Characteristics Of Wavelet Coefficients Research Articles

LW-XNet for segmentation and classification of skin lesions from dermoscopy images

The skin, one of the most crucial organs of the human body, serves as a barrier between the body and the external environment. Early detection of skin diseases is imperative to reduce mortality rates, as some untreated conditions may progress to skin cancer. Segmentation and classification of lesions represent pivotal and interrelated endeavors within the realm of skin disease diagnosis. For this purpose, this paper presents a comprehensive diagnostic framework for segmentation and classification of skin lesions, which integrates a Legendre multiwavelet transform-based fusion XNet (LW-XNet) with an improved soft attention dense connection convolutional network (ISA-DenseNet). LW-XNet combines the strengths of XNet in fusing different frequency components of images, along with the strong feature representation capability of LW bases with various regularities for overall contextual information and detailed information of dermoscopy images. Furthermore, its encoder devises a LWT channel concatenate (LCC) block to subdivide the image into eight wavelet coefficient feature images and perform concatenated processing on them, enabling it to better differentiate and comprehend the intricate features within dermoscopy images. Finally, ISA-DenseNet is utilized for multi-class classification of the segmented images. Experimental results demonstrate the superiority of the proposed framework over existing segmentation and classification methods.

Automatic detection of artifacts and improved classification models for emotional activity detection from multimodal physiological data

This manuscript proposes an automated artifacts detection and multimodal classification system for human emotion analysis from human physiological signals. First, multimodal physiological data, including the Electrodermal Activity (EDA), electrocardiogram (ECG), Blood Volume Pulse (BVP) and respiration rate signals are collected. Second, a Modified Compressed Sensing-based Decomposition (MCSD) is used to extract the informative Skin Conductance Response (SCR) events of the EDA signal. Third, raw features (edge and sharp variations), statistical and wavelet coefficient features of EDA, ECG, BVP, respiration and SCR signals are obtained. Fourth, the extracted raw features, statistical and wavelet coefficient features from all physiological signals are fed into the parallel Deep Convolutional Neural Network (DCNN) to reduce the dimensionality of feature space by removing artifacts. Fifth, the fused artifact-free feature vector is obtained for neutral, stress and pleasure emotion classes. Sixth, an artifact-free feature vector is used to train the Random Forest Deep Neural Network (RFDNN) classifier. Then, a trained RFDNN classifier is applied to classify the test signals into different emotion classes. Thus, leveraging the strengths of both RF and DNN algorithms, more comprehensive feature learning using multimodal psychological data is achieved, resulting in robust and accurate classification of human emotional activities. Finally, an extensive experiment using the Wearable Stress and Affect Detection (WESAD) dataset shows that the proposed system outperforms other existing human emotion classification systems using physiological data.

Evaluating the Canopy Chlorophyll Density of Maize at the Whole Growth Stage Based on Multi-Scale UAV Image Feature Fusion and Machine Learning Methods

Maize is one of the main grain reserve crops, which directly affects the food security of the country. It is extremely important to evaluate the growth status of maize in a timely and accurate manner. Canopy Chlorophyll Density (CCD) is closely related to crop health status. A timely and accurate estimation of CCD is helpful for managers to take measures to avoid yield loss. Thus, many methods have been developed to estimate CCD with remote sensing data. However, the relationship between the CCD and the features used in these CCD estimation methods at different growth stages is unclear. In addition, the CCD was directly estimated from remote sensing data in most previous studies. If the CCD can be accurately estimated from the estimation results of Leaf Chlorophyll Density (LCD) and Leaf Area Index (LAI) remains to be explored. In this study, Random Forest (RF), Support Vector Machines (SVM), and Multivariable Linear Regression (MLR) were used to develop CCD, LCD, and LAI estimation models by integrating multiple features derived from unmanned aerial vehicle (UAV) multispectral images. Firstly, the performances of the RF, SVM, and MLR trained over spectral features (including vegetation indices and band reflectance; dataset I), texture features (dataset II), wavelet coefficient features (dataset III), and multiple features (dataset IV, including all the above datasets) were analyzed, respectively. Secondly, the CCDP was calculated from the estimated LCD and estimated LAI, and then the CCD was estimated based on multiple features and the CCDP was compared. The results show that the correlation between CCD and different features is significantly different at every growth stage. The RF model trained over dataset IV yielded the best performance for the estimation of LCD, LAI, and CCD (R2 values were 0.91, 0.97, and 0.97, and RMSE values were 6.59 μg/cm2, 0.35, and 24.85 μg/cm2). The CCD directly estimated from dataset IV is slightly closer to the ground truth CCD than the CCDP (R2 = 0.96, RMSE = 26.85 μg/cm2) calculated from LCD and LAI. The results indicated that the CCD of maize can be accurately estimated from multiple multispectral image features at the whole growth stage, and both CCD estimation strategies can be used to estimate the CCD accurately. This study provides a new reference for accurate CCD evaluation in precision agriculture.

