• Journal of the Optical Society of Korea
• /
• 제20권1호
• /
• pp.36-41
• /
• 2016

Visible Light Communication (VLC) using Light Emitting Diodes (LEDs) within the existing lighting infrastructure can reduce the implementation cost and may gain higher throughput than radio frequency (RF) or Infrared (IR) based wireless systems. Current indoor VLC systems may suffer from poor downlink resource allocation problems and small system throughput. To address these two issues, we propose an algorithm called a conflict graph scheduling (CGS) algorithm, including a conflict graph and a scheme that is based on the conflict graph. The conflict graph can ensure that users are able to transmit data without interference. The scheme considers the user fairness and system throughput, so that they both can get optimum values. Simulation results show that the proposed algorithm can guarantee significant improvement of system throughput under the premise of fairness.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.111-117
• /
• 2023

시간-공간적 의존성을 모두 고려하는 방법으로 그래프 신경망과 순환 신경망을 함께 사용하는 연구가 많이 진행되고 있다. 특히 그래프 신경망은 새롭게 활발히 연구되고 있는 분야이다. 서울시 자전거 대여 서비스(일명 따릉이)는 서울시 곳곳에 대여소를 갖추고 있으며 각 대여소에서 대여 정보가 충실하게 기록되어 있는 시계열 자료이다. 각 대여소의 대여 정보는 시간에 따른 주기성을 보이는 시간적인 특성을 갖추고 있으며, 지역적인 특성도 대여 현황에 큰 영향을 미치리라고 생각된다. 지역적 상관관계는 그래프 신경망을 이용하여 잘 이해할 수 있다. 이 연구에서는 서울시 자전거 대여 서비스의 시계열 데이터를 그래프로 재구성하고 그래프 신경망과 순차 신경망을 결합한 대여 예측 모델을 개발하였다. 시간에 따른 주기성과 같은 시간 특성과 지역적인 특성 및 각 대여소의 중요도 정도를 고려하였다. 대여소의 중요도 정도는 대여량 예측에 중요한 인자로 사용됨을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.380-382
• /
• 2022

Extracting informative representation of molecules using graph neural networks(GNNs) is crucial in AI-driven drug discovery. Recently, the graph research community has been trying to replicate the success of self supervised in natural language processing, with several successes claimed. However, we find the benefit brought by self-supervised learning on applying varitional auto-encoders can be potentially effective on molecular data.

• 전자공학회논문지CI
• /
• 제42권1호
• /
• pp.27-34
• /
• 2005

본 논문에서는 그래프 임베딩 문제와 관련된 이항트리에서의 Q-에지 번호매김 방법을 제안한다. 이러한 연구결과는 신뢰성이 높은 통신망을 설계하는 최적화 문제인 "n 개의 노드와 e 개의 에지를 가지면서 연결도가 최대인 그래프를 구성하라."를 해결한 Harary 그래프의 일반화인 원형군 그래프(circulant graph)의 점프열로 Q-에지번호들을 이용하면 연결도가 최대인 신뢰성이 높은 새로운 상호연결망(interconnection networks)의 위상을 설계할 수 있다. 그리고 이러한 위상은 이항트리를 스패닝 트리로 가지므로 최적방송이 가능하다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.151-155
• /
• 2001

Mobile agent technology has been the subject of much attention in the last few years, mainly due to the proliferation of distributed software technologies combined with the distributed AI research field. In this paper, we present a design of communication networks of agents that cooperate with each other for forwarding messages to the specific mobile agent in order to make the overall system location transparent. In order to make the material accessible to general intelligent system researchers, we present the general ideas abstractly in terms of the graph theory. In particular, a proxy network is defined as a directed acyclic graph satisfying some structural conditions. In turns out that the definition ensures some kind of reliability of the network, in the sense that as long as at most one proxy agent is abnormal, there agent exists a communication path, from every proxy agent to the target agent, without passing through the abnormal proxy. As the basis for the implementation of this scheme, an appropriate initial proxy network is specified and the dynamic nature of the network is represented by a set of graph transformation rules. It is shown that those rules are sound, in the sense that all graphs created from the initial proxy network by zero or more applications of the rules are guaranteed to be proxy networks. Finally, we will discuss some implementation issues.

• Journal of applied mathematics & informatics
• /
• 제40권3_4호
• /
• pp.515-530
• /
• 2022

A factor graph and belief propagation can be used for finding stochastic values of link weights in biological networks. However it is not easy to follow the process of use and so we presented the process with a toy network of three nodes in our prior work. We extend this work more generally and present numerical example for a network of 100 nodes.

• 한국음향학회지
• /
• 제39권6호
• /
• pp.615-621
• /
• 2020

본 논문은 다중 관측소에서 측정된 지진 신호를 이용한 그래프 합성곱 신경망 기반 지진 이벤트 분류 방법을 제안한다. 기존의 딥러닝 기반 지진 이벤트 분류 방법은 대부분 단일 관측소에서 측정된 신호로부터 지진 이벤트를 분류한다. 지진 관측망에는 수많은 지진 관측소가 존재하며 하나의 관측소만 사용하는 방법보다 여러 관측소의 정보를 동시에 활용하는 방법이 지진 이벤트 분류 성능 향상을 이끌 수 있다. 본 논문에서는 단일 관측소에서 측정된 지진 신호들에 합성곱 신경망을 적용해 임베딩 특징을 추출한 후 그래프 합성곱 신경망을 이용해 단일 관측소들 사이의 정보를 융합하는 다중 관측소 기반 지진 이벤트 분류 구조를 제안한다. 관측소의 개수 변화 등 다양한 실험을 통해 제안한 모델의 성능 검증을 수행하였으며 실험 결과 제안하는 모델이 단일 관측소 기반 분류 모델보다 약 10 % 이상의 정확도와 이벤트 재현율 성능 향상을 보여주었다.

• Journal of Information Processing Systems
• /
• 제5권3호
• /
• pp.145-150
• /
• 2009

The awareness of boundaries in wireless sensor networks has many benefits. The identification of boundaries is especially challenging since typical wireless sensor networks consist of low-capability nodes that are unaware of their geographic location. In this paper, we propose a simple, efficient algorithm to detect nodes that are near the boundary of the sensor field as well as near the boundaries of holes. Our algorithm relies purely on the connectivity information of the underlying communication graph and does not require any information on the location of nodes. We introduce the 2-neighbor graph concept, and then make use of it to identify nodes near boundaries. The results of our experiment show that our algorithm carries out the task of topological boundary detection correctly and efficiently.

• 대한임베디드공학회논문지
• /
• 제14권4호
• /
• pp.219-226
• /
• 2019

One of the most widely studied protocols for tactical ad-hoc networks is Optimized Link State Routing Protocol (OLSR). As for OLSR research, most research work focus on reducing control traffic overhead and choosing relay point. In addition, because OLSR is mostly dependent on link detection and propagation, dynamic Hello timer become research challenges. However, different timer interval causes imbalance of link validity time by affecting link lifetime. To solve this problem, we propose a weighted topology graph model for constructing a robust network topology based on the link validity time. In order to calculate the link validity time, we use control message timer, which is set for each node. The simulation results show that the proposed mechanism is able to achieve high end-to-end reliability and low end-to-end delay in small networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.