Wavelet Transform Method Research Articles

Heart disease detection using hybrid of bacterial foraging and particle swarm optimization

Bacterial-foraging-optimization (BFO) has newly raised and one of the most useful nature inspired optimization algorithm for real parametric optimization. During the process of random walk, the BFO algorithm makes search in the random direction, which increases delay. To overcome the delay in reaching the global optimum and also to boost up the performance of BFO, we proposed an algorithm by mixing the features of BFO and particle swarm optimization (PSO) for detecting the abnormal cardiac beat. Computer simulations illustrate the usefulness of the developed approach compared to the basic versions of BFO and PSO. The main aim of the research is to develop new modifications of BFO and its combination with transform technique such as Wavelet Transform and machine learning method, support vector machines (SVMs) to test their performances in the detection of cardiac arrhythmia. Modification of BFO focuses for improving its convergence in terms of speed and accuracy. Provided results in this paper show that, for the detection of MI and BBB classes, the BFPSO algorithm with SVM gives 98.9% and 99.3% accuracy on MIT-BIH database by including NSR database also. Moreover, the results demonstrate the effectiveness of the proposed method to improve the detection of cardiac arrhythmia.

Using wavelet transform to analyse on-road mobile measurements of air pollutants: a case study to evaluate vehicle emission control policies during the 2014 APEC summit

Abstract. Vehicle emissions are a major source of air pollution in urban areas and thus greatly impact air quality in the megacity Beijing. Various vehicle emission control policies have been implemented at great cost, but there is a lack of appropriate methods to evaluate the effectiveness of such policies. Here we developed a wavelet transform method (WTM) to evaluate the effectiveness of vehicle emission control policies during the 2014 Asia-Pacific Economic Cooperation (APEC) summit, taking advantage of high-time-resolution mobile measurements of NO, NOx, BC, CO, SO2, and O3 made around the 4th Ring Road of Beijing. The WTM decomposed on-road mobile measurements into high- and low-frequency components, where the former represents immediate vehicle emissions, and the latter represents the atmospheric background in addition to accumulated on-road emissions. The high-frequency component of the WTM (CH_freq.), which represents the concentrations of pollutants from vehicle emissions (Cveh.), was used to evaluate the changes in vehicle emission intensity in the full-APEC period (3–12 November 2014) relative to the pre-APEC (28 October to 2 November 2014) and post-APEC (13–22 November 2014) periods, during which different vehicle emission control policies were implemented. Our results suggest that the Cveh. of NO, NOx, BC, and CO in the full-APEC period were 19.4 %, 17.7 %, 0.0 %, and 50.0 % lower, respectively, than those in the pre-APEC period during daytime and were 50.0 %, 47.3 %, 62.5 %, and 50.0 % lower than those in the post-APEC period during daytime. The Cveh. of NO, NOx, BC, and CO in the full-APEC period were 65.3 %, 65.4 %, 14.3 %, and 50.0 % lower than those in the post-APEC period during night-time. These results indicate that the vehicle emission control policies implemented during the full-APEC period were effective. Using on-road mobile measurements in combination with the WTM, we developed a new method for the evaluation of pollution control policies.

OPTIMIZATION OF ARTIFICIAL NEURAL NETWORKS USING ANT COLONY OPTIMIZATION TO IDENTIFY SIGNATURE IMAGES

Biometrics can be used in identification or recognition systems because it is a method for recognizing humans based on one or more physical features or unique behaviors, one of which is the Signature. In its application, signatures need to be examined (identification) because signatures are often imitated or falsified for various purposes. The signature that will be identified will be taken first by its characteristics by performing the feature extraction process using the Gabor Wavelet Transform (TGW) method. After extracting, the signature identification process is carried out using the Neural Network. In the process of applying the Neural Network method, optimization will be performed using Ant Colony Optimization. The results showed that the identification of signatures made using the Neural Network alone produced an accuracy of 77%, but after optimization using Ant Colony Optimization increased to 83%.

