Discrete Wavelet Decomposition Research Articles

Spatiotemporal characteristics of upper-crust seasonal velocity changes in North–South Seismic Belt and South China block in China

Investigating mechanisms and characteristics of the non-tectonic deformation has crucial implications for evaluating the subsurface stress evolution. In this study, we continuously tracked the seasonal velocity changes of Rayleigh wave at 2–10 s with the ambient noise interferometry and discrete wavelet decomposition, in different regions along the actively deforming North–South Seismic Belt (NSSB) and the stable Guangdong region in the South China block in China. The seasonal velocity changes exhibit strong lateral variations across different regions, with much larger seasonality (annual periodicity) and amplitude along the NSSB than those in the stable Guangdong region. There are also small-scale lateral variations inside of each region and generally larger amplitudes of the seasonal velocity changes at greater depth, but the phases (peaks, mostly in winter or summer) at different depths are consistent. The mechanism of the seasonal changes is most likely the direct loading effect of the precipitation, as indicated by consistency in their phases. However, the amplitudes of the seasonal velocity changes seem not controlled by the amount of precipitation, but are more dependent on the tectonic deformation at the different scales, from the correlation between the amplitude of the velocity change and the absolute strain rate. We demonstrate that the crustal media in the regions with larger tectonic background stress are more sensitive to the seasonal loadings. The new finding also highlights the role of the external seasonal loadings in the modulation of seismic activities and risk evaluations. Keypoints•Seasonal seismic velocity variations are found in different regions in China, likely from direct hydrological loadings of precipitation.•The spatial pattern of the seasonal velocity changes is consistent with the distribution of tectonic deformation at multi-scales.•The amplitude of the seasonal velocity changes is more dependent on the magnitude of local deformation than the amount of precipitation.

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Applications such as medical diagnosis, navigation, robotics, etc., require 3D images. Recently, deep learning networks have been extensively applied to estimate depth. Depth prediction from 2D images poses a problem that is both ill-posed and non-linear. Such networks are computationally and time-wise expensive as they have dense configurations. Further, the network performance depends on the trained model configuration, the loss functions used, and the dataset applied for training. We propose a moderately dense encoder-decoder network based on discrete wavelet decomposition and trainable coefficients (LL, LH, HL, HH). Our Nested Wavelet-Net (NDWTN) preserves the high-frequency information that is otherwise lost during the downsampling process in the encoder. Furthermore, we study the effect of activation functions, batch normalization, convolution layers, skip, etc., in our models. The network is trained with NYU datasets. Our network trains faster with good results.

Filtering and Compression of Signals by the Method of Discrete Wavelet Decomposition into One-Dimensional Series

Filtering and Compression of Signals by the Method of Discrete Wavelet Decomposition into One-Dimensional Series

Prediction of Vegetation Change by Discrete Wavelet Decomposition Based on Remote Sensing Time Series Images

Prediction of Vegetation Change by Discrete Wavelet Decomposition Based on Remote Sensing Time Series Images

Image caption generation using Visual Attention Prediction and Contextual Spatial Relation Extraction

Automatic caption generation with attention mechanisms aims at generating more descriptive captions containing coarser to finer semantic contents in the image. In this work, we use an encoder-decoder framework employing Wavelet transform based Convolutional Neural Network (WCNN) with two level discrete wavelet decomposition for extracting the visual feature maps highlighting the spatial, spectral and semantic details from the image. The Visual Attention Prediction Network (VAPN) computes both channel and spatial attention for obtaining visually attentive features. In addition to these, local features are also taken into account by considering the contextual spatial relationship between the different objects. The probability of the appropriate word prediction is achieved by combining the aforementioned architecture with Long Short Term Memory (LSTM) decoder network. Experiments are conducted on three benchmark datasets—Flickr8K, Flickr30K and MSCOCO datasets and the evaluation results prove the improved performance of the proposed model with CIDEr score of 124.2.

Fault Prognosis and Isolation of Lithium-Ion Batteries in Electric Vehicles Considering Real-Scenario Thermal Runaway Risks

Advanced safe battery storage systems with health prognostic performance are vital for electric vehicles. Various faults of lithium-ion batteries are usually undetectable in their early stage due to their concealment and graduality. This article presents a real-time fault diagnosis and isolation scheme for real-scenario batteries using the normalized discrete wavelet decomposition. The early frequency-domain features of the fault signals are extracted utilizing the high-frequency detail wavelet components, and a multilevel fault prognosis strategy is developed considering complex charging/driving characteristics under real-vehicle operating conditions. The verification results, implemented on loose wire connection batteries and real-scenario thermal runaway batteries, demonstrate that the proposed method can accurately extract and locate the hidden fault signals even under small magnitudes and effectively detecting and isolating battery faults before thermal runaway. Furthermore, significant reliability and stability of the proposed method are verified on more real-vehicle operation data, enabling online monitorable and traceable of battery faults before triggering thermal runaway, safeguarding drivers and passengers in real-world vehicular operation.

Combining discrete wavelet decomposition with soft computing techniques to predict monthly evapotranspiration in semi-arid Hakkâri province, Türkiye.

Accurate prediction of evapotranspiration values is important in planning agricultural irrigation, crop growth research, and hydrological modeling. This study is aimed at estimating monthly evapotranspiration (ET) values in Hakkâri province by combining support vector regression, bagged tree, and boosted tree methods with wavelet transform. For this purpose, precipitation, runoff, surface net solar radiation, air temperatures, and previous ET values were divided into sub-signals with various mother wavelets such as Daubechies 4, Meyer, and Symlet 2 and presented as input to machine learning (ML) algorithms. The study's main contribution to the literature is to reveal which wavelet-based machine learning model, mother wavelet type, and combination of meteorological data show the most realistic results in ET estimation. While establishing the models, the data were divided into 80% training and 20% testing. The models' performances were based on the widely used root mean square error, mean absolute error, determination coefficient, and Taylor diagrams. As a result of the study, it was revealed that the hybrid wavelet ML, which is established with input combinations separated into subcomponents by wavelet transform, generally produces more successful predictions than the stand-alone ML model. In addition, it was revealed that the optimum ET forecasting model was obtained with the wavelet bagged tree algorithm with Symlet 2 mother wavelet. Even though the best model established is based on the precipitation and temperature inputs, it was revealed that past ET, solar radiation, and runoff values are also effective inputs in ET prediction. The results can also be used in other regions of the world with semi-arid climates, such as Hakkâri. The study's outputs provide essential resources to decision-makers and planners to manage water resources and plan agricultural irrigation.

A Novel Motor Fault Diagnosis Method Based on Generative Adversarial Learning with Distribution Fusion of Discrete Working Conditions

Many kinds of electrical equipment are used in civil and building engineering. The motor is one of the main power components of this electrical equipment, which can provide stable power output. During the long-term use of motors, various motor faults may occur, which affects the normal use of electrical equipment and even causes accidents. It is significant to apply fault diagnosis for the motors at the construction site. Aiming at the problem that signal data of faulty motor lack diversity, this research designs a multi-layer perceptron Wasserstein generative adversarial network, which is used to enhance training data through distribution fusion. A discrete wavelet decomposition algorithm is employed to extract the low-frequency wavelet coefficients from the original motor current signals. These are used to train the multi-layer perceptron Wasserstein generative adversarial model. Then, the trained model is applied to generate fake current wavelet coefficients with the fused distribution. A motor fault classification model consisting of a feature extractor and pattern recognizer is built based on perceptron. The data augmentation experiment shows that the fake dataset has a larger distribution than the real dataset. The classification model trained on a real dataset, fake dataset and combined dataset achieves 21.5%, 87.2%, and 90.1% prediction accuracy on the unseen real data, respectively. The results indicate that the proposed data augmentation method can effectively generate fake data with the fused distribution. The motor fault classification model trained on a fake dataset has better generalization performance than that trained on a real dataset.

Are Torque-Induced Bone Texture Alterations Related to Early Marginal Jawbone Loss?

