Discrete Wavelet Transform Approach Research Articles

Detection of Alzheimer's Dementia by Using Signal Decomposition and Machine Learning Methods.

Dementia is one of the most common neurological disorders causing defection of cognitive functions, and seriously affects the quality of life. In this study, various methods have been proposed for the detection and follow-up of Alzheimer's dementia (AD) with advanced signal processing methods by using electroencephalography (EEG) signals. Signal decomposition-based approaches such as empirical mode decomposition (EMD), ensemble EMD (EEMD), and discrete wavelet transform (DWT) are presented to classify EEG segments of control subjects (CSs) and AD patients. Intrinsic mode functions (IMFs) are obtained from the signals using the EMD and EEMD methods, and the IMFs showing the most significant differences between the two groups are selected by applying previously suggested selection procedures. Five-time-domain and 5-spectral-domain features are calculated using selected IMFs, and five detail and approximation coefficients of DWT. Signal decomposition processes are conducted for both 1 min and 5 s EEG segment durations. For the 1 min segment duration, all the proposed approaches yield prominent classification performances. While the highest classification accuracies are obtained using EMD (91.8%) and EEMD (94.1%) approaches from the temporal/right brain cluster, the highest classification accuracy for the DWT (95.2%) approach is obtained from the temporal/left brain cluster for 1 min segment duration.

Efficient Contourlet Transformation Technique for Despeckling of Polarimetric Synthetic Aperture Radar Image

In Polarimetric SAR (PolSAR) and synthetic aperture radar (SAR) requires efficient filtering approach for effective processing of captured quad-polarized images. Due to polarization speckles arises in the captured PolSAR images which causes complexity in collection of data from PolSAR images. This limitation has been overcome through application of effective despeckling technique for efficient processing of PolSAR images. Several techniques have been evolved over past three decades to reduce those speckle in image captured by PolSAR, and recent research studies illustrated a efficient trend for filtering local single-point to non-local patch-based or global collaborative filtering. In this paper, applied contourlet technique for effective despeckling of PolSAR images. This contourlet transformation technique perform thresholding and transformation for efficient despeckling of captured images. Contourlet transformation technique is applied in PolSAR images with speckle and performance metrices are observed. Contourlet technique is comparatively examined with conventional transformation technique which involved in despeckling of images. Analysis of results exhibited that DWT (Discrete Wavelet Transform) approach exhibits similar performance related to contourlet transformation technique. Through analysis of results it is observed that computation time also significantly reduced in contourlet transformation rather than conventional technique. Further mean and window sizing also significantly maintained in contourlet technique for various noise variance.

Cardiac Severity Classification Using Pre Trained Neural Networks.

Electrocardiogram (ECG) is the most effective instrument for making decisions about various forms of heart disease. As a result, several researchers have focused on the ECG signal to extract the features of heartbeats with high precision and efficiency. This article offers a hybrid approach to classifying different cardiac conditions using the Feed Forward Back Propagation Neural Network (FFBPNN), by providing a pre-processed ECG signal as an excitation. The modified ECG signal is obtained through the combination of EMD (Empirical Mode Decomposition) and DWT (Discrete Wavelet Transform). In this proposed method, the input signal is first decomposed into the Intrinsic Mode Functions (IMF's) and the first three IMF's are combined to obtain a modified partially denoted ECG sample and then DWT is used to obtain an improved denoised signal. This pre-processed signal is classified using the Neural Network architecture. For the EMD approach, the ECG-based EMD-DWT signal provides improved classification accuracy of 67, 0762 percent, 90, 4305 percent for the DWT approach, and 95,0797 percent for the proposed technique. The methodology is applied to the MIT-BIH database and, in terms of classification accuracy, is found to be higher than the different methodologies.

Low-contrast Pattern-reversal Visual Evoked Potential in Different Spatial Frequencies.

PurposeTo evaluate the pattern-reversal visual evoked potential (PRVEP) in low-contrast, spatial frequencies in time, frequency, and time-frequency domains.MethodsPRVEP was performed in 31 normal eyes, according to the International Society of Electrophysiology of Vision (ISCEV) protocol. Test stimuli had checkerboard of 5% contrast with spatial frequencies of 1, 2, and 4 cycles per degree (cpd). For each VEP waveform, the time domain (TD) analysis, Fast Fourier Transform(FFT), and discrete wavelet transform (DWT) were performed using MATLAB software. The VEP component changes as a function of spatial frequency (SF) were compared among time, frequency, and time–frequency dimensions.ResultsAs a consequence of increased SF, a significant attenuation of the P100 amplitude and prolongation of P100 latency were seen, while there was no significant difference in frequency components. In the wavelet domain, an increase in SF at a contrast level of 5% enhanced DWT coefficients. However, this increase had no meaningful effect on the 7P descriptor.Conclusion At a low contrast level of 5%, SF-dependent changes in PRVEP parameters can be better identified with the TD and DWT approaches compared to the Fourier approach. However, specific visual processing may be seen with the wavelet transform.

