• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.10 no.4
• /
• pp.59-71
• /
• 2000

Due to the advance of computer and communication technology, intrusions or crimes using a computer have been increased rapidly while various information has been provided to users conveniently. As a results, many studies are necessary to detect the activities of intruders effectively. In this paper, a new association algorithm for the anomaly detection model is proposed in the process of generating user\`s normal patterns. It is that more recently observed behavior get more affection on the process of data mining. In addition, by clustering generated normal patterns for each use or a group of similar users, it is possible to identify the usual frequency of programs or command usage for each user or a group of uses. The performance of the proposed anomaly detection system has been tested on various system Parameters in order to identify their practical ranges for maximizing its detection rate.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.231-240
• /
• 2020

With the development in the IT industry and the growth in the game industry, user's game data is recorded in seconds according to various plays and options, and a vast amount of game data can be analyzed based on Bigdata. Combined with business, Bigdata is used to discover new values for profit creation in various fields, but it is utilized in the game industry in insufficient ways. In this study, considering the characteristics of the subdivided lines, we constructed a win-loss prediction model for each line using the game data of League of Legends, and derived the importance of variables. This study can contribute to planning of strategies for general game users to get information about team members in advance and increase the win rate by using the record search sites.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.1-13
• /
• 2022

With the development of network technologies, the security to protect organizational resources from internal and external intrusions and threats becomes more important. Therefore in recent years, the anomaly detection algorithm that detects and prevents security threats with respect to various security log events has been actively studied. Security anomaly detection algorithms that have been developed based on rule-based or statistical learning in the past are gradually evolving into modeling based on machine learning and deep learning. In this study, we propose a deep-autoencoder model that transforms LSTM-autoencoder as an optimal algorithm to detect insider threats in advance using various machine learning analysis methodologies. This study has academic significance in that it improved the possibility of adaptive security through the development of an anomaly detection algorithm based on unsupervised learning, and reduced the false positive rate compared to the existing algorithm through supervised true positive labeling.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1259-1265
• /
• 2022

Recently, AI, big data, and IoT technologies are being used in various solutions such as fire detection and gas or dangerous substance detection for safety accident prevention. According to the status of occupational accidents published by the Ministry of Employment and Labor in 2021, the accident rate, the number of injured, and the number of deaths have increased compared to 2020. In this paper, referring to the dataset construction guidelines provided by the National Intelligence Service Agency(NIA), the dataset is directly collected from the field and learned with YOLOv4 to propose a collision risk object detection system through object detection. The accuracy of the dangerous situation rule violation was 88% indoors and 92% outdoors. Through this system, it is thought that it will be possible to analyze safety accidents that occur in industrial sites in advance and use them to intelligent platforms research.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.123-130
• /
• 2022

In this paper is one of the measures to prevent concrete collapse accidents at construction sites in advance. Analyzed based on accumulated Meteorological Agency data. It is a reliable model that confirms the prediction of the decrease rate occurrence interval, and the verification items such as p_value is 0.5 or less and ecof appears in one direction through the SARIMA model, which is suitable for regular and clear time series data models, ensure reliability. Significant results were obtained. As a result of analyzing the temperature change by time zone and the water reduce ratio by section using the data secured based on such trust, the water reduce ratio is the highest in the 29-31 ℃ section from 12:00 to 13:00 from July to August. found to show. If a factor in the research result interval occurs using the research results, it is expected that the batch plant will produce Ready-mixed concrete that reflects the water reduce ratio at the time of designing the water-cement mixture, and prevent the decrease in concrete compressive strength due to the water reduce ratio.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.319-319
• /
• 2023

