• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.88-97
• /
• 2023

Traffic flow prediction is of great significance in urban planning and traffic management. As the complexity of urban traffic increases, existing prediction methods still face challenges, especially for the fusion of spatiotemporal information and the capture of long-term dependencies. This study aims to use the fusion model of graph neural network to solve the spatio-temporal information fusion problem in traffic flow prediction. We propose a new deep learning model Spatio-Temporal Information Fusion using Graph Neural Networks (STFGNN). We use GCN module, TCN module and LSTM module alternately to carry out spatiotemporal information fusion. GCN and multi-core TCN capture the temporal and spatial dependencies of traffic flow respectively, and LSTM connects multiple fusion modules to carry out spatiotemporal information fusion. In the experimental evaluation of real traffic flow data, STFGNN showed better performance than other models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.882-884
• /
• 2024

수많은 무선 네트워크 서비스의 등장과 함께 무선 네트워크를 대상으로 한 공격이 증가하고 있다. 이러한 공격을 탐지하기 위해 최근 많은 연구가 진행되고 있다. 특히 네트워크의 복잡한 연결 구조와 패턴을 효율적으로 분석할 수 있는 그래프 기반 인공지능 모델이 적용된 네트워크 침입 탐지 시스템(Network Intrusion Detection System, NIDS)에 관한 다양한 연구가 진행되고 있다. 이러한 배경을 바탕으로 본 논문에서는 무선 네트워크를 대상으로 한 공격의 정확하고 신속한 탐지를 위한 Graph Transformer Network(GTN) 기반 네트워크 침입 탐지 시스템을 제안하고 AWID3 데이터셋을 이용한 실험을 통해 GTN 기반 NIDS의 우수성을 검증한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.5 s.170
• /
• pp.87-94
• /
• 2005

This paper presents the development of a virtual robot design program. Robot design requires numerical software, robot solution software and multi-body dynamics software to complete several designs. However using a commercialized software implies some disadvantages, such as the waste of time and money it costs to learn how to use the software. We developed a virtual robot design program with which a user can design a robot with rapidity and reliability. The virtual robot design program is composed of robot kinematics module and robot dynamics module. The program is powerful software which may be used to solve various problems of a robot. The 3D animator and a 2D/3D graph of the program can analyze the design results into visual data. The virtual robot design program is expected to increase the competitiveness and efficiency of the robot industry.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.374-376
• /
• 2022

Community detection is meaningful research in social network analysis, and many existing studies use graph theory analysis methods to detect communities. This paper proposes a method to detect community by detecting maximal cliques and obtain the high influence cliques by high influence nodes, then merge the cliques with high similarity in social network.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.5
• /
• pp.177-188
• /
• 2018

The scale of graph data has been increased rapidly because of the growth of mobile Internet applications and the proliferation of social network services. This brings upon the imminent necessity of efficient distributed and parallel graph processing approach since the size of these large-scale graphs are easily over a capacity of a single machine. Currently, there are two popular parallel graph processing approaches, vertex-centric graph processing and block centric processing. While a vertex-centric graph processing approach can easily be applied to the parallel processing system, a block-centric graph processing approach is proposed to compensate the drawbacks of the vertex-centric approach. In these systems, the initial quality of graph partition affects to the overall performance significantly. However, it is a very difficult problem to divide the graph into optimal states at the initial phase. Thus, several dynamic load balancing techniques have been studied that suggest the progressive partitioning during the graph processing time. In this paper, we present a load balancing algorithms for the block-centric graph processing approach where most of dynamic load balancing techniques are focused on vertex-centric systems. Our proposed algorithm focus on an improvement of the graph partition quality by dynamically reassigning blocks in runtime, and suggests block split strategy for escaping local optimum solution.

• Journal of The Korean Association of Information Education
• /
• v.20 no.1
• /
• pp.93-100
• /
• 2016

Computer Science Unplugged is a collection of free learning activities that teach Computer Science through engaging games and puzzles that use cards, string, crayons and lots of running around. In spite of the success of unplugged activities, the unplugged resources for experiencing the concepts of data structures is lacked. In this study, we design, implement and survey the 3 hour lessons of the core concepts of graph theory and the shortest path algorithm for the primary students using computer science unplugged activities. Our survey results showed that our lesson plan is adequate for primary school students and will have a positive effects for primary school students.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.113-116
• /
• 2021

As artificial intelligence technologies, including deep learning, develop, these technologies are being introduced to code similarity analysis. In the traditional analysis method of calculating the graph edit distance (GED) after converting the source code into a control flow graph (CFG), there are studies that calculate the GED through a trained graph neural network (GNN) with the converted CFG, Methods for analyzing code similarity through CNN by imaging CFG are also being studied. In this paper, to determine which approach will be effective and efficient in researching code similarity analysis methods using artificial intelligence in the future, code similarity is measured through funcGNN, which measures code similarity using GNN, and Siamese Network, which is an image similarity analysis model. The accuracy was compared and analyzed. As a result of the analysis, the error rate (0.0458) of the Siamese network was bigger than that of the funcGNN (0.0362).

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.319-330
• /
• 2021

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.293-296
• /
• 2023

본 논문에서는 고속도로의 교통망의 연결성을 분석하고 예측하기 위하여 그래프 이론을 이용하여 접근성 지표의 알고리즘을 제안한다. 먼저 2025년 고속도로 교통망을 그래프로 나타낸 운송네트워크를 구한다. 그리고 그래프 이론의 연결수, 비교거리, 접근지표, 연결도, 산포지수, 지름 등의 개념을 이용하여 2025년 고속도로 교통망의 연결성을 분석하고 예측하기 위하여 주어진 운송네트워크로부터 다양한 접근성 지표를 쉽게 얻을 수 있는 알고리즘을 제시한다. 이를 통하여 고속도로의 운송네트워크에서 교통의 중심이 되는 도시를 찾을 수 있다.

• School Mathematics
• /
• v.11 no.1
• /
• pp.131-145
• /
• 2009

This research was designed to investigate the possibility to teach function concept and graph representation of functions in explicit manner toward at elementary level. Eight class-hours instruction was given to four Grade 5(age 11) students, and dynamic geometry software GSP was partially used in the class. Results indicate that the students could conceptualize the function relation, interpret linear function graphs, recognize the meaning of their slopes, and discuss the relationships among linear graphs and real life situation. Results also indicate that GSP helped students to recognize the relation between dots and the linear graph clearly and that GSP-line graph did decisive role for children to understand the meaning of graph representation of function.