• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.795-805
• /
• 2019

Recently, there is a growing interest in network anomaly detection technology to tackle unknown attacks. For this purpose, diverse studies using data mining, machine learning, and deep learning have been applied to detect network anomalies. In this paper, we evaluate the decision tree to see its feasibility for network anomaly detection on NSL-KDD data set, which is one of the most popular data mining techniques for classification. In order to handle the over-fitting problem of decision tree, we select 13 features from the original 41 features of the data set using chi-square test, and then model the decision tree using TensorFlow and Scik-Learn, yielding 84% and 70% of binary classification accuracies on the KDDTest+ and KDDTest-21 of NSL-KDD test data set. This result shows 3% and 6% improvements compared to the previous 81% and 64% of binary classification accuracies by decision tree technologies, respectively.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.149-161
• /
• 2018

The private military company(PMC) or the private military industry may be one of the most important, but little understood developments in security studies to have taken place over the last decade. This new industry, where firms not only supply the goods of warfare, but rather fulfill many of the professional service functions, is not only significant to the defence community, but has wider ramifications for global politics and warfare. The private military industry emerged in the early 1990s. Its underlying cause was the confluence of three momentous dynamics - the end of the Cold War and the vacuum this produced in the market of security, transformations in the nature of warfare, and the normative rise of privatization. In order to introduce MPFs(Military Provider Firms) into Korea, where in principle private citizens are prohibited to own a gun, unlike the United States, a special law should be enacted which allows them to possess weapons and fight in combat. Therefore, the National Assembly of Korea has been submitting and discussing "the Act on the Prevention and Conduction of Practice of Piracy" since 2014.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.1
• /
• pp.107-115
• /
• 2012

The level of information protection is relatively low, in comparison with the informatisation in this country. The budget for information protection is also quite marginal at 5% of the entire information-related policy budget. The passive information protection practices by companies, which focus more on the aftermaths, lead to repeated expenses for risk management. The responses to the violation of information protection should be changed from the current aftermaths-oriented focus to prevention and early detection of possible violations. We should also realize that the response to a violation of protected information is not a responsibility of an individual but a joint responsibility of the nation and the industry. South Korea has been working towards to building a systematic foundation since 2004 when guidelines were announced regarding the information protection policy and the safety diagnosis. The current level of safety policies cannot provide a perfect protection against actual violation cases in administrative, technological and physical ways. This research evaluates the level of prevention that the current systematic protection policy offers, and discusses its limitation and possible ways for improvement. It also recommends a list effective measures for protection against information violation that companies can employ to maintain the actual target safety level.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2022

In this paper, we propose a fire detection system based on CCTV images using an object tracking technology with YOLOv4 model capable of real-time object detection and a DeepSORT algorithm. The fire detection model was learned from 10800 pieces of learning data and verified through 1,000 separate test sets. Subsequently, the fire detection rate in a single image and fire detection maintenance performance in the image were increased by tracking the detected fire area through the DeepSORT algorithm. It is verified that a fire detection rate for one frame in video data or single image could be detected in real time within 0.1 second. In this paper, our AI fire detection system is more stable and faster than the existing fire accident detection system.

• Korean Journal of Organic Agriculture
• /
• v.30 no.1
• /
• pp.75-87
• /
• 2022

Reflux esophagitis (RE) is a gastroesophageal reflux disease (GERD) caused by repeated reflux of gastric acid into the esophagus. The present study investigated the protective effect of natural mineral water on esophageal injury induced by gastric acid reflux. The cytotoxicity of mineral water was confirmed using Cell viability, proliferation and cytotoxicity assay kit. The protective effect of mineral water on esophageal injury was investigated in RE rat model. The results showed that no cytotoxicity of mineral water was observed in RAW264.7 cells. Mineral water decreased the ratio of esophageal damage, inhibited the increase of inflammatory-protein expression levels and increased the mucosa protection and tight junction proteins expression level in RE control rat. The results suggest that mineral water may have the potential to protect esophageal damage caused by gastric acid reflux and the potential to alleviate reflux esophagitis.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.152-152
• /
• 2020

