• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.601-604
• /
• 2003

본 논문은 프로젝션 화면에서 사용자와 컴퓨터간의 상호작용을 위한 인터페이스인 리바이저를 제안한다. 리바이저는 프로젝션 화면에서 사용자의 손 제스처로 문서교정 부호를 인식하여 전자문서를 교정하는 인터페이스 시스템이다. 프로젝션 화면에서 이러한 제스처를 인식하려면 두 가지 문제가 있다. 하나는 다양한 빛의 변화와 복잡한 배경을 가지는 프로젝션 화면에서 전방물체를 검출하는 것이고, 다른 하나는 사용자의 연속적인 움직임에서 사용자의 의도를 알아내는 것이다. 전방물체를 검출하기 위해 프로젝터로 입력되는 영상과 카메라에 의해 캡쳐된 영상 사이의 색상정보를 사용한다. 이 색상정보는 다양한 빛의 변화와 복잡한 배경에서 전방물체를 구별할 수 있게 한다. 연속된 제스처를 인식하기 위해 적출과 인식이 포함된 새로운 제스처 적출방법을 제안한다. 실험결과 제안된 시스템에서 의미없는 움직임이 포함된 제스처 시퀀스에서 사용자 제스처의 인식률은 평균 93.22%로 만족할만한 결과를 보였다.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.289-295
• /
• 2014

Intrusion detection system is a means of security that detects abnormal use and illegal intension in advance in real time and reenforce the security of enterprises. Performance of intrusion detection system is judged by information collection, intrusion analysis, intrusion response, review and protection of intrusion detection result, reaction, loss protection that belong to the area of intrusion detection. In this paper, we developed a evaluation model based on the requirements of intrusion detection system and ISO international standard about software product evaluation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.388-390
• /
• 2019

운영체제는 해당 시스템이 운영되면서 생기는 흔적을 남길 수 있게 설계되었다. 디지털 포렌식에서 아티팩트는 보관증거 또는 데이터의 정보를 확증하는데 사용된다. 디지털 정보는 사용자의 생활방식에 따라 사용자의 습관, 사상, 감정에 영향을 받아 저장될 수 있다. 디지털 증거의 경우, 한 저장매체에 많은 데이터가 함께 저장되어 있을 뿐만 아니라 대형 서버 시스템의 경우에는 수많은 사람들의 정보도 저장되어 특정의 데이터만을 찾아내기가 쉽지 않다. 이러한 문제를 해결하기 위해 자연어 처리와 머신러닝 기술이 활용될 수 있다. 자연어 처리기술은 인간과 컴퓨터 간 인터페이스를 쉽고 편하게 하고, 자연어로 기록되어 있는 아티팩트를 머신러닝을 이용하여 빠른 분석을 가능하게 한다. 본 논문은 자연어처리와 머신러닝을 이용한 디지털 아티팩트 분석 방안을 제안한다. 자연어 처리와 머신러닝을 이용하여 아티팩트에서 사용자의 의도를 파악할 수 있음을 실험을 통하여 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.9-16
• /
• 2005

Recently, since the number of internet users is increasing rapidly and, by using the Public hacking tools, general network users can intrude computer systems easily, the hacking problem is setting more serious. In order to prevent the intrusion. it is needed to detect the sign in advance of intrusion in a Positive Prevention by detecting the various forms of hackers intrusion trials to know the vulnerability of systems. The existing network-based anomaly detection algorithms that cope with port-scanning and the network vulnerability scans have some weakness in intrusion detection. they can not detect slow scans and coordinated scans. therefore, the new concept of algorithm is needed to detect effectively the various. In this Paper, we propose a detection algorithm for session patterns and FCM.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.9
• /
• pp.844-853
• /
• 2016