The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals

This research studies the effects of both Daubechies wavelet basis function (DWBF) and decomposition level (DL) on the performance of detecting atrial fibrillation (AF) based on electrocardiograms (ECGs). ECG signals (consisting of 23 AF data and 18 normal data from MIT-BIH) were decomposed at various levels using several types of DWBF to obtain four wavelet coefficient features (WCFs), namely, minimum (min), maximum (max), mean, and standard deviation (stdev). These features were then classified to detect the presence of AF using a support vector machine (SVM) classifier. Distribution of training and testing data for the SVM uses the 5-fold cross-validation (CV) principle to produce optimum detection performance. In this study, AF detection performance is measured and analyzed based on accuracy, sensitivity, and specificity metrics. The results of the analysis show that accuracy tends to decrease with increases in the decomposition level. In addition, it becomes stable in various types of DWBF. For both sensitivity and specificity, the results of the analysis show that increasing the decomposition level also causes a decrease in both sensitivity and specificity. However, unlike the accuracy, changing the DWBF type causes both two metrics to fluctuate over a wider range. The statistical results also indicate that the highest AF accuracy detection (i.e., 94.17%) is obtained at the Daubechies 2 (DB2) function with a decomposition level of 4, whereas the highest sensitivity, 97.57%, occurs when the AF detection uses DB6 with a decomposition level of 2. Finally, DB2 with decomposition level 4 results in 96.750% for specificity. The finding of this study is that selecting the appropriate DL has a more significant effect than DWBF on AF detection using WCF.

Single-scale convolution wavelet feature optimization classification model based on electrocardiogram coded image

Premature beats are a cardiovascular disease, which can lead to complications of other diseases. An electrocardiograph (ECG) is the main tool for detecting premature beats, but accurate detection of premature beats still faces challenges. This work designs a single-scale convolution wavelet feature optimization (SSCWFO) classification model that is based on a single-scale convolutional neural network (SSCNN) model and optimized by Linear Discriminant Analysis (LDA) algorithm. First, the wavelet coefficient features are extracted from 12-lead ECG signals using Daubechies5, and then the 5th level detail coefficient features are transformed into images using Gramian Angular Difference Fields (GADFs). Thereafter the single-scale features are extracted by the SSCNN model. Next, the LDA algorithm was used to maximum inter-class distance and the minimum intra-class distance of each category. Finally, the Gaussian naive Bayes is used to classify-three types of signals. The results after LDA optimization show that the accuracy, precision, sensitivity, F1-score, and area under the ROC curve (AUC) of the SSCWFO model are improved to 91.12%, 92.29%, 92.55%, 92.13%, and 0.9197, respectively. Also, the network architectures of Resnet34, Resnet18, and LeNet 5 are used in this work for a comparison; their accuracy is 75.93%, 76.88%, and 68.48%, respectively. This shows that the method can effectively distinguish normal signals and two types of premature beat diseases and is helpful to the effective classification of diseases of premature beats.

