Digital Library[ Search Result ]
Opinion Classification in Professional Sports Fan Sites using Topic Keyword-Based Sentiment Analysis
Hyungho Byun, Sihyun Jeong, Chong-kwon Kim
http://doi.org/10.5626/JOK.2018.45.4.390
In this study, we propose the classification method using topic keyword-based sentiment analysis through the posts of professional sports fan sites in Korea. We studied ways to take into account the use of special communication methods or vocabulary in the community and defined keywords based on the characteristics of the topic or frequency of the community"s words. In addition, we presented a new sentiment analysis approach that utilizes the use of keyword pools and the proximity relation to keywords. Through three years of actual community dataset, sentiment analysis based on the topic keyword is more effective than the existing method and reflects the community environment.
Social Network Spam Detection using Recursive Structure Features
Boyeon Jang, Sihyun Jeong, Chongkwon Kim
http://doi.org/10.5626/JOK.2017.44.11.1231
Given the network structure in online social network, it is important to determine a way to distinguish spam accounts from the network features. In online social network, the service provider attempts to detect social spamming to maintain their service quality. However the spammer group changes their strategies to avoid being detected. Even though the spammer attempts to act as legitimate users, certain distinguishable structural features are not easily changed. In this paper, we investigate a way to generate meaningful network structure features, and suggest spammer detection method using recursive structural features. From a result of real-world dataset experiment, we found that the proposed algorithm could improve the classification performance by about 8%.
Rank Correlation Coefficient of Energy Data for Identification of Abnormal Sensors in Buildings
Naeon Kim, Sihyun Jeong, Boyeon Jang, Chong-Kwon Kim
Anomaly detection is the identification of data that do not conform to a normal pattern or behavior model in a dataset. It can be utilized for detecting errors among data generated by devices or user behavior change in a social network data set. In this study, we proposed a new approach using rank correlation coefficient to efficiently detect abnormal data in devices of a building. With the increased push for energy conservation, many energy efficiency solutions have been proposed over the years. HVAC (Heating, Ventilating and Air Conditioning) system monitors and manages thousands of sensors such as thermostats, air conditioners, and lighting in large buildings. Currently, operators use the building’s HVAC system for controlling efficient energy consumption. By using the proposed approach, it is possible to observe changes of ranking relationship between the devices in HVAC system and identify abnormal behavior in social network.
A Re-configuration Scheme for Social Network Based Large-scale SMS Spam
Sihyun Jeong, Giseop Noh, Hayoung Oh, Chong-Kwon Kim
The Short Message Service (SMS) is one of the most popular communication tools in the world. As the cost of SMS decreases, SMS spam has been growing largely. Even though there are many existing studies on SMS spam detection, researchers commonly have limitation collecting users" private SMS contents. They need to gather the information related to social network as well as personal SMS due to the intelligent spammers being aware of the social networks. Therefore, this paper proposes the Social network Building Scheme for SMS spam detection (SBSS) algorithm that builds synthetic social network dataset realistically, without the collection of private information. Also, we analyze and categorize the attack types of SMS spam to build more complete and realistic social network dataset including SMS spam.
A Method of Interoperating Heterogeneous Simulation Middleware for L-V-C Combined Environment
Kunryun Cho, Giseop No, Sihyun Jung, Nopphon Keerativoranan, Chongkwon Kim
Simulation is used these days to verify the hypothesis or the new technology. In particular, National Defense Modeling & Simulation (M&S) is used to predict wartime situation and conduct the military training. National Defense M&S can be divided into three parts, live simulation, virtual simulation, and constructive simulation. Live simulation is based on the real environment, which allows more realistic sumulation; however, it has decreased budget efficiency, but reduced depictions of reality. In contrast, virtual and constructive simulations which are based on the virtual environment, have increased budget efficiency, but reduced depictions of reality. Thus, if the three parts of the M&S are combined to make the L-V-C combined environment, the disadvantages of each simulation can be complemented to increases the quality of the simulation. In this paper, a method of interworking heterogeneous simulation middeware for L-V-C combined environment is proposed, and the test results of interworking between Data Distribution Service (DDS) and High Level Architecture (HLA) are shown.
Designing an Algorithm for the Priority Deciding and Recommending of the Logistic Support with Stationary Distribution
Giseop Noh, Sihyun Jeong, Chong-Kwon Kim, Hayoung Oh
One of the important roles used to ensure victory in a war is to maximize the overall military forces and to make sure that the capability of the military forces can be sustained as much as possible. Although several researchers have proposed various possible methodologies for logistics support, no research trials have been undertaken to investigate logistics support that considers all relevant elements of such. Unlike previous in trials that consider and analyze the system fault ratio as the main methodology, we propose an approach that simultaneously decides and recommends logistic priority by reflecting and combining item costs, transportation, fault-ratio, and system complexity. Also, we designed an algorithm that can recommend optimized logistics support priority using stationary distribution.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr