• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.321-324
• /
• 2017

Bubblesort graph is mathematically modeled with bubbling methods, which can arrange data. Bubblesort graph Bn's degree is n, it's routing path length ${\frac{n(n-1)}{2}}$, and its network cost is $O(n^3)$. In this paper we suggest the number of Bubblesort graph's degree reduced to half as a solution to improve the network cost of Bubblesort graph. The Bubblesort graph which has the following restriction is a connected graph randomly from node U to node V for routing.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.444-448
• /
• 2010

RCR network[1] is a topology for interconnection networks having many desirable properties for building scalable parallel machines. This had been analyzed by Hu and Cao[2] to deal with problems of disconnected graph, bisection width and diameter. We analyze some properties of RCR again and revise the condition for connected graph and network diameter. And we present an efficient algorithm for finding next node on a shortest path.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1920-1937
• /
• 2015

Network environment has been under constant threat from both malicious attackers and inherent vulnerabilities of network infrastructure. Existence of such threats calls for exhaustive vulnerability analyzing to guarantee a secure system. However, due to the diversity of security hazards, analysts have to select from massive alternative hardening strategies, which is laborious and time-consuming. In this paper, we develop an approach to seek for possible hardening strategies and prioritize them to help security analysts to handle the optimal ones. In particular, we apply a Risk Flow Attack Graph (RFAG) to represent network situation and attack scenarios, and analyze them to measure network risk. We also employ a multi-objective genetic algorithm to infer the priority of hardening strategies automatically. Finally, we present some numerical results to show the performance of prioritizing strategies by network risk and hardening cost and illustrate the application of optimal hardening strategy set in typical cases. Our novel approach provides a promising new direction for network and vulnerability analysis to take proper precautions to reduce network risk.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.2859-2870
• /
• 2022

Because nuclear power plants (NPPs) are safety-critical infrastructure, it is essential to increase their safety and minimize risk. To reduce human error and support decision-making by operators, several artificial-intelligence-based diagnosis methods have been proposed. However, because of the nature of data-driven methods, conventional artificial intelligence requires large amount of measurement values to train and achieve enough diagnosis resolution. We propose a graph neural network (GNN) based accident diagnosis algorithm to achieve high diagnosis resolution with limited measurements. The proposed algorithm is trained with both the knowledge about physical correlation between components and measurement values. To validate the proposed methodology has a sufficiently high diagnostic resolution with limited measurement values, the diagnosis of multiple accidents was performed with limited measurement values and also, the performance was compared with convolution neural network (CNN). In case of the experiment that requires low diagnostic resolution, both CNN and GNN showed good results. However, for the tests that requires high diagnostic resolution, GNN greatly outperformed the CNN.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1997.05a
• /
• pp.111-116
• /
• 1997

공학적 신뢰도 문제에서 부품의 신뢰도나 가동도가 주어진 후 시스템의 신뢰도 평가를 위한 수치적 계산이 자주 요구된다. 이때 주어진 system은 graph나 fault tree등으로 신뢰도 특성을 표현하게 된다. 보통 network이나 교통망 등은 graph로 표현되며 부품과 graph의 선이 1 : 1로 대응되는 linear graph 이다. 이러한 그래프에 대한 신뢰도를 분석하는 방법 중에 여러 가지가 있으나 본 연구에서는 domination이론을 이용하여 신뢰도를 계산한다. (중략)

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.67-80
• /
• 2021

The node embedding technique for learning graph representation plays an important role in obtaining good quality results in graph mining. Until now, representative node embedding techniques have been studied for homogeneous graphs, and thus it is difficult to learn knowledge graphs with unique meanings for each edge. To resolve this problem, the conventional Triple2Vec technique builds an embedding model by learning a triple graph having a node pair and an edge of the knowledge graph as one node. However, the Triple2 Vec embedding model has limitations in improving performance because it calculates the relationship between triple nodes as a simple measure. Therefore, this paper proposes a feature extraction technique based on a graph convolutional neural network to improve the Triple2Vec embedding model. The proposed method extracts the neighborliness vector of the triple graph and learns the relationship between neighboring nodes for each node in the triple graph. We proves that the embedding model applying the proposed method is superior to the existing Triple2Vec model through category classification experiments using DBLP, DBpedia, and IMDB datasets.

• 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 Korean Association of Computer Education
• /
• v.17 no.2
• /
• pp.115-124
• /
• 2014

Hypercube and star graph are widely known as interconnection network. The embedding of an interconnection network is a mapping of a network G into other network H. The possibility of embedding interconnection network G into H with a low cost, has an advantage of efficient algorithms usage in network H, which was developed in network G. In this paper, we provide an embedding algorithm between HCN and HON. HCN(n,n) can be embedded into HON($C_{n+1},C_{n+1}$) with dilation 3 and HON($C_d,C_d$) can be embedded into HCN(2d-1,2d-1) with dilation O(d). Also, star graph can be embedded to half pancake's value of dilation 11, expansion 1, and average dilation 8. Thus, the result means that various algorithms designed for HCN and Star graph can be efficiently executed on HON and half pancake, respectively.