• Proceedings of the KIEE Conference
• /
• 1998.07a
• /
• pp.359-361
• /
• 1998

본 연구에서는 시스템의 대규모 SCADA 시스템들에 효과적으로 적용될 수 있는 전문가 시스템을 설계한다. 전문가 시스템의 추론기관은 직관적 추론 기능과 논리적 추론기능이 연동되도록 설계한다. 직관적 추론기능은 패턴인식구조로, 논리적 추론기능은 휴리스틱에 근거한 심층추론을 통해 시스템 이벤트별로 다양한 시간제야조건을 만족하는 시스템 제어전략을 결정함과 동시에, 지식 생성자의 역할을 할 수 있도록 다중 추론구조로 설계한다.

• Proceedings of The KACE
• /
• 2018.08a
• /
• pp.147-149
• /
• 2018

음성인식, 행동패턴인식, 텍스트마이닝 등 사람의 자연스러운 사회적인 활동을 통해 감성을 분석하려는 연구는 지속적으로 증가하고 있다. 특히 SNS는 현대사회에서 없어서는 안 될 소통의 도구로 자리 잡았기 때문에 SNS의 비정형데이터를 이용한 감성분석은 마케팅 분야에서 중요한 활용도구로 사용되고 있다. 이러한 추세에 따라 한국어에 대한 감성인식 역시 다방면으로 분석, 활용되고 있고 한국어의 어순과 표현방식, 중의성, 방언 등의 몇 가지 특징으로 인해 영어와는 다른 방식으로의 접근방식에 대한 필요성이 많은 연구에서 논의되고 있다. 따라서, 이 연구에서는 이러한 한국어의 특징을 수용하여 분석할 수 있도록 시계열 분석에 유용한 LSTM과 중복단어에 대한 가중치를 적용하여 한국어 감성분석을 진행해보고자 한다.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.438-456
• /
• 2010

Iris recognition uses a unique iris pattern of user to identify person. In order to enhance the performance of iris recognition, it is reported that the diameter of iris region should be greater than 200 pixels in the captured iris image. So, the previous iris system used zoom lens camera, which can increase the size and cost of system. To overcome these problems, we propose a new method of enhancing the accuracy of iris recognition on low-resolution iris images which are captured without a zoom lens. This research is novel in the following two ways compared to previous works. First, this research is the first one to analyze the performance degradation of iris recognition according to the decrease of the image resolution by excluding other factors such as image blurring and the occlusion of eyelid and eyelash. Second, in order to restore a high-resolution iris image from single low-resolution one, we propose a new method based on multiple multi-layered perceptrons (MLPs) which are trained according to the edge direction of iris patterns. From that, the accuracy of iris recognition with the restored images was much enhanced. Experimental results showed that when the iris images down-sampled by 6% compared to the original image were restored into the high resolution ones by using the proposed method, the EER of iris recognition was reduced as much as 0.133% (1.485% - 1.352%) in comparison with that by using bi-linear interpolation

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.142-151
• /
• 1993

An intelligent mulitiple monitoring system to monitor tool/machining states synthetically was proposed and developed. It consists of 2 fundamental subsystems : the multiple sensor detection unit and the intellignet integrated diagnosis unit. Three signals, that is, spindle motor current, Z-axis motor current, and machining sound were adopted to detect tool/machining states more reliably. Based on the multiple sensor information, the diagnosis unit judges either tool breakage or degree of tool wear state using fuzzy reasoning. Tool breakage is diagnosed by the level of spindle/z-axis motor current. Tool wear is diagnosed by both the result of fuzzy pattern recognition for motor currents and the result of pattern matching for machining sound. Fuzzy c-means algorithm was used for fuzzy pattern recognition. Experiments carried out for drill operation in the machining center have shown that the developed system monitors abnormal drill/states drilling very reliably.