The reason why marginal bone loss (MBL) occurs after dental implant insertion without loading has not yet been clearly investigated. There are publications that confirm or reject the notion that there are factors that induce marginal bone loss, but no research investigates what exactly occurs in the bone surrounding the implant neck. In this study, 2196 samples of dental implant neck bone radiographs were analyzed. The follow-up period was 3 months without functional loading of the implant. Marginal bone loss was evaluated in relation to the torque used during the final phase of implant insertion. Radiographic texture features were also analyzed and evaluated. The analyses were performed individually for the anterior and posterior part of the alveolar crest in both the mandible and maxilla. After 3 months, an MBL relation with higher torque (higher than 40 Ncm; p < 0.05) was observed, but only in the lower jaw. The texture features Sum Average (SumAverg), Entropy, Difference Entropy (DifEntr), Long-Run Emphasis (LngREmph), Short-Run Emphasis (ShrtREmph), and discrete wavelet decomposition transform features were changed over time. This study presents that MBL is related to the torque value during dental implant insertion and the location of the procedure. The increasing values of SumAverg and LngREmph correlated with MBL, which were 64.21 to 64.35 and 1.71 to 2.01, respectively. The decreasing values of Entr, DifEntr, and ShrtREmph also correlated with MBL, which were 2.58 to 2.47, 1.11 to 1.01, and 0.88 to 0.84, respectively. The analyzed texture features may become good indicators of MBL in digital dental surgery.

Wavelet multi-scale analysis on particle dynamic characteristics of the vertical tubes in a horizontal-vertical pneumatic conveying system

To study the flow characteristics of particles in the vertical tube, the velocity is measured at the minimum pressure drop (MPD) by using a high-speed particle image velocimeter (PIV). Firstly, the pneumatic conveying system’s pressure drop and the particle velocity characteristics in the vertical tube were investigated. Then, for the axial fluctuation velocity of the particles, the continuous wavelet transform, and one-dimensional discrete orthogonal wavelet decomposition are used to reveal the dynamic characteristics of the particles based on the time-frequency characteristics, the contribution of wavelet levels to the energy of particle fluctuations, the auto-correlation of each wavelet level and the probability distribution of wavelet levels. The results demonstrate that large-scale movement dominates particle movement in the vertical tube, whereas small-scale movement increases as conveying height rises. The energy contribution of the low-frequency wavelet level is larger, and this contribution decreases with the acceleration of the particles along the tube. The high-frequency wavelet level’s auto-correlation coefficients decay more slowly and have a longer duration. At increasing wavelet levels, the skewness and kurtosis coefficients grow, and the departure of the Gaussian probability distribution becomes more obvious.

The interplay of the carbon market, the tradable green certificate market, and electricity market in South Korea: Dynamic transmission and spillover effects

The carbon emission trading scheme (ETS) and tradable green certificate (TGC) system have been widely used to encourage renewable technology and mitigate greenhouse gas emissions. Previous studies have discussed the interaction between these market-based instruments and the electricity market from a theoretical perspective. This research contributes to the literature by empirically examining the interplay of carbon market, the TGC market, and electricity market using a vector autoregressive (VAR) model to investigate the price transmission between different markets. A VAR-BEKK-GARCH model, based on discrete wavelet decomposition, was used to reveal the spillover effect between the three markets over multiple time scales. Based on evidence from the partially deregulated electricity market in South Korea, we do not find a significant short-term interaction between carbon market and the TGC market through the price transmission. However, the analysis over multiple time scales demonstrates that the return spillover between the carbon market and the TGC market is positive and bidirectional in the medium-term and long-term. In addition, the policy integration may create higher price risks to the carbon market and the TGC market, resulting from long-term risk spillovers. We explain these contrasting findings and discuss implications for the future deployment of these policies.

A wavelet-based deep learning pipeline for efficient COVID-19 diagnosis via CT slices