Extraction of EEG signals using the discrete wavelet transforms

This study focuses on feature extraction for Electro Encephalo Graph (EEG) signals using the Discrete Wavelet Transform method. The EEG signal is used to move up the cursor and the down cursor. In each subband of the EEG signal wave the average value is taken to characterize the EEG signal. Backpropagation Neural Network is used as an EEG signal classification to determine whether the up cursor or the down cursor. The data used in this study are EEG data derived from BCI competition 2003 (BCI Competition 2003). Decision-making is done in two stages. In the first stage, the mean value of each wavelet subband is used as a feature extraction of the EEG signal data. This feature is an input to the Backpropagation Neural Network. In the second stage of the classification process into two classes of class 0 (for the up cursor) and class 1 (for the down cursor), there are 260 training data file of EEG and 293 signals from EEG signal data testing file, so the whole becomes 553 data files of EEG signals. The result obtained for EEG signal classification is 77.2% of the tested signal data.

A Hybrid Image Steganography Method

This is age of fast communication and data revolution. Huge amount of data is transmitted and received in every second utilizing the current infrastructure. Providing the security and maintaining integrity of the data while it is being transferred through the public channels is a challenging task. Steganography can be used in this purpose by concealing the data inside text, image, audio or video file formats and send the files to the other end. This paper gives an overview of various image steganography methods. To hide secret information in images various steganographic methods are available which have their own pros and cons. In this paper we have discussed the types of image steganography. Here we propose two different image steganography methods using Modified Least Significant Bits (LSB) and Discrete Wavelet Transform (DWT) methods. Also, the results are analyzed using different parameters like Peak signal to noise ratio(PSNR), Mean Square Error(MSE) to find out the efficiency of the proposed methods.

Medical Image Authentication by SWT and SVD

The proposed paper work is implemented using Stationary Wavelet Transformation (SWT) with Singular Value Decomposition (SVD).Even though, there are many other transformations, the Stationary Wavelet Transformation method is chosen for its shift invariance property. The designed method has three steps; the first step is the decomposing of the Medical image into sub-bands using SWT to find the value of sub band and as a second step is to apply SVD, third step will combine both the images with scaling factor. The experiments were conducted over gray scale of MRI and CT Medical images. The statistics of proposed method indicates that imperceptibility of Watermarked Medical images have a Peak Signal to Noise Ratio (PSNR) value of 50 DB for medical images. The robustness is ensured by having Correlation Coefficient (CC) of 1 for the retrieved watermark images. Security for the watermark is extended by encrypting the watermark with chaotic sequence.

Temel Bileşen Analizi Yöntemleri Kullanarak Parkinson Hastalığının Otomatik Teşhisi

Parkinson's disease is a sneaky brain disorder that progresses very slowly. The diagnostic methods of this disease include the analysis of individual voices. The earliest detection of Parkinson's by voice analysis is made possible by various methods. In this study, the results obtained from the application of Tunable Q-factor Wavelet Transformation (TQWT) method to the recorded audio signals of 188 Parkinson's patients and 64 healthy individuals were used. The principal component analysis (PCA) and its types (kernel PCA (KPCA) and Probabilistic PCA (PPCA)) which are dimension reduction methods have been applied to the TQWT features. Afterwards, k-fold cross validation method was applied to the new data groups and the training-test data were obtained. In the next step, the data were separately classified by random forest (RF) algorithm to investigate the effectiveness of the dimension reduction methods and the results were also interpreted by statistical criteria. In terms of classification results, OTBA was the most successful in size reduction methods with 87.56% accuracy rate. In addition, as a result of this method, ROC and PRC area values reached a band of about 0.95, proving that patient and healthy class decomposition approached perfection. The performance results of this study, which is suitable for real-life applications, were compared with the single study in the literature in which the same data was used, and this study showed that higher statistical ratios were obtained in comparison to the other study. Moreover, the high number of people in whom the data was recorded compared to other studies in the literature increases the importance of the study in this field.

Digital pulse processing algorithm for neutron and gamma rays discrimination

This paper presents a proposed algorithm for discriminating neutron and gamma radiation events. In the proposed algorithm, discriminating features are extracted from the input radiation event. These features are extracted using charge integration, matched filtering, and Discrete Wavelet Transform (DWT) methods. The extracted features are then fed into the discriminator which is an Artificial Neural Network (ANN) discriminator or a Support Vector Machine (SVM) discriminator. The obtained results prove that the proposed algorithms can be used efficiently for the neutron and gamma ray discrimination purpose and that the DWT based method achieves the highest discrimination rates. For discriminators, the SVM discriminator achieves better performance with a slightly shorter processing time compared to the ANN discriminator.

