Wavelet transform on regression trend curve and its application in financial data

2020 ◽  
Vol 18 (05) ◽  
pp. 2050040 ◽  
Author(s):  
Xiaohui Zhou
Keyword(s):  
Wavelet Transform ◽  
Reconstruction Algorithm ◽  
Wavelet Function ◽  
Financial Data ◽  
Discrete Wavelet ◽  
Reconstruction Algorithms ◽  
Regression Curve ◽  
Growth Trend ◽  
Wavelet Filters ◽  
New Research

In this paper, wavelet transform on a regression curve is investigated by using length-preserving projection and its application in financial data is also discussed. First, properties of wavelet filters on the regression trend curves are studied and two-scale equation of wavelet function is deduced on the regression trend curves. Second, the decomposition and reconstruction algorithm of discrete wavelet transform on regression trend curves is derived. Finally, two examples in financial data are given for discussion, based on decomposition and reconstruction algorithms on regression trend curves. Some new research interpretations are presented in dealing with financial data such as “volatility on regression growth trend”, “error on regression growth trend”, and so on.

MULTIVARIATE SPECTRAL ANALYSIS USING HILBERT WAVELET PAIRS

2004 ◽  
Vol 02 (04) ◽  
pp. 567-587 ◽  
Author(s):  
BRANDON WHITCHER ◽  
PETER F. CRAIGMILE
Keyword(s):  
Time Series ◽  
Spectral Analysis ◽  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Multivariate Time Series ◽  
Discrete Wavelet ◽  
Pass Filter ◽  
Wavelet Filters ◽  
The Hilbert Transform ◽  
High Pass

We investigate the use of Hilbert wavelet pairs (HWPs) in the non-decimated discrete wavelet transform for the time-varying spectral analysis of multivariate time series. HWPs consist of two high-pass and two low-pass compactly supported filters, such that one high-pass filter is the Hilbert transform (approximately) of the other. Thus, common quantities in the spectral analysis of time series (e.g., power spectrum, coherence, phase) may be estimated in both time and frequency. Compact support of the wavelet filters ensures that the frequency axis will be partitioned dyadically as with the usual discrete wavelet transform. The proposed methodology is used to analyze a bivariate time series of zonal (u) and meridional (v) winds over Truk Island.

scholarly journals Prediction of Glioma Grades Using Deep Learning with Wavelet Radiomic Features

2020 ◽  
Vol 10 (18) ◽  
pp. 6296 ◽  
Author(s):  
Gökalp Çinarer ◽  
Bülent Gürsel Emiroğlu ◽  
Ahmet Haşim Yurttakal
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Wavelet Transform ◽  
Brain Tumors ◽  
World Health ◽  
Tumor Segmentation ◽  
Discrete Wavelet ◽  
Wavelet Filters ◽  
3D Wavelet Transform ◽  
Grade Classification

Gliomas are the most common primary brain tumors. They are classified into 4 grades (Grade I–II-III–IV) according to the guidelines of the World Health Organization (WHO). The accurate grading of gliomas has clinical significance for planning prognostic treatments, pre-diagnosis, monitoring and administration of chemotherapy. The purpose of this study is to develop a deep learning-based classification method using radiomic features of brain tumor glioma grades with deep neural network (DNN). The classifier was combined with the discrete wavelet transform (DWT) the powerful feature extraction tool. This study primarily focuses on the four main aspects of the radiomic workflow, namely tumor segmentation, feature extraction, analysis, and classification. We evaluated data from 121 patients with brain tumors (Grade II, n = 77; Grade III, n = 44) from The Cancer Imaging Archive, and 744 radiomic features were obtained by applying low sub-band and high sub-band 3D wavelet transform filters to the 3D tumor images. Quantitative values were statistically analyzed with MannWhitney U tests and 126 radiomic features with significant statistical properties were selected in eight different wavelet filters. Classification performances of 3D wavelet transform filter groups were measured using accuracy, sensitivity, F1 score, and specificity values using the deep learning classifier model. The proposed model was highly effective in grading gliomas with 96.15% accuracy, 94.12% precision, 100% recall, 96.97% F1 score, and 98.75% Area under the ROC curve. As a result, deep learning and feature selection techniques with wavelet transform filters can be accurately applied using the proposed method in glioma grade classification.

scholarly journals Penentuan Notasi Gamelan Rindik Menggunakan Metode Transformasi Wavelet

2018 ◽  
Vol 17 (3) ◽  
pp. 319
Author(s):  
I Gusti Made Meri Utama Yasa ◽  
Linawati Linawati ◽  
N Paramaita
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Wavelet Transform ◽  
Probabilistic Neural Network ◽  
Wavelet Function ◽  
Discrete Wavelet ◽  
Daubechies Wavelet ◽  
Data Process ◽  
Average Accuracy ◽  
Accuracy Level

Abstract—This paper present about recognition of gamelan rindik pattern using wavelet transform. Wavelet transform is used to find the special characteristic of gamelan rindik, which had previously been recorded and stored in computer with format *.wav. The data was subsequently used as training and tested data, Probabilistic Neural Network (PNN) was used to recognize gamelan rindik pattern using. The training and tasted data process used four different rindics, consisting 0f 240 gamelan rindik data. Discrete Wavelet Transform (DWT) was used as the method of feature extraction, with Symlet, Haar, and Daubechies Wavelet function. Those three functions of the wavelet  shows the average accuracy level for Symlet 94.58%, Haar 93.33%, and wavelet Daubechies 94.58%.

