• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.79-84
• /
• 2021

메신저 사용의 증가와 함께 관련 범죄와 사고가 증가하고 있어 메시지 사용자 검증의 필요성이 대두되고 있다. 본 연구에서는 그래프 기반의 인스턴트 메세지 분석 모델을 제안하여 채팅 사용자를 검증하고자 한다. 사용자 검증은 주어진 두 개의 텍스트의 작성자가 같은지 여부를 판단하는 문제다. 제안 모델에서는 사용자의 이전 대화를 토대로 n-gram 전이 그래프를 구축하고, 작성자를 알 수 없는 메세지를 이용해 전이 그래프를 순회한 랜덤워크의 특성을 추출한다. 사용자의 과거 채팅 습관과 미지의 텍스트에 나타난 특징 사이의 관계를 분석한 모델은 10,000개의 채팅 대화에서 86%의 정확도, 정밀도, 재현율로 사용자를 검증할 수 있었다. 전통적인 통계 기반 모델들이 명시적 feature를 정의하고, 방대한 데이터를 이용해 통계 수치로 접근하는데 반해, 제안 모델은 그래프 기반의 문제로 치환함으로써 제한된 데이터 분량에도 안정적인 성능을 내는 자동화된 분석 기법을 제안했다.

• The Journal of Society for e-Business Studies
• /
• v.20 no.2
• /
• pp.155-166
• /
• 2015

RWR (Random Walk with Restart) is frequently used by many graph-based ranking algorithms, but it does not consider a signed graph where edges may have negative weight values. In this paper, we apply the Balance Theory by F. Heider to RWR over a signed graph and propose a novel RWR, Balanced Random Walk (BRW). We apply the proposed technique into the domain of recommendation system, and show by experiments its effectiveness to filter out the items that users may dislike. In order to provide the reasonable performance of BRW in the domain, we modify the existing Top-k algorithm, BCA, and propose a new algorithm, Bicolor-BCA. The proposed algorithm yet requires employing a threshold. In the experiment, we show how threshold values affect both precision and performance of the algorithm.

• The Journal of Engineering Geology
• /
• v.33 no.1
• /
• pp.201-211
• /
• 2023

This study investigated the damage range of the debris flow to predict the amount of collapsed soil in a landslide event. The height of the collapsed slope and the distance traveled by the collapsed soil were used to predict the total trajectory distance using a random walk model. Debris flow trajectory probabilities were calculated through 10,000 Monte Carlo simulations and were used to calculate the damage range as measured from the landslide scar to its toe. Compiled information on debris flows that occurred in the Cheonwangbong area of Mt. Jirisan was used to test the accuracy of the proposed random walk model in estimating the damage range of debris flow. Results of the comparison reveal that the proposed model shows reasonable accuracy in estimating the damage range of debris flow and that using 10 m × 10 m cells allows the damage range to be reproduced with satisfactory precision.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.444-446
• /
• 2021

MANETs(Mobile Ad-hoc Networks) are composed of mobile nodes that are not subordinate to fixed networks and have the feature that can form their own networks. they are used in various fields for specific goals. The mobility model in MANET can be applied in various ways depending on the purpose of usage. The random mobility model has the advantage of being simple and easy to implement, so it is being used the most. In a MANET, it is assumed that each node moves independently. The random movement model is a good model for expressing this independence of each node. However, it is insufficient to express the characteristics of all nodes with only random properties of individual nodes. This paper limits the stochastic mobility model applicable in MANET. we compare the proposed stochastic mobility model and the random mobility model. We confirm that the proposed mobility model is applied to the routing protocol to show improved characteristics in terms of energy consumption efficiency.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.5
• /
• pp.1-7
• /
• 2014

Distance based mobility management schemes have been considered as a major issue in the wireless network research area. Accordingly, many efforts have been made to analyze them numerically with suitable mobility models. In particular, bidirectional random walk model has been employed frequently due to its simplicity. Nevertheless, the exact equations are not presented so far. In this paper, we provide the exact equations regarding the bidirectional random walk model, which is very useful for the analysis of the distance based mobility management schemes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.5
• /
• pp.911-916
• /
• 2016

The nearest-neighbor multihop routing with/without infrastructure support is known to achieve the optimal capacity scaling in a large packet-erasure network in which multiple wireless nodes and relay stations are regularly placed and packets are erased with a certain probability. In this paper, a throughput scaling law is shown for an infrastructure-supported erasure network where wireless nodes are randomly distributed, which is a more feasible scenario. We use an exponential decay model to suitably model an erasure probability. To achieve high throughput in hybrid random erasure networks, the multihop routing via highway using the percolation theory is proposed and the corresponding throughput scaling is derived. As a main result, the proposed percolation highway based routing scheme achieves the same throughput scaling as the nearest-neighbor multihop case in hybrid regular erasure networks. That is, it is shown that no performance loss occurs even when nodes are randomly distributed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12C
• /
• pp.738-743
• /
• 2011

For the high quality 3-D broadcasting, depth maps are important data. Although commercially available depth cameras capture high-accuracy depth maps in real time, their resolutions are much smaller than those of the corresponding color images due to technical limitations. In this paper, we propose the depth map up-sampling method using a high-resolution color image and a low-resolution depth map. We define a random walk probability model in an operation unit which has nearest seed pixels. The proposed method is appropriate to match boundaries between the color image and the depth map. Experimental results show that our method enhances the depth map resolution successfully.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.502-504
• /
• 2004

이동성이 중요시되는 네트워크에서 특정 프로토콜의 성능 평가를 위해서는 노드의 이동패턴을 정확하게 표현할 수 있는 Mobility Model이 필요하다. 노드의 연속적인 이동패턴을 필요로 하는 Mobile Ad-hoc 네트워크를 위해선 Markov process 기반의 Gauss-Markov Mobility Model이 적절하다. 그러나 맵의 엣지 부근에서 노드 이동의 부적절한 처리로 인해, 기존의 Gauss-Markov Model은 편중된 이동 패턴을 야기한다. 본 논문은 엣지 부근의 평균 이동각도를 랜덤하게 조정함으로써 기존의 모델이 가진 문제를 해결하고, 시뮬레이션을 통해서 이를 검증한다.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.333-341
• /
• 2006

Recently, Random Constant worm is increasing The worm retards the availability of the overall network by exhausting resources such as CPU resource and network bandwidth, and damages to an uninfected system as well as an infected system. This paper analyzes the Power-Law network which possesses the preferential characteristics to restrain the worm from spreading. Moreover, this paper suggests the model which dynamically controls the spread of the worm using information about depth distribution of the delivery node which can be seen commonly in such network. It has also verified that the load for each node was minimized at the optimal depth to effectively restrain the spread of the worm by a simulation.