• Journal of KIISE:Software and Applications
• /
• v.28 no.11
• /
• pp.864-873
• /
• 2001

In this paper, a new approach to building a registration authority for issuing PKI-based certificates is presented to make the process of identifying an individual more secure and reliable by utilizing human iris recognition technology. The tasks of the proposed system associated with the manipulation of irises except for the general functions of registration authorities can be categorized into three modules, the acquisition of iris images, the registration of iris information, and the verification of users by means of iris patterns. The information among the three modules is safely exchanged through encryption and decryption with a symmetric cryptographic method. As a feature extraction method for a given iris image, a wavelet transform is applied to represent a feature vector with a small dimension of information obtained by subsampling an image corresponding to lower frequency bands successively without loss of information. Through the experiments on human iris recognition technology we proposed and applied to the registration authority, the potential of biometric technology in various applications is confirmed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.597-602
• /
• 2014

We propose hybrid-sensing system for human tracking. This system uses laser scanners and image sensors and is applicable to wide and crowded area such as hallway of university. Concretely, human tracking using laser scanners is at base and image sensors are used for human identification when laser scanners lose persons by occlusion, entering room or going up stairs. We developed the method of human identification for this system. Our method is following: 1. Best-shot images (human images which show human feature clearly) are obtained by the help of human position and direction data obtained by laser scanners. 2. Human identification is conducted by calculating the correlation between the color histograms of best-shot images. It becomes possible to conduct human identification even in crowded scenes by estimating best-shot images. In the experiment in the station, some effectiveness of this method became clear.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.824-827
• /
• 2005

The need to be able to identify other individual human beings is fundamental to the security and has been true since the beginning of human history. Physical or behavioral characteristics (finger-scan, face-scan, voice, palm, iris, retina, signature, human DNA, keystroke, vain, gait etc.) of a person are used to authenticate the person. The biometric technologies allow for a greater reliability of authentication as compared with password systems for physical access, network security, e-commerce, and so on. In this paper, we describe various technologies, market analysis, multi-modal system, standardization, privacy issue and future prospect of biometrics.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.571-576
• /
• 2020

When a user visits a specific site through various devices, the hero image located in the main area that can be viewed without scrolling includes multiple slides and has various carousel navigation patterns. While there is a negative perception that the carousel design does not receive the user's choice due to the hidden slide, it can be seen that its usefulness can vary depending on the user's context. In addition, the navigation pattern of the carousel design is the factor that has the greatest influence on the user experience. The left and right arrow navigation pattern, the bottom pagination navigation pattern, the accordion type navigation pattern, the thumbnail type navigation pattern, the divided slide type navigation pattern, and the last. It could be divided into six types of left and right slide navigation patterns.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.250-252
• /
• 2003

패턴 인식 분야에서 다중 분류기 시스템은 여러 분류기의 결과들을 조합하여 전체 성능을 항상 시키는 시스템이다. 다중 분류기를 사용함으로써 단일 분류기 보다 더 나은 결과를 얻을 수 있음은 이미 널리 알려진 사실이다. 서로 다른 구조를 갖는 분류기들은 상호 보완적인 정보를 제공하기 때문에 각 분류기마다 입력 공간에 대해서 지역적으로 좋은 성능을 갖는다. 본 논문에서는 지역적으로 가장 좋은 성능을 보이는 분류기 선택 방법을 제안한다. 제안하는 방법은 주어진 입력 공간에 비해 각 분류기들을 학습하는 과정에서 자기조직화지도를 생성하고 각 노드별로 평가함으로써 입력이 주어지면, 해당 노드에서 가장 성능이 좋은 분류기를 선택하여 전체 성능을 향상시키는 시스템이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.451-454
• /
• 2005

본 논문에서는 수정된 CNN(Convolutional Neural Network) 모델과 다중 필터가 상호 결합된 형태의 얼굴 패턴 검출 기법을 소개 한다. 이는 로봇 시각의 응용문제에서 실내영상의 실시간 인식문제를 대상으로 한다. 검출 과정의 효율성 향상을 위하여 도입된 다중 필터는 후보 영역의 개수와 범위를 줄일 수 있게 한다. 제안된 모델에서 CNN 신경망은 가보변환(Gabor Transform)계층을 두어 검출 과정의 첫 단계에서 영상 내의 기본 특징 지도를 생성 하도록 하였다. 보다 강인한 검출기능을 위하여 조명보정 기법이 시스템의 전처리 단계로 구현 된다. 실제 영상을 통한 실험 결과로부터 제안된 이론의 타당성을 고찰 한다.