Enhancing detection of retinal blood vessels by combined approach of DWT, Tyler Coye and Gamma correction

Retinal imaging plays the most significant roles among all the medical imaging technology, because of its ability to derive various features that is related to various eye diseases. Thus, precise extraction is highly required for the blood vessels that lead to accurate identification of the diseases. Because of some instabilities in the retinal images such as noise, non-uniform illumination etc. it may motivate towards a false detection. This paper suggests an automated method to extract the blood vessels from fundus by integrating discrete wavelet transform (DWT) with Tyler Coye algorithm. Furthermore, in the retinal blood vessel segmentation methods the most vital step is to enhance the contrast. The authenticity of the segmentation is purely subjected to the uniformity of the contrast over the image. Thus, an illumination normalization technique known as Gamma correction is also utilized for the contrast enhancement. Three different types of experiments are carried out: original Tyler Coye algorithm, DWT with different wavelet filters integrated with Tyler Coye, and Gamma correction normalization applied to the integrated model. The approaches are tested with DRIVE dataset. The performance of the normalization-integrated model is found superior to the other two approaches.

Design of Digital Video Watermarking Technique Based on Motion Frames

The availability of high internet bandwidth instantaneously transfer the digital video multimedia object between two or work workstations. Additionally, the advent of digital technology can be mistreating by malicious user to replicate multiple identical copies of the original video illegally. These capabilities introduce the issue of developing the methods for protecting the copyright of video multimedia objects. The proposed technique suggested detecting the motion part of the video by applying heuristic method of histogram difference between two consecutive frames. Then powerful transformations, Singular Value Decomposition (SVD), Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) are used to insert the different segment of the scrambled watermarks into different motion frames of the video. The experimental results show that the scheme is robust to unintentional and intentional video specific attacks which considered being frequently occurring attacks. The proposed algorithm has been contrasted with an existing DWT, DCT or hybrid-based approaches and is found to exhibit better robustness.

A critical fault detection analysis & fault time in a UPFC transmission line

This paper discusses a critical study of fault detection and fault time analysis in a Unified Power Flow Controller (UPFC) transmission line. Here the Discrete Wavelet Transform (DWT) and Discrete Fourier Transform (DFT) approach are used for processing the faulty current signal to obtain fundamental current signal. The extracted fault current signals from the current transformer are fed to DWT and DFT approach for computing spectral energy (SE). The differential spectral energy (DSE) of phase currents are evaluated by taking the difference of SE obtained at sending and receiving end. The DSE is the key factor for deciding the fault in any of the phase or not. The Daubechy mother wavelet (db4) is used here because of its high accuracy of detection with less processing time. The novelty of the scheme is that it can accurately detect the critical fault variation of the line. Number of simulations are validated at the extreme condition of the line and compared to other conventional existing scheme. Multi-phase fault in double circuit line, CT saturation, UPFC operating condition (series voltage and angle), UPFC location and wind speed variation including wind farm simulation are validated to verify the performance of the scheme. The advantages of the scheme is that it works effectively to detect the fault at any stage of critical condition of the line and fault detection time remains within 20 msec (less than one cycle period). This scheme protects both internal and external zone including parameter variation of the line.

DWT approach based differential relaying scheme for single circuit and double circuit transmission line protection including STATCOM

Abstract This paper describes fault detection and classification in a double–circuit transmission line with presence of STATCOM (Static Synchronous compensator) in one circuit. DWT (Discrete Wavelet Transform) approach based differential relaying scheme is used to detect and classify the fault pattern in the above transmission line. The scheme starts with current signals extracted from both end of the transmission line synchronously and processed through DWT to obtain Spectral Energy (SE). The Differential Spectral Energy (DSE) is computed by subtracting SE obtained from both sending end and receiving end of the line which is the key indicator for fault detection and classification. The proposed scheme is extensively tested on faulted conditions with wide variation in operating parameters and the test result indicate that it can reliably detect and classify fault both in single and double circuit line in presence of STATCOM with a relay response time of less than one cycle.

