Dyadic Wavelet Research Articles

Time dimension feature extraction and classification of high-dimensional large data streams based on unsupervised learning

In order to solve the problem of low accuracy of time dimension feature extraction and classification of high-dimensional large data streams, this paper proposes a time dimension feature extraction and classification algorithm of high-dimensional large data streams based on unsupervised learning. Analyze the trend of high-dimensional data flow changes under machine learning, and achieve dimensionality reduction of high-dimensional large traffic time dimensional data through local save projection. Analyze the spatial relationship between feature attributes and feature space, segment and fit high-dimensional big data streams and time dimensional feature data streams, further segment time dimensional sequences using sliding windows, and complete feature extraction through discrete dyadic wavelet transform. According to the clustering algorithm, cluster the time dimension feature data stream, calculate the cosine similarity of the feature data, model the time dimension feature stream of training samples, use the feature classification function to minimize the classification loss, and use unsupervised learning to achieve the final classification task. The test results show that this method can improve the temporal feature extraction and classification accuracy streams.

On generalizations of the nonwindowed scattering transform

In this paper, we generalize finite depth wavelet scattering transforms, which we formulate as Lq(Rn) norms of a cascade of continuous wavelet transforms (or dyadic wavelet transforms) and contractive nonlinearities. We then provide norms for these operators, prove that these operators are well-defined, and are Lipschitz continuous to the action of C2 diffeomorphisms in specific cases. Lastly, we extend our results to formulate an operator invariant to the action of rotations R∈SO(n) and an operator that is equivariant to the action of rotations of R∈SO(n).

Power-Efficient VLSI Architecture of a New Class of Dyadic Gabor Wavelets for Medical Image Retrieval

Gabor wavelet is widely used in the analysis of texture features. It is found that Gabor wavelet filter bank (FB) requires infinite precision (due to irrational coefficients) to extract accurate directional textural features for which it needs numerous computations and external memory access. Due to this, there is a requirement for huge digital hardware, increased dynamic power dissipation, and increased processing time. In order to solve these issues, this article presents the first dyadic Gabor wavelet FB (DGWFB) based on the slight alteration in orientation parameter without disturbing the remaining Gabor wavelet parameters. In addition, this article introduces a separable VLSI architecture for the proposed DGWFB. The proposed VLSI architecture is implemented in field-programmable gate array (FPGA) through Xilinx Kintex 7 platform. It is observed that the proposed DGWFB has reduced processing time, dynamic power dissipation and digital hardware requirement significantly. The effectiveness of the designed DGWFB is evaluated in medical image retrieval application using three different publicly available medical databases namely NEMA, OASIS, and EXACT09. The proposed DGWFB achieved better performance as compared to existing Gabor wavelet FBs with significantly reduced digital hardware and processing time.

Haemoglobin Measurement from Eye Anterior Ciliary Arteries through Borescope Camera

Nowadays, smartphones are used as self-health monitoring devices for humans. Self-health monitoring devices help clinicians with big data for accurate diagnosis and guidance for treatment through repetitive measurement. Repetitive measurement of haemoglobin requires for pregnant women, pediatric, pulmonary hypertension and obstetric patients. Noninvasive haemoglobin measurement through conjunctiva leads to inaccurate measurement. The inaccuracy is due to a decrease in the density of goblet cells and acinar units in Meibomian glands in the human eye as age increases. Furthermore, conjunctivitis is a disease in the eye due to inflammation or infection at the conjunctiva. Conjunctivitis is in the form of lines in the eyelid and covers the white part of the eyeball. Moreover, small blood vessels in eye regions of conjunctiva inflammations are not visible to the human eye or standard camera. This paper proposes smartphone-based haemoglobin (SBH) measurement through a borescope camera from anterior ciliary arteries of the eye for the above problem. The proposed SBH method acquires images from the anterior ciliary arteries region of the eye through a smartphone attached with a high megapixel borescope camera. The anterior ciliary arteries are projected through transverse dyadic wavelet transform (TDyWT) and applied with delta segmentation to obtain blood cells from the ciliary arteries of the eye. Furthermore, the Gaussian regression algorithm measures haemoglobin (Hb) with more accuracy based on the person, eye arteries, red pixel statistical parameters obtained from the left and right eye, age, and weight. Furthermore, the experimental result of the proposed SBH method has an accuracy of 96% in haemoglobin measurement.

