• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• 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.

• Journal of Information Processing Systems
• /
• 제6권4호
• /
• pp.511-520
• /
• 2010

This paper proposes two new methods to detect the fingerprints of different persons based on one-dimensional and two-dimensional discrete wavelet transformations (DWTs). Recent literature shows that fingerprint detection based on DWT requires less memory space compared to pattern recognition and moment-based image recognition techniques. In this study four statistical parameters - cross correlation co-efficient, skewness, kurtosis and convolution of the approximate coefficient of one-dimensional DWTs are used to evaluate the two methods involving fingerprints of the same person and those of different persons. Within the contexts of all statistical parameters in detection of fingerprints, our second method shows better results than that of the first method.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 하계학술대회 논문집 Vol.3 No.2
• /
• pp.927-930
• /
• 2002

The HFPD measurement method is a technique to analyze aging state of high voltage insulation materials and detect higher frequency signals than conventional PD measurement method therefore it takes less noise effect and could execute active line measurement. It is possible to analyze main discharge phenomena and obtain access to aging progress occurred in insulation materials through accumulation of HFPD signals during determined interval and expression of fractal dimension using statistical process of accumulated signals. In this study, the statistical parameters (skewness & kurtosis) and fractal dimensions are changed by discharge patterns that is shown up different characteristics with applied voltages and times.

• 대한설비공학회지:설비저널
• /
• 제16권5호
• /
• pp.516-524
• /
• 1987

This paper presents experimental data of fluctuation characteristics of local void fraction of air-water two-phase flow which are associated with the flow pattern, annular gap size and radial location in vertical concentric annuli with coefficient of skewness and kurtosis. The annular gap widths are 13mm, 11mm, and 9mm for a 38m inner diameter as the lucite outer tube. A electrical conductivity probe was used to measure the local void fraction and traversed diametrically from inner wall to outer wall using radial increments of 2mm. It was shown that distribution of the coefficient of skewness and kurtosis, which is related that the one is the asymmetry and the other peakness of local void fraction distribution was influenced by flow pattern, annular gap size and radial location.

• E2M - 전기 전자와 첨단 소재
• /
• 제10권3호
• /
• pp.247-254
• /
• 1997

Internal voids in insulators give rise to partial discharge, which causes a local breakdown and even entire insulation breakdown. Recently, the necessity of establishing the way to diagnose the aging of insulation materials and to predict of insulation breakdown become important. The purpose of our work are to investigate the treeing phenomena with an artificial needle shaped void by the charge of discharge and acoustic emission pulse in each phase angle area at the same time. We analyzed the .PHI.-QA-t pattern and .PHI.-AEA-t pattern using statistic operators such as pulse magnitude, pulse number, skewness, kurtosis. Therefore, the relation between the charge of discharge and acoustic emission pulse will be helpful to predict the breakdown just before the breakdown occur.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 D
• /
• pp.1478-1480
• /
• 1998

Inception and propagation of electrical tree and properties of partial discharge(PD) pulses accompanying with tree in low density polyethylene were discussed. We observed the characteristics of process of electrical tree by using optical microscope and investigated the statistical characteristics of the PD pulses by analyzing PD quantities and distribution patterns. The PD pulses were analyzed by q-n, $\phi$-n and $\phi$-q distribution. The statistical operators used were skewness(s), kurtosis(k) and average phase angle. The skewness and average discharge phase angle of PD pulses increased as the Propagation of tree. The kurtosis was about 1.8 at the Inception of tree, but It increased as the propagation of tree.

• 한국안전학회지
• /
• 제15권1호
• /
• pp.100-105
• /
• 2000

Correlation between propagation of bush-type electrical tree and internal partial discharges(PD) was discussed. We used specimens with needle-plane electrode system made of LDPE(Low Density Polyethylene), observed inception and propagation of electrical tree by optical microscope interfaced with computer and investigated characteristics of phase resolved PD pulses accompanying with propagation of electrical tree. Electrical tree generally growed bush-type tree. PD data detected and analyzed were average discharge current and statistical operator of q-n, $\psi$- $q_{avg}$, $\psi$-n, ${\psi}-q_{max}$ distribution. Parameters used were skewness, kurtosis, average discharge phase, cross-correlation factor, asymmetry and etc. In generally, average discharge current had good linear relationship with propagation of bush type electrical tree on this experiment. Peak discharge magnitude and repetition rate were increased, but they had not good linear relationship.p.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.421-436
• /
• 2012

Different types of fingerprint detection algorithms that are based on extraction of minutiae points are prevalent in recent literature. In this paper, we propose a new algorithm to locate the virtual core point/centroid of an image. The Euclidean distance between the virtual core point and the minutiae points is taken as a random variable. The mean, variance, skewness, and kurtosis of the random variable are taken as the statistical parameters of the image to observe the similarities or dissimilarities among fingerprints from the same or different persons. Finally, we verified our observations with a moment parameter-based analysis of some previous works.

• Communications for Statistical Applications and Methods
• /
• 제5권3호
• /
• pp.887-894
• /
• 1998

Let T=( $T_1$,…, $T_{k}$;k$\geq$2) be a minimal sufficient and complete statistic for a k-parameter exponential model. Consider a partition of T into ( $T_1$, $T_2$), where $T_1$=( $T_1$,…, $T_{r}$ and $T_2$=( $T_{r+1}$,…, $T_{k}$1$\leq$r$\leq$k-1/). This article represents a way to obtain higher moments such as skewness and kurtosis for the distribution T and the conditional distribution of $T_1$, given $T_2$= $t_2$. These results are illustrated by some examples.s.les.s.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 추계학술대회 발표논문집
• /
• pp.92-95
• /
• 2006

The purpose of this study is to find the acoustic parameters on frequency domain to distinguish the Korean nasals, /m, n, ng/ from each other. Since it is not easy to characterize the antiformant on frequency domain, we suggest the new parameters that are calculated by LTAS(Long term average spectrum). Maximum energy value and its frequency and minimum energy and its frequency of zero are obtained from the spectrum respectively. In addition, slope1, slope2, total energy value, centroid, skewness, and kurtosis are suggested as new parameters as well. The parameters that are revealed as to be statistically signigicant difference are roughly peak1_a, zero_f, slope_1, slope_2, highENG, zero_ENG, and centroid.