A novel relaying approach of combined discrete wavelet transform and artificial neural network-based relaying scheme in a unified power flow controller integrated wind fed transmission line

This paper focuses a novel relaying approach of combined discrete wavelet transform (DWT) and artificial neural network (ANN)-based relaying scheme in unified power flow controller (UPFC) integrated wind fed transmission line. The novelty of the scheme illustrates the fault detection time reduces drastically to 5 msec (quarter period cycle time). The comparisons are made with DWT and the combined approach of DWT and ANN. It is seen that using combined approach, performance is better as compared to DWT alone. The process starts with DWT processor to find spectral energy (SE) of each phase current. The differential spectral energy (DSE) is computed using the difference value of SE at both end of the line. The computed DSE value obtained from DWT is fed to ANN fault detector to register the fault pattern. Further it is trained and tested with different parameter variation of the line to obtain fault detection time.

Vibration analysis using wavelet transform and fuzzy logic for shaft misalignment

In most of rotating kind of machinery, misalignment is commonly observed defect. Though machines are installed to zero-zero aligned condition in initial stage, in due course of run time operation misalignment get introduced due thermal distortion, asymmetry of forces exerted and inadequate assembly of parts. This paper presents a method of misalignment prediction from output vibration signal which is based on combined DWT (Discrete Wavelet Transform) and Fuzzy Logic approach. DWT helps in multilevel decomposition of vibration signal to understand where and at what instant misalignment occurs. This involves selection of mother wavelet. The FIS (Fuzzy Inference System) is combined with DWT to predict degree of misalignment present. An inclusion of FIS has improved prediction accuracy of Degree of Misalignment (DoM) which has claimed error less than one percent (1 %).

LAND USE AND LAND COVER CLASSIFICATION OF MULTISPECTRAL LANDSAT-8 SATELLITE IMAGERY USING DISCRETE WAVELET TRANSFORM

Abstract. Land use and land cover (LULC) classification of satellite imagery is an important research area and studied exclusively in remote sensing. However, accurate and appropriate land use/cover detection is still a challenge. This paper presents a wavelet transform based LULC classification using Landsat 8-OLI data. The study area for the present work is a small part of Varanasi district, Uttar Pradesh, India. The atmospheric correction of the image was performed using Quick Atmospheric Correction (QUAC) method. The image was decomposed into its approximation and detail coefficients up to eight levels using discrete wavelet transform (DWT) method. The approximation images were layer stacked with the original image. The minimum distance classifier was used for classifying the image into six LULC classes namely water, agriculture, urban, fallow land, sand, and vegetation. The classification accuracy for all decomposition levels was compared with that of classified product based on original multispectral image. The classification accuracy for multi-spectral image was found to be 75.27%. Whereas, the classification accuracies were found to improve up to 85.97%, 88.87%, 93.47%, 95.03%, 93.01, 92.32% and 90.80% for second, third, fourth, fifth, six, seventh and eight level decomposition, respectively. The significantly improved accuracy was found for images decomposed at level five. Thus, the approach of DWT for LULC classification can be used to increase the classification accuracy significantly.

Characterization of Temporal and Spatial Variability of Phosphorus Loading to Lake Erie from the Western Basin Using Wavelet Transform Methods

The characterization of temporal and spatial patterns in phosphorus (P) loading in Lake Erie is essential in order to continue monitoring the excessive P condition that comes from the western Lake Erie Basin. This study aims to perform such a characterization using the continuous wavelet transform (CWT) and the discrete wavelet transform (DWT) methods. These wavelet transformations were conducted on streamflow data, TP loads, and soluble reactive phosphorus (SRP) of six stations located near Lake Erie of Northern Ohio. These stations are located near the outlet of Cuyahoga, Grand, Maumee, Vermilion, Raisin, and Sandusky watersheds. Long-term continuous P loading data, in which some dated back to 1970, were used in the analysis. The results obtained from the CWT and DWT approaches were found to complement each other. Streamflow had significant mixed variability at 1, 2, and 4 years. The variability for SRP was limited to 1 and 2 years while the TP variability was only seen at the 1-year scale. It was interesting to find that strong temporal patterns of SRP were observed in most of the watersheds only after the mid-1990s. The CWT wavelet spectra also reflected the land use characteristics of each watershed. For example, the wavelet spectra of surface runoff and TP for the agricultural watersheds (i.e., Raisin, Sandusky, and Maumee Rivers) were similar and characterized by significant variability primarily at the annual scale and at the two to four-year periodicities. The urbanized watershed (i.e., Cuyahoga River) did not show any association between either phosphorus (TP or SRP) with surface runoff and baseflow, which indicates that P in the urbanized watershed was not driven by the flow.

