Translation Invariant Wavelet Research Articles

Partial discharge based recognition of water droplets location in high voltage insulator using convolutional neural network – Bacterial foraging algorithm based optimized machine learning classifier

Measurement and analysis of Partial Discharge (PD) patterns have appeared as an emerging field in assessing insulation failure in High Voltage apparatus. This paper uses a PD signal combined with the deep convolution-optimized learning machine classifier (DC-OLMC) to predict the location of water droplets in 11 kV polymer insulators subjected to alternating currents. There are two major confront when applying the proposed algorithm: i) Contamination is a significant issue in PD signal measurement, which causes a reduction in recognition rate (RR), and ii) with minimal computing time, high-level feature extraction and recognition. Traditional condition monitoring methods of insulators concentrated on extracting fewer priority features from the input patterns. In the current work, to address this problem, an Alexnet with Bacterial Foraging Algorithm (BFO) based optimized kernel parameter classifier and Translation Invariant Wavelet Transform (TIWT) is employed to remove interference from PD signals. The analysis demonstrates that the suggested technique, with an identification rate of 99.17%, is considered a valuable tool for locating water droplets in high-voltage insulators.

Research on prediction of coal and gas outburst risk based on TIWTD-CNSA

When processing the current coal and gas outburst risk index data, it is observed that the data sequence does not have intuitive regularity, and the acquired data signals are generally mixed with different degrees of noise, which hinders data processing and prediction. To reduce the influence of noise signal on prediction, it is proposed to use Translation-invariant Wavelet Threshold Denoising (TIWTD) to process signal data, and the result shows that the noise signal in the original data is significantly reduced. On this basis, a Compact Negative Selection Algorithm (CNSA) is introduced to detect abnormal signals exceeding the critical value in the data and make predictions. After training the model with the gas hazard index feature subset collected during the excavation process of No. 11192 mining face in a coal mine from Guizhou province in China, input the processed indicator data into the model for prediction. The results show that the model can effectively identify the anomalies in the data and accurately predict the risk of coal and gas outburst, the TIWTD-CNSA model can be used to guide engineering practice.

Application of translation wavelet transform with new threshold function in pulse wave signal denoising.

The wrist pulse wave under the optimal pulse pressure plays an important role in detecting human body's physiological and pathological information. Wavelet threshold filtering is a common method for pulse wave de-noising. However, traditional filtering methods cannot smoothen the whole pulse wave well and highlight the details. In view of this, an attempt is made in this paper to propose the pulse wave denoising algorithm for pulse wave under optimal pulse pressure according to the translation invariant wavelet transform (TIWT) and the new threshold function. Firstly, by using hyperbolic tangent curve and combining the advantages of soft threshold function and hard threshold function, the new threshold function is derived. Secondly, based on the TIWT, pseudo-Gibbs phenomenon gets suppressed. The experiments show that in comparison to the traditional wavelet filtering algorithm, the novel algorithm can better maintain the pulse wave geometric characteristics and has a higher signal to noise ratio (SNR). The TIWT with improved new threshold compensates the shortcomings of the traditional wavelet threshold denoising methods in a better way. It lays a foundation for extracting time-domain characteristics of pulse wave.

Translation-invariant functional clustering on COVID-19 deaths adjusted on population risk factors

Abstract This paper focuses on clustering the COVID-19 death rates reported in Europe and the United States. Several methods have been developed to cluster such functional data. However, these methods are not translation-invariant (TI) and thus cannot handle different times of arrivals of the disease, nor can they consider external covariates and so are unable to adjust for the population risk factors of each region. We propose a novel three steps clustering method to circumvent these issues. First, feature extraction is performed by TI wavelet decomposition, which permits to deal with the different onsets. Then, single-index regression is used to neutralize disparities caused by population risk factors. Finally, a nonparametric mixture is fitted on the regression residuals to achieve the region clustering.

