• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.140-149
• /
• 2009

Traffic anomaly detection is one of important technology that should be considered in network security and administration. In this paper, we propose an abnormal traffic detection mechanism that includes traffic monitoring and traffic analysis. We develop analytical passive monitoring system called WISE-Mon which can inspect traffic behavior. We establish a criterion by analyzing the characteristics of a traffic training set. To detect abnormal traffic, we derive a hyperplane by using Fisher linear discriminant and chi-square distribution as well as the analyzed characteristics of traffic. Our mechanism can support reliable results for traffic anomaly detection and is compatible to real-time detection. In addition, since the trend of traffic can be changed as time passes, the hyperplane has to be updated periodically to reflect the changes. Accordingly, we consider the self-learning algorithm which reflects the trend of the traffic and so enables to increase the pliability of detection probability. Numerical results are presented to validate the accuracy of proposed mechanism. It shows that the proposed mechanism is reliable and relevant for traffic anomaly detection.

• Journal of the Korean Society for information Management
• /
• v.36 no.4
• /
• pp.83-105
• /
• 2019

This study aims to suggest an effective method for the automatic classification of keywords with similar patterns by calculating pattern similarity of temporal data. For this, large scale news on the Web were collected and time series data composed of 120 time segments were built. To make training data set for the performance test of the proposed model, 440 representative keywords were manually classified according to 8 types of trend. This study introduces a Dynamic Time Warping(DTW) method which have been commonly used in the field of time series analytics, and proposes an application model, MA-DTW based on a Moving Average(MA) method which gives a good explanation on a tendency of trend curve. As a result of the automatic classification by a k-Nearest Neighbor(kNN) algorithm, Euclidean Distance(ED) and DTW showed 48.2% and 66.6% of maximum micro-averaged F1 score respectively, whereas the proposed model represented 74.3% of the best micro-averaged F1 score. In all respect of the comprehensive experiments, the suggested model outperformed the methods of ED and DTW.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.1
• /
• pp.1-11
• /
• 2003

In this study, TOPMODEL(TOPography based hydrologic MODEL) was tested linked with Muskingum river routing technique for $581.7km^2$ Anseong-cheon watershed. Linear trend surface interpolation was used to give flow direction for flat areas located in downstream watershed. MDF (multiple flow direction) algorithm was adopted to derive the distribution of ln(a/$tan{\beta}$) values of the model. Because the coarser DEM resolution, the greater information loss, the watershed was divided into subwaterhseds to keep DEM resolution, and the simulation result of the upstream watershed was transferred to downstream watershed by Muskingum techniques. Relative error of the simulated result by 500 m DEM resolution showed 27.2 %. On the other hand, the relative error of the simulated result of 300 m DEM resolution by linked 2 subwatersheds with Muskingum method showed 15.8 %.

• Journal of Bio-Environment Control
• /
• v.25 no.1
• /
• pp.30-41
• /
• 2016

Korean government has planned to increase the productivity of horticultural crops and to expand supply smart greenhouse for energy saving by modernization of horticultural facilities based on ICT in policy. However, the diversity and linkages of monitoring and control are significantly insufficient in the agricultural sector in the current situation. Therefore, development of a service system with smart-farm based on the internet of things(IoT) for intelligent systemization of all the process of agricultural production through remote control using complex algorithm for diverse monitoring and control is required. In this study, domestic and international research trend related to ICT-based horticultural facilities was briefly introduced and limits were analyzed in the domestic application of the advanced technology. Finally, future core technologies feasible to graft in agricultural field were reviewed.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.129.1-129.1
• /
• 2011

We have applied an advanced multi-aperture indexing photometry and sophisticated de-trending method to existing Taiwanese-American Occultation Survey (TAOS) data sets. TAOS, a wide-field ($3^{\circ}{\times}3^{\circ}$) and rapid photometry (5Hz) survey, is designed to detect small objects in the Kuiper Belt. Since TAOS has fast and multiple exposures per zipper mode image, point spread function (PSF) varies in a given image. Selecting appropriate aperture among various size apertures allows us to reflect these variations in each light curve. The survey data turned out to contain various trends such as telescope vibration, CCD noise, and unstable local weather. We select multiple sets of stars using a hierarchical clustering algorithm in such a way that the light curves in each cluster show strong correlations between them. We then determine a primary trend (PT) per cluster using a weighted sum of the normalized light curves, and we use the constructed PTs to remove trends in individual light curves. After removing the trend, we can get each synthetic light curve of star that has much higher signal-to-noise ratio. We compare the efficiency of the synthetic light curves with the efficiency of light curves made by previous existing photometry pipelines. Our photometric method is able to restore subtle brightness variation that tends to be missed in conventional aperture photometric methods, and can be applied to other wide-field surveys suffering from PSF variations and trends. We are developing an analysis package for the next generation TAOS survey (TAOS II) based on the current experiments.

