• Water Engineering Research
• /
• v.1 no.3
• /
• pp.209-222
• /
• 2000

A spectral formalism was applied to quantify the sampling errors due to spatial and/or temporal gaps in soil moisture measurements. The lack of temporal measurements of the two-dimensional soil moisture field makes it difficult to compute the spectra directly from observed records. Therefore, the space-time soil moisture spectra derived by stochastic models of rainfall and soil moisture was used in their record. Parameters for both models were tuned with Southern Great Plains Hydrology Experiment(SGP'97) data and the Oklahoma Mesonet data. The structure of soil moisture data is discrete in space and time. A design filter was developed to compute the sampling errors for discrete measurements in space and time. This filter has the advantage in its general form applicable for all kinds of sampling designs. Sampling errors of the soil moisture estimation during the SGP'97 Hydrology Experiment period were estimated. The sampling errors for various sampling designs such as satedlite over pass and point measurement ground probe were estimated under the climate condition between June and August 1997 and soil properties of the SGP'97 experimental area. The ground truth design was evaluated to 25km and 50km spatial gap and the temporal gap from zero to 5 days.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.1
• /
• pp.171-182
• /
• 2015

The general wavelet transform has profitable property in non-stationary signal analysis specially. The tunable Q-factor wavelet transform is a fully-discrete wavelet transform for which the Q-factor Q and the asymptotic redundancy r, of the transform are easily and independently specified. In particular, the specified parameters Q and r can be real-valued. Therefore, by tuning Q, the oscillatory behavior of the wavelet can be chosen to match the oscillatory behavior of the signal of interest, so as to enhance the sparsity of a sparse signal representation. The TQWT is well suited to fast algorithms for sparsity-based inverse problems because it is a Parseval frame, easily invertible, and can be efficiently implemented. The transform is based on a real valued scaling factor and is implemented using a perfect reconstruction over-sampled filter bank with real-valued sampling factors. The transform is parameterized by its Q-factor and its over-sampling rate, with modest over-sampling rates being sufficient for the analysis/synthesis functions to be well localized. This paper describes filter design of 2D discrete-time wavelet transform for which the Q-factor is easily specified. With the advantage of this transform, perfect reconstruction filter design and implementation for performance improvement are focused in this paper. Hence, the 2D transform can be tuned according to the oscillatory behavior of the image signal to which it is applied. Therefore, application for performance improvement in multimedia communication field was evaluated.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• Journal of Korean Society for Quality Management
• /
• v.32 no.4
• /
• pp.252-264
• /
• 2004

Variable sampling Interval (VSI) control charts vary the sampling interval according to value of the control statistic while the sample size is fixed. It is known that control charts with 2-state VSI scheme, which uses only two sampling intervals, give good statistical properties. Variable sample size (VSS) control charts vary the sample size according to value of the control statistic while the sampling interval is fixed. In the VSS scheme no optimal results are known for the number of sample sizes. It is also known that the variable sampling rate (VSR) $\bar{X}$ control chart with 2-state VSS and 2-state VSI scheme leads to large improvements In performance over the fixed sampling rate (FSR) $\bar{X}$ chart, but the optimal number of states for sample size Is not known. In this paper, the VSR Χ charts with multi-state VSS and 2-state VSI scheme are designed and compared to 2-state VSS and 2-state VSI scheme. The multi-state VSS scheme is considered to, achieve an additional improvement by switching from the 2-state VSS scheme. On the other hand, the multi-state VSI scheme is not considered because the 2-state scheme is known to be optimal. The 3-state VSS scheme improves substantially the sensitivity of the $\bar{X}$ chart especially for small and moderate mean shifts.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.867-877
• /
• 2004

The sequential sampling inspection method is an extension of the multiple-sampling methods, and its theory is based on the sequential probability ratio test (SPRT) of Wald. In this paper, the characteristics of SPRT for testing the number of defects are approximated by using the estimated excess over the boundaries. The use of the estimated excess shows good performances in estimating the operating characteristic function and the average sample number of SPRT compared to the method by neglecting the excess. It also makes it possible to determine the boundary values which satisfy the desired error probabilities.