Discussion of the Influence of Multiscale PCA Denoising Methods with Three Different Features.

Bioinformation is information generated from biological movement. By using a variety of modern technologies, we can use this information to form a meaningful model for researchers to study. An electromyographic (EMG) signal is one type of bioinformation that is used in many areas to help people study human muscle movement. This information can help in both clinical areas and industrial areas. EMG is a very complicated signal, so processing it is vital. The processing of EMG signals is divided into collection, denoising, decomposition, feature extraction and classification steps. In this article, the wavelet denoising step and several decomposition processes are discussed to show the usage of this technique in the final classification step. At the end of the study, we find that after the wavelet denoising step, the classification accuracy, which uses the K-nearest neighbor of the independent component analysis features, improves, but the accuracy of the wavelet coefficient features and autoregression coefficient features decreases.

A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox

It is significant to boost the performance of fault diagnosis of wind turbine gearboxes. In this paper, a hybrid attention improved residual network (HA-ResNet) based method is proposed to diagnose the fault of wind turbines gearbox by highlighting the essential frequency bands of wavelet coefficients and the fault features of convolution channels. First, the paper performed wavelet packet transformation (WPT) on the raw signal and improved the ResNet by the band attention to highlight features of wavelet coefficients. Second, a fault diagnosis framework based on channel attention is designed to effectively improve the nonlinear feature extraction ability of deep convolutional networks. The proposed method is verified by a simulation dataset of the drivetrain diagnostic simulator (DDS) and the measured data from a wind farm. The results illustrate the superior performance of the HA-ResNet based fault diagnosis method for time–frequency feature extraction of vibration signals, frequency band information enhancement, and recognition accuracy improvement.

Enhanced multiresolution wavelet analysis of complex dynamics in nonlinear systems.

Multiresolution wavelet analysis (MWA) is a powerful data processing tool that provides a characterization of complex signals over multiple time scales. Typically, the standard deviations of wavelet coefficients are computed depending on the resolution level and such quantities are used as measures for diagnosing different types of system behavior. To enhance the capabilities of this tool, we propose a combination of MWA with detrended fluctuation analysis (DFA) of detail wavelet coefficients. We find that such an MWA&DFA approach is capable of revealing the correlation features of wavelet coefficients in independent ranges of scales, which provide more information about the complex organization of datasets compared to variances or similar statistical measures of the standard MWA. Using this approach, we consider changes in the dynamics of coupled chaotic systems caused by transitions between different types of complex oscillations. We also demonstrate the potential of the MWA&DFA method for characterizing different physiological conditions by analyzing the electrical brain activity in mice.

Localisation of inter-layer partial discharges in transformer windings by logistic regression and different features extracted from current signals

Partial discharge (PD) investigations can identify and localise incipient failures in power transformers early, thus avoiding considerable financial losses. The feature extraction of PD signals is a fundamental step for the development of such location techniques since it directly influences the performance of a location method. This study presents a detailed comparative analysis of four traditional approaches for the obtaining of attributes towards a better set of signal features for the location of PDs. The approaches were critically compared regarding their ability to locate experimentally generated discharges between adjacent layers of a prototype winding. In order to perform such analysis, a localisation structure based on logistic regression models was elaborated, capable of determining both layers and sections of the winding affected by PDs and easily applicable in practice. The results show energy features of wavelet coefficients, obtained through the decomposition of high-frequency current signals acquired at the winding endings, achieve better performance in the PD localisation, accurately indicating discharge occurrence points among layers and sections of the winding.

Deep learning based method for false data injection attack detection in AC smart islands

This paper investigates the false data injection attacks (FDIA) in an AC smart island and the detection solution of the attack on distributed energy resources in a smart island. In this study, a new scheme of FDIA detection is proposed based on wavelet singular values as input index of deep learning algorithm. In the proposed method, switching surface based on sliding mode control breaks down for adjusting accurate factors of wavelet transform and then features of wavelet coefficients are extracted by singular value decomposition. Indexes are determined according to the wavelet singular values in switching surface of voltage and current which defines the input indexes of deep machine learning and detecting FDIA. This cyber-protection plan has been put forward for cyber diagnostic and examined in different types of attacks happening in voltage and current signals derivation of measuring sensors as well as sending and receiving data from communication and control systems. The main priority of the suggested detection plan is the high capability to detect FDIA with a high accuracy. To show the effectiveness of the proposed method, simulation studies are performed on AC smart island in MATLAB/Simulink environment.