가뭄은 장기간에 걸쳐 광범위하게 발생하는 특징으로 인해 자연재해뿐만 아니라 사회·경제적으로도 큰 피해를 야기한다. 즉, 가뭄으로 인한 댐의 용수 공급 부족은 공업·농업뿐만 아니라 국민들의 생활에도 상당한 피해를 미친다. 하지만, 가뭄으로 인한 지역의 피해정도는 해당 지역의 특성 또는 가뭄에 대한 지역의 대처 능력에 따라 매우 상이하게 나타난다. 따라서, 가뭄에 의한 피해를 저감시키고 안전한 용수공급이 이루어질 수 있도록 지역의 특성 및 용수 공급 체계를 고려한 위험 정도를 분석하는 것이 필요하며, 사람들과 직접적인 연관성이 높은 물수급 관련 인자들을 고려하여 가뭄의 잠재적 영향 및 피해정도를 파악할 수 있는 가뭄 위험도 평가가 수행되어야 한다. 그러나 용수공급 및 수요 현황을 반영한 가뭄 노출성 및 취약성 평가는 아직 부족한 실정이며, 각 인자에 대한 가중치를 산정하는데 설문조사 또는 단순평균방법이 많이 이용되고 있다. 본 연구에서는 용수공급 체계 및 지역적 특성을 고려하고 객관적인 가중치 산정방안이 적용된 확률·통계적 가뭄 위험도를 평가방법을 제시하였다. 먼저, 용수공급 실패 사상의 발생 확률이 적용된 결합가뭄관리지수(Joint Drought Management Index, JDMI)를 통해 가뭄노출성지수(Drought Hazard Index, DHI)를 산정하고, 각 인자에 대한 영향정도를 객관적으로 판단할 수 있는 가우스 혼합 모델을 활용하여 가뭄취약성지수(Drought Vulnerability Index, DVI)를 산정하였다. 이 두 지수를 결합하여 가뭄위험도지수(Drought Risk Index, DRI)를 계산하고 위험도 평가를 수행하였다. 충청지역에 적용한 결과, DHI는 용수공급 실패 사상의 발생확률이 큰 보령시가 가장 높게 나타났으며, DVI는 농업적 요소의 가중치가 크게 산정됨에 따라 청주시가 가장 높게 산정되었다. DHI와 DVI가 결합된 DRI의 경우는 청주시가 가장 위험한 것으로 나타났다. 따라서, DRI가 가장 높은 청주시는 충정 지역의 가뭄 위험 경감을 위한 대응 수립시 우선적으로 고려되어야 한다.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.185-192
• /
• 2024

The aviation has improved safety through technological innovation and strengthened flight safety through safety regulations and supervision by aviation authorities. As the industry's safety approach has evolved into a systematic approach to the aircraft system, airlines have established a safety management system. Technical defects or abnormal data in an aircraft can be warning signs that could lead to an accident, and the risk of an accident can be reduced by identifying and responding to these signs early. Therefore, management of abnormal warning signs is an essential element in promoting data-based decision-making and enhancing the operational efficiency and safety level of airlines. In this study, we present a model to statistically analyze quick access recorder (QAR) flight data in the preliminary analysis stage to analyze the patterns and causes of crab landing events that can lead to runway departures when landing an aircraft, and provide a precursor to a landing event. We aim to identify signs and causes and contribute to increasing the efficiency of safety management.

• Journal of The Korean Association of Information Education
• /
• v.4 no.2
• /
• pp.147-158
• /
• 2001

Humanity education is the urgent and final problem of education all over the world. This study tries to promote intimate relationship, reliability, and openness between children and teacher which lack in intensive class, and establishes "Class Management System for Humanity Education" to experience an affirmative human relationship with children' s mutual group activities. "Class Management System for Humanity Education" is an integral system guiding a humanity factor only not presenting data, and is an appropriate system model for meeting information-oriented society actively as well as applying computer.

• Korean Business Review
• /
• v.20 no.1
• /
• pp.1-18
• /
• 2007

Teachers are faced with multiple social needs that they should not only fulfill their traditional duties but also cope with various educational situation because of the rapidly shifting education environment. Like this the latest tendency around teachers' job offers more important issue related teachers' socialization tactics. In spite of these strong argument for the gravity of the teachers' socialization tactics, there are few articles about teachers' socialization tactics and its effect. This paper aims to design the theoretical model for the next empirical research plan that will investigate outcomes(job satisfaction, organizational commitment) of teachers' socialization tactics through literature and former study.