Differential confocal measurement of microstructure surface topography based on centering error optimization and wavelet threshold denoising

This paper proposes a precise differential confocal measurement method based on centering error optimization and wavelet threshold denoising (DCM-COWD), which can realize non-contact measurement of microstructure surface topography with high precision and efficiency. Firstly, the influence of pinhole diaphragm size and offset on axial response curve is analyzed through multiple experiments to obtain the optimal pinhole diaphragm diameter and offset of the differential confocal measurement system. Secondly, a probe centering method based on grating rotation successive approximation is designed, in order to reduce the centering error of 3D topography measurement during the spiral scanning process. Thirdly, a translation invariant (TI) wavelet threshold denoising algorithm based on median filtering and whale optimization (WOA) is proposed, which can improve the signal-to-noise ratio (SNR) and reduce the root mean square error (RMSE), and effectively suppress the Pseudo-Gibbs phenomenon of discontinuous points. Finally, the surface topography of a standard sample is measured based on DCM-COWD system. The measurement results show that the center error is within 0.75 μm and the maximum deviation is within 1.45 %. The measurement results show high accordance with the commercial white light interferometer, and the processing speed is improved by 4.17 times. The proposed method has great application potential for the precise and efficient measurement of 3D surface topography.

A Hybrid Fault Diagnosis Method Using Translation Invariant Wavelet Denoising, Hierarchical Entropy, and Support Vector Machine with PSO Algorithm

The rolling element bearing is used in various machinery and produces vibration due to imperfections, surface irregularities during manufacture, damaged bearings, and inaccuracies in the allied element. Also, the rolling element bearing vibration generally shows non-linear dynamic characteristics and is masked with heavy background noise. This noble investigation advances a hybrid technique for removing background noise from the vibration signal and detecting bearing defects. Translation invariant wavelet denoising is the initial stage in this hybrid method for noise removal from the signal. The second phase uses Hierarchical Entropy (HE) for defect feature frequency extraction. Hierarchical entropy at scale four and SampEns of eight hierarchical decomposition nodes was utilized to determine the defect feature vector. In particular, low-frequency components are investigated through multi-scale entropy (MSE), but hierarchical entropy (HE) incorporates low-frequency and high-frequency components and can extract more defective information. Implemented a multi-class support vector machine (SVM) for extracting Hierarchical entropy as feature vectors. These feature vectors are trained by utilizing particle swarm optimization (PSO). To accomplish a prediction model, examine the optimal SVM parameters and then various bearing conditions with the variation of type, size, speed, and load severity identified by SVM. The investigation results show that hierarchical entropy can adequately and more precisely express the features of bearing vibration signals. It is beyond MSE, and the proposed Nobel hybrid Translation invariant wavelet denoising and Hierarchical entropy-based method will effectively remove the noisy background signal. Also, it distinguishes different bearings successfully, indicates the bearing conditions correctly, and is more prominent than those found on MSE.

Pedestrian detection using a translation-invariant wavelet residual dense super-resolution.

Pedestrian detection is an important research area and technology for car driving, gait recognition, and other applications. Although a lot of pedestrian detection techniques have been introduced, low-resolution imaging devices still exist in real life, so detection in low-resolution images remains a challenging problem. To address this issue, we propose a novel end-to-end Translation-invariant Wavelet Residual Dense Super-Resolution (TiWRD-SR) method to upscale LR images to SR images and then use Yolov4 for detection to address the low detection problem performance on low-resolution images. To make the enlarged SR image not only effectively distinguish the foreground and background of images but also highlight the characteristic structure of pedestrians, we decompose the image into low-frequency and high-frequency parts by stationary wavelet transform (SWT). The high- and low-frequency sub-images are trained through different network structures so that the network can reconstruct the high-frequency image edge information and the low-frequency image structure in a more detailed manner. In addition, a high-to-low branch information transmission (H2LBIT) is proposed to import high-frequency image edge information into the low-frequency network to make the reconstructed low-frequency structure more detailed. In addition, we also propose a novel loss function, which enables the SR network to focus on the reconstruction of image structure in the network by the characteristics of wavelet decomposition, thereby improving its detection performance. The experimental results indicate that the proposed TiWRD-SR can effectively improve detection performance.

