Dyadic Wavelet Transform Research Articles

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.

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

Complex-Pan-Tompkins-Wavelets: Cross-channel ECG beat detection and delineation

The Electro Cardiogram (ECG) provides insight into the different phases of a heart beat and various kinds of disorders which may affect them. For the identification and treatment of these conditions it is crucial to properly detect each heartbeat and delineate P-, QRS and T-waves. The presented Complex-Pan-Tompkins-Wavelets (CPTW) algorithm aims at detecting and delineating heart beats in real-time across any number of channels between one and 64 sampled between 256 Hz and 4.8 kHz. It merges three well established single channel algorithms, the complex-lead by Christov, the Pan-Tompkins and the discrete dyadic wavelet-transform, such that the shortcomings of one algorithm are compensated by the strength of the other. A first study testing the CPTW algorithm was conducted using 75 records of 30 min duration provided by the INCART database. An initial implementation in Python 3 allows to localize and detect QRS complexes with an average sensitivity of 99.57% and a precision of 99.58% could be achieved. The average time required to process a single data set thereby was 12 min. In a second test which included 3 recordings of 3 min duration the scalability of the algorithm with respect to number of channels and sampling rates was accessed. Incrementing the number of channels by a factor of 5.2–62 channels resulted in an 3.1 fold increment in run-time. Raising the sampling rate from 256 Hz to 4.8 kHz elongated the run-time by a factor of just 3.2.

Metode Wavelet-MFCC dan Korelasi dalam Pengenalan Suara Digit

Voice is the sound emitted from living things. With the development of Automatic Speech Recognition (ASR) technology, voice can be used to make it easier for humans to do something. In the ASR extraction process the features have an important role in the recognition process. The feature extraction methods that are commonly applied to ASR are MFCC and Wavelet. Each of them has advantages and disadvantages. Therefore, this study will combine the wavelet feature extraction method and MFCC to maximize the existing advantages. The proposed method is called Wavelet-MFCC. Voice recognition method that does not use recommendations. Determination of system performance using the Word Recoginition Rate (WRR) method which is validated with the K-Fold Cross Validation with the number of folds is 5. The research dataset used is voice recording digits 0-9 in English. The results show that the digit speech recognition system that has been built gives the highest average value of 63% for digit 4 using wavelet daubechies DB3 and wavelet dyadic transform method. As for the comparison results of the wavelet decomposition method used, that the use of dyadic wavelet transformation is better than the wavelet package.

A novel integrated price and load forecasting method in smart grid environment based on multi-level structure

Prediction of load and price are two critical key in power system planning and operation. Most of the recent works in this area forecast the load and price signals separately but, a dynamic model in smart grid is evaluated while, the customers may have opportunity to react the proposed prices changing through shifting the electricity usages from expensive to cheaper hours. So, the load and price signals are coupled strongly which made the previous prediction models ineffective. In this research, a synthetic prediction approach has been proposed by considering the load and price signals, simultaneously. This method works as multi-input multi-output (MIMO) model based on least square support vector machine (LSSVM) forecast engine. Furthermore, a dyadic wavelet transform (DWT) is suggested in this approach to decompose the original signal into different small sub-signals. Beside of that, the modified mutual information (MMI) filter has been used to choose the best candidate input of forecast engine. The learning section is also coupled with novel modified optimization algorithm based on gravitational search algorithm (GSA) which called as modified GSA (MGSA). Finally, various forecasting errors have been considered as average mean absolute percentage error and error variance to get the comparison outcomes and performance of forecasting approaches. For this purpose, different markets have been considered as test case to show the efficiency of suggested approach.

Epidermal antenna in palmar arch region for anaemia detection to avoid peripheral perfusion artifact in optical sensor during hemoglobin measurement

The anaemia disease diagnosed with various test such as complete blood count (CBC), ferritin measure, reticulocyte count, peripheral smear and blood gas analyser. The ferritin measure the storage and usage of iron in human body, reticulocyte count assess young red blood cell, and Peripheral smear analyse the cell colour, size, and shape of red blood cell through microscopic image. The blood gas analyser measures methemoglobin (MetHb) and carboxyhaemoglobin. Different test measure haemoglobin, since iron level show normal in blood for the patient with low total body iron. The iron deficiency never show symptom or sign in the human body. In this paper, we propose a new non-invasive method for anaemia measure through epidermal antenna over ulnar region of palm and acquire radiating signal from Haemoglobin protein. The acquired signal from epidermal antenna analysed with Transverse Dyadic Wavelet Transform for haemoglobin protein level in red blood cell. The epidermal antenna signal from ulnar region haemoglobin measurement avoids the peripheral perfusion artifact of optical or image sensor which arise during measurement. The experimental analysis show signal of epidermal antenna measure the haemoglobin more accurately, through regression modelling than existing optical and image based point of care device. Experimental result of haemoglobin measurement from ulnar region has validated with blood gas analyser.