Biometric human recognition system based on ECG

The ECG (electrocardiogram) is an emerging technology for biometric human identification. In this paper, the performance of an ECG biometric recognition system is evaluated. Signal processing techniques are utilized to extract the ECG features. In preprocessing stage, digital filters eliminate the noises and hence improve the signal to noise ratio. The process of ventricular complex (QRS Complex) detection depends on Pan and Tompkins approach that achieves an efficient QRS detection, and hence enhancing the feature extraction process. The main classifiers applied to the extracted features are Neural Network (NN), Fuzzy Logic (FL), Nearest Mean Classifier (NMC), Linear Discriminant Analysis (LDA), and Euclidean Distance (ED) are utilized to classify QRS fragments. ECG of an unknown subject is acquired; the classifiers are applied to wavelet coefficient features set between the unknown subject and all enrolled subjects. The Performance of the different approaches is evaluated by utilizing Sensitivity, Specificity, and efficiency, EER (Equal Error Rate) and ROC (Receiver Operating Characteristic) curve. The experiments are conducted on 112 individuals MIT-BIH database and the accuracy is up to 98.99%.

A Model for Yellow Tea Polyphenols Content Estimation Based on Multi-Feature Fusion

Polyphenols are one of the important ingredients determining the quality of tea, which play an important role in affecting tea quality standards and quality control. At present, NIR spectroscopy technology has been widely used in tea quality detection to achieve good results. However, due to the lack of spatial features, it is difficult to meet the accuracy requirements to comprehensively judge the quality of both inside and outside of tea. With the development of hyperspectral imaging system (HIS), although progress has been made in the estimation of tea texture based on gray level co-occurrence matrix (GLCM) extraction, there are still some obstacles in practical applications. When the resolution is low, the texture features of the image are not significantly different, and a small number of features cannot more fully represent the image features, resulting in lower model accuracy. When the resolution is higher, the increase in the dimension of the feature leads to a more complex model. Therefore, it is necessary to extract multi-scale features from the hyperspectral image while preserving the original information of the hyperspectral image. In this study, a multi-feature fusion method is proposed to improve the accuracy of tea polyphenols content estimation. The process includes multi-scale wavelet decomposition, and feature fusion based on wavelet coefficient features, GLCM texture features and wavelet texture features. Experiments were carried out on five kinds of yellow tea by comparing different models based on different features, including partial least squares regression (PLSR) and support vector regression (SVR). Results indicated that the model based on multi-feature fusion is more accurate than the individual indicators, and models based on SVR perform better than PLSR.

Condition monitoring of bevel gear box using Morlet wavelet coefficients and naïve Bayes classifier

A naive Bayes classifier is used for classifying the faults of a gear box. The rotating equipment like gear box has enough scope for condition monitoring its conditions as it plays a significant role as a prime mover in many engineering applications. This paper discusses about the extraction of Morlet wavelet coefficients from the vibration signal for different conditions of the gear box under investigation, and application of naive Bayes classifier for its condition monitoring and diagnostics. In this paper fault diagnostics of spur bevel gear box is treated as a pattern classification problem. The major steps in pattern classification are feature extraction, and classification. This work investigates the usefulness of statistical features of Morlet wavelet coefficients and naive Bayes for classification. The results show that the developed method can reliably diagnose different conditions of the gear box and the algorithm can be applied for online applications of supervised machine learning.

