• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.12
• /
• pp.18-25
• /
• 2005

This paper presents a supercompact multi-wavelet scheme and its application to fluid simulation data. The supercompact wavelet method is an appropriate wavelet for fluid simulation data in the sense that it can provide compact support and avoid unnecessary interaction with remotely located data (e.g. across a shock discontinuity or vortices). thresholding for data compression is applied based on a covariance vector structure of multi-wavelets. The extension of this scheme to three dimensions is analyzed. The numerical tests demonstrate that it can allow various analytic advantages as well as large data compression ratios in actual practice.

• Earthquakes and Structures
• /
• v.3 no.6
• /
• pp.839-852
• /
• 2012

Earthquake records are often analyzed in various earthquake engineering problems, making time-frequency analysis for such records of primary concern. The best tool for such analysis appears to be based on wavelet functions; selection of which is not an easy task and is commonly carried through trial and error process. Furthermore, often a particular wavelet is adopted for analysis of various earthquakes irrespective of record's prime characteristics, e.g. wave's magnitude. A wavelet constructed based on records' characteristics may yield a more accurate solution and more efficient solution procedure in time-frequency analysis. In this study, a low-pass reconstruction filter is obtained for each earthquake record based on multi-resolution decomposition technique; the filter is then assigned to be the normalized version of the last approximation component with respect to its magnitude. The scaling and wavelet functions are computed using two-scale relations. The calculated wavelets are highly efficient in decomposing the original records as compared to other commonly used wavelets such as Daubechies2 wavelet. The method is further advantageous since it enables one to decompose the original record in such a way that a clear time-frequency resolution is obtained.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.30-41
• /
• 2020

Lines and textures are natural properties of the surface of natural objects, and their images can be sparsely represented in suitable frames such as wavelets, curvelets and wave atoms. Based on characteristics that the curvelets framework is good at expressing the line feature and wavesat is good at representing texture features, we propose a model for the weighted sparsity constraints of the two frames. Furtherly, a multi-step iterative fast algorithm for solving the model is also proposed based on the split Bergman method. By introducing auxiliary variables and the Bergman distance, the original problem is transformed into an iterative solution of two simple sub-problems, which greatly reduces the computational complexity. Experiments using standard images show that the split-based Bergman iterative algorithm in hybrid domain defeats the traditional Wavelets framework or curvelets framework both in terms of timeliness and recovery accuracy, which demonstrates the validity of the model and algorithm in this paper.

• 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.

• East Asian Economic Review
• /
• v.19 no.2
• /
• pp.189-220
• /
• 2015

Multi-scale representations are effective in characterising the time-frequency characteristics of financial return series. They have the capability to reveal the properties not evident with typical time domain analysis. Given the aforesaid, this study derives crucial insights from multi scale analysis to investigate the co-movements between Indian and emerging Asian equity markets using wavelet correlation and wavelet coherence measures. It is reported that the Indian equity market is strongly integrated with Asian equity markets at lower frequency scales and relatively less blended at higher frequencies. On the other hand the results from cross correlations suggest that the lead-lag relationship becomes substantial as we turn to lower frequency scales and finally, wavelet coherence demonstrates that this correlation eventually grows strong in the interim of the crises period at lower frequency scales. Overall the findings are relevant and have strong policy and practical implications.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.7
• /
• pp.328-336
• /
• 2005

Power quality has become concern both utilities and their customers with wide spread use of electronic and power electronic equipment. The poor quality of electric power causes malfunctions, instabilities and shorter lifetime of the load. In power system operation, power system disturbances such as faults, overvoltage, capacitor switching transients, harmonic distortion and impulses affects power quality. For diagnosing power quality problem, the causes of the disturbances should be understood before appropriate actions can be taken. In this paper we present a new approach to detect, localize, and investigate the feasibility of classifying various types of power quality disturbances. This paper deals with the use of a multi-resolution analysis by a discrete wavelet transform to detect power system disturbances such as interruption, sag, swell, transients, etc. We also proposed do-noising and threshold technique to detect power system disturbances in a noisy environment. To find the better mother wavelet for detecting disturbances, we compared the performance of the disturbance detection with the several mother wavelets such as Daubechies, Symlets, Coiflets and Biorthogonals wavelets. In our analysis, we adopt db4 wavelet as mother wavelet because it shows better results for detecting several disturbances than other mother wavelets. To show the effectiveness of the proposed method, a various case studies are simulated for the example system which is constructed by using PSCAD/EMTDC. From the simulation results. proposed method detects time Points of the start and end time of the disturbances.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.3
• /
• pp.21-28
• /
• 2007

The symmetric dual filters are essential for the construction of biorthogonal multiresolution an analyses and wavelets. We propose an algorithm to seek for dual symmetric trigonometric filters $\tilde{m}_0$ for for the given symmetric trigonometric filter $m_0$ and illustrate our algorithm by examples.

• Kyungpook Mathematical Journal
• /
• v.55 no.4
• /
• pp.1053-1067
• /
• 2015

A two-direction multiscaling function ${\phi}$ satisfies a recursion relation that uses scaled and translated versions of both itself and its reverse. This offers a more general and flexible setting than standard one-direction wavelet theory. In this paper, we investigate how to find and normalize point values and derivative values of two-direction multiscaling and multiwavelet functions. Determination of point values is based on the eigenvalue approach. Normalization is based on normalizing conditions for the continuous moments of ${\phi}$. Examples for illustrating the general theory are given.