Prediction of rotor slot width in induction motor using Dyadic wavelet transform and softmax regression

Abstract Predictive maintenance is required for Induction Motor (IM) to avoid sudden breakdown. In this paper, multimodal sensor data are used for prediction of the rotor slot width variation during runtime of IM. Moreover sensor data are visualized through visual image obtained using Scale Invariant Feature Transform (SIFT) and matching dictionary for various faults in motor such as overload, high speed, Broken Rotor bar (BRB), and unbalance magnetic pull. The multimodal sensor signals data acquired from different parts of three phase induction motor are analysed using various transforms such as Over Complete Rational Dilation Wavelet Transform (ORaDWT), Tuneable Q Wavelet Transform (TQWT), Polynomial Chirplet Transform (PCT) and Dyadic Wavelet Transform (Dyadic WT) for various fault conditions and rotor slot width mentioned during runtime condition of motor. The rotor slot width is predicted using Multiple Linear Regression (MLR), Polynomial Regression (PR), Logistic Regression (LR) and Soft-max Regression (SR) methods through the mean value and energy band of the acquired sensor signal. The Dyadic WT and SR perform better for rotor width prediction. The proposed method such as Dyadic WT and SR provides the prediction accuracy of about 95.2%. From experimental results the rotor slot width expansion more than 2% needs immediate attention to avoid breakdown of motor.

Fast and robust star detection algorithm based on the dyadic wavelet transform

Fast and robust star detection algorithm based on the dyadic wavelet transform

RDLNN-based Image Forgery Detection and Forged Region Detection Using MOT

Image forgery detection TEMPhas become an emerging research area due to the increasing number of forged images circulating on the internet and other social media, which leads to legal and social issues. Image forgery detection includes the classification of an image as forged or authentic and as well as localizing the forgery wifin the image. In this paper, we propose a Regression Deep Learning Neural Network (RDLNN) based image forgery detection followed by Modified Otsu Thresholding (MOT) algorithm to detect the forged region. The proposed model comprises five steps that are preprocessing, image decomposition, feature extraction, classification and block matching. In the preprocessing step, the RGB images are converted to YCbCr color format. Then, the images are decomposed using the new Polar Dyadic Wavelet Transform (PDyWT), followed by the extraction of important features. The classification phase called RDLNN effectively classifies the normal image and the forged image. For localization of the forgery, the forged image is divided into a number of blocks, and then Genetic Three Step Search (GTSS) algorithm is exploited to identify the dissimilar blocks. To get the exact forged region in the image, the dissimilar blocks are analyzed by the Modified Otsu Thresholding (MOT) algorithm. The proposed algorithm is compared wif widely used image forgery detection algorithms. The results show that the proposed method improves the forgery detection accuracy and precision by at least 6.04% and 3.77%, respectively, as compared to the already existent techniques such as ANFIS, KNN, ANN, and SVM. Moreover, the training time of the proposed network is lower by at least 64.3 % than the above existing techniques

Random noise attenuation using the novel Estimated Noise Pattern Denoising Algorithm

This paper introduces the estimated pattern denoising (EPD) wavelet transform for random noise attenuation in geophysical data. The proposed approach combines the capability of the Gaussian filter and dual-tree rational dilation wavelet transform (DT-RADWT) in random noise detection and suppression; we called this method Estimated Pattern Denoising (EPD). The EPD is an innovative approach in terms of estimation of the location and amplitude of the noise pattern, directly from the data. The employed approach produces a higher quality factor (Q-factor) than the conventional dyadic discrete wavelet transform (DWT) and separates the noise from the signal with higher accuracy. The EPD provides a data-driven scheme that resolves the complexity of the random noise model in noise suppression, using an auxiliary Gaussian filter. This approach does not require prior information about the noise source, statistical distribution, or frequency range. We show successful suppression of random noise using the proposed approach on synthetic and real field data.