Condition monitoring of bevel gear box using Morlet wavelet coefficients and naïve Bayes classifier

A naïve Bayes classifier is used for classifying the faults of a gear box. The rotating equipment like gear box has enough scope for condition monitoring its conditions as it plays a significant role as a prime mover in many engineering applications. This paper discusses about the extraction of Morlet wavelet coefficients from the vibration signal for different conditions of the gear box under investigation, and application of naïve Bayes classifier for its condition monitoring and diagnostics. In this paper fault diagnostics of spur bevel gear box is treated as a pattern classification problem. The major steps in pattern classification are feature extraction, and classification. This work investigates the usefulness of statistical features of Morlet wavelet coefficients and naïve Bayes for classification. The results show that the developed method can reliably diagnose different conditions of the gear box and the algorithm can be applied for online applications of supervised machine learning.

Using wavelet analysis of hyperspectral remote-sensing data to estimate canopy chlorophyll content of winter wheat under stripe rust stress

ABSTRACTChlorophyll content can be used as an indicator to monitor crop diseases. In this article, an experiment on winter wheat stressed by stripe rust was carried out. The canopy reflectance spectra were collected when visible symptoms of stripe rust in wheat leaves were seen, and canopy chlorophyll content was measured simultaneously in laboratory. Continuous wavelet transform (CWT) was applied to process the smoothed spectral and derivative spectral data of winter wheat, and the wavelet coefficient features obtained by CWT were regarded as the independent variable to establish estimation models of chlorophyll content. The hyperspectral vegetation indices were also regarded as the independent variable to build estimation models. Then, two types of models above-mentioned were compared to ascertain which type of model is better. The cross-validation method was used to determine the model accuracies. The results indicated that the estimation model of chlorophyll content, which is a multivariate linear model constructed using wavelet coefficient features extracted by Mexican Hat wavelet function processing the smoothed spectrum (WSMH1 and WSMH2), is the best model. It has the highest estimation accuracy with modelled coefficient of determination (R2) of 0.905, validated R2 of 0.913, and root mean square error (RMSE) of 0.288 mg fg−1. The univariate linear model built by wavelet coefficient feature of WSMH1 is secondary and the modelled R2 is 0.797, validated R2 is 0.795, and RMSE is 0.397 mg fg−1. Both estimation models are better than those of all hyperspectral vegetation indices. The research shows that the feature information of canopy chlorophyll content of winter wheat can be captured by wavelet coefficient features which are extracted by the method of CWT processing canopy reflectance spectrum data. Therefore, it could provide theoretical support on detecting diseases of crop by remote sensing quantitatively estimating chlorophyll content.

EEG emotion recognition using reduced channel wavelet entropy and average wavelet coefficient features with normal Mutual Information method.

Recognizing emotion from EEG signals is a complicated task that requires complex features and a substantial number of EEG channels. Simple algorithms to analyse the feature and reduce the EEG channel number will give an indispensable advantages. Therefore, this study explores a combination of wavelet entropy and average wavelet coefficient (WEAVE) as a potential EEG-emotion feature to classify valence and arousal emotions with the advantage of the ability to identify the occurrence of a pattern while at the same time identify the shape of a pattern in EEG emotion signal. The complexity of the feature was reduced using the Normalized Mutual Information (NMI) method to obtain a reduced number of channels. Classification with the WEAVE feature achieved 76.8% accuracy for valence and 74.3% for arousal emotion, respectively. The analysis with NMI shows that the WEAVE feature has linear characteristics and offers possibilities to reduce the EEG channels to a certain number. Further analysis also reveals that detection of valence emotion with reduced EEG channels has a different combination of EEG channels compared to arousal emotion.

Transforming the SMV model into MMV model based on the characteristics of wavelet coefficients

Sparse signal recovery or compressed sensing (CS) theory has recently received attention in the image compression field. CS has proven that the successful recovery rate of the multiple measurement vectors (MMVs) model is higher than that of the single measurement vector (SMV) case. Most existing algorithms have focused on sparse signal recovery using the MMV model, without considering converting the general SMV model into the MMV model. In this study, a simple transforming model that takes advantage of the correlations among wavelet coefficients is proposed, such that the MMV model can be used for general images rather than only certain special signals. To further enhance the performance of the MMV model, the improved MMV model based on the similarity of image blocks is proposed. Simulation results have shown that the obtained solution matrix can be used in the MMV model, and that the proposed algorithm provides better reconstruction quality than many state-of-the-art algorithms.