Image steganalysis based on convolutional neural network and feature selection

SummarySteganalysis is to detect whether or not the seemly innocent image hiding message. It is an important research topic in information security. With the development of steganography technology, steganalysis becomes more and more difficult. Some steganalysis methods have been proposed to improve the performance. Most research work concentrates on special steganography information detection and the image steganography features are designed manually. Few research works concentrate on universal steganalysis methods. In this paper, as the first several attempts, a novel image steganalysis method based on deep neural network is proposed. First, image high‐frequency features are extracted with wavelet transformation method because that most image hiding message are high frequency. Second, high‐dimensional image steganography features are extracted with deep neural networks according to the high‐frequency images and informative features combination is selected with a novel feature selection method based on entropy. Then, a parallel SVM model is proposed to build the steganalysis model based on large scale training samples. At last, the efficiency of the proposed method is illustrated through analyzing a practical image steganalysis example.

Transient simulation on closure of wicket gates in a high-head Francis-type reversible turbine operating in pump mode

To solve the problem of grid instabilities, regulation in the Pumped Hydro Energy Storage (PHES) plants should quickly respond to the variation of electricity produced by unpredictable renewable energy. In this paper, a power reduction scenario applied to a pump turbine of a PHES is simulated considering the transient closure process of wicket gate. A novel dynamic mesh technique is applied to simulate the rotation of wicket gate vanes from best efficiency point to shutdown condition. Detached Eddy Simulation (DES) turbulence model is utilized to capture complex unsteady flow and the water weak compressibility effect is considered in the transient simulation. Flow rate, torque, power and pressure are analysed by the Fast Fourier Transform (FFT) and Continuous Wavelet Transform (CWT) methods. The results illustrate the delay between the performance parameters flow rate and power and the wicket gate opening angle. The closure of wicket gates affects the flow characteristics downstream the wicket gates greatly, causing intensive pressure fluctuations. The magnitude of pressure fluctuations downstream the wicket gate becomes the highest with the wicket gate closure of about 60%. Aside the blade passage frequency, a low frequency occurs, with the appearance of unsteady flow in pump turbine. Moreover, strong torque pulsations occur on the pin of the wicket vane when the percentage of closure is between 60% and 80%, with peaks much higher than that at the best efficiency point. The transient results can provide meaningful reference to the regulation law of wicket gate for safe operation of the pump turbine.

Investigation of a Signal Demodulation Method based on Wavelet Transformation for OFDR to Enhance Its Distributed Sensing Performance.

Optical fiber distributed sensing that is based on optical frequency domain reflectometer (OFDR) is a promising technology for achieving a highest spatial resolution downwards to several millimeters. An OFDR signal demodulation method that is based on Morlet wavelet transformation (WT) is demonstrated in detail to improve the resolution of distributed sensing physical quantity under a high spatial resolution, aiming at the trade-off between spatial and spectrum resolution. The spectrum resolution, spatial interval of the measured gauges, and spatial resolution can be manually controlled by adjusting the wavelet parameters. The experimental results that were achieved by the wavelet transformation (WT) method are compared with these by short time Fourier transformation (STFT) method and they indicate that significant improvements, such as strain resolution of 1 με, spatial resolution of 5 mm, average repeatability of 4.3 με, and stability of 7.3 με within one hour, have been achieved. The advantages of this method are high spatial and spectral resolution, robust, and applicability with current OFDR systems.

Simulation of Performance Comparison between Discrete Wavelet Transform and Discrete Cosine Transform Methods for Radar Signal Processing in High-Noise Area

Detection of low signal and determination target locations are tremendously important in the radar system. Performance of radar can be enhanced by improving the signal-to-noise ratio of the received signal at the receiver. In this paper, we demonstrate an algorithm in radar signal processing, due to extract the signal target in the place of noise. This algorithm is based on Discrete Cosines Transform (DCT) and Discrete Wavelet Transform (DWT) methods. DWT signal processing analyses and comparatives with mother wavelet Haar, Daubechies-12, Coiflet-5 and Symlet-8. In addition, DCT signal processing analyses and comparatives with the same window function and uses to restrict the signal. Window function has influenced the signal resolution in frequency domain. Window functions that are used in this research are Rectangular, Hamming, Hanning and Dolph-Chebyshev. The results of the simulation and analysis show that mother wavelet with DWT, wavelet Daubechies-12 and Symlet-8 gives the best performance while mother wavelet Haar gives a bad performance. Wavelet Daubechies-12 gives the biggest signal to noise ratio that is 32.0603 dB. Mother wavelet Symlet-8 gives 32.6589 dB. Mother wavelet Haar gives 14.6692 dB. Testing DCT window function, window Dolph-Chebyshev gives the best performance, which gives the best separation of the signal. Analysis of signal reflection that accepted by radar shows the result that DWT is giving better performance than DCT in breaking of noise.

Perancangan Perangkat Lunak Kompresi Citra Menggunakan Transformasi Wavelet dan PCA

<p>Now days, The most needed of digital images is influenced by the people will that want to take a part of moment life into digital image. The good digital image has the big filesize, so it will need more space memory to saving more images. There is technique in image processing to decrease file size that is compression. By combine wavelet transformation method and Principal Component Analysis in developing application can produce the good compression technique.</p>

Wavelet Analysis as a Tool for Studying the Road Traffic Characteristics in the Context of Intelligent Transport Systems with Incomplete Data

A frequent problem of traffic flow characteristics acquisition is data loss, which leads to uneven time series analysis. An effective approach to uneven data analysis is the spectral analysis, which requires obtaining process with a constant sampling interval, for example, by restoring missing data, which leads to the appearance of dating error. Thus, the main purpose of this study is to develop a method and software for wavelet analysis of traffic flow characteristics without restoring the missing data.
 To analyze and interpret non-stationary uneven time series obtained from traffic monitoring systems, we propose the wavelet transformation method with adjustment of the sampling intervals, which results in a time-frequency domain with a constant sampling interval. Wavelet analysis is applied to the macroscopic traffic flow characteristics.
 We developed the software for traffic flow wavelet analysis on the "ITSGIS" intelligent transport geo-information framework using the attribute-oriented approach.
 Wavelet analysis of traffic flows characteristics using Morlet wavelets was accomplished for data analysis of the city of Aarhus, Denmark. Wavelet spectra and scalograms were constructed and analyzed, general dependencies in the frequency distribution of extremes, and differences in spectral power were revealed.
 The developed software is being experimentally tested in solving practical problems of municipalities and road agencies in Russia.

Space-Time Spectral Analysis of 2-D Signal on the Globe Using Spherical Harmonics and Wavelet Transform Methods

In this research, a method to analyze wave-number and frequency spectra from time series of global 2-D geophysical data has been developed. Spherical Harmonics (SH) transform method is used to analyze wave structures in both longitude and latitude, while the temporal evolution of frequency content in the data is analyzed using complex wavelet transform. The frequency spectra of longitudinally propagating waves are separated into their westward- and eastward components by wavelet transforms of the corresponding to complex SH coefficients and their complex conjugate. The method was applied to analyze daily OLR (Outgoing Long-wave Radiation) data of 27 years record (1987-2013) as a proxy for large-scale convective pattern. It proved that the method enables us to identify the existence of various wave structures representing the convectively coupled planetary atmospheric waves. As SH and wavelet transform methods are generic tools for signal analysis, our space-time spectral analysis method should also be applicable to other geophysical data whose properties are characterized with embedded planetary scale waves.

ANALYSIS OF APPLICATION OF NEURAL NETWORKS TO IMPROVE THE RELIABILITY OF ACTIVE THERMAL NDT

Background. The relevant question of increasing the informative content and reliability of the thermal non-destructive testing is considered in this article. The most promising algorithms of digital processing of sequences of thermograms are given.Objective. The main aim of this research is to determine the advantages and disadvantages of the application of each considered method of digital processing of thermograms. Secondary, the possibilities of testing automation with the use of the selected methods of digital processing of thermograms are analyzed in this article.Methods. Computer simulation software was used to obtain the artificial sequence of the thermograms. Methods of wavelet analysis, principal components analysis and neural networks were used to process the received data.Results. The simulation of active thermal testing process is carried out in this research. The artificial thermogram sequence with a high level of noise is obtained for the object of testing. In order to quantify the results of application of considered methods, relative errors of determining the area of defects were calculated. Also values of Tanimoto criterion are obtained. The advantages of the neural network processing of digital data in thermal non-destructive testing have been established and proved in this article. Shape of defects on a binary map built by the neural network was closest to true compared with principal components analysis method. The effectiveness of neural networks is also confirmed by quantitative estimates.Conclusions. The method of wavelet transformation has a high sensitivity. This method is ineffective in the conditions of uneven heating and high noise. The principal components analysis method allows increasing the SNR and improving the visual perception of thermograms, but does not provide complete separation of information about defects and noises caused by uneven heating. Methods of artificial neural networks theory provide the best reproduction of the shape and size of the defects, but the training process requires significant time and computing resources.

Separation and Interpretation of Gravity Field Data Based on Two Dimensional Normal Space-Scale Transform (NSST2D) Algorithm: A Case Study of Kauring Airborne Gravity Test Site, Western Australia

The gravity field signal observed on the surface of the earth is the superposition of the gravitational effects produced mainly by the mass sources at different locations and depths from the surface down to the underground. Reliable geophysical interpretation of gravity anomalies is highly dependent on the validity of the data processing methods and the rationality of the calculated results. This paper proposes a novel potential field separation method based on two-dimensional Normal Space-Scale Transform (NSST2D) algorithm to implement the residual-regional field separation. Compared with the two dimensional Discrete Wavelet Transform (DWT2D) method often appeared in the previous potential field separation studies, the NSST2D algorithm can keep the shape of the separated field from distortion by normalizing the conventional two-dimensional wavelet transform kernels. Based on gravity field of synthetic models, the separated residual-regional fields respectively derived from DWT2D with five different wavelet bases and those from NSST2D are compared. The experimental results verify the effectiveness and superiority of the proposed NSST2D algorithm. Finally, the NSST2D algorithm is also applied to the separation of the complete Bouguer gravity anomaly in the Kauring airborne gravity test site, Western Australia. The results show that the characteristics of the separated field from the corresponding mass sources with different depths maintain relatively good consistency with the feature of the three-dimensional inversion density contrast distribution.

Characteristics of microseismic waveforms induced by hydraulic fracturing in coal seam for coal rock dynamic disasters prevention

Coal rock dynamic disasters have been a persistent threat to mine safety. Hydraulic fracturing(HF) technique has been proved to be an effective method for preventing coal rock dynamic disasters in underground coal mines. In order to monitor the crack extent of HF in coal seam, highly precision microseismic(MS) data acquisition apparatus and sensitive sensors are employed to monitor the cracks induced by coal seam HF in Xieqiao Coal Mine. Lots of effective and weak MS waveforms induced by HF are successfully recorded. Some useful methods such as wavelet transformation, Hilbert-Huang transformation, envelope analysis and curve fitting method help to make comprehensive insights into the amplitude-frequency, time-frequency, duration and peak following attenuation characteristics of these HF induced MS waveforms. The frequency, duration time and peak following attenuation characteristics of MS waveforms induced by mining, blast and coal seam HF are statistically studied. The results show that these characteristic parameters, peak frequency, duration time and peak following attenuation, are very sensitive to distinguish these three typical kinds of induced MS waveforms. Further study shows that the principles of fractures’ propagation influenced by the pressurized water and the backfill effect of pores by large volume of pressurized water injection and the pressurized water itself are the key factors influencing the characteristics of MS waveforms. The conclusions are the theoretical basis of locating the cracks and monitoring the effect of HF in coal seams by using MS technique, which can provide the basis reference for designing optimized, safe and effective HF program to prevent the coal rock dynamic disasters, and will be of great significance to coal mine safety.

