• 응용통계연구
• /
• 제13권2호
• /
• pp.415-425
• /
• 2000

붓스트랩 표본추출과 pairwise coupling의 알고리즘을 결합한 새로운 분류 알고리즘을 제안하고, 이를 선형판별분석과 2차 판별분석에 적용하였다. 그리고 새로운 분류 알고리즘의 정확도를 비교하기위해 널리 사용되는 waveform 자료 등을 분석한 후, 그 결과를 기존 분류 방법과 비교하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.877-882
• /
• 1993

An adaptive EEG waveform detection is presented. The method is based on a layered process model. The model allows the bilateral information exchange across the layers. The criteria for the waveform detection and epoch-wise classification can be adapted according to the higher layer context information embedded in a wider range of adjacent signals. The designed system is experimentally tested to show the adaptive operation of the waveform detection.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.181.4-181
• /
• 2001

In this study, we have developed the digital hardware system which performs signal processing necessary for the filtering to eliminate noises by inputting pulse wave signals from the sensor group. With a view to obtain clinically effective information, we analyzed structural elements of pulse waveform and, thus, conducted a systematic classification. What is more, this study has conducted researches in the web-based diagnosis data management system of pulse waveform as well as the method of transmitting the data of pulse waveform. In order to set the standard for the documents of the pulse ...

• 한국군사과학기술학회지
• /
• 제21권2호
• /
• pp.133-140
• /
• 2018

In electronic warfare(EW), low probability of intercept(LPI) radar signal is a survival technique. Accordingly, identification techniques of the LPI radar waveform have became significant recently. In this paper, classification and extracting parameters techniques for 7 intrapulse modulated radar signals are introduced. We propose a technique of classifying intrapulse modulated radar signals using Convolutional Neural Network(CNN). The time-frequency image(TFI) obtained from Choi-William Distribution(CWD) is used as the input of CNN without extracting the extra feature of each intrapulse modulated radar signals. In addition a method to extract the intrapulse radar modulation parameters using binary image processing is introduced. We demonstrate the performance of the proposed intrapulse radar waveform identification system. Simulation results show that the classification system achieves a overall correct classification success rate of 90 % or better at SNR = -6 dB and the parameter extraction system has an overall error of less than 10 % at SNR of less than -4 dB.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.33-39
• /
• 2019

In this paper, we propose deep convolutional neural network(CNN) with bottleneck structure which improves the performance of earthquake classification. In order to address all possible forms of earthquakes including micro-earthquakes and artificial-earthquakes as well as large earthquakes, we need a representation and classifier that can effectively discriminate seismic waveforms in adverse conditions. In particular, to robustly classify seismic waveforms even in low snr, a deep CNN with 1x1 convolution bottleneck structure is proposed in raw seismic waveforms. The representative experimental results show that the proposed method is effective for noisy seismic waveforms and outperforms the previous state-of-the art methods on domestic earthquake database.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권4호
• /
• pp.167-172
• /
• 2014

In this paper we propose a waveform design algorithm that localizes the maximum output power in the target direction. We extend existing monostatic radar optimal waveform design schemes to bistatic multiple-input multiple-output (MIMO) radar systems. The algorithm simultaneously calculates the direction of departure (DoD) and the direction of arrival (DoA) using a two-dimensional multiple signal classification (MUSIC) method, and successfully localizes the maximum transmitted power to the target locations by exploiting the calculated DoD. The simulation results confirm the performance of the proposed algorithm.

• 비파괴검사학회지
• /
• 제31권2호
• /
• pp.165-173
• /
• 2011

음향방출기법은 대형 구조물의 구조건전성감시(SHM)를 위한 매우 효율적인 방법이지만, 롤러코스터 지지구조물처럼 승용물의 운행으로 인한 매우 큰 잡음이 일상적으로 존재하는 경우에는 균열 진전 신호만을 분류하여 실시간 감시를 수행하기가 쉽지 않다. 이와 같은 문제의 해결을 위해 본 연구에서는 실시간으로 음원의 분류가 가능한 파형 파라미터 필터링 기법을 제안하였다. 파형 파라미터 필터링 기법은 음향방출 신호의 파형 파라미터를 이용하여 음향방출 히트를 사전에 필터링함으로써 실시간으로 감시하고자 하는 대상 음원만을 분류해내는데 매우 유리한 점이 있다. 다양한 음원에 대해 음향방출 파형 파라미터를 측정 및 분석하여 제안한 기법의 타당성을 살펴보았다. 또한 파형 파라미터 필터가 내장된 음향 방출 시스템을 구축하고 이를 실제 롤러코스터 지지구조물에 적용하여 실시간 균열진전 감시를 위한 가능성을 타진하였다.

• 전기학회논문지
• /
• 제67권7호
• /
• pp.962-968
• /
• 2018

In this study, we developed novel indicators to assess postoperative pain based on PPG derivative waveform. As the candidate indicator of postoperative pain assessment, the time from the start of beating to the n-th peak($T_n$) and the n-th peak amplitude($A_n$) of the PPG derivative were selected. In order to verify derived indicators, each candidate indicator was derived from the PPG of 78 subjects before and after surgery, and it was confirmed whether significant changes were observed after surgery. Logistic classification was performed with each proposed indicator to calculate the pain classification accuracy, then the classification performance was compared with SPI(Surgical Pleth Index, GE Healthcare, Chicago, US). The results showed that there were significant differences(p < 0.01) in all indicators except for $T_3$ and $A_3$. The coefficient of variation(CV) of every time-related indicators were lower than the CV of SPI(30.43%), however, the CV in amplitude-related parameters were higher than that of SPI. Among the candidate indicators, amplitude of the first peak, $A_1$, showed that highest accuracy in post-operative pain classification, 68.72%, and it is 15.53% higher than SPI.

• 동력기계공학회지
• /
• 제7권2호
• /
• pp.29-35
• /
• 2003

The monitoring and diagnostics of the rotating machinery have been received considerable attention for many years. The objectives are to classify the machinery condition and to find out the cause of abnormal condition. This paper describes a classification method of diagnosing the small reciprocating compressor for refrigerators using the artificial neural network and the wavelet transform. In order to extract salient features, the wavelet transform are used from primary noise signals. Since the wavelet transform decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, more and better features can be obtained easier than time-waveform analysis. In the training phase for classification, self-organizing feature map(SOFM) and learning vector quantization(LVQ) are applied, and the accuracies of them ate compared with each other. This paper is focused on the development of an advanced signal classifier to automatize the vibration signal pattern recognition. This method is verified by small reciprocating compressors, for refrigerator and normal and abnormal conditions are classified with high flexibility and reliability.

• 음성과학
• /
• 제4권2호
• /
• pp.41-54
• /
• 1998

Speech signals are, depending on the characteristics of waveform, classified as voiced sound, unvoiced sound, and silence. Voiced sound, produced by an air flow generated by the vibration of the vocal cords, is quasi-periodic, while unvoiced sound, produced by a turbulent air flow passed through some constriction in the vocal tract, is noise-like. Silence represents the ambient noise signal during the absence of speech. The need for deciding whether a given segment of a speech waveform should be classified as voiced, unvoiced, or silence has arisen in many speech analysis systems. In this paper, a voiced/unvoiced/silence classification algorithm using spectral change in the wavelet transformed signal is proposed and then, experimental results are demonstrated with our discussions.