• The Korean Journal of Applied Statistics
• /
• v.36 no.5
• /
• pp.399-413
• /
• 2023

Recently, monitoring and detecting anomalies in social networks have become an interesting research topic. In this study, we investigate the detection of abnormal changes in a network modeled by the DCSBM (degree corrected stochastic block model), which reflects the propensity of both individuals and communities. To this end, we propose three methods for anomaly detection in the DCSBM networks: One method for monitoring the entire network, and two methods for dividing and monitoring the network in consideration of communities. To compare these anomaly detection methods, we design and perform simulations. The simulation results show that the method for monitoring networks divided by communities has good performance.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.757-758
• /
• 2020

국가적 차원에서 MERS 와 같은 재난을 잘 대처하기 위해서는 기존의 대응 네트워크를 분석할 필요가 있다. 본 논문에서는 2015 년 대한민국에서 일어난 MERS 대응 네트워크를 커뮤니티 탐지 기법을 이용하여 네트워크를 분석한다. 커뮤니티 탐지 기법은 네트워크 분석방법 중 하나로 이 기법을 통해 MERS 대응 네트워크에서 유사한 역할을 수행하는 기관들끼리 그룹핑 할 수 있다. 또한 기관들을 그룹핑 한 결과와 각 기관의 지리적인 정보를 활용하여 전국적으로 기관들이 어떻게 분포되어 있는지 살펴본다.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.719-728
• /
• 2016

In this paper, we analyzed IoT patent data using the social network analysis of keyword community network in patents related to Internet of Things technology. To identify the difference of IoT patent trends between Korea and USA, 100 Korea patents and 100 USA patents were collected, respectively. First, we first extracted important keywords from IoT patent abstracts using the TF-IDF weight and their correlation and then constructed the keyword network based on the selected keywords. Second, we constructed a keyword community network based on the keyword community and performed social network analysis. Our experimental results showed while Korea patents focus on the core technologies of IoT (such as security, semiconductors and image process areas), USA patents focus on the applications of IoT (such as the smart home, interactive media and telecommunications).

• Journal of KIISE
• /
• v.44 no.10
• /
• pp.1105-1111
• /
• 2017

Influence maximization (IM) is the problem of finding a seed set composed of k nodes that maximizes the influence spread in social networks. However, one of the biggest problems of existing solutions for IM is that it takes too much time to select a k-seed set. This performance issue occurs at the micro and macro levels. In this paper, we propose a fast hybrid method that addresses two issues at micro and macro levels. Furthermore, we propose a path-based community detection method that helps to select a good seed set. The results of our experiment with four real-world datasets show that the proposed method resolves the two issues at the micro and macro levels and selects a good k-seed set.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1115-1122
• /
• 2015

In recent years, the use of game bots by illegal programs has been expanded from individual to group scale; this brings about serious problems in online game industry. The gold farmers group creates an in-game social community so-called "guild" to obtain a large amount of game money and manage game bots efficiently. Although game developers detect game bots by detection algorithms, the algorithms can detect only part of the gold farmers group. In this paper, we propose a detection method for the gold farmers group on a basis of normal and bot guilds characteristic analysis. In order to differentiate normal and bots guild, we analyze transaction patterns for individuals, auction house and chatting. With the analyzed results, we can detect game bot guilds. We demonstrate the feasibility of the proposed methods with real datasets from one of the popular online games named AION in Korea.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.

• Journal of Digital Forensics
• /
• v.12 no.3
• /
• pp.39-54
• /
• 2018

Recently, discussions for the eradication of illegal shooting have been carried out in a socially-oriented way. The government has established comprehensive measures to eradicate cyber sexual violence crimes such as illegal shooting. Although the social interest in illegal shooting has increased, the illegal film shooting case is evolving more and more due to the development of information and communication technology. Applications that can hide confused videos are constantly circulating around the market and community sites. As a result, field investigators and professional analysts are experiencing difficulties in collecting and analyzing evidence. In this paper, we propose an evidence collection and analysis framework for illegal shooting cases in order to give practical help to illegal shooting investigation. We also proposed a system that can detect hidden applications, which is one of the main obstacles in evidence collection and analysis. We developed a detection tool to evaluate the effectiveness of the proposed system and confirmed the feasibility and scalability of the system through experiments using commercially available concealed apps.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.58-72
• /
• 2021

In July 2021, UNCTAD classified Korea as a developed country. After the Korean War in the 1950s, economic development was promoted despite difficult conditions, resulting in epoch-making national growth. However, in order to respond to the rapidly changing global economy, it is necessary to continuously study the domestic industrial ecosystem and prepare strategies for continuous change and growth. This study analyzed the industrial ecosystem of the automobile industry where it is possible to obtain transaction data between companies by applying complexity spatial network analysis. For data, 295 corporate data(node data) and 607 transaction data (link data) were used. As a result of checking the spatial distribution by geocoding the address of the company, the automobile industry-related companies were concentrated in the Seoul metropolitan area and the Southeastern(Dongnam) region. The node importance was measured through degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality, and the network structure was confirmed by identifying density, distance, community detection, and assortativity and disassortivity. As a result, among the automakers, Hyundai Motor, Kia Motors, and GM Korea were included in the top 15 in 4 indicators of node centrality. In terms of company location, companies located in the Seoul metropolitan area were included in the top 15. In terms of company size, most of the large companies with more than 1,000 employees were included in the top 15 for degree centrality and betweenness centrality. Regarding closeness centrality and eigenvector centrality, most of the companies with 500 or less employees were included in the top 15, except for automakers. In the structure of the network, the density was 0.01390522 and the average distance was 3.422481. As a result of community detection using the fast greedy algorithm, 11 communities were finally derived.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.89-96
• /
• 2018

In online communities, a large number of participants can exchange their opinion using replies without time and space restrictions. While the online space provides quick and free communication, it also easily triggers unnecessary quarrels and conflicts. The network established on the discussion participants is an important cue to analyze the confrontation and predict serious disputes. In this paper, we present a quantitative measure for polarity observed on the discussion network built from reply exchanges in online communities. The proposed method uses the comment exchange information to establish the user interaction network graph, computes its maximum spanning tree, and then performs vertex coloring to assign two colors to each node in order to divide the discussion participants into two subsets. Using the proportion of the comment exchanges across the partitioned user subsets, we compute the polarity measure, and quantify how discussion participants are bipolarized. Using experimental results, we demonstrate the effectiveness of our method for detecting polarization and show participants of a specific discussion subject tend to be divided into two camps when they debate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1595-1603
• /
• 2020

Online defamation incidents such as Internet news comments on portal sites, SNS, and community sites are increasing in recent years. Bias and hate expressions threaten online service users in various forms, such as invasion of privacy and personal attacks, and defamation issues. In the past few years, academia and industry have been approaching in various ways to solve this problem The purpose of this study is to build a dataset and experiment with deep learning classification modeling for detecting various bias expressions as well as hate expressions. The dataset was annotated 7 labels that 10 personnel cross-checked. In this study, each of the 7 classes in a dataset of about 137,111 Korean internet news comments is binary classified and analyzed through deep learning techniques. The Proposed technique used in this study is multi-channel CNN model with attention. As a result of the experiment, the weighted average f1 score was 70.32% of performance.