One-Dimensional Dyadic Wavelets

One-Dimensional Dyadic Wavelets

Multiscale Wavelet Transfer Entropy With Application to Corticomuscular Coupling Analysis

Functional coupling between the motor cortex and muscle activity is commonly detected and quantified by cortico-muscular coherence (CMC) or Granger causality (GC) analysis, which are applicable only to linear couplings and are not sufficiently sensitive: some healthy subjects show no significant CMC and GC, and yet have good motor skills. The objective of this work is to develop measures of functional cortico-muscular coupling that have improved sensitivity and are capable of detecting both linear and non-linear interactions. A multiscale wavelet transfer entropy (TE) methodology is proposed. The methodology relies on a dyadic stationary wavelet transform to decompose electroencephalogram (EEG) and electromyogram (EMG) signals into functional bands of neural oscillations. Then, it applies TE analysis based on a range of embedding delay vectors to detect and quantify intra- and cross-frequency band cortico-muscular coupling at different time scales. Our experiments with neurophysiological signals substantiate the potential of the developed methodologies for detecting and quantifying information flow between EEG and EMG signals for subjects with and without significant CMC or GC, including non-linear cross-frequency interactions, and interactions across different temporal scales. The obtained results are in agreement with the underlying sensorimotor neurophysiology. These findings suggest that the concept of multiscale wavelet TE provides a comprehensive framework for analyzing cortex-muscle interactions. The proposed methodologies will enable developing novel insights into movement control and neurophysiological processes more generally.

Wavelet transform-based cross-correlation in the time-delay estimation applications

The article discusses the application of wavelet analysis for the time-frequency time-delay estimation. The proposed algorithm is wavelet transform-based cross-correlation time delay estimation that applies discrete time wavelet transform to filter the input signal prior to computation of cross-correlation function. The distinguishing feature of the algorithm that it uses the variation of continuous wavelet transform to process the discrete signals instead of dyadic wavelet transform that is normally applied to the case. Another feature that the implication of convolution theorem is used to compute coefficients of the wavelet transform. This makes possible to omit redundant discrete Fourier transforms and significantly reduce the computational complexity. The principal applicability of the proposed method is shown in the course of a computational experiments with artificial and real-world signal. So the method demonstrated expected selectivity for the signals localized in the different frequency bands. The application of the method to practical case of pipeline leak detection was also successful. However, the study concluded that this method provides no specific advantages in comparison with the conventional one. In the future, alternative applications in biological signal processing will be considered.

Detection of crankshaft faults by means of a modified Welch-Bartlett periodogram

Detection, diagnostic and isolation of crankshaft failures is of vital importance to ensure reliable operation during the course of their services. However, many times the fault may be submerged in a strong background noise making the feature extraction process difficult. To solve this problem, this paper shows a new method for extracting features from the signal immersed in background noise. This method is based on linking the dyadic Wavelet transform and the Welch-Bartlett classic periodogram, obtaining a modified Welch-Bartlett periodogram; which provides a dyadic spectrum of frequencies with multiple sensitivities. The validation process was based on two scenarios. The first one did not generate a fault, while the second one presented a fault with a signal to noise ratio of 0.3269 dB. The results show that the dyadic wavelet function to be used is the Daubechies 45 as it provides an attenuation of the rejection bands close to 150 dB. Through the new modified Welch-Bartlett periodogram, an engine vibration signature detected, 29 Hz, the component 120 Hz corresponding to the deformation of the magnetic fields of the engine and the component of 177.5 Hz inherent in squirrel-cage induction motors. A final result showed that the new modified Welch-Bartlett periodogram maximizes sensitivity in frequency component analysis. In addition, the results were superior to those achieved with the procedures reported in the literature reviewed.

