• International Journal of Knowledge Content Development & Technology
• /
• v.8 no.4
• /
• pp.75-98
• /
• 2018

In this study, the network analysis of researchers, institutions, and research principal agent was conducted to understand structure characteristics of international cooperation research project implemented from 1997 to 2018. The network of researchers and institutions were decentralized structure. On the other hands, the network of research principal agent was centralized structure. The Soul National University is the leading organization of international cooperation research project. In terms of research principal agent, corporation is the leading principal agent. In additions, the results of the network centroid analysis of the researchers and institutions were correlated with the research funds. As a result, it was confirmed that the network centroid of research organization was linearly related to research funds.

• Journal of the Korean Society of Mechanical Technology
• /
• v.20 no.6
• /
• pp.776-782
• /
• 2018

After CNN basic structure was introduced by LeCun in 1989, there has not been a major structure change except for more deep network until recently. The deep network enhances the expression power due to improve the abstraction ability of the network, and can learn complex problems by increasing non linearity. However, the learning of a deep network means that it has vanishing gradient or longer learning time. In this study, we proposes a CNN structure with MLP layer. The proposed CNNs are superior to the general CNN in their classification performance. It is confirmed that classification accuracy is high due to include MLP layer which improves non linearity by experiment. In order to increase the performance without making a deep network, it is confirmed that the performance is improved by increasing the non linearity of the network.

• Journal of Navigation and Port Research
• /
• v.28 no.3
• /
• pp.221-225
• /
• 2004

This paper deals with a nonlinear system modelling using neural network and genetic algorithm Application q{ neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. in this paper, we optimize a neural network structure using genetic algorithm The genetic algorithm uses binary coding for neural network structure and searches for an optimal neural network structure of minimum error and fast response time. Through an extensive simulation, the optimal neural network structure is shown to be effective for identification of nonlinear system.

• Knowledge Management Research
• /
• v.12 no.2
• /
• pp.69-80
• /
• 2011

This paper reports on a structural view of a knowledge network comprised of clubs and organisationsexpressly concerned with cultural activities in a regional Australian city. Social network analysis showed an uneven distribution of power, influence, and prominence in the network. The network structure consisted of two modules of vertices clustered around particular categories of creative arts and these modules were linked most frequently by several organisations acting as communication hubs and boundary spanners. The implications of the findings include 'network weaving' for improving the network structure and developing a systemic approach for exploring the structures of social action that form community-based knowledge networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.736-740
• /
• 1990

The communication structure in iron & steel plants are described. The specifications of the management network, the plant network and the field network are investigated. Data link methods between level 1, and level 2 are studied. Several network examples are illustrated.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1986.04a
• /
• pp.142-145
• /
• 1986

The traffic characteristics of digital switch network depend on the structure, blocking probability, path searching method and etc. This paper presents the study of TDX-1 switch network traffic capacity by considering some decisive factors such as call processing software, switch network structure and control scheme. Conclusively the study shows that the switch network of TDX-1 can handle approximatly up to 1650 Erlang.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.433-440
• /
• 2018

I investigated whether network structure of legislators affects legislative performance in a cosponsorship network. I presented the theoretical basis with network closure and structural holes, and analyzed the network in the 19th National Assembly of Republic of Korea. In the directed and weighted network, each tie means that cosponsors support the bill sponsors proposed. The performance was measured by the number of initiatives and the ratio of reflected legislation, and the network structure was measured by size, density, hierarchy, and constraint. I found that the legislators with brokerage structure have a lot of initiatives in making connection with many legislators in various groups and the legislators with hierarchical structure have the higher ratio of reflected legislation with the continuous and strong support from the members of their group. I also found that the network of ruling party lawmaker is more hierarchical than the network of opposition lawmaker.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.4
• /
• pp.5-26
• /
• 2017

A cross-cultural comparison of social networking structure on McDonald's Facebook fan sites between Taiwan and the USA was conducted utilizing the individualism/collectivism dimension proposed by Hofstede. Four network indicators are used to describe the network structure of McDonald's Facebook fan sites: size, density, clique and centralization. Individuals who post on both Facebook sites for the year of 2012 were considered as network participants for the purpose of the study. Due to the huge amount of data, only one thread of postings was sampled from each month of the year of 2012. The final data consists of 1002 postings written by 896 individuals and 5962 postings written by 5532 individuals from Taiwan and the USA respectively. The results indicated that the USA McDonald's Facebook fan network has more fans, while Taiwan's McDonald's Facebook fan network is more densely connected. Cliques did form among the overall multiplex and within the individual uniplex networks in two countries, yet no significant differences were found between them. All the fan networks in both countries are relatively centralized, mostly on the site operators.