• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.263-264
• /
• 1998

In this paper, we present the result of feature points recognition and classification of radial pulse by the shape of pulse wave. And we analyze radial pulse in frequency domain. The recognition algorithm use the method which runs in parallel with both the data of ECG and differential pulse simultaneously to recognize the feature points. Also fie specified 3-time elements of pulse wave as main parameters for diagnosis and measured them by execution of algorithm, then we classify the shape of radial pulse by existence and position of feature points. lastly we execute frequency analysis on the feature points and get the power spectrum of radial pulse.

• 한국통신학회논문지
• /
• 제22권3호
• /
• pp.481-492
• /
• 1997

This paper presents an algorithm for recognizing surface mount device(SMD) IC pattern based on the error back propoagation(EBP) neural network and discrete cosine transform(DCT). In this approach, we chose such parameters as frequency, angle, translation and amplitude for the shape informantion of SMD IC, which are calculated from the coefficient matrix of DCT. These feature parameters are normalized and then used for the input vector of neural network which is capable of adapting the surroundings such as variation of illumination, arrangement of objects and translation. Learning of EBP neural network is carried out until maximum error of the output layer is less then 0.020 and consequently, after the learning of forty thousand times, the maximum error have got to this value. Experimental results show that the rate of recognition is 100% in case of the random pattern taken at a similar circumstance as well as normalized training pattern. It also show that proposed method is not only relatively relatively simple compare with the traditional space domain method in extracting the feature parameter but also able to re recognize the pattern's class, position, and existence.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1995년도 추계학술대회 학술발표 논문집
• /
• pp.11-14
• /
• 1995

A Fuzzy Classifier which deals with very confusing objects is proposed. Naturally this classifier heavily relies on the nulti-feature decision-making procedure. For a simple example, this classifier is applied to the recognition of confusing handwritten numerals 4,6 and 9 The characteristic variables used in this paper are the existence of a loop and the relative location of the starting or ending points(SEP). Thus each sample of handwritten numerals 4, 6 and 9 is classified in one of the 6 groups which are divided according to the sample structure. Each group has its own classifying rules. Also the method of rule-generation using genetic algorithms in each group is proposed.

• 유통과학연구
• /
• 제17권4호
• /
• pp.17-26
• /
• 2019

Purpose - Today's companies concentrate intensively on building consumer value and corporate reputation for continuing growth and advancement in an ever-changing global business management environment. This research intended to study the correlation between consumer value and corporate social responsibility (CSR) activities in building corporate reputation with consumers. Research design, data, and methodology - Online and offline surveys were conducted among male and female adults across Korea. Surveys were conducted for three weeks from August 21, 2018 to September 8, 2018. The samples consisted of 350 offline and 112 online surveys, and a combined total of 462 samples was used for final analysis. Result - Higher consumer value means a greater chance that consumers will select that company's products over those of competitors. For competitive advantage purposes, companies use various consumer management strategies to bolster consumer value and corporate reputation with consumers. Conclusions - Brand assets are subject to ethical responsibility, which is a dimension of corporate social responsibility. Of note, one relevant finding about brand assets (similar to findings in previous research) is the existence of confusion about brand recognition and brand image as perceived by customers.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.143-149
• /
• 2019

플로팅 홀로그램은 광고나 콘서트와 같이 넓은 공간에서 현장감과 실존감이 뛰어난 3D 입체영상을 제공하면서, 3D 안경의 불편함, 시각적 피로, 공간 왜곡 현상 발생을 감소할 수 있는 기술이다. 따라서 본 논문은 좁은 공간에서도 사용가능한 플로팅 홀로그램 환경에서 캐릭터 조작을 위한 사용자 제스처 인식 시스템을 구현한다. 제안된 방법은 하르 특징기반의 캐시케이드((Harr feature-based cascade classifier) 분류기를 이용하여 얼굴 영역을 검출하고, 검출된 얼굴 영역을 기준으로 실시간으로 체스쳐 차영상으로부터 사용자 제스쳐의 발생 위치 정보를 이용하여 사용자 제스쳐를 인식한다. 그리고 각각 인식된 제스쳐 정보는 플로팅 홀로그램 환경에서 생성된 캐릭터 움직임을 조작하기 위하여 상응하는 행위에 맵핑된다. 제안된 플로팅 홀로그램 캐릭터 조작을 위한 사용자 제스처 인식 시스템의 성능평가를 위해서는 플로팅 홀로그램 디스플레이 장치를 제작하고, 몸 흔들기, 걷기, 손 흔들기, 점프 등의 각 제스처에 따른 인식률을 반복 측정한 결과 평균 88%의 인식률을 보였다.