• Journal of Digital Convergence
• /
• v.15 no.9
• /
• pp.231-239
• /
• 2017

Solar energy is attracting attention as an alternative to fossil fuels. However, there was a lack of discussion on the overall research direction and future direction of research in technology development. In order to develop more effective technology, we analyzed and discussed the technology trend of solar energy using patent data and thesis data. As an analysis method, topics were selected by using topic modeling and text mining, the increase of included keywords was analyzed, and the direction of development of solar technology was analyzed. Research on solar power generation technology is expected to proceed steadily, and it is analyzed that intensive research will be done especially on high efficiency and high performance technology. Future studies could be conducted by adding overseas patent data and various paper data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.5
• /
• pp.207-214
• /
• 2020

Nowadays, the use of smart phones and various electronic devices is increasing, the Internet and SNS are activated, and we live in the flood of information. The amount of information has grown exponentially, making it difficult to look at a lot of information, and more and more people want to see only key keywords in a document, and the importance of research to extract topics that are the core of information is increasing. In addition, it is also an important issue to extract the topic and compare it with the past to infer the current trend. Topic modeling techniques can be used to extract topics from a large volume of documents, and these extracted topics can be used in various fields such as trend prediction and data analysis. In this paper, we inquire the topic of the three-year papers of 2016, 2017, and 2018 in the field of computing using the LDA algorithm, one of Probabilistic Topic Model Techniques, in order to analyze the rapidly changing trends and keep pace with the times. Then we analyze trends and flows of research.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.1
• /
• pp.1-6
• /
• 2010

The lens distortion in the machine vision system is inevitable phenomenon. Distortion is getting worse, due to the selection of lens in the trend of reducing prices and size of the system. In this trend, the distortion correction becomes more important. But, the traditional correction methods has problems, such as complexity and requiring more operations. Effective distorted digital image correction is the precondition of target detection and recognition based on vision inspection. To overcome the disadvantage of traditional distortion correction algorithms, such as complex modeling, massive computation and marginal information loss, an image distortion correction algorithm based on photogrammetry method is proposed in this paper. In our method, we use the lattice image as the measurement target. Through the experimental results, we could find that we can reduce the processing time by 4ms. And also the inspection failure rate of our method was reduced by 2.3% than human-eyes inspection method.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.31-38
• /
• 2021

In this paper, in order to obtain the optimization of the RNN model used for sentiment analysis, the correlation of each model was studied by observing the trend of loss and accuracy according to hyperparameter tuning. As a research method, after configuring the hidden layer with LSTM and the embedding layer that are most optimized to process sequential data, the loss and accuracy of each model were measured by tuning the unit, batch-size, and embedding size of the LSTM. As a result of the measurement, the loss was 41.9% and the accuracy was 11.4%, and the trend of the optimization model showed a consistently stable graph, confirming that the tuning of the hyperparameter had a profound effect on the model. In addition, it was confirmed that the decision of the embedding size among the three hyperparameters had the greatest influence on the model. In the future, this research will be continued, and research on an algorithm that allows the model to directly find the optimal hyperparameter will continue.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.27 no.1
• /
• pp.87-96
• /
• 2023

As the number of security vulnerabilities increases yearly, security threats continue to occur, and the vulnerability risk is also important. We devise a security threat score calculation reflecting trends to determine the risk of security vulnerabilities. The three stages considered key elements such as attack type, supplier, vulnerability trend, and current attack methods and techniques. First, it reflects the results of checking the relevance of the attack type, supplier, and CVE. Secondly, it considers the characteristics of the topic group and CVE identified through the LDA algorithm by the Jaccard similarity technique. Third, the latest version of the MITER ATT&CK framework attack method, technology trend, and relevance between CVE are considered. We used the data within overseas sites provide reliable security information to review the usability of the proposed final formula CTRS. The scoring formula makes it possible to fast patch and respond to related information by identifying vulnerabilities with high relevance and risk only with some particular phrase.