treur, Jan. "On the applicability of Network-Oriented Modelling based on temporal-causal networks: why network models do not just model networks." Journal of Information and Telecommunication 1, no. 1 (January 2, 2017): 23–40. http://dx.doi.org/10.1080/24751839.2017.1295653.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Xia, Kelin, Kristopher Opron, and Guo-Wei Wei. "Multiscale Gaussian network model (mGNM) and multiscale anisotropic network model (mANM)." Journal of Chemical Physics 143, no. 20 (November 28, 2015): 204106. http://dx.doi.org/10.1063/1.4936132.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

JIN, Tian, and Haiyan JIN. "Network Delay Model for Overlay Network Application." International Journal of Communications, Network and System Sciences 02, no. 05 (2009): 400–406. http://dx.doi.org/10.4236/ijcns.2009.25045.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Kim, Pureun, and Byungnam Kahng. "Fractal Network in Protein Interaction Network Model." Journal of the Korean Physical Society 56, no. 3(1) (March 15, 2010): 1020–24. http://dx.doi.org/10.3938/jkps.56.1020.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Luu, Duc, Ee-Peng Lim, Tuan-Anh Hoang, and Freddy Chua. "Modeling Diffusion in Social Networks Using Network Properties." Proceedings of the International AAAI Conference on Web and Social Media 6, no. 1 (August 3, 2021): 218–25. http://dx.doi.org/10.1609/icwsm.v6i1.14259.

Full text

Abstract:

Diffusion of items occurs in social networks due to spreading of items through word of mouth and exogenous factors. These items may be news, products, videos, advertisements or contagious viruses. Previous research has studied diffusion process at both the macro and micro levels. The former models the number of item adopters in the diffusion process while the latter determines which individuals adopt item. In this paper, we establish a general probabilistic framework, which can be used to derive macro-level diffusion models, including the well known Bass Model (BM). Using this framework, we develop several other models considering the social network’s degree distribution coupled with the assumption of linear influence by neighboring adopters in the diffusion process. Through some evaluation on synthetic data, this paper shows that degree distribution actually changes during the diffusion process. We therefore introduce a multi-stage diffusion model to cope with variable degree distribution. By conducting experiments on both synthetic and real datasets, we show that our proposed diffusion models can recover the diffusion parameters from the observed diffusion data, which allows us to model diffusion with high accuracy.

APA, Harvard, Vancouver, ISO, and other styles

49

Liu, Yong Kui, Lin Zhang, Fei Tao, and Long Wang. "An Evolving Web Service Interaction Network Model." Applied Mechanics and Materials 610 (August 2014): 559–67. http://dx.doi.org/10.4028/www.scientific.net/amm.610.559.

Full text

Abstract:

With the rapid growth of Web services on the Internet, the atomic Web services as nodes and their functionality dependency relationships as edges form a complex Web service network. Various interactions between Web services can occur along the edges, such as collaboration, competition and substitution, etc. So far, however, there lack of an effective and scalable model for generating Web service interaction networks capturing the aforementioned types of interactions, which hinders the relevant researches such as development of new service composition algorithms and the investigation of evolution mechanisms of service networks. In this paper, we propose a model which is able to generate two types of Web service interaction networks, namely complementary Web service interaction network (CWSIN) and similar Web service interaction network (SWSIN). We show that CWSIN exhibits some of the typical characteristics reported in the previous empirical studies.

APA, Harvard, Vancouver, ISO, and other styles

50

Landro, Nicola, Ignazio Gallo, and Riccardo La Grassa. "Is One Teacher Model Enough to Transfer Knowledge to a Student Model?" Algorithms 14, no. 11 (November 15, 2021): 334. http://dx.doi.org/10.3390/a14110334.

Full text

Abstract:

Nowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance. In this paper, we designed a transfer learning methodology that combines the learned features of different teachers to a student network in an end-to-end model, improving the performance of the student network in classification tasks over different datasets. In addition to this, we tried to answer the following questions which are in any case directly related to the transfer learning problem addressed here. Is it possible to improve the performance of a small neural network by using the knowledge gained from a more powerful neural network? Can a deep neural network outperform the teacher using transfer learning? Experimental results suggest that neural networks can transfer their learning to student networks using our proposed architecture, designed to bring to light a new interesting approach for transfer learning techniques. Finally, we provide details of the code and the experimental settings.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Network model'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles