• 전기학회논문지
• /
• 제57권2호
• /
• pp.320-326
• /
• 2008

In this paper, we propose a new algorithm emulating the DNA characteristics for noise-tolerant pattern matching problem on digital system. The digital pattern matching becomes core technology in various fields, such as, robot vision, remote sensing, character recognition, and medical diagnosis in particular. As the properties of natural DNA strands allow hybridization with a certain portion of incompatible base pairs, DNA-inspired data structure and computation technique can be adopted to bio-signal pattern classification problems which often contain imprecise data patterns. The key feature of noise-tolerance of DNA computing comes from control of reaction temperature. Our hardware system mimics such property to diagnose cardiovascular disease and results superior classification performance over existing supervised learning pattern matching algorithms. The hardware design employing parallel architecture is also very efficient in time and area.

• The International Journal of Costume Culture
• /
• 제12권1호
• /
• pp.13-25
• /
• 2009

This research is progressed to look out for efficient expression-elements of eroticism used in advertisements. Since these expressions of eroticism appealing to sex which is one of the primitive instincts of mankind are increasing in advertisements of cosmetic products which are used more often by recent high-rate-growth and the elevation of living conditions. The most usual expression-elements of eroticism in advertisement are exposure, pose, fashion style, make up, hair style and color. To analyze those expression-elements we made four pieces of fashion advertisement photos with four different types and surveyed both fashion majored students and non-fashion majored students. We applied regression analysis, ANOVA, and frequency analysis to verify the hypothesis. We found that in eroticism, the pose was the most important cognitive feature among the expression-elements and degree of cognition are varied according to major field and sexual interest. As a result, degree of cognition which effected by expression-elements will be varied even in same advertisement. In particular, convincing that the pose was the significant factor of eroticism cognition, expression of eroticism in advertisement would be more diverse and daring.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(1)
• /
• pp.133-136
• /
• 2002

VoiceXML is designed for creating audio dialogs that feature synthesized speech, degitized audio, recognition of spoken and DTMF key input, recording of spoken input, telephony, and mixed-initiative conversations. Uses the VoiceXML and there is a Place objective which does information home appliance machinery and tools control. When it uses tile VoiceXML, il will be able to provide a bias characteristic to the user The XML base the gearing with different civil official system is possible. With studying YoiceXML and OSGi, this paper has designed and implemented the control architecture of Information home appliances.

• 로봇학회논문지
• /
• 제11권2호
• /
• pp.108-114
• /
• 2016

This paper presents a sensor-based cane mechanism for walking aid of the visually impaired person. We also describe an approach to decide properly the length of the specified cane mechanism. The cane mechanism has some sensors to identify the possibility of a collision between the cane user and an object and/or a person, and a signal processing unit that enables the user to recognize such a collision is attached in the mechanism. Thus, the walker using this cane can recognize in advance the possibility of such a collision in his walking process. Consequently, it is helpful for the visually impaired person to walk on a pedestrian road safely. The feature of the proposed cane mechanism and its availability have been shown through experimental works in a typical walking environment.

• 대한산업공학회지
• /
• 제18권1호
• /
• pp.155-167
• /
• 1992

This paper presents an automatic setup planning system for turning operation of symmetric rotational parts. The proposed setup planning system determines workpiece holding method, number of setup, clamping surface, and workpiece holding device by using design data, part description database and part feature recognition information. The workpiece holding method is based on functional name and length/diameter ratio of the given part, and number of setup is determined by part profile type and its technological constraints. Clamping surface and workpiece holding device are determined by using information about the results of workpiece holding method and number of setup, and capacity of workpiece holding devices. A case study is performed to show the performance of the proposed system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.29.2-29
• /
• 2001

For the design of human-centered systems in which a human and machine such as a robot form a human-in system, human-friendly interaction/interface is essential. Human-friendly interaction is possible when the system is capable of recognizing human biosigns such as5 EMG Signal, hand gesture and facial expressions so the some humanintention and/or emotion can be inferred and is used as a proper feedback signal. In the talk, we report our experiences of applying the Soft computing techniques including Fuzzy, ANN, GA and rho rough set theory for efficiently recognizing various biosigns and for effective inference. More specifically, we first observe characteristics of various forms of biosigns and propose a new way of extracting feature set for such signals. Then we show a standardized procedure of getting an inferred intention or emotion from the signals. Finally, we present examples of application for our model of rehabilitation robot named.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1543-1561
• /
• 2020