Variational mode decomposition based ECG denoising using non-local means and wavelet domain filtering.

This paper presents a novel electrocardiogram (ECG) denoising approach based on variational mode decomposition (VMD). This work also incorporates the efficacy of the non-local means (NLM) estimation and the discrete wavelet transform (DWT) filtering technique. Current ECG denoising methods fail to remove noise from the entire frequency range of the ECG signal. To achieve the effective ECG denoising goal, the noisy ECG signal is decomposed into narrow-band variational mode functions (VMFs) using VMD method. The idea is to filter out noise from these narrow-band VMFs. To achieve that, the center frequency information associated with each VMFs is used to exclusively divide them into lower- and higher-frequency signal groups. The higher frequency VMFs were filtered out using DWT-thresholding technique. The lower frequency VMFs are denoised through NLM estimation technique. The non-recursive nature of VMD enables the parallel processing of NLM estimation and DWT filtering. The traditional DWT-based approaches need large decomposition levels to filter low frequency noises and at the same time NLM technique suffers from the rare-patch effect in high-frequency region. On the contrary, in the proposed framework both NLM and DWT approaches complement each other to overcome their individual ill-effects. The signal reconstruction is performed using the denoised high frequency and low frequency VMFs. The simulation performed on the MIT-BIH Arrhythmia database shows that the proposed method outperforms the existing state-of-the-art ECG denoising techniques.

A Robustness Comparison of Two Algorithms Used for EEG Spike Detection.

Spikes and sharp waves recorded on scalp EEG may play an important role in identifying the epileptogenic network as well as in understanding the central nervous system. Therefore, several automatic and semi-automatic methods have been implemented to detect these two neural transients. A consistent gold standard associated with a high degree of agreement among neuroscientists is required to measure relevant performance of different methods. In fact, scalp EEG data can often be corrupted by a set of artifacts and are not always served as data of gold standard. For this reason, the use of intracerebral EEG data mixed with gaussian noise seems to best resemble the output of scalp EEG brain and serves as a consistent gold standard. In the present framework, we test the robustness of two important methods that have been previously used for the automatic detection of epileptiform transients (spikes and sharp waves). These methods are based respectively on Discrete Wavelet Transform (DWT) and Continuous Wavelet Transform (CWT). Our purpose is to elaborate a comparative study in terms of sensitivity and selectivity changes via the decrease of Signal to Noise Ratio (SNR), which is ranged from 10 dB up to -10 dB. The results demonstrate that, DWT approach turns to be more stable in terms of sensitivity, and it successfully follows the detection of relevant spikes with the decrease of SNR. However, CWT-based approach remains more stable in terms of selectivity, so that, it performs well in terms of rejecting false spikes compared to DWT approach.

Video Compressed Sensing framework for Wireless Multimedia Sensor Networks using a combination of multiple matrices

Wireless multimedia sensor networks (WMSNs) have been used for sensitive applications such as video surveillance and monitoring applications. In a WMSN, storage and transmission become complicated phenomena that can be simplified by the use of compressed sensing, which asserts that sparse signals can be reconstructed from very few measurements. In this paper, memory-efficient measurement matrices are proposed for a discrete wavelet transform (DWT)–discrete cosine transform (DCT) hybrid approach based video compressed sensing (VCS). The performance of the framework is evaluated in terms of PSNR, storage complexity, transmission energy and delay. The results show that the proposed matrices yield similar or better PSNR and consume less memory for generating the matrix when compared with a Gaussian matrix. The DWT–DCT based VCS yields better quality and compression when compared with DCT and DWT approaches. The transmission energy is 50% less and the average delay is 52% less when compared to raw frame transmission.