Magnetic Resonance Imaging Based on Wavelet Algorithm in the Diagnosis and Treatment of Tibial Osteomyelitis Wound Infection

This study was to explore the therapeutic effect of magnetic resonance imaging (MRI) images based on the image processing algorithm under the correlation of dyadic wavelet coefficients on the diagnosis of tibial osteomyelitis patients. 32 tibial osteomyelitis patients admitted to hospital were randomly selected as the research objects. According to the patients’ wishes, patients who were willing to use new MRI imaging techniques for disease detection were set as the experimental group and conventional MRI imaging detection methods were set as the control group. The application effect of the new MRI imaging technology was evaluated by comparing the treatment effect of the two groups of patients. It was found that the mean square error (MSE) (38.5642) and signal-to-noise ratio (SNR) (18.5122) processed by the improved wavelet algorithm were much better than those of unimproved dyadic wavelet algorithm (59.1096 and 15.2341) ( P < 0.05 ). The possibilities of soft tissue swelling, bone invasion or destruction, thickening and sclerosis of bone cortex, bone abscess, periosteum response, dense dead bone, and bone sinus of patients in the experimental group were higher than those of the control group, which were 100% vs. 55%, 100% vs. 80%, 92% vs. 65%, 50% vs. 25%, 42% vs. 15%, 67% vs. 45%, and 50% vs. 15%, respectively ( P < 0.05 ). The healing time of osteomyelitis (22.89 ± 2.19 d vs. 32.32 ± 2.81 d) and the recovery of wound infection (14% vs. 45%) in the patients in control and experimental groups showed that the results of the experimental group were obviously better than those of the control group. The kappa value of the diagnosis results and tissue biopsy of the experimental group was higher than that of the control group (0.45 vs. 0.34) ( P < 0.05 ). In conclusion, the results of the enhanced and improved MRI images were relatively more accurate and the treatment methods adopted were more symptomatic, resulting in more effective treatment. In addition, the wavelet algorithm had certain application value in the enhancement processing of medical images and showed a good development prospect.

A High-Resolution Dyadic Transform for Non-Stationary Signal Analysis

This article shows a new Te-transform and its periodogram for applications that mainly exhibit stochastic behavior with a signal-to-noise ratio lower than −30 dB. The Te-transform is a dyadic transform that combines the properties of the dyadic Wavelet transform and the Fourier transform. This paper also provides another contribution, a corollary on the energy relationship between the untransformed signal and the transformed one using the Te-transform. This transform is compared with other methods used for the analysis in the frequency domain, reported in literature. To perform the validation, the authors created two synthetic scenarios: a noise-free signal scenario and another signal scenario with a signal-to-noise ratio equal to −69 dB. The results show that the Te-transform improves the sensitivity in the frequency spectrum with respect to previously reported methods.

A Novel Design of Dyadic db3 Orthogonal Wavelet Filter Bank for Feature Extraction

The irrational coefficients of orthogonal wavelet filters require a large amount of hardware for their implementation. This results in huge memory requirement, increased power dissipation and reduction in speed of operation. This paper presents a new class of multiplier free db3 orthogonal wavelet filter bank with significantly reduced power dissipation, adders and shifters. In this paper, dyadic filter coefficients of db3 have been obtained by slightly altering double-shifting orthogonality property for perfect reconstruction. The proposed db3 wavelet filter improved time–frequency product, Sobolev regularity and frequency selectivity. Also, the VLSI architecture is suggested for the proposed db3 wavelet filter banks to analyse the hardware computational complexity. The performance of the proposed db3 wavelets achieved satisfactory performance for feature extraction in medical image retrieval and fingerprint recognition of infants and toddlers.

Mixed pixel removal in north Tamil Nadu region for accurate area measurement

AbstractIn remote sensing, vegetation and water areas delineation from satellite image plays a vital role for urban and rural planning. Delineation of vegetation and water area is a challenging task due to mixed pixels and geometric distortion over the boundary region. Geometric distortion arises due to change in velocity and speed of satellite during image acquisition, and mixed pixels arises due to different surfaces in a particular area. Traditional methods apply classifier algorithms such as support vector machine, neural network, and fuzzy for vegetation and water area delineation. The traditional methods require more training dataset and consume more interpretation time for delineation. In this article, we propose transverse dyadic wavelet transform (TDyWT) to delineate vegetation and water area from Landsat 8 images. The TDyWT method enhances the boundary and curvature area of satellite image for accurate delineation. From the experimental results, the proposed TDyWT approach delineates the area of subclass for vegetation and water areas with 95% of accuracy with respect to the ground truth.