Generally, the compromising electromagnetic emanations are generated from LCD(Liquid Crystal Display) monitor which is typical output component of computer. Because display information transmitted to LCD monitor is included in these emanations, there are risks about information leakage of monitor by eavesdropping of leaked signal. So, analysis about possibility of information leakage is necessary because electromagnetic security through the electromagnetic emanations is being at issue. In this paper, the possibility of display information leakage are demonstrated by analyzing the electromagnetic emanations from desktop and laptop monitors. The characteristics of leaked signal from LCD monitor is verified by analyzing display mechanism and the electromagnetic emanations are measured in the long distance by eavesdropping experiment. Also, threat of information leakage is confirmed by recovering display information with several signal processing technique and comprising with target display.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.5
• /
• pp.11-19
• /
• 2015

Our research introduces a novel system for creating 3D vehicle animation. Our system is for intuitively authoring vehicle accident scenes according to videos or based on user-drawn trajectories. Our system has been implemented by combining three existing ideas. The first part is for obtaining 3D trajectory of a vehicle from black-box videos. The second part is a tracking algorithm that controls a vehicle to follow a given trajectory with small errors. The last part optimizes the vehicle control parameters so that the error between the input trajectory and simulated vehicle trajectory is minimized. We also simulate the deformation of the car due to an impact to achieve believable results in real-time.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.38-43
• /
• 2016

As smart environment is spread out in our living environments, the needs of an approach related to Human Computer Interaction(HCI) is increases. One of them is head pose estimation. it related to gaze direction estimation, since head has a close relationship to eyes by the body structure. It's a key factor in identifying person's intention or the target of interest, hence it is an essential research in HCI. In this paper, we propose an approach for head pose estimation with pre-defined several directions by random forest classifier. We use canny edge detector to extract feature of the different facial image which is obtained between input image and averaged frontal facial image for extraction of rotation information of input image. From that, we obtain the binary edge image, and make two accumulated histograms which are obtained by counting the number of pixel which has non-zero value along each of the axes. This two accumulated histograms are used to feature of the facial image. We use CAS-PEAL-R1 Dataset for training and testing to random forest classifier, and obtained 80.6% accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.225-232
• /
• 2022

This study aims to empirically examine whether consumers' perceptions of Chinese e-commerce firms's CSR activities, along with psychological construct of company-consumer identification, and corporate trust affect their purchase intention based on theory of reasoned action. The study used a survey method for data collection to confirm research hypotheses with a total of 240 respondents used for final analysis. The results showed that economic responsibility, ethical responsibility, and legal responsibility have a positive effect on consumers' purchase intention. In addition, corporate trust and company-consumer identification were found to mediate the relationship between consumers' CSR perceptions and purchase intention. The result of this study is expected to provide useful theoretical as well as practical implications to advance the current understanding on the effects of consumers' CSR perception on business performance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.223-233
• /
• 2024

This study investigates the impact of personalization recommendation systems on customer loyalty in e-commerce, focusing on the role of information presentation, system interaction, and social community functions. It examines how these elements influence flow state, word of mouth (WOM), and repurchase intention (RPI). Using structural equation modeling (SEM) and data collected from 500 respondents in SPSS and AMOS, the study finds that all three personalization aspects significantly enhance flow state, which, in turn, positively affects WOM and RPI. System interaction directly boosts both WOM and RPI, while information presentation and social community functions influence only one of these loyalty measures. Flow state mediates the relationship between personalization factors and loyalty outcomes. These findings suggest e-commerce platforms should enhance system interaction and embed social community features to foster customer loyalty.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1539-1545
• /
• 2015

GPS (global positioning system) is a popular system that provides location information by measuring arrival time difference at the receiver between several GPS satellite signals. GPS is widely used in commercial area as well as military systems. Reliable GPS signal reception is more important in the military systems. However, since the carrier frequencies of the GPS signals are well known, the GPS receivers are vulnerable to intentional jamming attacks. To remove jammers but maintain GPS signals at the received signals, a popular technique is an adaptive beam steering method based on array antenna. Among adaptive beam steering techniques, this paper considers MVDR (minimum variance distortionless response) algorithm, and proposes a new adaptive technique that preserves the received signals at desired direction, but removes the jamming signals adaptively. The performance of the proposed method is verified through computer simulation.