• Database Research
• /
• v.34 no.3
• /
• pp.99-123
• /
• 2018

Due to the ever expanding nature of the Web, separating more valuable information from the noisy data is getting more important. Although recommendation systems are widely used for addressing the information overloading issue, their performance does not seem meaningfully improved in currently suggested approaches. Hence, to investigate the issues, this study discusses different characteristics of popular, existing recommendation approaches, and proposes a new profiling technique that uses collaborative tags and test whether it successfully compensates the limitations of the existing approaches. In addition, the study also empirically evaluates rating/tagging patterns of users in various recommendation approaches, which include the proposed approach, to learn whether those patterns can be used as effective cues for improving the recommendations accuracy. Through the sensitivity analyses, this study also suggests the potential associated with a single recommendation system that applies multiple approaches for different users or items depending upon the types and contexts of recommendations.

• Journal of the Korea Convergence Society
• /
• v.10 no.5
• /
• pp.35-42
• /
• 2019

Recently, as the Internet and various wearable devices have appeared, Internet technology has contributed to obtaining more convenient information and doing business. However, as the internet is used in various parts, the attack surface points that are exposed to attacks are increasing, Attempts to invade networks aimed at taking unfair advantage, such as cyber terrorism, are also increasing. In this paper, we propose a feature selection method to improve the classification performance of the class to classify the abnormal behavior in the network traffic. The UNSW-NB15 dataset has a rare class imbalance problem with relatively few instances compared to other classes, and an undersampling method is used to eliminate it. We use the SVM, k-NN, and decision tree algorithms and extract a subset of combinations with superior detection accuracy and RMSE through training and verification. The subset has recall values of more than 98% through the wrapper based experiments and the DT_PSO showed the best performance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.2
• /
• pp.225-238
• /
• 2012

Among the various security threats in online games, the use of game bots is the most serious problem. In this paper, we propose a framework for user behavior analysis for bot detection in online games. Specifically, we focus on party play that reflects the social activities of gamers: In a Massively Multi-user Online Role Playing Game (MMORPG), party play log includes a distinguished information that can classify game users under normal-user and abnormal-user. That is because the bot users' main activities target on the acquisition of cyber assets. Through a statistical analysis of user behaviors in game activity logs, we establish the threshold levels of the activities that allow us to identify game bots. Also, we build a knowledge base of detection rules based on this statistical analysis. We apply these rule reasoner to the sixth most popular online game in the world. As a result, we can detect game bot users with a high accuracy rate of 95.92%.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.65-72
• /
• 2022

In this paper, a zero trust-based complex biometric authentication was proposed in a passwordless environment. The linkage of FIDO 2.0 (Fast IDENTITY Online) transaction authentication platforms was designed in conjunction with metaverse. In particular, it was applied with the location information of a smart terminal according to a geomagnetic sensor, an accelerator sensor, and biometric information for multi-factor authentication(MFA). At this time, a FIDO transaction authentication platform was presented for adaptive complex authentication with user's environment through complex authentication with secondary authentication based on situational awareness such as illuminance and temperature/humidity. As a result, it is possible to authenticate secondary users based on zero trust with behavior patterns such as fingerprint recognition, iris recognition, face recognition, and voice according to the environment. In addition, it is intended to check the linkage result of the FIDO platform for complex integrated authentication and improve the authentication accuracy of the linkage platform for transaction authentication using FIDO2.0.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.90-101
• /
• 2022

Buses are a popular means of transportation. As such, thorough preparation is needed for passenger safety management. However, the safety system is insufficient because there are accidents such as a death accident occurred when the bus departed without recognizing the elderly approaching to get on in 2018. There is a safety system that prevents pinching accidents through sensors on the back door stairs, but such a system does not prevent accidents that occur in the process of getting on and off like the above accident. If it is possible to predict the intention of bus passengers to get on and off, it will help to develop a safety system to prevent such accidents. However, studies predicting the intention of passengers to get on and off are insufficient. Therefore, in this paper, we propose a 1×1 CNN3D-based getting on and off intention prediction model using skeleton keypoints of passengers extracted from the camera image attached to the bus through UDP-Pose. The proposed model shows approximately 1~2% higher accuracy than the RNN and LSTM models in predicting passenger's getting on and off intentions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.249-251
• /
• 2022

In this paper, we present machine learning to control drone flight using EEG signals. We defined takeoff, forward, backward, left movement and right movement as control targets and measured EEG signals from the frontal lobe for controlling using Fp1. Fp2 Fp2 two-channel dry electrode (NeuroNicle FX2) measuring at 250Hz sampling rate. And the collected data were filtered at 6~20Hz cutoff frequency. We measured the motion image of the action associated with each control target open for 5.19 seconds. Using Matlab's classification learner for the measured EEG signal, the triple layer neural network, logistic regression kernel, nonlinear polynomial Support Vector Machine(SVM) learning was performed, logistic regression kernel was confirmed as the highest accuracy for takeoff and forward, backward, left movement and right movement of the drone in learning by class True Positive Rate(TPR).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.91-91
• /
• 2020