IMAGE RESOLUTION ENHANCEMENT OF SATELLITE IMAGES USING DYADIC INTEGER COEFFICIENT WAVELET FILTER FOR WAVELET TRANSFORM

In this paper, image resolution enhancements for satellite images are proposed using dyadic integer coefficients based wavelet filter (DICWF). We proposes a technique in which discrete wavelet transform and stationary wavelet transform using DICWF which is used to obtain a high resolution image and this image is derived from frequency subbands. The satellite images play a very vital role now days in the development of technical aspects which needs to be enhanced. These satellite images are superresolved with the help of dyadic integer coefficient-based wavelet filters, which reduces the hardware complexity and computational difficulties due to the rational and integer coefficients of these filter banks. The value of the peak signal-to-noise ratio (PSNR) of the proposed method and the resultant visual images of the proposed method show the effectiveness of this algorithm over other existing algorithms using discrete wavelet transform. Noise can be minimized by applying thresholding on different frequency subbands which obtained by the application of DICWF to the noisy, blurred input images.

Fractal geometry of wavelet decomposition in mechanical signature analysis

Multiple modes of vibration are usually incorporated in a single record of vibration measurement in condition monitoring of rotating machinery. Wavelet transform is an effective tool to detect and isolate transient fault features from other interfering modes. The conventional dyadic wavelet transform decomposes the signal into wavelet subspaces with distinct central frequencies and specific frequency bandwidths. In this paper, we propose a novel theory of centralized multiresolution analysis (CMR) and reveal the implicit fractal geometry properties in CMR. A concept of nested centralized wavelet packet space (NCWPS) is introduced to describe the self-similarity phenomenon in CMR. Within the theoretical framework, the classical dyadic wavelet packet is assimilated as a subordinated proper-subset of the augmented NCWPS. Moreover, the generalized CMR characterized by tunable and flexible frequency-scale topology configuration is established using harmonic wavelet transform. The CMR can be regarded as an improved transient signature dictionary. Therefore, the CMR is combined with an improved stationary signature dictionary to ensure enhanced performance in fault feature extraction in multiple modes coupled vibration measurements. The effectiveness of the proposed method is validated using numerical simulations, a rub-impact experiment, and a case study of vibration signal analysis in steel making industry.

CFST arch bridge seismic response analysis considering near-fault ground motion pulse characteristics

Based on a long-span CFST arch bridge finite element model, nonlinear time-history response analysis is carried out. It is found that the key section of the connection of arch rib and bridge deck is a particular location with larger seismic response. The fling-step type TCU068-E is more liable to excite a greater seismic response at arch rib sections. Through seismic wave dyadic wavelet analysis, the wavelet component in the structure fundamental frequency band is reconstructed to be a new seismic excitation. The results indicate that the low-frequency component of TCU068-E is strong, and larger structural seismic response is generated accordingly.

Integrated approach based on flexible analytical wavelet transform and permutation entropy for fault detection in rotary machines

This paper presents an integrated approach for the detection and classification of the faults of rolling bearing in rotary machines. Permutation entropy (PE) is integrated with a flexible analytical wavelet transform (FAWT). The signals from healthy and faulty bearing systems with different operating conditions are decomposed by FAWT. To compare effectiveness of the proposed methodology, dyadic discrete wavelet transform (DWT) is also used in integration with PE. PE values of decomposed signals are calculated and are then fed as feature vectors to support vector machine (SVM) classifier for the classification of different types and fault sizes. The classification results of both approaches are compared. The results demonstrate the effectiveness and robustness of FAWT-integrated-PE over the DWT integrated with PE, for detection of bearing faults and their classification.