• 대한음성학회지:말소리
• /
• 제50호
• /
• pp.85-97
• /
• 2004

One of the important problems in speech recognition is to accurately detect the existence of speech in adverse environments. The speech detection problem becomes severer when recognition systems are used over the telephone network, especially in a wireless network and a noisy environment. In this paper, we propose a robust speech detection algorithm, which detects speech boundaries accurately by selecting useful bands adaptively to noisy environments. The bands where noises are mainly distributed, so called, noise-centric bands are introduced. In this paper, we compare two different speech detection algorithms with the proposed algorithm, and evaluate them on noisy environments. The experimental results show the excellence of the proposed speech detection algorithm.

• 한국실내디자인학회논문집
• /
• 제23권5호
• /
• pp.41-50
• /
• 2014

In relation to spatial expression, the remediation theory of Jay David Bolter & Richard Grusin shows a sufficient possibility of providing extended idea and experience through the space of critical representation. The remediation theory discussed in the scope of new media says about the existence method and the development process of media through immersion into media and awakening, and one attribute of remediation which aims at the extension of another realistic experience and recognition through various media, contains common denominators which display diversity and complexity of installation space, and use the audience as expression elements. Therefore, this study aims to apply the remediation theory in order to interpret space using more diverse and multisensory expression methods. For achieving this purpose, this study found the connection among characteristics of hypermediacy which is an axis of installation and remediation theory, and analyzed diverse cases regarding installation space and characteristics of hypermediacy, depending on external aspects of form and expression and internal aspects of experience and cognition. The method of hypermediation expression in installation space converts the recognition about the basic custom of new experience, space and representation. This means that the logic of remediation could approach space by leading to more extended form and recognition. In conclusion, the characteristics of space and the possibility of extended expression revealed in the relationship between installation space and hypermediacy logic would provide another developmental significance for research on space design.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.92-94
• /
• 2004

We become an industry information society which is advanced to the altitude with the today. The information to be loading various goods each other together at a circumstance environment is increasing extremely. The restriction recognizes the data of many Quantity and it follows because the human deals the task to classify. The development of a mathematical formulation for solving a problem like this is often very difficult. But Artificial intelligent systems such as neural networks have been successfully applied to solving complex problems in the area of pattern recognition and classification. So, in this paper a neural network approach is used to recognize and classification problem was broken into two steps. The first step consist of using a neural network to recognize the existence of purpose pattern. The second step consist of a neural network to classify the kind of the first step pattern. The neural network leaning algorithm is to use error back-propagation algorithm and to find the weight and the bias of optimum. Finally two step simulation are presented showing the efficacy of using neural networks for purpose recognition and classification.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.134-143
• /
• 2017

Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines. Generally, it is very difficult to diagnose a machine fault by conventional methods based on mathematical models because of the complexity of the real world systems and the obvious existence of nonlinear factors. This study develops an automatic machine fault diagnosis system that uses pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The sounds emitted by the operating machine, a drill in this case, are obtained and analyzed for the different operating conditions. The specific machine conditions considered in this research are the undamaged drill and the defected drill with wear. Principal component analysis is first used to reduce the dimensionality of the original sound data. The first principal components are then used as the inputs of a neural network based classifier to separate normal and defected drill sound data. The results show that the proposed PCA-ANN method can be used for the sounds based automated diagnosis system.

• 정보처리학회논문지B
• /
• 제17B권1호
• /
• pp.1-8
• /
• 2010

시선 인식에 관한 연구는 현재 사용자가 응시하고 있는 위치를 파악하는 것으로 많은 응용 분야를 가지며 지속적으로 발전되어 왔다. 기존의 시선 인식에 관한 대부분의 연구는 적외선 LED 및 카메라, 고가의 헤드마운티드 장비 등을 이용하였기 때문에 범용 사용에 문제점을 가지고 있다. 이에 본 논문에서는 한 대의 PC용 웹 카메라를 사용한 SVM(Support Vector Machine) 기반의 시선 인식 시스템을 제안하고 구현한다. 제안한 시스템은 4방향과 9방향의 시선을 인식하기 위해 모니터를 가로 6, 세로 6, 총 36개의 시선 위치로 나누어 각각 9개, 4개씩 그룹핑 및 학습하여 사용자의 시선을 인식한다. 또한, 시선 인식의 성능을 높이기 위해 차영상 엔트로피를 이용한 영상 필터링 방법을 적용한다. 제안한 시스템의 성능을 평가하기 위하여 기존에 제시되었던 차영상 엔트로피 기반의 시선 인식 시스템, 눈동자 중심점과 눈의 끝점을 이용한 시선 인식 시스템, PCA 기반의 시선 인식 시스템을 구현하고 비교 실험을 수행하였다. 실험 결과 본 논문에서 제안한 SVM 기반의 시선 인식 시스템이 4방향은 94.42%, 9방향은 81.33%의 인식 성능을 보였으며, 차영상 엔트로피를 이용한 영상 필터링 방법을 적용하였을 경우에 4방향은 95.37%, 9방향은 82.25%의 성능을 보여 기존의 시선 인식 시스템보다 높은 성능을 나타내었다.