• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.826-828
• /
• 2017

그래프는 객체와 객체 간의 관계를 표현하는 데에 있어 효과적인 데이터 표현 방법이다. 그래프 데이터는 웹 그래프, 사회 관계망 서비스, 신약 개발, 생명정보학 등의 다양한 분야에서 활용되고 있으며, 그래프 마이닝 응용에서 활용되기 위한 효율적인 처리 기술을 필요로 한다. 최근까지 그래프 데이터의 처리 및 분석을 위한 많은 시스템들이 개발되었다. 본 논문에서는 최신 분산 그래프 처리 시스템 중에서 대표적인 그래프 분석 질의인 페이지랭크(pagerank)와 너비 우선 탐색(breadth first search)를 수행하고 시스템의 성능을 평가한다.

• 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.

• Journal of information and communication convergence engineering
• /
• v.12 no.1
• /
• pp.33-38
• /
• 2014

This paper investigates the shaping operation problem introduced by Callahan et al., namely the k-fragility maximization problem (k-FMP), whose goal is to find a subset of personals within a terrorist group such that the regeneration capability of the residual group without the personals is minimized. To improve the impact of the shaping operation, the degree centrality of the residual graph needs to be maximized. In this paper, we propose a new greedy algorithm for k-FMP. We discover some interesting discrete properties and use this to design a more thorough greedy algorithm for k-FMP. Our simulation result shows that the proposed algorithm outperforms Callahan et al.'s algorithm in terms of maximizing degree centrality. While our algorithm incurs higher running time (factor of k), given that the applications of the problem is expected to allow sufficient amount of time for thorough computation and k is expected to be much smaller than the size of input graph in reality, our algorithm has a better merit in practice.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.686-710
• /
• 2019

This work proposes a model to solve the problem of Network Coding over a one-session multicast network. The model is based on a system of restrictions that defines the packet flows received in the sink nodes as functions of the outgoing flows from the source node. A multicast network graph is used to derive a directed labeled line graph (DLLG). The successive powers of the DLLG adjacency matrix to the convergence in the null matrix permits the construction of the jump matrix Source-Sinks. In its reduced form, this shows the dependency of the incoming flows in the sink nodes as a function of the outgoing flows in the source node. The emerging packets for each outgoing link from the source node are marked with a tag that is a linear combination of variables that corresponds to powers of two. Restrictions are built based on the dependence of the outgoing and incoming flows and the packet tags as variables. The linear independence of the incoming flows to the sink nodes is mandatory. The method is novel because the solution is independent of the Galois field size where the packet contents are defined.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.89-95
• /
• 2023

In recent decades, human action recognition (HAR) has demonstrated potential applications in sports analysis, human-robot interaction, and large-scale signage content. In this paper, spatial temporal attention graph convolutional network (STAGCN)-based HAR system is proposed. Spatioal-temmporal features of skeleton sequences are assigned different weights by STAGCN, enabling the consideration of key joints and viewpoints. From simulation results, it has been shown that the performance of the proposed model can be improved in terms of classification accuracy in the NTU RGB+D dataset.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.5
• /
• pp.398-409
• /
• 2013

This paper provides an overview of distance-based formation control. Firstly, in this paper, we introduce preliminary background materials that are used in defining the distance-based formation control. Then, based on the preliminary background, we briefly review main results developed thus far in this field. Lastly, we provide some issues that need to be studied further in future works.

• International Journal of Advanced Culture Technology
• /
• v.6 no.2
• /
• pp.117-122
• /
• 2018

As evidenced through rapidly growing digital repositories and web resources, automatic metadata generation is becoming ever more critical, especially considering the costly and complex operation of manual metadata creation. Also, automatic metadata generation is apt to consistent metadata application. In this sense, metadata quality and interoperability can be enhanced by utilizing a mechanism for automatic metadata generation. In this article, a mechanism of automatic metadata extraction called ExMETA is introduced in order to alleviate issues dealing with inconsistent metadata application and semantic interoperability across ever-growing digital collections. Conceptual graph, one of formal languages that represent the meanings of natural language sentences, is utilized for ExMETA as a mediation mechanism that enhances the metadata quality by disambiguating semantic ambiguities caused by isolation of a metadata element and its corresponding definition from the relevant context. Hence, automatic metadata generation by using ExMETA can be a good way of enhancing metadata quality and semantic interoperability.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2018

The following research questions are examined in this paper. What hinders quality metadata generation and metadata interoperability? What kind of semantic representation technique can be utilized in order to enhance metadata quality and semantic interoperability? This paper suggests a way of handling semantic ambiguity for metadata generation. The conceptual graph is utilized to disambiguate semantic ambiguities caused by isolation of a metadata element and its corresponding definition from the relevant context. The mechanism introduced in this paper has the potential to alleviate issues dealing with inconsistent metadata application and interoperability across digital collections.

• Journal of information and communication convergence engineering
• /
• v.17 no.2
• /
• pp.149-160
• /
• 2019

Web applications typically interact with databases. Therefore, it is very crucial to understand which web components access which database resources when maintaining web apps. Existing research identifies interactions between Java web components, such as JavaServer Pages and servlets but does not extract dependencies between the web components and database resources, such as tables and attributes. This paper proposes a dynamic analysis of Java web apps, which extracts such dependencies from a Java web app and represents them as a graph. The key responsibility of our analysis method is to identify when web components access database resources. To fulfill this responsibility, our method dynamically observes the database-related objects provided in the Java standard library using the proxy pattern, which can be applied to control access to a desired object. This study also experiments with open source web apps to verify the feasibility of the proposed method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.517-518
• /
• 2023

본 논문에서는 인공지능 신경망의 하이퍼 파라미터들이 그래프 신경망 모델의 성능에 미치는 영향을 알아보기 위하여 대규모 그래프 데이터를 기반으로 이진 분류 문제를 예측하는 그래프 합성곱 신경망 모델(Graph Convolution Network Model)을 구현하고 모델의 다양한 하이퍼 파라미터 중 손실함수와 활성화 함수를 여러 가지 조합으로 적용하며 모델 학습과 예측 실험을 시행하였다. 실험 결과, 활성화 함수보다는 손실함수의 선택이 모델의 예측 성능에 좀 더 큰 영향을 미치는 것을 확인하였다.