• 대한산업공학회지
• /
• 제30권1호
• /
• pp.44-49
• /
• 2004

The aim of this study is to compare the methods in analyzing bio-signals representing measure driver's psychophysiological staus. This study has considered three approaches: first, the deterministic approach calculating the mean and standard deviation of bio-signal, second, probabilistic approach converting driver's bio-signal values to probability density function and identifying individual state relative to overall distribution, and third, diagnostic approach identifying the pattern change of signal over certain period of time. For evaluation of analysis methods, driver's bio-signal was collected under various road conditions, and three analysis approaches were applied respectively. In result, the deterministic approach was found to be simple to use, but generated a large variability of bio-signal. The probabilistic approach provide a relative status of individual driver among overall population, but too much affected by temporal variability of individual driver. The diagnostic approach seemed to reasonably find driver's psychophysiological change over certain period of time, but still needs to develop quantification method of the bio-signal.

• 융합신호처리학회논문지
• /
• 제8권1호
• /
• pp.6-14
• /
• 2007

요역동학검사는 하부요로계의 이상증상을 진단하기위하여 수행된다. 일반적으로 임상에서 행해지는 요역동학검사에서는 침습적인 방법으로 방광을 채운 후 배뇨하는 절차를 거친다. 하지만 이러한 방법은 카테터를 삽입해야하므로 환자에게 고통을 수반하게 한다. 본 연구에서는 비침습적이고 보다 편리한 방법으로 하부요로계의 기능을 평가할 수 있는 시스템을 구현하고자 하였다. 비침습적인 방법으로 하부요로증상(lower urinary tract symptoms, LUTS)의 진단을 위하여 배뇨시 요속, 요류음, 비침습적 방광내압을 측정할 수 있는 시스템을 구현하였다. 구현된 시스템은 센서부, 신호처리부, FPGA를 이용한 시스템 제어부 그리고 PC모니터링 프로그램으로 구성하였다. 그리고 구현된 계측시스템의 평가를 위하여 FPGA 시스템 제이부의 시뮬레이션을 수행하였고 인체의 하부요로계를 모식화한 실험장치를 구현하였다. 실험장치를 이용한 측정부의 평가결과 요속측정부의 평균에러율이 1.08%, 계수변화율이 1.48로 평가되었다. 그리고 비침습적 방광내압부는 평균에러율이 2.41%, 계수변화율이 2.81로 나타났다. 요류음신호의 시간영역과 주파수영역에서의 분석위해 평균실효치전력(average RMS power)과 주파수영역에서의 중심주파수(median frequency, MF)를 분석하였으며, 그 결과 $60{\sim}160Hz$의 중심주파수대에서 폐색을 가장 잘 반영하였다.

• 동력기계공학회지
• /
• 제14권2호
• /
• pp.60-64
• /
• 2010

This paper introduces reliability improvement and time saving in eddy current inspection by signal characteristic optimization of multi-coil eddy current array probe. In the past, Multi-coil array probe and single probe were used for the gas turbine rotor surface inspection & defect evaluation. The multi-coil array probe was used for the broad area inspection. But the signal deviations among multi-coil array probe are maximum 28% in commercial probe. This differences were considered to impedance differences among coils, so it is very difficult to evaluate exact defect size. The signal deviations among multi-coil array probe are maximum 28% in commercial probe. So, single coil inspection was used for exact defect sizing. The purpose of this study is to improve signal deviations of multi-coil array probe. The introduced new technology can improves this deviation by adjusting input voltage in each coil. At first, apply same voltage in each coil and collect signal amplitude of each coil. And calculate new input voltage based on signal amplitude of each coil. If the signal amplitude deviation is within 5% among multi-coil array probe, the signal amplitude of multi-coil array probe is reliable. The proposed technology gives 2% signal deviation among multi-coil array probe. The proposed new technology gives reliability improvement and inspection time saving in eddy current inspection.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.402-411
• /
• 2020

Power line noise in electrocardiogram signals makes it difficult to diagnose cardiovascular disease. ECG signals without power line noise are needed to increase the accuracy of diagnosis. In this paper, it is proposed DNN(Deep Neural Network) model to remove the power line noise in ECG. The proposed model is learned with noisy ECG, and clean ECG. Performance of the proposed model were performed in various environments(varying amplitude, frequency change, real-time amplitude change). The evaluation used signal-to-noise ratio and root mean square error (RMSE). The difference in evaluation metrics between the noisy ECG signals and the de-noising ECG signals can demonstrate effectiveness as the de-noising model. The proposed DNN model learning result was a decrease in RMSE 0.0224dB and a increase in signal-to-noise ratio 1.048dB. The results performed in various environments showed a decrease in RMSE 1.7672dB and a increase in signal-to-noise ratio 15.1879dB in amplitude changes, a decrease in RMSE 0.0823dB and a increase in signal-to-noise ratio 4.9287dB in frequency changes. Finally, in real-time amplitude changes, RMSE was decreased 0.3886dB and signal-to-noise ratio was increased 11.4536dB. Thus, it was shown that the proposed DNN model can de-noise power line noise in ECG.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2003년도 추계학술발표회
• /
• pp.45-51
• /
• 2003

선박 신호음은 공기, 장애물, 외란 둥에 의해서 흡수, 반사, 방해되어 확산된다. 이 현상은 기적음원의 방향을 오판하여 발생되는 해양사고의 한 가지 원인이 된다. 이 연구의 최종목적은 선박 신호음 간섭을 분석 평가하는 기법을 이용하여 근본적인 해양사고를 예방하는데 있다. 이 논문에서는 해상환경에 따른 다양한 음향 전달특성을 시뮬레이션하기 위한 3차원 음장제어 모델을 제안했다. 그리고, 가상현실 기반 선박 시뮬레이터를 이용하여 모델의 유효성을 평가했다.

