• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.11-19
• /
• 2013

This paper proposes an algorithm using vibration signals and texture analysis for mechanical fault diagnosis of an induction motor. We analyze characteristics of contrast and pattern of an image converted from vibration signal and extract three texture features using gray-level co-occurrence model(GLCM). Then, the extracted features are used as inputs of a multi-level support vector machine(MLSVM) which utilizes the radial basis function(RBF) kernel function to classify each fault type. In addition, we evaluate the classification performance with varying the parameter from 0.3 to 1.0 for the RBF kernel function of MLSVM, and the proposed algorithm achieved 100% classification accuracy with the parameter of the RBF from 0.3 to 1.0. Moreover, the proposed algorithm achieved about 98% classification accuracy with 15dB and 20dB noise inserted vibration signals.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.7
• /
• pp.927-936
• /
• 2002

This paper presents the extraction of a feature by motion vector for efficient content-based retrieval for digital video. in this paper, divided by general size block for the current frame by video, using BMA(block matching algorithm) for an estimate by block move based on a time frame. but in case BMA appeared on a different pattern fact of motion in the vector obtain for the BMA. solve in this a problem to application for full search method this method is detected by of on many calculations. I propose an alternative plan in this paper Limit the search region to $\pm$15 and search is a limit integer pixel. a result, in this paper is make an estimate motion vector in more accurately using motion vector in adjoin in blocks. however, refer to the block vector because occurrence synchronism. Such addition information is get hold burden receive to transmit therefore, forecasted that motion feature each block and consider for problems for establish search region. in this paper Algorithm based to an examination Motion Estimation method by for motion Compensation is proposed.

• Kyungpook Mathematical Journal
• /
• v.28 no.1
• /
• pp.45-50
• /
• 1988

Circulant and multiblock circulant matrices have many important applications, and therefore their inverses are of considerable interest. A simple recursive algorithm is presented to compute the inverse of a multiblock circulant matrix. The algorithm only uses complex variables, roots of unity and normal matrix/vector operations.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.198-198
• /
• 2004

• Journal of IKEEE
• /
• v.12 no.2
• /
• pp.124-130
• /
• 2008

Vector Graphics describes an image with mathematical statements instead of pixel information. Which enables easy scalability without loss in image quality and usually results in a much smaller file size compared with bitmap images. In this paper, we propose Vector Graphics Accelerator for mobile device with scan-line edge flag algorithm to render vector image without sorting process of edge. Proposed Vector Graphics Accelerator was verified with OpenVG 2D Vector image. The estimated processing time of proposed Accelerator with Tiger image is 12ms on Tessellation process, and total rendering time is 208ms. Estimated rendering performance with Tiger image is about 5 frame per second

• The Transactions of the Korean Institute of Power Electronics
• /
• v.12 no.4
• /
• pp.310-317
• /
• 2007

In this paper, the system equation for the balanced two-phase induction motor is derived and the characteristics for speed control is also analyzed in the region of constant torque and constant power. The modified vector control theory is applied to two-phase motor drive system. The speed of two-phase motor drive can be controlled precisely by the modified indirect vector control theory. The modified vector control theory is simpler comparing to the conventional vector control because of the simpler axis transformation. The computer simulations and the experimental results presented to confirm the vector control for two-phase inverter fed two phase induction motor system.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.565-574
• /
• 2015

Falls are the main cause of serious injuries and accidental deaths in people over the age of 65. Due to widespread adoption of smartphones, there has been a growing interest in the use of smartphones for detecting human behavior and activities. Modern smartphones are equipped with a wide variety of sensors such as an accelerometer, a gyroscope, camera, GPS, digital compass and microphone. In this paper, we introduce a new method that determines the fall direction of human subjects by analyzing the three axis components of acceleration vector.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.993-998
• /
• 2006

본 논문은 기존의 휴대폰과 같은 모바일 환경에서의 제약적인 화면을 극복하기 위하여 가상의 스크린을 만들고 이를 사용자가 손쉽게 제어할 수 있는 인터페이스에 대해서 제안하였다. 기존의 방법은 버튼을 반복적으로 눌러 스크롤 했던 것에 반해 제안된 인터페이스는 휴대폰 카메라를 통해 입력되는 영상 신호를 기반으로 움직임 벡터 값을 추출하고 이를 통하여 사용자가 움직이는 방향대로 화면을 움직여 줌으로서 사용자에게 편리하고 직관적인 인터페이스를 제공함으로서 휴대폰의 제한적인 화면을 극복 하였다. 모바일 환경에서의 움직임 벡터 값을 추출하기 위한 알고리즘을 제안하고, 제한적인 화면으로 인하여 정보 표현에 한계가 있던 점을 극복하여 모바일 환경에서의 새로운 인터페이스를 제안하였다.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.420-427
• /
• 2017

This paper proposes a new method using Wide Line Detector based statistical shape Feature (WLDF) to identify whether or not a tongue is cracked; a cracked tongue is one of the most frequently used visible features for diagnosis in traditional Chinese Medicine (TCM). We first detected a wide line in the tongue image, and then extracted WLDF, such as the maximum length of each detected region, and the ratio between maximum length and the area of the detected region. We trained a binary support vector machine (SVM) based on the WLDF to build a classifier for cracked tongues. We conducted an experiment based on our proposed scheme, using 196 samples of cracked tongues and 245 samples of non-cracked tongues. The results of the experiment indicate that the recognition accuracy of the proposed method is greater than 95%. In addition, we provide an analysis of the results of this experiment with different parameters, demonstrating the feasibility and effectiveness of the proposed scheme.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.267-272
• /
• 2003

음성 합성 시스템 구축에 있어서 입력 텍스트를 정확한 발음 표기로 변환하는 것은 매우 중요하다. 중국어에는 하나의 한자가 의미나 사용에 따라 다르게 발음되는 다음자(polyphony)들이 존재한다. 다음자의 처리는 상당히 복잡한 문제이기 때문에 본 논문에서는 그 중 가장 발음에 영향을 미치는 요소인 인명과 지명에 대한 미등록어 처리를 수행했다. 무엇보다 실시간 음성 합성 시스템을 위해서는 처리 속도의 향상이 요구된다. 따라서 본 연구에서는 미등록어 후보 구간 선정을 선행하고, 선정된 후보에 대해 추정하는 두 단계로 진행하였다. 후보 구간 선정은 단일 한자 단어(monosyllable word)의 확률과 간단한 패턴들을 이용한다. 최종 선정된 후보의 미등록어 추정은 SVM(Support Vector Machine)을 기반으로 실시하였다.