• Water Engineering Research
• /
• v.1 no.1
• /
• pp.49-61
• /
• 2000

Magnitude-frequency relationships are used in the design of dams, highway bridges, culverts, water supply systems, and flood control structures. In this paper, possible techniques for analyzing flood frequency at a site are presented. A currently used approach to flood frequency analysis is based on the concept of parametric statistical inference. In this analysis, the assumption is make that the distribution function describing flood data in known. However, such an assumption is not always justified. Even though many people have shown that the nonparametric method provides a better fit to the data than the parometric method and gives more reliable flood estimates. the noparpmetric method implies a small probability in extrapolation beyond the highest observed data in the sample. Therefore, a remedy is presented in this paper by introducing an estimator which mixes parametric and nonparametric density estimate.

• Water Engineering Research
• /
• v.2 no.1
• /
• pp.1-10
• /
• 2001

The frequency analyses for the precipitation data in Korea were performed. We used daily maximum series, monthly maximum series, and annual series. For nonparametric frequency analyses, variable kernel estimators were used. Nonparametric methods do not require assumptions about the underlying populations from which the data are obtained. Therefore, they are better suited for multimodal distributions with the advantage of not requiring a distributional assumption. In order to compare their performance with parametric distributions, we considered several probability density functions. They are Gamma, Gumbel, Log-normal, Log-Pearson type III, Exponential, Generalized logistic, Generalized Pareto, and Wakeby distributions. The variable kernel estimates are comparable and are in the middle of the range of the parametric estimates. The variable kernel estimates show a very small probability in extrapolation beyond the largest observed data in the sample. However, the log-variable kernel estimates remedied these defects with the log-transformed data.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.4
• /
• pp.1117-1123
• /
• 2014

Water is a necessary condition of plants, animals and human. The state of the water shortage, that drought is globally one of the most feared disasters. This study was calculated target standardized precipitation index with unit of region for judgment and preparation of drought in consideration of the regional characteristics. First of all, Standardized Precipitation Index (3) were calculated by monthly rainfall data from rainfall data more than 30 years of 88 stations. Parametric frequency and nonparametric frequency using boundary kernel density function were analysed using annual minimum data that were extracted from calculated SPI (3). Also, Target return period sets up 30 year and target SPI analysed unit of region using thiessen by result of nonparametric frequency. Analyzed result, Drought was entirely different from severity and frequency by region. This study results will contribute to a national water resources plan and disaster prevention measures with data foundation for judgment and preparation of drought in korea.

• Journal of the Korean Statistical Society
• /
• v.34 no.1
• /
• pp.49-60
• /
• 2005

In this paper we introduce a nonparametric method for estimating the probability density function of detection distances in line transect sampling. The estimator is obtained using a frequency histogram density estimation method. The asymptotic properties of the proposed estimator are derived and compared with those of the kernel estimator under the assumption that the data collected satisfy the shoulder condition. We found that the asymptotic mean square error (AMSE) of the two estimators have about the same convergence rate. The formula for the optimal histogram bin width is derived which minimizes AMSE. Moreover, the performances of the corresponding k-nearest-neighbor estimators are studied through simulation techniques. In the absence of our knowledge whether the shoulder condition is valid or not a new semi-parametric model is suggested to fit the line transect data. The performances of the proposed two estimators are studied and compared with some existing nonparametric and semiparametric estimators using simulation techniques. The results demonstrate the superiority of the new estimators in most cases considered.

• 한국방재학회:학술대회논문집
• /
• 2007.02a
• /
• pp.575-578
• /
• 2007

The objective of this study is to analyze the regionalization of point rainfall by statistical methods for regional frequency analysis of the rainfall. The rainfall data used in this study are annual maximum rainfall at 57 stations during the period of more than 30 years for 12 durations(10min, 1, 2, 3, 4, 5, 6, 8, 10, 12, 18, 24hr) in Korea. The Mann-Whitney U test, Kruskal-Wallis one-way analysis of variance of nonparametric test the principal component and the cluster analysis have been performed to analyze the regionalization of rainfall. The results of this study are as follows; (1) The region which hydrological homogeneous is accepted does not exist for whole duration in Korea. (2) The result of nonpametric test shows that hydrological homogeneous regions of point rainfall are divided by 5 regions. (3) In case of cluster analysis hydrological homogeneous regions of point rainfall are divided by 6 regions and 4 other areas.

• Journal of Korea Water Resources Association
• /
• v.38 no.10 s.159
• /
• pp.885-894
• /
• 2005

Since the 1970s, rapid Industrialization has brought urbanization nationwide. In this paper, thirty one years data(1973-2003) ate used to evaluate variability of major cities. Before assessing the context between urbanization and variability of rainfall, the rural areas are selected to compare with urban ones. Thus, average, trends, variations, and nonparametric frequency analysis methods were employed for evaluating variation of annual precipitation, seasonal precipitation, 1 hour annual maximum design rainfall and 24 hour annual maximum design rainfall for both urban and rural areas. The result have shown that summer precipitation relatively increased In urban areas compared to that in rural areas.

• Journal of Korea Water Resources Association
• /
• v.39 no.6 s.167
• /
• pp.495-502
• /
• 2006

The importance of the bandwidth selection has been more emphasized than the kernel function selection for nonparametric frequency analysis since the interpolation is more reliable than the extrapolation method. However, when the extrapolation method is being applied(i.e. recurrence interval more than the length of data or extreme probabilities such as $200{\sim}500$ years), the selection of the kernel function is as important as the selection of the bandwidth. So far, the existing kernel functions have difficulties for extreme value estimations because the values extrapolated by kernel functions are either too small or too big. This paper suggests a Modified Cauchy kernel function that is suitable for both interpolation and extrapolation as an improvement.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.125-128
• /
• 1999

A linear time-invariant model can be described either by a parametric model or by a nonparametric model. Nonparametric models, for which a priori information is not necessary, are basically the response of the dynamic system such as impulse response model and frequency models. Parametric models, such as transfer function models, can be easily described by a small number of parameters. In this paper aiming to take benefit from both types of models, we will use linear-combination of basis fuctions in an impulse response using a few parameters. We will expand and generalize the Kautz functions as basis functions for dynamical system representations and we will consider estimation problem of transfer functions using Kautz function. And so we will present the influences of poles settings of Kautz function on the identification accuracy.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.596-599
• /
• 2003

In this paper, we designed the digital pulse motor control chip including a circular interpolation function. The proposed algorithm in this paper is a nonparametric cure generation algorithm (Jordan's algorith) and a very simple algorithm. So the design for this algorithm used a small number of gates. Also an average error is fairly low. The max output speed is 4Mpps(Pulse per second), the max input frequency is 16MHz and the chip is useful for the stepping and servo motors. The software contains one or two, and many axes linear interpolation algorithm and two axes circular interpolation algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.165-168
• /
• 1996

In this paper, we propose a design method of PID adaptive controller based on frequency domain analysis. The method is based on the estimation of a nonparametric process model in the frequency domain and the determination of the PID controller parameters by achieving partial model matching so as to minimize a performance function concerning to relative model error between the loop transfer function of the control system and the desired system. In the design method the process is represented only by a discrete set of points on the Nyquist curve of the process. Therefore it is not necessary to estimate a full order parameterized process model.