The quick diagnosis of the novel coronavirus (COVID-19) disease is vital to prevent its propagation and improve therapeutic outcomes. Computed tomography (CT) is believed to be an effective tool for diagnosing COVID-19, however, the CT scan contains hundreds of slices that are complex to be analyzed and could cause delays in diagnosis. Artificial intelligence (AI) especially deep learning (DL), could facilitate and speed up COVID-19 diagnosis from such scans. Several studies employed DL approaches based on 2D CT images from a single view, nevertheless, 3D multiview CT slices demonstrated an excellent ability to enhance the efficiency of COVID-19 diagnosis. The majority of DL-based studies utilized the spatial information of the original CT images to train their models, though, using spectral–temporal information could improve the detection of COVID-19. This article proposes a DL-based pipeline called CoviWavNet for the automatic diagnosis of COVID-19. CoviWavNet uses a 3D multiview dataset called OMNIAHCOV. Initially, it analyzes the CT slices using multilevel discrete wavelet decomposition (DWT) and then uses the heatmaps of the approximation levels to train three ResNet CNN models. These ResNets use the spectral–temporal information of such images to perform classification. Subsequently, it investigates whether the combination of spatial information with spectral–temporal information could improve the diagnostic accuracy of COVID-19. For this purpose, it extracts deep spectral–temporal features from such ResNets using transfer learning and integrates them with deep spatial features extracted from the same ResNets trained with the original CT slices. Then, it utilizes a feature selection step to reduce the dimension of such integrated features and use them as inputs to three support vector machine (SVM) classifiers. To further validate the performance of CoviWavNet, a publicly available benchmark dataset called SARS-COV-2-CT-Scan is employed. The results of CoviWavNet have demonstrated that using the spectral–temporal information of the DWT heatmap images to train the ResNets is superior to utilizing the spatial information of the original CT images. Furthermore, integrating deep spectral–temporal features with deep spatial features has enhanced the classification accuracy of the three SVM classifiers reaching a final accuracy of 99.33% and 99.7% for the OMNIAHCOV and SARS-COV-2-CT-Scan datasets respectively. These accuracies verify the outstanding performance of CoviWavNet compared to other related studies. Thus, CoviWavNet can help radiologists in the rapid and accurate diagnosis of COVID-19 diagnosis.

A Study on the Application of Discrete Wavelet Decomposition for Fault Diagnosis on a Ship Oil Purifier

With the development of the Internet of things, big data, and AI leading the 4th industrial revolution, it has become possible to acquire, manage, and analyze vast and diverse condition signals from various industrial machinery facilities. In addition, it has been revealed that various and large amounts of signals acquired from the facilities can be utilized for fault diagnosis. Currently, while data-driven fault diagnosis techniques applicable to the facilities are being developed, it has been tried to apply the techniques for the development of fully autonomous ships in the shipbuilding and shipping industry. Since the autonomous ships must be able to detect and diagnose the failures on their own in real time, the overall research is required on how to acquire signals from the ship facilities and use them to diagnose their failures. In this study, a fault diagnosis framework was proposed for condition-based maintenance (CBM) of ship oil purifiers, which are an auxiliary facility in the engine system of a ship. First, an oil purifier test-bed for simulating faults was built to obtain data on the state of the equipment. After extracting features using discrete wavelet decomposition from the data, the features were visualized by using t-distributed stochastic neighbor embedding, and were used to train support vector machine-based diagnostic models. Finally, the trained models were evaluated with Accuracy and F1 score, and some models scored 0.99 or higher, confirming high diagnostic performance. This study can be used as a reference for establishing CBM system and fault diagnosis system. Furthermore, this study is expected to improve the safety and reliability of oil purifiers in Degree 4 MASS.

Automated Computer-Aided Diagnosis of Diabetic Retinopathy Based on Segmentation and Classification using K-nearest neighbor algorithm in retinal images

Abstract Diabetic retinopathy (DR) is an eye oddity where the human retina is afflicted because of the ever-increasing quantity of insulin in the blood. It leads to the loss of sight. Preliminary diagnosis of DR assists to improve to inhibit future injury. Proper DR screening has been recognized as an economical way to accumulate health services. Automated retinal analysis become known as the most significant screening approach for primitive DR diagnosis, which leads to diminishing the workload related to manual screening and also, cost-effective and less time-consuming efforts. In the proposed work, the preprocessing, removal of applicant lesion pixels, and formulation of feature set have been examined which is fully appropriate for the classification task. In preprocessing approach, the framework removes the unwanted pixels, eliminates the optic disc, and extraction of the blood vessels from the retinal images. Morphological operations are applied to extract the boundaries of the blood vessels and then 2D discrete wavelet decomposition is applied to estimate the horizontal, vertical and diagonal coefficients. The candidate lesion pixels i.e. dark and bright DR pixels are detected using an adaptive threshold that uses local statistical, geometrical, and location-based characteristics of the background image. The extracted feature set is processed using a K-nearest neighbor (KNN) classifier with 80% of training data and 20% of testing data to diagnose the severity level of the disease. The proposed scheme is evaluated by the DIARETDB1 benchmark dataset with the performance parameters, i.e. 95% of accuracy, 92.6% of sensitivity and 87.56% specificity achieved with less computation time required.