A Condition Monitoring System Based On Dyadic Wavelet Transform Using Thermal Image

Wavelet analysis is broadly and effectively utilized in image processing and analysis. Because of the simple and fast algorithm, the dyadic wavelet transform has generally used. A dyadic wavelet transform gives an excellent output because of the different levels of the wavelet coefficient of the image. The proposed method presents an optimal value such as mean, standard deviation and entropy for the decomposition and reconstruction of the thermal image. The original results demonstrate which technique can find the induction motor faults clearly and effectively.

A Robust Passive Blind Copy-Move Image Forgery Detection

Image forensic is the important research area which deals to verify the authenticity of the digital image. Copy-move forgery is common type of forgery used to modify the image. This paper proposes passive blind forensic copy-move forgery detection technique. The combination of dyadic wavelet transform (DyWT) and scale invariant feature transform (SIFT) is used. Finally, RANSAC is used to improve the detection accuracy. The performance of the algorithm is verified with 45 original/forged images considering various attacks, such as scaling, rotation, small object and multiple copy-move pasting. The experimental results reveal that the proposed technique identifies and locates the forged area accurately for all attacks. The comparison of the proposed method is done with existing methods in terms of detection accuracy, recall, and precision. The simulation results show that for the most of the cases the proposed method outperforms the existing methods.

A general scheme for finding the static rate–distortion optimized ordering for the bits of the coefficients of all subbands of an [formula omitted]-level dyadic biorthogonal DWT

The expected distortion decrease per bit attained by conveying the significance and refinement information of transform coefficients is derived taking into consideration their Probability Distribution Function (PDF) and their entropy. A general scheme for finding the static rate–distortion optimized ordering for the bits of the coefficients for all subbands of a generic N-level dyadic biorthogonal Discrete Wavelet Transform (DWT) is given by weighting their distortion decrease per bit using the gain of each decomposition subband. Specific formulation for the Exponential Power Distribution (EPD) family is given and closed formulae are derived for the special cases of the Uniform and Laplace distributions. It is shown that under certain circumstances some refinement information of larger magnitude coefficients should be conveyed before the significant information of the current ones. The results can be applied by both conventional context modeling entropy coding algorithms or by set-partitioning algorithms which use multiple lists to keep track of significant and refinement coefficients. A very fast set-partitioning compression algorithm (Depth Embedded Block Tree — DEBT) has been developed based on variable-depth blocks and trees which uses the results presented here and achieves excellent compression ratios along with many other desired properties, e.g., embedded rate–distortion optimized lossy or lossless stream, quality or resolution scalability, and region of interest, among others. Tests show that the rate–distortion curves of most images show a significant improvement when using the weighting derived by the appropriate Exponential Power Distribution fitting in comparison to using a priori standard Uniform or Laplace Probability Distribution Function when using a non orthogonal Discrete Wavelet Transform.

Feature Enhancement of Noisy Image by Dyadic Wavelet Analysis

The image de-noising method is proposed by multiresolution representations of the dyadic wavelet transformation. Firstly, the original image are decomposed using dyadic wavelet transformation, then the image can be de-noised by way of adopting different thresholds according to the different scales of wavelet coefficients, and finally nonlinear enhancing function are applied for wavelet coefficients with the enhancement method in the corresponding scales. Experiments of the medical images show that compared to the image enhancement method, our approach improves the information entropy and contrast improvement index of the images, enhances edge texture of images.

Dyadic wavelet analysis and detection of sinusitis using near infrared sensor

<p class="abstract"><strong>Background:</strong> Sinusitis is a chronic infection or inflammation which affects the paranasal sinus cavities and the associated nasal cavities. As the symptoms of sinusitis greatly resemble upper respiratory infections, diagnosing sinusitis clinically is a major issue.<strong> </strong>Though imaging techniques serves as a standard in confirming the diagnosis of chronic sinusitis, the availability at the primary care settings, affordability and diagnosing acute cases calls upon an alternative technique in practice. Recent researches confirming the diagnosis of sinusitis using Near-infrared imaging gives us hope in taking up the research using optical sensing. The objective of the study was to successfully diagnose sinusitis using NIR-LED optical sensor and to signal process the data obtained from the patients using Dyadic Wavelet Transform (DyWT) to confirm and to validate diagnosis using regression analysis. The study also correlates the plain radiographic findings with the NIR device sensing to make the device feasible.</p><p class="abstract"><strong>Methods:</strong> This was a one year pilot study (June 2014–May 2015) conducted with forty patients suspected of sinusitis and with clinical history along with ten healthy individuals as controls. </p><p class="abstract"><strong>Results:</strong> Patients age ranged from 18-65 years were included in the study. Results from NIR sensing device well correlate with the radiographic examination of the registered candidates. The regression result perfectly matches with the dyadic wavelet results of the patients, confirming the diagnosing of sinusitis using near- infrared sensor. Radiographic examination well correlates with the results from the NIR diagnostic device providing a valuable evidence of the hardware.</p><p class="abstract"><strong>Conclusions:</strong> NIR-LED sensor device can provide qualitative evidence in differentiating the mild and severe patients based on air-fluid level present in the sinus. The results strongly recommend that NIR sensing device can be a best alternative in case of frequently sinus affected patients and for the unaffordable patients without the risk of radiation.</p>