The efficiency of using wavelet transforms for filtering noise in the signals of measuring transducers

2021 ◽  
pp. 16-21
Author(s):  
Yuriy K. Taranenko
Keyword(s):  
Wavelet Transform ◽  
Wavelet Transforms ◽  
Threshold Value ◽  
Wavelet Function ◽  
Threshold Function ◽  
Discrete Wavelet ◽  
Threshold Method ◽  
Wavelet Filtering ◽  
Vanishing Moments ◽  
Measuring Signal

Methods of wavelet filtering of noise in signals of measuring transducers using the threshold method of discrete wavelet transform are considered. To study the methods of wavelet filtering of noise, special model signals were used to estimate the filtering errors. A method has been developed for determining the parameters of wavelet filtering of noise with a threshold for all levels of decomposition, which makes it possible to determine the wavelet function, threshold function and filtering threshold of the detailing coefficients of the discrete wavelet decomposition. The influence of the parameters of the noise distribution, the noise level, the number of vanishing moments of the Daubechies wavelet function, the nature of the threshold function and the threshold value on the filtering error caused by the noises of non-stationary measuring signals has been investigated by the method of a computational experiment. The results of the study of six threshold functions are given with the addition of noise to the measuring signal with nonstationary amplitude, frequency and duty cycle of rectangular pulses. The signal of the Doppler sensors is investigated, the wavelet filtering parameters are calculated, which provide the minimum error. The obtained parameters are used to construct graphs of signals before and after filtering directly in the time domain using the inverse wavelet transform.

Improving model performance with the integrated wavelet denoising method

2015 ◽  
Vol 19 (4) ◽  
Author(s):  
Yi-Ting Chen ◽  
Edward W. Sun ◽  
Min-Teh Yu
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
High Frequency ◽  
Model Performance ◽  
Score Function ◽  
Wavelet Denoising ◽  
Financial Data ◽  
Evaluation Procedure ◽  
Discrete Wavelet ◽  
Denoising Method

AbstractIntelligent pattern recognition imposes new challenges in high-frequency financial data mining due to its irregularities and roughness. Based on the wavelet transform for decomposing systematic patterns and noise, in this paper we propose a new integrated wavelet denoising method, named smoothness-oriented wavelet denoising algorithm (SOWDA), that optimally determines the wavelet function, maximal level of decomposition, and the threshold rule by using a smoothness score function that simultaneously detects the global and local extrema. We discuss the properties of our method and propose a new evaluation procedure to show its robustness. In addition, we apply this method both in simulation and empirical investigation. Both the simulation results based on three typical stylized features of financial data and the empirical results in analyzing high-frequency financial data from Frankfurt Stock Exchange confirm that SOWDA significantly (based on the RMSE comparison) improves the performance of classical econometric models after denoising the data with the discrete wavelet transform (DWT) and maximal overlap discrete wavelet transform (MODWT) methods.

Compact Nonlinear Signal Representation in Machine Tool Operations

1999 ◽  
Author(s):  
Satish T. S. Bukkapatnam
Keyword(s):  
Wavelet Transform ◽  
Machine Tool ◽  
Nonlinear Dynamical Systems ◽  
Initial Conditions ◽  
Compact Representation ◽  
Discrete Wavelet ◽  
Biorthogonal Wavelets ◽  
Wavelet Filters ◽  
Reconstructed Signal ◽  
Periodic Signals

Abstract Effective processing and compact representation of signals from manufacturing processes is necessary for sensor-based modeling (Venuvinod 98), and real-time diagnosis and control purposes. However, the processing and the representation of signals emerging from nonlinear processes remains largely ignored. This article focuses on the compact representation of near-periodic signals (signals containing a dominant period), emerging from nonlinear dynamical systems with known initial conditions. Such signals commonly occur in machine tool operations. We propose the concept of pseudoprobability space and provide an approach based on lifting scheme to customize wavelet filters to compactly represent near-periodic signals, and validate the approach for acoustic emission signals emanating from machine tool operations. Here, we focus on the concentration of the reconstructed signal using the coefficients from lifting on a single scale. We provide a detailed assessment of our approach, including a detailed study of the relationship between the discrete wavelet transform (DWT) and the discrete-time wavelet transform (DTWT). We derive the pyramid algorithm for DTWT with non-biorthogonal wavelets, which is necessary for our assessment. Our numerical experiments establish the viability of our approach.

Condition Identification of Bolted Joints Based on Wavelet Analysis

2011 ◽  
Vol 101-102 ◽  
pp. 1109-1113
Author(s):  
Hang Rui Yan ◽  
Guo Ying Zeng ◽  
Deng Feng Zhao ◽  
Mei Zi Tian
Keyword(s):  
Wavelet Transform ◽  
Experimental System ◽  
Wavelet Function ◽  
Bolted Joints ◽  
Experimental Result ◽  
Discrete Wavelet ◽  
Mean Square ◽  
Bolted Joint ◽  
Significant Difference ◽  
Acceleration Signals

In this paper, discrete wavelet transform (DWT) is used to analyze the acceleration signals near to the loose bolt, in order to study the characteristics of bolted joint condition. Firstly, an experimental system is built based on the NI data acquisition equipment. Secondly, based on qualitative analysis of the loose process of the bolted joints and spectrum analysis of response signals, an appropriate wavelet function is chosen and decomposed levels are determined. Lastly, according to the amplitude of each level, the contour diagrams are drawn and the Root Mean Square (RMS) of detailed coefficients at the sensitive level is calculated. Experimental result shows that both DWT contour diagrams and RMS at sensitive level have significant difference when preload changes.

Sign in / Sign up

Export Citation Format

Share Document