Optimal knee osteoarthritis diagnosis using hybrid deep belief network based on Salp swarm optimization method

AbstractOsteoarthritis (OA) damages the articular cartilage of the knee and is a severe degenerative joint condition. Currently, OA diagnosis is carried out by symptom analysis and progressive evaluation of the radiographs, although the method is subjective. This work presents a novel computer aided diagnostic system to diagnose the severity of the disease in its early stages. The proposed method comprises of stages that include image pre‐processing, extraction of features based on discrete wavelet decomposition, histogram, GLCM and texture features, and classification by stacked up‐RBM Deep Belief Networks (Hybrid DBN) finally. The performance of HDBN is improved by optimizing the hyper parameters with the Salp Swarm Optimization Algorithm (SSA). Experiments conducted on the Kaggle database consisting of 7503 images demonstrated an overall accuracy of 99.45% with 100% sensitivity and specificity. The impact on isolated and combined feature contributions is also analyzed using 10‐fold cross validation (CV). The robustness of the algorithm is tested on degraded images of salt‐pepper, Gaussian, and Poisson noise, which proved the effectiveness of the method. Comparison of the method proposed with similar techniques is done by employing different optimization algorithms and classifiers.

Neuromorphic Architecture Accelerated Automated Seizure Detection in Multi-Channel Scalp EEG.

Epileptic focal seizures can be localized in the brain using tracer injections during or immediately after the incidence of a seizure. A real-time automated seizure detection system with minimal latency can help time the injection properly to find the seizure origin accurately. Reliable real-time seizure detection systems have not been clinically reported yet. We developed an anomaly detection-based automated seizure detection system, using scalp-electroencephalogram (EEG) data, which can be trained using a few seizure sessions, and implemented it on commercially available hardware with parallel, neuromorphic architecture—the NeuroStack. We extracted nonlinear, statistical, and discrete wavelet decomposition features, and we developed a graphical user interface and traditional feature selection methods to select the most discriminative features. We investigated Reduced Coulomb Energy (RCE) networks and K-Nearest Neighbors (k-NN) for its several advantages, such as fast learning no local minima problem. We obtained a maximum sensitivity of and a specificity of with 5 s epoch duration. The system’s latency was 12 s, which is within most seizure event windows, which last for an average duration of 60 s. Our results showed that the CD feature consumes large computation resources and excluding it can reduce the latency to 3.6 s but at the cost of lower performance 80% sensitivity and 97% specificity. We demonstrated that the proposed methodology achieves a high specificity and an acceptable sensitivity within a short delay. Our results indicated also that individual-based RCE are superior to population-based RCE. The proposed RCE networks has been compared to SVM and ANN as a baseline for comparison as they are the most common machine learning seizure detection methods. SVM and ANN-based systems were trained on the same data as RCE and K-NN with features optimized specifically for them. RCE nets are superior to SVM and ANN. The proposed model also achieves comparable performance to the state-of-the-art deep learning techniques while not requiring a sizeable database, which is often expensive to build. These numbers indicate that the system is viable as a trigger mechanism for tracer injection.

Removing Clinical Motion Artifacts During Ventilation Monitoring With Electrical Impedance Tomography: Introduction of Methodology and Validation With Simulation and Patient Data.