Preserving the border and curvature of fetal heart chambers through TDyWT perspective geometry wrap segmentation

Congenital heart defect leads to the structural abnormality in neonatal. Congenital heart defect (CHD) is the major cause for 20% perinatal mortality and 50% infant mortality. However, the fetal cardiac screening plays a vital role to diagnose the CHD during second –trimester. Evaluation of fetal cardiac chamber structure is difficult due to small in size and movement. Four-chamber view has become the first and foremost view of echocardiography to detect structural malformations in the fetal heart. Furthermore, trained obstetricians, Pediatric cardiologists, maternal-fetal medicine specialists, and radiologists need proper knowledge and skills to identify the chamber structure from echocardiography. In addition, the effective diagnosis of fetal heart four-chamber view consumes more time and needs extremely skilled radiologists owing to their low quality, small signal to noise ratio and rapid movement of fetal heart ultrasound images. Thus, the diagnosis of CHD is the most challenging task. In this paper, we propose the Transverse Dyadic Wavelet Transform (TDyWT) algorithm to preserve the border and curvature of four chambers from 18 to 22 weeks ultrasound fetal heart image. We validate the proposed TDyWT algorithm with normal and abnormal images from Mediscan radiological centre. The performance of the TDyWT algorithm analyses qualitatively and quantitatively to prove border and curvature of the chambers is superior to other conventional methods.

Copy-Move Forgery Detection Using DyWT

In this paper, we proposed a passive method for copy-move region duplication detection using dyadic wavelet transform (DyWT). DyWT is better than discrete wavelet transform (DWT) for data analysis as it is shift invariant. Initially we decompose the input image into approximation (LL1) and detail (HH1) sub-bands. Then LL1 and HH1 sub-bands are divided into overlapping sub blocks and find the similarity between the blocks. In LL1 sub-band the copied and moved blocks have high similarity rate than the HH1 sub-band, this is just because, there is noise inconsistency in the moved blocks. Then we sort the LL1 sub-band blocks pair based on high similarity and in HH1 blocks are sorted based on high dissimilarity. Then we apply threshold to get the copied moved blocks. Here we also applied some post processing operations to check the robustness of our method and we get the satisfactory results to validate the copy move forgery detection.

Image Retrieval Method Utilizing Texture Information Derived from Discrete Wavelet Transformation Together with Color Information

Image retrieval method utilizing texture information which is derived from Discrete Wavelet Transformation: DWT together with color information is proposed. One of the specific features of the texture information extracted from portions of image is based on Dyadic wavelet transformation with forming texture feature vector by using energy derived from Gabor transform on 7 by 7 pixel neighbor of significant points. Using the Wang`s dataset, the proposed method is evaluated with retrieval success rate (precision and recall) as well as Euclidian distance between the image in concern (Query image) and the other images in the database of interest and is compared to the other method. As the result through the experiments, it is found that the DWT derived texture information is significantly effective in comparison to the color information.

A blind digital image watermarking method based on the dyadic wavelet packet transform and fast interval arithmetic techniques

We propose a new digital image watermarking method based on the dyadic wavelet packet transform (DYWPT) and fast interval arithmetic (IA) techniques. Because the DYWPT has a redundant representation, like the dyadic wavelet transform (DYWT), the amount of information that the watermark must contain is greater than in the case of methods based on ordinary discrete wavelet transforms (DWTs) and the discrete wavelet packet transform (DWPT). However, the order of the high frequency components is not necessarily the same as the order of their frequency domain. Therefore, in our approach, we rearrange the order of the high frequency components in descending order of frequency components and embed a watermark selectively into higher frequency components. Our watermark is a ternary-valued logo that is embedded into higher frequency components through use of the DYWPT and fast IA techniques. We describe our watermarking procedure in detail and present experimental results demonstrating that our method produces watermarked images that have better quality and are robust with respect to various types of attacks, including marking, clipping, median filtering, contrast tuning (histeq and imadjust commands in the MATLAB Image Processing Toolbox), addition of Gaussian white noise, addition of salt & pepper noise, JPEG and JPEG 2000 compressions, rotation, and resizing.