IPCC (Intergovernmental Panel on Climate Change) 5차 평가보고서에 의하면 최근 배출 온실가스의 양은 관측 이래 최고 수준이며 온실가스로 인한 기후변화는 인간계와 자연계에 광범위한 영향을 주고 있다고 보고하였다. 기후변화의 영향은 국제적으로 빙하 감소, 사막화, 해수면 상승 등 뚜렷하게 나타나고 있다. 이러한 기후변화에 대응하기 위해 온실가스 완화 정책과 동시에 새로운 기후변화 환경에 적응하는 것이 필요하다. 기후변화 적응이란 현재 나타나고 있거나 미래에 나타날 것으로 예상되는 기후변화의 파급효과와 영향에 대응할 수 있도록 하는 모든 행동이며 이를 위해서는 기후변화 영향분석이 수반되어야 한다. MOTIVE 연구단에서는 기후변화 적응대책 수립의 지원을 목표로 7개 부문(건강, 물관리, 농업, 산림, 생태, 해양, 수산)에서 "한국형 통합평가 모형"을 개발하고 있다. 각 부문에서 개발하는 프로세스 모델은 시스템에 대한 지식을 가진 상황에서 사용하면 신뢰할 수 있는 예측 결과를 얻을 수 있지만, 부문별 통합을 통한 영향 분석 시 타 분야에 대한 지식이 수반되어야 하는 어려움을 가진다. 이를 위해 본 연구에서는 시스템 내의 물리적 프로세스에 대한 요구 없이 입출력 데이터만을 이용하여 결과를 신속하게 추정하는 데이터 모델링(기계학습)을 이용하였다. 데이터 모델링을 위한 데이터는 다양한 자연 현상에 대한 BANPOL(수질 프로세스 모델) 분석을 통한 자료를 이용하여 학습 자료를 구축하였다. 즉, 데이터 모델링은 BANPOL 모델을 대리하는 메타모델이며, 낙동강 표준유역에 대한 유량 및 수질을 높은 상관성으로 추정하였다. 원 모델보다 정확도는 낮을 수 있으나 메타모델의 개발을 통한 웹 시스템을 개발하여 비전문가의 구동 및 신속한 기후 시나리오를 적용할 수 있는 환경을 개발하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.428-428
• /
• 2021

상수관망 내 수질사고는 매우 다양한 원인과 상황에서 시·공간적으로 광범위하게 발생가능하다. 일반적인 수질사고의 정성적 정의는 "정상적인 운영에 비하여 상대적으로 비정상적인 활동이나 행동에 의해 발생되는 수질문제"라고 할 수 있으나, 이는 매우 광의적이라 할 수 있으며 실제 현장에서는 발생 가능한 모든 수질사고 시나리오를 미리 예측하여 대비하기에 한계가 있다. 본 연구에서는 국외 및 국내 지자체, 그리고 K-water 등의 자료를 확보하여, 상수도 공급계통에서 발생한 수질사고 사례 및 발생 빈도 등을 분석하였다. 이를 상수도 관망 내에서 발생빈도가 잦고 피해영향이 큰 대표 수질사고 발생 시나리오 선정에 활용하였다. 과거 사례를 분석한 결과, 관망 내 대표적인 수질사고는 정상적 운영조건 (예, 정수처리문제에 의한 유출수내 고탁도 발생)뿐 만 아니라, 비정상적인 운영조건 (수계전환, 밸브조작 등에 의한 유속, 수압 변동에 의한 고탁도 발생)에서 발생 가능함을 확인하였다. 이와 같은 대표적 수질사고는 수리학적 조건의 변화에 따라 관망 내 수질이 변화되어 발생되므로, 수질사고의 현실적인 모의를 위해서는 합리적인 수리학적 관망해석이 수반되어야 한다. 상수관망 시스템의 수리해석 기법은 크게 수요기반해석(Demand Driven Analysis; DDA)과 수압기반해석(Pressure Driven Analysis; PDA)로 구분 가능하다. 기본적으로 정상적 운영조건은 수요기반해석의 수행이 적절하며, 비정상적 운영조건은 수압저하에 의한 수리적상태가 변동하므로 수압기반해석이 필수적이라 할 수 있다. 본 연구에서는 대표적 수질사고의 모의 시 필요한 적정수리해석 기법을 제안하고, 각 적정 해석기법 별 검·보정이 필요한 인자들에 대해 제시하였다. 이와 같은 수리해석 기법을 적절히 활용할 경우, 관망 내 탁수사고 발생 가능성이 높은 지점 등을 결정하는 방법론의 정확도가 높아질 것으로 기대된다.

• Korean Journal of Culture and Social Issue
• /
• v.12 no.4
• /
• pp.77-99
• /
• 2006

The purpose of this study was to find out the effects of auto-mobile tinting upon driver's cognitive responses and behaviors through two laboratory experiments, a field experiment and a traffic accident data. The results of two laboratory experiments showed that there were higher false alarm responses under the conditions of 65%, 50%, 35% tinting level than thoses under the 100% level condition. It was also shown that the drivers who had bad sight made more missing responses than the drivers who had normal vision. The main results of the laboratory experiment were repliceted through both the field experiment and the survey research of car accidents. The results of this study were discussed in terms of the previous studies performed abroad. We strongly suggested 70% tinting level as a regulation standard for safe driving and the strategies for implementing the regulation rule.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.25-41
• /
• 2024

For the scenario of open pit mining, at present, manual periodic verification is mainly carried out in China with the help of video surveillance, which requires continuous investment in labor cost and has poor timeliness. In order to solve this difficult problem of early warning and monitoring, this paper researches a spatialized algorithmic model and designs an early warning system for open-pit mine transboundary mining, which is realized by calculating the coordinate information of the mining and extracting equipments and comparing it with the layer coordinates of the approval range of the mines in real time, so as to realize the determination of the transboundary mining behavior of the mines. By taking the Pingxiang area of Jiangxi Province as the research object, after the field experiment, it shows that the system runs stably and reliably, and verifies that the target tracking accuracy of the system is high, which can effectively improve the early warning capability of the open-pit mines' overstepping the boundary, improve the timeliness and accuracy of mine supervision, and reduce the supervision cost.