• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.548-554
• /
• 2009

We propose an automatic inspection system for hologram with multiple patterns. The system hardware consists of illuminations, camera, and vision processor. Multiple illuminations using LEDs are arranged in different directions to acquire each image of patterns. The system software consists of pre-processing, pattern generation, and pattern matching. The acquired images of input hologram are compared with their reference patterns by developed matching algorithm. To compensate for the positioning error of input hologram, reference patterns of hologram for different position should be generated in on-line. We apply a frequency transformation based CGH(computer-generated hologram) method to generate reference images. For the fast pattern matching, we also apply the matching method in the frequency domain. Experimental results for hologram of Korean currency are then presented to verify the usefulness of proposed system.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.33-41
• /
• 2013

In this paper, we implemented the pattern matching with the Arduino and App Inventor platform under the bluetooth mobile environment between Android phone and Arduino Platform. The combination between Arduino and App Inventor makes the feasibility of Android programming easy by wireless communications and provides the opportunity to broaden the functionality for mobile device. We used the softwares which were Arduino IDE, VC++, OpenCV, Processing and App Inventor. And also compared the performance of mobile Arduino platform with LabView GUI programming, we reduced the usage of libraries that compiled and executed the pattern matching programming. We experimented the mobile embedded platform performance under bluetooth communication and verified the functionality of the mobile Arduino platform design for identifying the pattern matching.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.721-726
• /
• 2005

In this study, researchers classifying the artificial flaws in semiconductor. packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2007년도 춘계학술대회 논문집
• /
• pp.368-370
• /
• 2007

AAO(Anodic Aluminum Oxidation) method has been known that it is practically useful for the fabrication of nano-structures and makes it possible to fabricate the highly ordered nano masters on large surface and even on the 2.5 or 3D surface at low cost comparing to the expensive e-beam lithography or the conventional silicon processing. In this study, by using the multi-step anodizing and etching processes, highly ordered nano patterned master with concave shapes was fabricated. By varying the processing parameters, such as initial matter and chemical conditions; electrical and thermal conditions; time scheduling; and so on, the size and the pitch of the nano pattern can be controlled. Consequently, various alumina/aluminum nano structures can be easily available in any size and shape by optimized anodic oxidation in various aqueous acids. The resulting good filled uniform nano molded structure through hot embossing molding process shows the validity of the fabricated nano pattern masters.

• 대한음성학회지:말소리
• /
• 제62호
• /
• pp.33-49
• /
• 2007

The purpose of this study is 1) to investigate the phoneme inventories and phonological processes of cochlear implant(CI) children and 2) to describe their utterances using narrow phonetic transcription method. All ten subjects had more than 2 year-experience with CI and showed more than 85 % open-set sentence perception abilities. Average consonant accuracy was 81.36 % and it was improved up to 87.41% when distortion errors were not counted. They showed similar phonological processing patterns to HA or normal hearing children in some way as well as different phonological processing patterns from HA or normal hearing children. The prominent distortion error pattern was weakening of consonants. Every subject had his/her idiosyncratic error pattern that demanded his/her own individualized therapy program.

• 한국산학기술학회논문지
• /
• 제4권2호
• /
• pp.87-95
• /
• 2003

Dynamic Programming Matching (DPM)은 순차적으로 구성된 문제를 수학적으로 최적화 시키는 기술로서 패턴인시 분야에서 다년간 중요한 역할을 해왔다. 서명인식을 위한 대부분의 실제적 적용에서는 Sakoe and Chiba [9]의 실제구현 버전이 기반이 되어 왔는데, 일반적으로 slope constraint p = 0의 방법이 적용되어 왔다. 이 논문에서는 이 경우에는 전진탐색에 의한 휴리스틱한 방법을 적용한 MDPM이 상당한 처리시간의 단축 뿐만 아니라 약간의 인식능력 향상을 가질 수 있음을 보여준다.

• Journal of Information Processing Systems
• /
• 제4권2호
• /
• pp.67-76
• /
• 2008

This research proposes a new strategy where documents are encoded into string vectors and modified version of k means algorithm to be adaptable to string vectors for text clustering. Traditionally, when k means algorithm is used for pattern classification, raw data should be encoded into numerical vectors. This encoding may be difficult, depending on a given application area of pattern classification. For example, in text clustering, encoding full texts given as raw data into numerical vectors leads to two main problems: huge dimensionality and sparse distribution. In this research, we encode full texts into string vectors, and modify the k means algorithm adaptable to string vectors for text clustering.

• 한국멀티미디어학회논문지
• /
• 제4권2호
• /
• pp.189-196
• /
• 2001

퍼지 논리의 추론과정에서 일부의 정보가 무시되어 적절하지 못한 추론 결과를 초래 할 수 있다. 한편 신경망은 패턴 처리에는 적합하지만 인간의 지식을 모델링하기 위해서 필요한 논리적인 추론에는 부적합하다. 그러나 신경망의 변형인 신경 논리망을 이용하면 논리적인 추론이 가능하다. 따라서 본 논문에서는 기존의 신경 논리망을 기반으로 하는 추론네트워크를 확장하여 퍼지 추론 네트워크를 구성한다. 그리고 기존의 추론 네트워크에서 사용되는 전파규칙을 보완하여 적용한다. 퍼지 추론 네트워크상에서 퍼지 규칙의 실행부에 해당하는 명제의 믿음 값을 결정하기 위해서는 추론하고자 하는 명제에 연결된 노드들을 탐색해야 한다.

• Journal of Information Processing Systems
• /
• 제14권2호
• /
• pp.523-538
• /
• 2018

Keystroke dynamics user authentication is a behavior-based authentication method which analyzes patterns in how a user enters passwords and PINs to authenticate the user. Even if a password or PIN is revealed to another user, it analyzes the input pattern to authenticate the user; hence, it can compensate for the drawbacks of knowledge-based (what you know) authentication. However, users' input patterns are not always fixed, and each user's touch method is different. Therefore, there are limitations to extracting the same features for all users to create a user's pattern and perform authentication. In this study, we perform experiments to examine the changes in user authentication performance when using feature vectors customized for each user versus using all features. User customized features show a mean improvement of over 6% in error equal rate, as compared to when all features are used.