• Journal of computational fluids engineering
• /
• v.16 no.4
• /
• pp.100-109
• /
• 2011

Large eddy simulation(LES) of fully developed turbulent pipe flow has been performed to investigate the effect of Reynolds number on the flow field at $Re_{\tau}$=180, 395, 590 based on friction velocity and pipe radius. A dynamic subgrid-scale model for the turbulent subgrid-scale stresses was employed to close the governing equations. The mean flow properties, mean velocity profiles and turbulent intensities obtained from the present LES are in good agreement with the previous numerical and experimental results currently available. The Reynolds number effects were observed in the higher-order statistics(Skewness and Flatness factor). Furthermore, the budgets of the Reynolds stresses and turbulent kinetic energy were computed and analyzed to elucidate the effect of Reynolds number on the turbulent structures.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.4
• /
• pp.1171-1181
• /
• 2014

Different power quality (PQ) disturbance sources can have major impacts on the power supply grid. This study proposes, for the first time, an early warning approach to identifying PQ problems and providing early warning prompts based on the monitored data of PQ disturbance sources. To establish a steady-state power quality early warning index system, the characteristics of PQ disturbance sources are analyzed and summed up. The higher order statistics anomaly detection (HOSAD) algorithm, based on skewness and kurtosis, and hierarchical power quality early warning flow, were then used to mine limit-exceeding and abnormal data and analyze their severity. Cases studies show that the proposed approach is effective and feasible, and that it is possible to provide timely power quality early warnings for limit-exceeding and abnormal data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.895-898
• /
• 2004

본 논문에서는 기존의 개인 식별 방법의 한계를 해결하는 대안으로 떠오르고 있는 생체인식 기술 중 인식률이 뛰어난 홍채인식 시스템에 대해 연구하고자 한다. 먼저 홍채인식 시스템의 구현을 위해 신호처리 분야에서 많이 사용되고 있는 wavelet 변환 중 Haar wavelet과 고차 국소 자기 상관 특징을 이용하여 홍채의 특징을 추출하여 특징벡터의 크기를 최소화 하였다. 또, 인식률을 높이기 위해 오류 역전파 학습 알고리즘을 이용하여 홍채패턴에 기반한 신원 확인 및 검증을 위한 개선된 방법을 제시하였다. 학습이 완료된 신경망에 대한 학습데이터와 테스트 데이터의 인식률을 실험한 결과 학습된 데이터는 평균 인식률 $97.4\%$, 테스트 데이터는 $95.5\%$의 인식률을 보였다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.7
• /
• pp.278-285
• /
• 1999

This paper is concerned with the development of useful engineering techniques to detect and anlayse nonlinearities in mechanical systems. The methods developed are based on the concepts of higher order spectra. The study of higher order statistics has been dominated by work on the bispectrum. The bispectrum can be viewed as a decomposition of the third moment(skewness) of a quadratic phase coupling(QPC) can be analyzed by bicoherence function. Finally, the application of these techiques to data from actual mechanical systems will be performed insecond report.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.05a
• /
• pp.235-239
• /
• 1999

This thesis is concerned with the development of useful engineering techniques to detect and analyze nonlinearities in mechanical systems. The methods developed are based on the concepts of higher order spectra, in particular the bispectrum. The study of higher order statistics has been dominated by work on the bispectrum. The bispectrum can be viewed as a decomposition of the third moment(skewness) of a signal over frequency and as such is blind to symmetric nonlinearities. Initially auto higher order spectra are studied in detail with particular attention being paid to normalization method. Traditional method based on the bicoherence are studied. Under certain conditions, notably narrow band signals, the above normalization method is shown to fail and so a new technique based on prewhitening the signal in the time domain is developed.

• Communications for Statistical Applications and Methods
• /
• v.4 no.1
• /
• pp.177-183
• /
• 1997

A data-adaptive order selection procedure is proposed for local polynomial nonparametric regression. For each given polynomial order, bias and variance are estimated and the adaptive polynomial order that has the smallest estimated mean squared error is selected locally at each location point. To estimate mean squared error, empirical bias estimate of Ruppert (1995) and local polynomial variance estimate of Ruppert, Wand, Wand, Holst and Hossjer (1995) are used. Since the proposed method does not require fitting polynomial model of order higher than the model order, it is simpler than the order selection method proposed by Fan and Gijbels (1995b).

• The Korean Journal of Applied Statistics
• /
• v.29 no.2
• /
• pp.279-289
• /
• 2016

Bioequivalence trials based on higher order crossover designs have recently been conducted for highly variable drugs since the Ministry of Korea Food and Drug Safety (MFDS) added new regulations in 2013 to widen bioequivalence limits for highly variable drugs. However, a statistical discussion of higher order crossover designs have not been discussed yet. This research proposes the statistical inference of bioequivalence based on $3{\times}3$ crossover design and discusses it with the MFDS regulations. An illustrated example is also given.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.5
• /
• pp.268-277
• /
• 1999

Impulsive acoustic and vibration signals within gear are often induced by impacting of fault tooths in gear. Thus the detection of these impulses can be useful for fault diagnosis. Recently there is an increasing trend towards the use of higher order statistics for fault detection within mechanical systems based on the observation that impulsive signals then to increase the kurtosis values. We show that the fourth order Wigner Moment Spectrum, called the Wigner Trispectrum, has found superior detection performance to second order Wigner distribution for typical impulsive signals in a condition monitoring application. These methods are also applied to data sets measured within an industrial gear box.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.163-166
• /
• 2003

In conventional patchwork, the difference of the mean values of two groups is compared for watermark detection. We propose two modified patchwork schemes based on order statistics, which achieves significant improvements over conventional patchwork. First, we propose that the mean comparison is replaced by the median comparison, to get PSNR improvement due to informed watermarking. Second, we propose a majority voting scheme of a sequential comparison of pixel pairs in a sorted order, which produces significantly lower BER. The performance improvements are mathematically analyzed and tested. In experimental results, PSNR is about 5㏈～10㏈ higher in the first method and BER is about 1/5～l/2 times lower in the second method than conventional patchwork.