ObjectiveElectrical impedance tomography (EIT) is a bedside tool for lung ventilation and perfusion assessment. However, the ability for long-term monitoring diminished due to interferences from clinical interventions and motion artifacts. The purpose of this study is to investigate the feasibility of the discrete wavelet transform (DWT) to detect and remove the common types of motion artifacts in thoracic EIT.MethodsBaseline drifting, step-like and spike-like interferences were simulated to mimic three common types of motion artifacts. The discrete wavelet decomposition was employed to characterize those motion artifacts in different frequency levels with different wavelet coefficients, and those motion artifacts were then attenuated by suppressing the relevant wavelet coefficients. Further validation was conducted in two patients when motion artifacts were introduced through pulsating mattress and deliberate body movements. The db8 wavelet was used to decompose the contaminated signals into several sublevels.ResultsIn the simulation study, it was shown that, after being processed by DWT, the signal consistency improved by 92.98% for baseline drifting, 97.83% for the step-like artifact, and 62.83% for the spike-like artifact; the signal similarity improved by 77.49% for baseline drifting, 73.47% for the step-like artifact, and 2.35% for the spike-like artifact. Results from patient data demonstrated the EIT image errors decreased by 89.24% (baseline drifting), 88.45% (step-like artifact), and 97.80% (spike-like artifact), respectively; the data correlations between EIT images without artifacts and the processed were all > 0.95.ConclusionThis study found that DWT is a universal and effective tool to detect and remove these motion artifacts.

Optimized use of Wavelet Packet Trees for the analysis of electrical waveforms

Wavelet packet trees represent a topic which grows in popularity when it comes to analysis of electrical waveforms. It allows for time-frequency analysis providing information on narrower ranges of frequency (as compared to the faster Discrete Wavelet Decomposition), but the computational resources are significantly greater than that involved in other types of wavelet-based analysis. In order to allow for this type of analysis to be usable in real-time applications, that is – to reduce the runtime, original algorithms were conceived and tested. In the first part of this work, previously implemented algorithms are briefly described, along with their pros and cons. Afterward, a new runtime optimization algorithm is proposed. Details on data structures, workflow, tests and study of errors are provided. This algorithm diminishes with up to 59% the runtime required by the application of the superposition theorem in order to evaluate the contribution of clustered harmonics using WPT.

Minimization of errors in discrete wavelet filtering of signals during ultrasonic measurements and testing

Error minimizing methods for discrete wavelet filtering of ultrasonic meter signals are considered. For this purpose, special model signals containing various measuring pulses are generated. The psi function of the Daubechies 28 wavelet is used to generate the pulses. Noise is added to the generated pulses. A comparative analysis of the two filtering algorithms is performed. The first algorithm is to limit the amount of detail of the wavelet decomposition coefficients in relation to signal interference. The minimum value of the root mean square error of wavelet decomposition signal deviation which is restored at each level from the initial signal without noise is determined. The second algorithm uses a separate threshold for each level of wavelet decomposition to limit the magnitude of the detail coefficients that are proportional to the standard deviation. Like in the first algorithm, the task is to determine the level of wavelet decomposition at which the minimum standard error is achieved. A feature of both algorithms is an expanded base of discrete wavelets ‒ families of Biorthogonal, Coiflet, Daubechies, Discrete Meyer, Haar, Reverse Biorthogonal, Symlets (106 in total) and threshold functions garotte, garrote, greater, hard, less, soft (6 in total). The model function uses random variables in both algorithms, so the averaging base is used to obtain stable results. Given features of algorithm construction allowed to reveal efficiency of ultrasonic signal filtering on the first algorithm presented in the form of oscilloscopic images. The use of a separate threshold for limiting the number of detail coefficients for each level of discrete wavelet decomposition using the given wavelet base and threshold functions has reduced the filtering error.

A Hybrid Model for Vessel Traffic Flow Prediction Based on Wavelet and Prophet

Accurate vessel traffic flow prediction is significant for maritime traffic guidance and control. According to the characteristics of vessel traffic flow data, a new hybrid model, named DWT–Prophet, is proposed based on the discrete wavelet decomposition and Prophet framework for the prediction of vessel traffic flow. First, vessel traffic flow was decomposed into a low-frequency component and several high-frequency components by wavelet decomposition. Second, Prophet was trained to predict the components, respectively. Finally, the prediction results of the components were reconstructed to complete the prediction. The experimental results demonstrate that the hybrid DWT–Prophet outperformed the single Prophet, long short-term memory, random forest, and support vector regression (SVR). Moreover, the practicability of the new forecasting method was improved effectively.