Pipeline Damage Detection Based on Metal Magnetic Memory

The metal magnetic memory detection technology can detect early stress concentration and invisible damage of the pipeline. It can be detected under the action of the geomagnetic field, without the need to magnetize the pipeline in advance, which has the advantage of non-destructive testing. Since the magnetic memory signal is relatively weak, the actual detected signal will be affected by environmental noise, sensor jitter, and pipeline surface deposits. Therefore, the magnetic memory signal needs to be denoised. In this article, the translation invariant wavelet denoising method, which is improved based on the wavelet threshold denoising method, is used to denoise the collected pipeline magnetic memory signals. The experimental results show that the signal-to-noise ratio (SNR) obtained by this method is 1.15% higher than the unmodified wavelet threshold denoising, and the signal obtained is more stable. To solve the problem of fewer data samples for magnetic memory detection, three methods including support vector regression machine, back propagation (BP) neural network, and particle swarm optimization multiple output least-squares support vector regression (MLS-SVR) are compared and analyzed to inverse the overall defect size of pipeline defects. The experiments show that the MLS-SVR inversion result based on particle swarm optimization is the best, and the overall mean square error reaches 0.27 mm. In the end, a pipeline damage detection system is built to detect the magnetic memory signals of pipelines with different sizes of defects, and the defect depth and radius are inverted.

Radar Life Signal Processing Algorithm Based on Improved EEMD

Non-contact measurement of human vital signs is of great significance to the construction of smart homes and hospitals. The vital signal extracted from the FMCW radar contains a lot of noise. In order to reduce the noise impact and improve the life signal detection results accuracy, Ensemble Empirical Mode Decomposition (EEMD) algorithm is studied, and a new method based on the combination of EEMD and Translation Invariant Wavelet Transform (TIWT) is proposed. This method firstly decomposes the original signal using EEMD to obtain several Intrinsic Mode Function (IMF) components, and then changes the arrangement order of IMF by Translation Invariant Wavelet Transform to change the position of the singularity in the whole signal to reduce or eliminate the oscillations. Finally, signal screening is completed and life signals are reconstructed. Experiments show that, the proposed method has better detection accuracy in detecting vital signs collected by radar.

Research on Denoising Method of Metal Magnetic Memory Signal

As the main transportation mode of oil and gas, oil and gas pipelines play an irreplaceable role in energy transportation. Metal magnetic memory detection technology can detect early stress concentration and invisible damage, and can be detected under the action of the geomagnetic field, without the need to magnetize the pipeline in advance. Since the magnetic memory signal is relatively weak, the actual detected signal will be affected by environmental noise, sensor jitter, and pipeline surface deposits. Therefore, the magnetic memory signal needs to be denoised. In this paper, the translation invariant wavelet denoising method, which is improved based on wavelet threshold denoising method, is used to denoise the collected pipeline magnetic memory signals. The experimental results show that the signal-to-noise ratio (SNR) obtained by this method is 4.97 % higher than the unmodified wavelet threshold denoising, and 3.18 % higher than the SNR obtained by the particle swarm optimization wavelet threshold denoising.

Non-blind RGB watermarking approach using SVD in translation invariant wavelet space with enhanced Grey-wolf optimizer

Sharing or transmitting the digital information in online is increasing day by day since the usage of internet has become a habituation for everyone, which led to the large-scale violation of copyright issues. Now a days, majority of the data is being shared in the form of digital images which is quite easy for the copyright violators to forge and fake those images and then shared for profit. To deal with these copyright violations, digital watermarking came into existence as a potential solution that utilizes the concept of data hiding. This article proposed an approach for a non-blind color image watermarking (NB-CIW) by employing the algorithm named as singular value decomposition in translation invariant wavelet (SVD-TIW) domain. In addition, to further optimize the proposed SVD-TIW algorithm, enhanced grey-wolf optimizer (E-GWO) is presented which is an efficacious optimization approach in meta-heuristic algorithms. Further, to disclose the robustness and effectiveness of proposed NB-CIW using SVD-TIW-EGWO approach, different sort of attacks is enforced on watermarked image and extracted the accurate watermark image. Simulations on various test images with comparison to the state-of-art NB-CIW methodologies demonstrate the superiority of proposed NB-CIW using SVD-TIW-EGWO approach with respect to quality evaluation metrics like normalized cross correlation (NCC), root mean square error (RMSE), structural similarity (SSIM) index and even that of peak signal-to-noise ratio (PSNR) as well.

New approach of ECG denoising based on 1-D double-density complex DWT and SBWT

ABSTRACT In this paper we propose a new ECG denoising approach based on the application of double-density complex denoising method in the stationary bionic wavelet transform () domain. This approach consists at the first step in applying the to the noisy ECG signal in order to obtain two noisy coefficients and . The latter is an approximation coefficient and is a detail one. The latter is then denoised using Soft thresholding for obtaining a denoised coefficient, . The double-density complex denoising method is applied to and we obtain a denoised coefficient, . The denoised ECG signal is finally obtained from the application of the inverse of the , to and . This proposed technique is evaluated and compared to the double-density complex denoising one, the denoising technique based on Wavelets and Hidden Markov Models, the technique based on Non-Local Means and our previous proposed approach based on and (translation invariant forward wavelet transform). The simulation results obtained from the computations of SNR (ratio), MAE (mean absolute error), PSNR (peak SNR) and CC (cross-correlation), show that the proposed technique outperforms the other techniques used in our evaluation

Partial discharge pattern analysis using multi-class support vector machine to estimate cavity size and position in solid insulation

Partial discharge (PD) measurement is used for a diagnosis and performance assessment of the solid insulation material inside the high-voltage (HV) equipment. PD measurement indicates the presence of voids, cracks and imperfection present in solid insulation material. The major problem associated with this measured PD signal is heavily contaminated by noise which results in reduction in PD pattern recognition. The objective of this work is to measure and de-noise the PD signal due to cavity and recognize two different size of cavities present in three different locations, namely near HV electrode, center and lower electrode. In first part, the measured PD signal is de-noised using translation invariant wavelet transform. In second part, the three-dimensional (φ–q–n) PD patterns are extracted from the de-noised PD data. Then, it is subjected to canny edge detection technique, and the features like horizontal and vertical fractal dimension averages are evaluated using fractal image compression-based semi-variance technique. For classification, multi-class nonlinear support vector machine has been proposed to classify position and size of the cavity based on the PD fingerprints. The findings of this proposed work can be used to design a solid basis for an recognition of cavity size and position in an electrical apparatus.

Multiresolution correction of GC bias and application to identification of copy number alterations.

Whole-genome sequencing (WGS) data are affected by various sequencing biases such as GC bias and mappability bias. These biases degrade performance on detection of genetic variations such as copy number alterations. The existing methods use a relation between the GC proportion and depth of coverage (DOC) of markers by means of regression models. Nonetheless, severity of the GC bias varies from sample to sample. We developed a new method for correction of GC bias on the basis of multiresolution analysis. We used a translation-invariant wavelet transform to decompose biased raw signals into high- and low-frequency coefficients. Then, we modeled the relation between GC proportion and DOC of the genomic regions and constructed new control DOC signals that reflect the GC bias. The control DOC signals are used for normalizing genomic sequences by correcting the GC bias. When we applied our method to simulated sequencing data with various degrees of GC bias, our method showed more robust performance on correcting the GC bias than the other methods did. We also applied our method to real-world cancer sequencing datasets and successfully identified cancer-related focal alterations even when cancer genomes were not normalized to normal control samples. In conclusion, our method can be employed for WGS data with different degrees of GC bias. The code is available at http://gcancer.org/wabico. Supplementary data are available at Bioinformatics online.

Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification

On-machine monitoring of tool wear in machining processes has found its importance to reduce equipment downtime and reduce tooling costs. As the tool wears out gradually, the contact state of the cutting edge and the workpiece changes, which has a significant influence on the vibration state of the spindle. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of dynamic signals, which requires expert knowledge and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. In this paper, we present a novel intelligent technique for tool wear state recognition using machine spindle vibration signals. The proposed technique combines derived wavelet frames (DWFs) and convolutional neural network (CNN). Constructed based on dual tree wavelets, DWF are equipped with merits of centralized multiresolution and nearly translation-invariance. In this method, DWFs are employed to decompose the original signal into frequency bands of different bandwidths and different center frequencies, which are more pronounced as the tool wears. Further, the reconstructed sub-signals are stacked into a 2-D signal matrix to match the structure of 2-D CNN while retaining more dynamic information. The 2-D convolutional neural network is utilized to automatically recognize features from the multiscale 2-D signal matrix. End-milling experiments were performed on a S45C steel workpiece at different machining parameters. The experiment results of the recognition for tool wear state show the feasibility and effectiveness of the proposed method.

BER Analysis of Translation Invariant Wavelet Based Orthogonal Frequency Division Multiplexing System for 5G Wireless Communication Networks

BER Analysis of Translation Invariant Wavelet Based Orthogonal Frequency Division Multiplexing System for 5G Wireless Communication Networks

Circular Array of Ultrasonic Sensor based DOA estimation: Location of multiple Partial Discharge in Transformer oil

Location of Partial Discharge (PD) in transformers is very important, and many methodologies that have been carried forward in previous decades have a restriction theoretically, specially, in power transformers they cannot locate multiple PDs. Based on array signal processing a novel multiple partial discharges localization is presented in this paper. Ultrasonic signal emission occurs when the partial discharge occurs inside the transformer oil tank. Using ultrasonic sensor arrays located on the wall of the transformer tank, emitted ultrasonic signals is detected. Generally a single partial discharge will not occur in transformer there may be multiple partial discharge occur at different location. For detection of multiple partial discharges, we have used circular array of ultrasonic sensors (CAUS) in our proposed method. Primarily, by using Translation Invariant Wavelet Transform the partial discharge signals are de noised. To change the wide-band signal received by CAUS to the narrowband one Total Least Square algorithm is utilized. After this, the number of PD signals is estimated and to find the directions of arrival (DOA) of the signal sparse representation of array covariance vector technique is utilized. Lastly, on the basis of estimation of DOA position of PD source is detected with the help of optimization algorithm in order to find the exact coordinates of the PD source.

Translation Invariant Wavelet De-noising of CO2 Gas Shielded Arc Welding Electrical Signal

Translation Invariant Wavelet De-noising of CO2 Gas Shielded Arc Welding Electrical Signal

Analysis of translation invariant wavelet transform for epileptic seizure detection using support vector machine

Electroencephalogram (EEG) signal of human provide important information about the changes in the brain. Based on the information, epileptic seizure can be easily identified. In this paper, Translation Invariant Wavelet Transform (TIWT) based EEG signal classification is presented. At first, signals are represented by TIWT to extract information. TIWT representation of EEG signal produces Low Frequency Band (LFB) and High Frequency Band (HFB). From LFB and HFB features are extracted and Support Vector Machine (SVM) classifier evaluates them into either Normal Signal (NS) or Epileptic Signal (ES). Experimental results prove that TIWT representation of EEG signals provides average classification accuracy of 97.5% at 3rd level representation.

Translation-invariant wavelet denoising of full-tensor gravity –gradiometer data

Denoising of full-tensor gravity-gradiometer data involves detailed information from field sources, especially the data mixed with high-frequency random noise. We present a denoising method based on the translation-invariant wavelet with mixed thresholding and adaptive threshold to remove the random noise and retain the data details. The novel mixed thresholding approach is devised to filter the random noise based on the energy distribution of the wavelet coefficients corresponding to the signal and random noise. The translationinvariant wavelet suppresses pseudo-Gibbs phenomena, and the mixed thresholding better separates the wavelet coefficients than traditional thresholding. Adaptive Bayesian threshold is used to process the wavelet coefficients according to the specific characteristics of the wavelet coefficients at each decomposition scale. A two-dimensional discrete wavelet transform is used to denoise gridded data for better computational efficiency. The results of denoising model and real data suggest that compared with Gaussian regional filter, the proposed method suppresses the white Gaussian noise and preserves the high-frequency information in gravity-gradiometer data. Satisfactory denoising is achieved with the translation-invariant wavelet.