A wavelet transform method for studying the energy distribution characteristics of microseismicities associated rock failure

Microseismicity signals released during rock failure process are firstly recorded using microseismicity monitoring system. A wavelet transform scheme is then developed on the basis of the discrete wavelet transform and implemented into MATLAB to study the energy distribution characteristics of the monitored microseismicity signals. The wavelet transform scheme decomposes the recorded microseismicity signals into various wavelets at seven scales and eight frequency bands. The microseismicity energy at each frequency band is then calculated by integrating the wavelets in each scale. It is found that, for the microseismicity signals recorded during the uniaxial loading of the granite, the microseismicity energies are mainly distributed between the bands 7.8125–15.625 kHz, 15.625–31.250 kHz and 31.25–62.5 kHz and the percentages of the released energies at these frequency bands are 8.24%, 62.72%, 28.08% of the total energies, respectively. The results reveal that the microseismicity energies at these levels are directly related to the damage mechanisms of the granite although further studies are need to identify the failure modes. Then these monitored signals were processed using wavelet transformation to find out the frequency distribution rule and the frequency band energy varying rule of the acoustic emission (AE) signals during the different rock damage and failure stages. The rock failure mechanism was interpreted from the perspective of the relationship between AE signal frequency change and crack propagation. The frequency band energy distribution histograms of the microseismicity signals at different damage stages were computed and drawn by the energy calculation method of wavelet transformation implemented into MATLAB. The energy percentage of the low frequency band (d7-a7) and that of the dominated frequency band (d4-d6) and their variation rule were analyzed especially. Accordingly, the critical damage point is that the low frequency energy percentage is above a certain threshold. This index could be used as the failure precursor criterion for rock mass instability monitoring and early warning, since it provided a theoretical guidance for evaluating internal damage of rock. Finally, it is concluded that the proposed wavelet transform method may provide a new mean for the characteristics analysis of the microseismicity signals recorded by the microseismicity monitoring system and may stimulate the application of the microseismicity monitoring technology in the geotechnical and mining engineerings through analyzing the energy of the microseismicity signals to understand the law of microseismicity emitted by rockmass.

Influence of denoising of input signal on classification of object location by artificial neural network in ultrawideband radiointroscopy

Background: A wide usage of impulse ultrawideband subsurface radars for a number of practical approaches in archeology, construction and humanitarian demining is holding back because of presence of noises and clutters of high level in the reflected field. It often makes the object classification practically unreal for at not big depths and distances from receiving and transmitting antennas. Besides of using special antenna system designs to improve recognition results, it is interesting to apply modern digital signal filtering techniques. Objectives: To investigate the influence of denoising on the quality of artificial neural network recognition of subsurface objects and their coordinates for a model of additive gaussian noise of a different noise level. Materials and methods: In this paper the idea of improving the stability of recognition of hidden objects in the presence of outside noise by previous processing of input signals with the latest popular noise reduction methods, such as the caterpillar method and wavelet transform method is verified. To eliminate the randomness of the result of the neural network response for each realization of the additive noise of a given level, a sufficient number of attempts are calculated for each of the methods, and statistics are provided to illustrate the effectiveness of each of the approaches. To check the hypothesis of the efficiency of input signal denoising the numerical simulation of the model of a real ground surface with subsurface object is carried out by means of Finite Difference Time Domain method (FDTD). The artificial neural network is trained on the obtained ideal time dependences of the amplitudes of the reflected field to correctly recognize the position of the object. The training is subsequently checked on the same input signals with additional noise of a certain level. Recognition errors in the last case are compared with similar errors when popular noise reduction procedures are applied to noisy input signals. Results: It is demonstrated that artificial neural networks have good approximating properties capable to effectively resist the noises in the input signals It is shown that for all noise levels, the caterpillar method statistically degrades the quality of an object recognition. The wavelet-transform method statistically improves slightly the classification of objects than for absence of denoising, but this result is not stable. Conclusion: For effective application of methods of noise filtration in received signals of impulse radar it is nessusary to have previous knowledge about noise character or peculiarities of useful signal. Implementation of denoising techniques without the use of this knowledge cannot improve the recognition quality of surface objects.