Heart rate variability analysis during central hypovolemia using wavelet transformation

Detection of hypovolemia prior to overt hemodynamic decompensation remains an elusive goal in the treatment of critically injured patients in both civilian and combat settings. Monitoring of heart rate variability has been advocated as a potential means to monitor the rapid changes in the physiological state of hemorrhaging patients, with the most popular methods involving calculation of the R-R interval signal's power spectral density (PSD) or use of fractal dimensions (FD). However, the latter method poses technical challenges, while the former is best suited to stationary signals rather than the non-stationary R-R interval. Both approaches are also limited by high inter- and intra-individual variability, a serious issue when applying these indices to the clinical setting. We propose an approach which applies the discrete wavelet transform (DWT) to the R-R interval signal to extract information at both 500 and 125 Hz sampling rates. The utility of machine learning models based on these features were tested in assessing electrocardiogram signals from volunteers subjected to lower body negative pressure induced central hypovolemia as a surrogate of hemorrhage. These machine learning models based on DWT features were compared against those based on the traditional PSD and FD, at both sampling rates and their performance was evaluated based on leave-one-subject-out fold cross-validation. Results demonstrate that the proposed DWT-based model outperforms individual PSD and FD methods as well as the combination of these two traditional methods at both sample rates of 500 Hz (p value <0.0001) and 125 Hz (p value <0.0001) in detecting the degree of hypovolemia. These findings indicate the potential of the proposed DWT approach in monitoring the physiological changes caused by hemorrhage. The speed and relatively low computational costs in deriving these features may make it particularly suited for implementation in portable devices for remote monitoring.

Fault Detection and Classification Based on DWT and Modern Approaches for T.L Compensated with FACTS

A new approach for detecting and classifying a fault for transmission line compensated with Flexible AC Transmission System (FACTS) is presented in this paper. Unified Power Flow Controller (UPFC) is one of the most advanced FACTS devices that can simultaneously and independently control both the real and reactive power flow in a transmission line. The proposed technique consists of preprocessing module based on Discrete Wavelet Transform (DWT) in combination with Artificial Neural Network (ANN) or Gaussian Process (GP) for detecting and classifying fault events.

A Hybrid Approach of DWT and DCT for Rational Dither Modulation Watermarking

In this paper, on the basis of the theories and methods of Watson’s perceptual model and rational dither modulation (RDM), a hybrid quantization-based watermarking in the discrete wavelet transform (DWT) and discrete cosine transform (DCT) domains is studied. In the design of the quantization-based watermarking, quantization step-size plays an important role in many watermarking algorithms. RDM at both the embedder and decoder adopts a gain-invariant adaptive quantization step-size. Therefore, we investigated combining the modified Watson’s perceptual model with RDM. Its improved robustness is due to the embedding in the high entropy region of low-frequency sub-band image and adaptive control of its quantization step-size. The Euclidean distance decoder is used to extract the watermark data. The performance of the proposed scheme is analytically calculated and verified by simulation. Experimental results confirm the imperceptibility of the proposed watermarking and its higher robustness against attacks compared to alternative watermarking methods in the literature.

Wavelet-Based Feature Extraction for Improved Endmember Abundance Estimation in Linear Unmixing of Hyperspectral Signals

This paper shows that the use of appropriate features, such as discrete wavelet transform (DWT)-based features, can improve the least squares estimation of endmember abundances using remotely sensed hyperspectral signals. On average, the abundance estimation deviation is reduced by 30% to 50% when using the DWT-based features, as compared to the use of original hyperspectral signals or conventional principal component analysis (PCA)-based features. Theoretical analyses further reveal that the increase of endmember separability is a fundamental reason leading to this improvement. In addition, the robustness of the DWT-based features is verified experimentally. Finally, the idea is generalized as a point that the remote sensing community needs to investigate feature extraction (or dimensionality reduction) methods that are based on signal classification, such as the DWT approach, for linear unmixing problems, rather than using feature extraction methods that are based on signal representation, such as the conventional PCA approach.

Geologic lithofacies identification using the multiscale character of seismic reflections

A forward acoustic model shows that geologic lithofacies groups can be identified by the character of the wavelet transform of their seismic reflection response even for incident signals with a wavelength much larger than the dominant bed thickness. The same model shows that multiple interbed reflections can be neglected. This allows the use of an analytical relation of the linear reflection response expressed as a convolution between the incident signal and the scaled derivative of the acoustic impedance. The relation is applied to solve the inverse problem for the acoustic impedance, using orthogonal discrete wavelet transform (DWT) and Fourier transform methods; good agreement is obtained between the well log wavelet spectrum and both the forward modeled seismic data and the real seismic data. It is found that the DWT approach is superior, having a better signal-to-noise ratio and more localized deconvolution artifacts. A population of well logs containing a wide range of lithologies and bed thicknesses, which are categorized into lithofacies groups, is used to define the conditional probability of a wavelet transform response given a lithofacies group. These conditional probabilities are used to estimate the lithofacies probability given a seismic wavelet response via a Bayesian inversion.