Taxonomy of human brain activity is a complicated rather challenging procedure. Due to its multifaceted aspects, including experiment design, stimuli selection and presentation of images other than feature extraction and selection techniques, foster its challenging nature. Although, researchers have focused various methods to create taxonomy of human brain activity, however use of multivariate pattern analysis (MVPA) for image recognition to catalog the human brain activities is scarce. Moreover, experiment design is a complex procedure and selection of image type, color and order is challenging too. Thus, this research bridge the gap by using MVPA to create taxonomy of human brain activity for different categories of images, both colored and gray scale. In this regard, experiment is conducted through EEG testing technique, with feature extraction, selection and classification approaches to collect data from prequalified criteria of 25 graduates of University Technology PETRONAS (UTP). These participants are shown both colored and gray scale images to record accuracy and reaction time. The results showed that colored images produces better end result in terms of accuracy and response time using wavelet transform, t-test and support vector machine. This research resulted that MVPA is a better approach for the analysis of EEG data as more useful information can be extracted from the brain using colored images. This research discusses a detail behavior of human brain based on the color and gray scale images for the specific and unique task. This research contributes to further improve the decoding of human brain with increased accuracy. Besides, such experiment settings can be implemented and contribute to other areas of medical, military, business, lie detection and many others.

• 한국정보통신학회논문지
• /
• 제21권3호
• /
• pp.558-567
• /
• 2017

본 연구에서는 다수의 키넥트 센서를 이용하여 효율적인 실시간 운동 자세 추정 시스템을 설계하고 개발하였다. 이 시스템은 정면과 측면에 키넥트 센서를 사용하여, 한 개로 추적이 어려웠던 사용자의 특정 자세 (예를 들어, 무릎컬 또는 런지)를 보다 정확하게 측정하고 인식하는 것을 목적으로 한다. 그리고 추후 다양한 자세를 지원할 수 있도록 확장 가능하고 모듈화 된 방법으로 설계되었다. 이 시스템은 여러 클라이언트와 유니티 3D 서버로 구성된다. 클라이언트는 키넥트 골격 데이터를 처리하여 서버로 전송한다. 서버는 다중 키넥트를 보정하고, 각도와 거리를 기반으로 한 특징 값 추출하며 여러 대의 키넥트로부터 계산된 특징 값의 가중 평균을 사용하여 자세 인식 모델을 기반으로 자세 추정 알고리즘을 적용한다. 본 논문은 다중 키넥트 센서를 이용한 인간 운동 자세 추정 시스템의 설계 및 구현 방법을 제시하고, 체험형 유니티 3D 운동 게임에 적용한 예시를 설명한다.

• 한국CDE학회논문집
• /
• 제11권4호
• /
• pp.289-302
• /
• 2006

It is becoming a common trend that many designers work on a very complex assembly together in a collaborative environment. In this environment, every designer should be able to see the whole assembly in a full detail or in a rough shape at least. Even though the hardware technology is being improved very rapidly, it is very difficult to display a very complex assembly at a speed to allow smooth interactions for designers. This problem could be solved if a designer could manipulate his portion of the assembly in a full resolution while the remaining portion of the assembly is displayed in a rough resolution. It is also desired that the remaining portion is converted to the full resolution when needed. To realize this environment, the capabilities to simplify the portions of an assembly and to reset to the original resolution should be added to the current CAD systems. Thus operators realizing multi-resolution on B-rep are proposed in this paper. They are: wrap-around, smooth-out, and thinning operator. Through appropriately applying these operators sequentially, an assembly model of any desired resolution can be easily generated. Of course, the assembly can go back to the finer resolution. In this paper, the data structures and the processes to realize these operators are described and a prototype modeling system with these operators is also demonstrated.

• 정보처리학회논문지B
• /
• 제10B권3호
• /
• pp.311-320
• /
• 2003

고유의 텍스쳐 성분에만 최적 반응을 하는 최적 필터(optimal filter)는 다중 텍스쳐 영상으로부터 원하는 텍스쳐 성분을 추출하기 위한 가장 뛰어난 기술이다. 그러나 기존의 최적필터 설계 방법들은 영상에 내재된 텍스쳐 정보가 사전에 주어지는 교사적 방법이 대부분이며, 내재된 텍스쳐 인식을 기반으로 하는 완전 비교사적인 방법에 관한 연구는 거의 이루어지고 있지 않은 실정이다. 따라서 본 논문에서는 효율적인 텍스쳐 분석을 위한 비교사 학습 방법과 가버필터의 주파수 대역 통과형 특징을 이용한 새로운 최적 필터 설계 방법을 제안한다. 제안한 방법은 자기조직형 신경회로망에 의해서 영상에 내재된 텍스쳐 영역을 블록 단위로 군화(clustering)하며, 가버필터의 최적 주파수는 인식된 텍스쳐 오브젝트(texture objects)의 공간 주파수를 분석한 최적 주파수에 동조(turning)한다. 그리고 설계된 최적 가버필터의 성능 평가를 위해서는 다양한 형태의 다중 텍스쳐 영상을 생성하여 내재된 텍스쳐 오브젝트를 추출함으로써 성공적인 결과를 보인다.