• 한국통신학회논문지
• /
• 제40권4호
• /
• pp.619-627
• /
• 2015

본 논문은 비음수 행렬 인수분해(NMF)를 이용한 음성향상 기법을 다루고 있다. 음성과 잡음에서 적절한 훈련을 통해 각각의 기저(basis) 행렬을 구하고 이 행렬들을 이용하여 두 음원을 분리 하는 것이다. 그 중에서도 음성향상의 성능은 사용하게 되는 기저 행렬에 따라 크게 달라짐을 보인다. 기존의 독립적으로 구한 음성 기저 행렬에 비해서, 잡음 데이터를 복원하는데 부적합한 방향으로 최적화시킨 음성 기저 행렬을 사용하였을 때 더 높은 음성향상 성능을 보임을 실험으로 확인하였다. 이 때 잡음 데이터의 복원 오차 자체를 크게 해주는 방향과 해당 인코딩 행렬(encoding matrix) 원소의 값을 작게 해주는 두 가지 방법을 적용하여 비교하였다. 좀 더 음성 복원에만 특화된 기저 행렬을 구함으로서 음성 기저 행렬이 잡음 데이터 복원에 사용되는 것을 최소화 하였다. 실험 결과에서는 perceptual evaluation speech quality값과 signal to distortion ratio를 지표로 사용하였고, 기존 기법에서 사용하는 기저 행렬 보다 더 높은 성능을 보임을 확인 하였다.

• 문화기술의 융합
• /
• 제9권4호
• /
• pp.563-568
• /
• 2023

심전도(electrocardiogram, ECG)는 심박동의 속도와 규칙성, 심실의 크기와 위치, 심장 손상 여부를 측정하는 데 사용되며, 모든 심장질환의 원인을 찾아낼 수 있다. ECG-KIT를 이용하여 획득한 ECG 신호는 ECG 신호에 잡음을 포함하기 때문에 딥러닝에 적용하기 위해서는 ECG 신호에서 잡음을 제거해야만 한다. 본 논문에서는, ECG 신호에 포함된 잡음은 Digital FIR 해밍 창함수를 이용한 저역통과 필터를 사용하여 제거하였다. LSTM의 딥러닝 모델을 사용하여 3가지 활성화 함수인 sigmoid(), ReLU(), tanh() 에 대한 성능 평가를 비교했을 때, 오차가 가장 작은 활성화 함수는 tanh() 함수 임을 확인하였고, batch size가 작은 경우가 큰 경우보다 시간이 많이 소요되었다. 또한 GRU 모델의 성능 평가의 결과가 LSTM 모델보다 우수한 것을 확인하였다.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2004년도 학술대회지
• /
• pp.360-364
• /
• 2004

The objective of this study is to estimate the feasibility of acoustic emission method Jar the internal leak from the valves in nuclear power plants. The acoustic emission method was applied to the valves at the site, and the background noise was measured for the abnormal plant condition. From the comparison of background noise data with the experimental results as to relation between leak flow and acoustic signal, the minimum leak flow rates that am be detected by acoustic signal was suggested. When the background noise level are higher than the acoustic signal, the method described below was considered that the analysis the remainder among the background noise frequency spectrum and the acoustic signal spectrum.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.682-685
• /
• 2004

This paper investigated a method for classifying emotional states by using pulse wave signal. It focused on finding effective features for emotional state classification. The emptional states considered here consisted of interest and neutral. Classification experiments utilized 65 and 60 samples of interest and neutral states respectively. We have investigated 19 features derived from pulse wave signals by using both time domain and frequency domain analysis methods with 2 classifiers of minimum distance (normalized Euclidean distanece) and ${\kappa}$-Nearest Neighbour. The Leave-one-out cross validation was used as an evaluation mehtod. Based on experimental results, the most efficient features were a combination of 4 features consisting of (i) the mean of the first differences of the smoothed pulse rate time series signal, (ii) the mean of absolute values of the second differences of thel normalized interbeat intervals, (iii) the root mean square successive difference, and (iv) the power in high frequency range in normalized unit, which provided 80.8% average accuracy with ${\kappa}$-Nearest Neighbour classifier.

• 비파괴검사학회지
• /
• 제11권1호
• /
• pp.7-12
• /
• 1991

The multi-frequency eddy current technique has been used for evaluation of various type of defects in tubings. However, this technique is not sufficient to detect and evaluate the defect in tubings if the defect is located in the geometrically complicated area(e. g. tube support plate, anti-vibration bar, tubesheet area) and mixing residue signal is significant to the defect signal. In order to improve the reliability of the multi-frequency eddy current technique, the effect of the interaction of mixing residue after frequency mixing with a function of distances between the defect and the tube support plate boundary has been analyzed theoretically. The experimental results have been discussed with the theoretical developments. The calculation shows the interaction between the two neighboring signal sources could be significant within the range of approximately 1.0mm with the experimental condition.