• Journal of Communications and Networks
• /
• v.10 no.1
• /
• pp.55-62
• /
• 2008

Bandpass sampling (BPS) techniques for the direct down-conversion of RF bandpass signals have become an essential technique for software defined radio (SDR), due to their advantage of minimizing the radio frequency (RF) front-end hardware dependency. This paper proposes an algorithm for finding the minimum BPS frequency for simultaneously down-converting multiple RF signals through full permutation over all the valid sampling ranges found for the multiple RF signals. We also present a scheme for reducing the computational complexity resulting from the large scale of the purmutation calculation involved in searching for the minimum BPS frequency. In addition, we investigate the BPS frequency allowing for the guard-band between adajacent down-converted signals, which help lessen the severe requirements in practical implementations. The performance of the proposed method is compared with those of other pre-reported methods to prove its effectiveness.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.11 no.17
• /
• pp.67-80
• /
• 1988

This study is concerned with the comparison of two time homogeneous Poisson processes. Traditionally, the methods of testing equality of Poisson processes were based on the binomial distribution or its normal approximations. The sampling plans used in these methods are to observe the processes concurrently over a predetermined time interval, possibly different for each process. However, when the values of the intensities of the processes are small, inverse type sampling plans are more appropriate since there may be cases where only a few or even no events are observed in the predetermined time interval. This study considers 9 inverse type sampling plans for the comparison of two Poisson processes. For each sampling plans considered, critical regions and the design parameters of the sampling plan are determined to guarantee the significance level and the power at some values of the alternative hypothesis. The Problem of comparing of two Weibull processes are also considered.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.65-85
• /
• 2024

The tail probability of a function of a multivariate random variable is not easy to estimate by the crude Monte Carlo simulation. When the occurrence of the function value over a threshold is rare, the accurate estimation of the corresponding probability requires a huge number of samples. When the explicit form of the cumulative distribution function of each component of the variable is known, the inverse transform likelihood ratio method is directly applicable scheme to estimate the tail probability efficiently. The method is a type of the importance sampling and its efficiency depends on the selection of the importance sampling distribution. When the cumulative distribution of the multivariate random variable is represented by a copula and its marginal distributions, we develop an iterative algorithm to find the optimal importance sampling distribution, and show the convergence of the algorithm. The performance of the proposed scheme is compared with the crude Monte Carlo simulation numerically.

• Journal of Forest and Environmental Science
• /
• v.33 no.4
• /
• pp.295-304
• /
• 2017

This study compared and analyzed the construction of a land use change matrix for the Intergovernmental Panel on Climate Change's (IPCC) land use, land use change, and forestry area (LULUCF). We used National Forest Inventory (NFI) permanent sample plots (with a sample intensity of 4 km) and permanent sample plots with 500 m sampling intensity. The land use change matrix was formed using the point sampling method, Level-2 Land Cover Maps, and forest aerial photographs (3rd and 4th series). The land use change matrix using the land cover map indicated that the annual change in area was the highest for forests and cropland; the cropland area decreased over time. We evaluated the uncertainty of the land use change matrix. Our results indicated that the forest land use, which had the most sampling, had the lowest uncertainty, while the grassland and wetlands had the highest uncertainty and the least sampling. The uncertainty was higher for the 4 km sampling intensity than for the 500 m sampling intensity, which indicates the importance of selecting the appropriate sample size when constructing a national land use change matrix.

• Geomechanics and Engineering
• /
• v.9 no.6
• /
• pp.743-755
• /
• 2015

It is well known that the quality of sample significantly determines the accuracy of soil parameters for laboratory testing. Although sampling disturbance has been studied over the last few decades, the theoretical investigation of soil disturbance due to sampling penetration has been rarely reported. In this paper, an analytical solution for estimating the soil disturbance due to sampling penetration was presented using cavity expansion method. Analytical results in several cases reveal that the soil at different location along the sample centerline experiences distinct phases of strain during the process of sampling penetration. The magnitude of induced strain is dependent on the position of the soil element within the sampler and the sampler geometry expressed as diameter-thickness ratio D/t and length-diameter ratio L/D. Effects of sampler features on soil disturbance were also studied. It is found that the induced maximum strain decreases exponentially with increasing diameter-thickness ratio, indicating that the sampling disturbance will reduce with increasing diameter or decreasing wall thickness of sampler. It is also found that a large length-diameter ratio does not necessarily reduce the disturbance. An optimal length-diameter ratio is suggested for the further design of improved sampler in this study.