• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.39-48
• /
• 2005

This paper proposes novel texture segmentation method using Bayesian estimation method and neural networks. We use multi-scale wavelet coefficients and the context information of neighboring wavelets coefficients as the input of networks. The output of neural networks is modeled as a posterior probability. The context information is obtained by HMT(Hidden Markov Tree) model. This proposed segmentation method shows better performance than ML(Maximum Likelihood) segmentation using HMT model. And post-processed texture segmentation results as using multi-scale Bayesian image segmentation technique called HMTseg in each segmentation by HMT and the proposed method also show that the proposed method is superior to the method using HMT.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.175-186
• /
• 1999

Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support fer multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To date, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques' results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.175-186
• /
• 1999

Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support for multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To data, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.646-661
• /
• 2003

It is not easy that we visualize the large volume data stored in the every client computers of the web environment. One solution is as follows. First we compress volume data, second store that in the database server, third transfer that to client computer, fourth visualize that with direct-volume-rendering in the client computer. In this case, we usually use wavelet transform for compressing large data. This paper reports the experiments for acquiring the wavelet bases and the compression ratios fit for the above processing paradigm. In this experiments, we compress the volume data Engine, CThead, Bentum into 50%, 10%, 5%, 1%, 0.1%, 0.03% of the total data respectively using Harr, Daubechies4, Daubechies12 and Daubechies20 wavelets, then visualize that with direct-volume-rendering, afterwards evaluate the images with eyes and image comparison metrics. When compression ratio being low the performance of Harr wavelet is better than the performance of the other wavelets, when compression ratio being high the performance of Daubechies4 and Daubechies12 is better than the performance of the other wavelets. When measuring with eyes the good compression ratio is about 1% of all the data, when measuring with image comparison metrics, the good compression ratio is about 5-10% of all the data.

• Journal of Korea Water Resources Association
• /
• v.52 no.8
• /
• pp.575-587
• /
• 2019

This study evaluated the effect of a mother wavelet in the wavelet analysis of various times series made by combining white noise and/or sine function. The result derived is also applied to short-memory arctic oscillation index (AOI) and long-memory southern oscillation index (SOI). This study, different from previous studies evaluating one or two mother wavelets, considers a total of four generally-used mother wavelets, Bump, Morlet, Paul, and Mexican Hat. Summarizing the results is as follows. First, the Bump mother wavelet is found to have some limitations to represent the unstationary behavior of the periodic components. Its application results are more or less the same as the spectrum analysis. On the other hand, the Morlet and Paul mother wavelets are found to represent the non-stationary behavior of the periodic components. Finally, the Mexican Hat mother wavelet is found to be too complicated to interpret. Additionally, it is also found that the application result of Paul mother wavelet can be inconsistent for some specific time series. As a result, the Morlet mother wavelet seems to be the most stable one for general applications, which is also assured by the recent trend that the Morlet mother wavelet is most frequently used in the wavelet analysis research.

• Journal of applied mathematics & informatics
• /
• v.17 no.1_2_3
• /
• pp.747-757
• /
• 2005

A physical variable is customarily thought of as a function. Another way of describing a physical variable is to specify it as a functional, whose special type is called a distribution. It turns out that the distribution concept provide a better mechanism for analyzing certain physical phenomena than does the function concept. By using wavelets with high regularity we give a resolution of functions with slow growth.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.373-376
• /
• 2002

In this paper, we give the definition of the two dimensional q-Gabor wavelet. It consists of the q-normal distribution, which is also given in this paper. If the q-normal distribution is used as a kernel of the Gabor wavelet instead of the normal distribution, the q-Gabor wavelet is obtained. Furthermore, the q-Gabor wavelet is compared with the Gabor and the Haar wavelets to show how good The q-Gabor wavelet is.

• Journal of Urban Science
• /
• v.6 no.2
• /
• pp.49-57
• /
• 2017

A new Fiber Bragg Grating (FBG) wavelength demodulation scheme is studied in the paper, which consists of an improved de-noising method and Gaussian fitting peak searching algorithm. The improved translational invariant wavelet without threshold adjust factor is proposed to get a better de-noising performance for FBG sensor signal and overcome the drawbacks of soft or hard threshold wavelets. In order to get a high wavelength demodulation precision of FBG sensor signal, this de-noising method is designed to combine with Gaussian fitting peak searching algorithm. The simulation results show that the wavelength maximum measurement error is lower than 1pm, and can get a much higher accuracy.

• Journal of applied mathematics & informatics
• /
• v.4 no.2
• /
• pp.529-534
• /
• 1997

Even though the Shannon wavelet is a prototype of wavelets are assumed to have. By providing a sufficient condition to compute the size of Gibbs phe-nomenon for the Shannon wavelet series we can see the overshoot is propotional to the jump at discontinuity. By comparing it with that of the Fourier series we also that these two have exactly the same Gibbs constant.

• Journal of the Korean Mathematical Society
• /
• v.36 no.6
• /
• pp.1075-1090
• /
• 1999

This paper deals with Littlewood-Paley type estimates of the Besov spaces {{{{ { B}`_{p,q } ^{$\alpha$ } }}}} on the d-dimensional unit cube for 0< p,q<$\infty$ by two certain classes. These classes are including biorthogonal wavelet systems or dual multiscale systems but not necessarily obtained as the dilates or translates of certain fixed functions. The main assumptions are local supports of both classes, sufficient smoothness for one class, and sufficiently many vanishing moments for the other class. With these estimates, we characterize the Besov spaces by coefficient norms of decompositions with respect to biorthogonal wavelet systems on the cube.