Logarithmic dyadic wavelet transform with its applications in edge detection and reconstruction

In this paper, based on the logarithmic image processing model and the dyadic wavelet transform (DWT), we introduce a logarithmic DWT (LDWT) that is a mathematical transform. It can be used in image edge detection, signal and image reconstruction. Comparative study of this proposed LDWT-based method is done with the edge detection Canny and Sobel methods using Pratt's Figure of Merit, and the comparative results show that the LDWT-based method is better and more robust in detecting low contrast edges than the other two methods. The gradient maps of images are detected by using the DWT- and LDWT-based methods, and the experimental results demonstrate that the gradient maps obtained by the LDWT-based method are more adequate and precisely located. Finally, we use the DWT- and LDWT-based methods to reconstruct one-dimensional signals and two-dimensional images, and the reconstruction results show that the LDWT-based reconstruction method is more effective.

Periodic Impulsive Fault Feature Extraction of Rotating Machinery Using Dual-Tree Rational Dilation Complex Wavelet Transform

Fault diagnosis of rotating machinery is very important to guarantee the safety of manufacturing. Periodic impulsive fault features commonly appear in vibration measurements when local defects occur in the key components like rolling bearings and gearboxes. To extract the periodic impulses embedded in strong background noise, wavelet transform (WT) is suitable and has been widely used in analyzing these nonstationary signals. However, a few limitations like shift-variance and fixed frequency partition manner of the dyadic WT would weaken its effectiveness in engineering application. Compared with dyadic WT, the dual-tree rational dilation complex wavelet transform (DT-RADWT) enjoys attractive properties of better shift-invariance, flexible time-frequency (TF) partition manner, and tunable oscillatory nature of the bases. In this article, an impulsive fault features extraction technique based on the DT-RADWT is proposed. In the routine of the proposed method, the optimal DT-RADWT basis is constructed dynamically and adaptively based on the input signal. Additionally, the sensitive wavelet subband is chosen using kurtosis maximization principle to reveal the potential weak fault features. The proposed method is applied on engineering applications for defects detection of the rolling bearing and gearbox. The results show that the proposed method performs better in extracting the fault features than dyadic WT and empirical mode decomposition (EMD), especially when the incipient fault features are embedded in the frequency transition bands of the dyadic WT.

Blind Detection of Copy-Move Forgery in Digital Images Based on Dyadic Wavelet Transform

This paper proposed a detection algorithm for copy-move in same image based on dyadic wavelet transform. First of all, four sub images could be got through the decomposition of detecting image by dyadic wavelet transform. Secondly, high-frequency and low-frequency sub image were decomposed into blocks without any overlap and two sub image’s dyadic wavelet coefficients were regarded as the eigenvalue of the image block. At Last, both the high similarity among the low-frequency sub image blocks and the low similarity among the high-frequency sub image blocks were selected as a distorted image block. A kind of image edge processing methods was used to improve the tampering region at the same time. Through the experiments, it shows that the algorithm got the higher detection rate and lower error rates.

Image Retrieval Based on Color, Shape, and Texture for Ornamental Leaf with Medicinal Functionality Images

This research is focusing on ornamental leaf with dual functionalities, which are ornamental and medicinal functionalities. However, only few people know about the medicinal functionality of this plant. In Indonesia, this plant is also easy to find because mostly cultivates in front of the house. If its medicinal function and that easiness are taken into consideration, this leaf should be an option towards the full chemical-based medicines. This image retrieval system utilizes color, shape, and texture features from leaf images. HSV-based color histogram, Zernike complex moments, and Dyadic wavelet transformation are the color, shape, and texture features extractor methods, respectively. We also implement the Bayesian automatic weighting formula instead of assignment of static weighting factor. From the results, this proposed method is very powerful from any rotation, lighting, and perspective changes.

A Novel Medical Image Enhancement Algorithm Based on Dyadic Wavelet Transform

In clinical application, medical images tend to be low contrast, bigger or more speckle noise, and they will affect the effective use of medical images. Medical image enhancement can solve the problem of the low contrast of the image, so as to get more clear details of images. An algorithm of the medical image enhancement is proposed based on the binary wavelet transform in the paper. Firstly, the medical image was carried through dyadic wavelet transform, then the high-frequency information was de-noised, and then to enhance the high frequency information which was de-noised; at last, the enhanced high-frequency sub-images and the low-frequency sub-images were reconstructed by inverse dyadic wavelet transform. Finally, a better visual effect can be got by a subsection grayscale transform. The experiment results show the enhanced effect of proposed method is better than those of the wavelet transform.