Single Trial EEG Patterns for the Prediction of Individual Differences in Fluid Intelligence.

Assessing a person's intelligence level is required in many situations, such as career counseling and clinical applications. EEG evoked potentials in oddball task and fluid intelligence score are correlated because both reflect the cognitive processing and attention. A system for prediction of an individual's fluid intelligence level using single trial Electroencephalography (EEG) signals has been proposed. For this purpose, we employed 2D and 3D contents and 34 subjects each for 2D and 3D, which were divided into low-ability (LA) and high-ability (HA) groups using Raven's Advanced Progressive Matrices (RAPM) test. Using visual oddball cognitive task, neural activity of each group was measured and analyzed over three midline electrodes (Fz, Cz, and Pz). To predict whether an individual belongs to LA or HA group, features were extracted using wavelet decomposition of EEG signals recorded in visual oddball task and support vector machine (SVM) was used as a classifier. Two different types of Haar wavelet transform based features have been extracted from the band (0.3 to 30 Hz) of EEG signals. Statistical wavelet features and wavelet coefficient features from the frequency bands 0.0–1.875 Hz (delta low) and 1.875–3.75 Hz (delta high), resulted in the 100 and 98% prediction accuracies, respectively, both for 2D and 3D contents. The analysis of these frequency bands showed clear difference between LA and HA groups. Further, discriminative values of the features have been validated using statistical significance tests and inter-class and intra-class variation analysis. Also, statistical test showed that there was no effect of 2D and 3D content on the assessment of fluid intelligence level. Comparisons with state-of-the-art techniques showed the superiority of the proposed system.

Target Detection Using Multi Resolution Analysis for Camouflaged Images

Target detection is a challenging problem having many applications in defense and civil. Most of the targets in defense are camouflaged. It is difficult for a system to detect camouflaged targets in an image. A novel and constructive approach is proposing to detect object in camouflage images. This method uses various methodologies such as 2-D DWT, gray level co-occurrence matrix (GLCM), wavelet coefficient features, region growing algorithm and canny edge detection. Target detection is achieved by calculating wavelet coefficient features from GLCM of transformed sub blocks of the image. Seed block is obtained by evaluating wavelet coefficient features. Finally the camouflage object is highlighted using image processing schemes. The proposed target detection system is implemented in Matlab 7.7.0 and tested on different kinds of images.

Epileptic Focus Localization Using Discrete Wavelet Transform Based on Interictal Intracranial EEG

Over the past decade, with the development of machine learning, discrete wavelet transform (DWT) has been widely used in computer-aided epileptic electroencephalography (EEG) signal analysis as a powerful time-frequency tool. But some important problems have not yet been benefitted from DWT, including epileptic focus localization, a key task in epilepsy diagnosis and treatment. Additionally, the parameters and settings for DWT are chosen empirically or arbitrarily in previous work. In this work, we propose a framework to use DWT and support vector machine (SVM) for epileptic focus localization problem based on EEG. To provide a guideline in selecting the best settings for DWT, we decompose the EEG segments in seven commonly used wavelet families to their maximum theoretical levels. The wavelet and its level of decomposition providing the highest accuracy in each wavelet family are then used in a grid search for obtaining the optimal frequency bands and wavelet coefficient features. Our approach achieves promising performance on two widely-recognized intrancranial EEG datasets that are also seizure-free, with an accuracy of 83.07% on the Bern-Barcelona dataset and an accuracy of 88.00% on the UBonn dataset. Compared with existing DWT-based approaches in epileptic EEG analysis, the proposed approach leads to more accurate and robust results. A guideline for DWT parameter setting is provided at the end of the paper.