Flows of water in the environment (e.g. in a river or estuary) generally occur in complex conditions. This complexity can hinder a general understanding of flows and their related sedimentary processes, such as erosion and deposition. To gain insight in simplified, controlled conditions, hydraulic flumes are a popular type of laboratory research equipment. Linear flumes use pumps to recirculation water. This isn't appropriate for the investigation of cohesive sediments as pumps can break fragile cohesive sediment flocs. To overcome this limitation, the rotating annular flume (RAF) was developed. While not having pumps, a side-effect is that unwanted secondary circulations can occur. To counteract this, the top and bottom lid rotate in opposite directions. Furthermore, a larger flume is considered better as it has less curvature and secondary circulation. While only a few RAFs exist, they are important for theoretical research which often underlies numerical models. Many of the first-generation of RAFs have come into disrepair. As new measurement techniques and models become available, there is still a need to research cohesive sediment erosion and deposition in facilities such as a RAF. New RAFs also can have the advantage of being automatic instead of manually operated, thus improving data quality. To further advance our understanding of cohesive sediment erosion and deposition processes, a large, automatic RAF (1.72 m radius, 0.495 m channel depth, 0.275 m channel width) has been constructed at the Hydraulic Laboratory at Chungnam National University (CNU), Korea. The RAF has the ability to simulate both unidirectional (river) and bidirectional (tide) flows with supporting instrumentation for measuring turbulence, bed shear stress, suspended sediment concentraiton, floc size, bed level, and bed density. Here we present the current status and future prospect of the CNU RAF. In the future, calibration of the rotation rate with bed shear stress and experiments with unidirectional and bidirectional flow using cohesive kaolinite are expected. Preliminary results indicate that the CNU RAF is a valuable tool for fundamental cohesive sediment transport research.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.627-634
• /
• 2006

Now, in a domestic country, the rebuilding and redevelopment of existing houses has been rapidly increasing with an economic growth and the improvement of living condition. As a result of that, a lot of C&D waste has been also produced. Nevertheless, it is not easy to find the research results for appropriate treatment and management of C&D waste in domestic. Therefore this study suggests the optimum deconstruction management system for minimizing construction waste and increasing reuse or recycle rate of material different from traditional demolition. The system makes it possible to plan and manage in advance quantity of C&D waste, demolition methods of each structural elements and application methods of produced C&D waste through an integrated and computerized system. The purpose of the system is ultimately to contribute to minimizing environmental damages and reducing construction waste quantity of a country. This system is largely composed of four modules such as planning of preliminary demolition survey, estimating of demolition quantity, planning of demolition schedule and planning of construction waste management and each module can be also used individually according to the purpose of a user.

• Journal of Advanced Navigation Technology
• /
• v.27 no.6
• /
• pp.865-870
• /
• 2023

Recently, accidents caused by black ice, a road freezing phenomenon caused by natural power, are increasing. Black ice is difficult to identify directly with the human eye and is more likely to misunderstand it as standing water, so there is a high accident rate caused by car sliding. To solve this problem, this paper presents a method of detecting black ice centered on LiDAR sensors. With a small, inexpensive, and high-accuracy light detection and ranging (LiDAR) sensor, the temperature and inclination angle are set differently to detect black ice and asphalt by setting different reflection angles of asphalt and black ice differently in temperatures and inclinations. The LIDARO carried out in the study points out that additional research and improvement are needed to increase accuracy, and through this, more reliable black ice detection methods can be suggested. This method suggests a method of detecting black ice through early system design research by preventing accidents caused by black ice in advance.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.38-45
• /
• 2024

Most previous works about magnetic effect on plasma emission were interested in emission enhancement which was useful to various fields of plasma application. On the contrary, the following work is interested in plasma dissipation rarely reported in prior researches and expected to help advance plasma-controlling technique. Nd:YAG laser (1064 nm, 6 ns) was focused on three kinds of metals (Al, Ti and STS) and air. The permanent magnetic field (0.4 T) of Nd₂Fe₁₄B magnet was provided passing throughout laser-induced plasma. The spectra of plasma in both the presence and absence of the magnetic field were observed with varying laser power and delay time of the spectrograph. In this work it was uniquely discovered that the plasma always dissipated easily in the presence of magnetic field irrespective of the laser power. With the O I(777.42 nm)-line shape function fitted to Lorentz profile, its half width at half maximum (HWHM) was evaluated to verify that the magnetic field increased the plasma density. It is concluded that magnetic field facilitates not only plasma emission enhancement but also plasma dissipation, increasing recombination rate which is proportional to plasma density.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.93-98
• /
• 2024

With the rapid advance in AI (artificial intelligence) and high-performance computing technologies, deep learning is being used in various fields. Deep learning proceeds training by randomly reading a large amount of data and repeats this process. A large number of files are randomly repeatedly referenced during deep learning, which shows different access characteristics from traditional workloads with temporal locality. In order to cope with the difficulty in caching caused by deep learning, we propose a new sampling method that aims at reducing the randomness of dataset reading and adaptively operating on existing buffer cache algorithms. We show that the proposed policy reduces the miss rate of the buffer cache by 16% on average and up to 33% compared to the existing method, and improves the execution time by up to 24%.