Wavelet Energy Features Research Articles

Non-Invasive Method-Based Estimation of Battery State-of-Health with Dynamical Response Characteristics of Load Surges

Battery state-of-health (SOH) estimation is an effective approach to evaluate battery reliability and reduce maintenance costs for battery-based backup power supply systems. This paper proposes a novel SOH estimation method for batteries, which only uses the response characteristics of load surges and is, therefore, non-destructive to the estimated battery and its system. The discrete wavelet transform (DWT) method based on multi-resolution analysis (MRA) is used for wavelet energy features extraction, and the fuzzy cerebellar model neural network (FCMNN) is introduced to design the battery SOH estimator. The response voltage signals to load surges are used in the training and detection process of the FCMNN. Compared to conventional methods, the proposed method only exploits characteristics of online response signals to the inrush currents rather than injecting interference signals into the battery. The effectiveness of the proposed method is validated by detailed simulation analysis and experiments.

Spectrum sensing in cognitive radio networks using an ensemble of machine learning frameworks and effective feature extraction

From the signal received on a particular frequency band, spectrum sensing (SS) is used in cognitive radio (CR) to assess whether the primary user (PU) is using the spectrum and, consequently, whether the secondary user (SU) can utilize the spectrum. The main issue with SS is determining the presence of the primary signal in a low signal-to-noise ratio (SNR). Compared to conventional technologies, machine learning techniques are more effective and accurate at identifying the qualities of input data. This paper proposes a machine learning (ML) based SS model for CR with effective feature extraction and reduction techniques. The proposed work comprises five phases: noise removal, wavelet transform, feature extraction, dimensionality reduction, and classification. Firstly, noise filtering is done on the received signal to remove the noise present in the input signal using the filters such as moving median filter (MMF), Gaussian filter (GF), and Gabor filter (GBF). After that, the filtered signal is transformed into a wavelet domain using Discrete Wavelet Transform (DWT) algorithm. Then the statistical features such as average absolute value, wavelet energy, variance, standard deviation, and peak value features are extracted from the DWT. Next, the dimensionality reduction (DR) is performed using Linear Discriminant Analysis (LDA). Finally, the classification is performed using the ensemble ML classifiers such as Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbour (KNN), which classify whether the PU signal is active or not. Simulations are carried out to analyze the efficiency of the presented models for SS. The results proved that SVM obtains the best performance for SS with higher accuracy and lower SNR.

A FOREST FIRE IDENTIFICATION METHOD FOR UNMANNED AERIAL VEHICLE MONITORING VIDEO IMAGES

An automatic forest fire monitoring system based on UAV (unmanned aerial vehicle) acquired video images was studied in this paper. This novel method was proposed to address current problems in forest fire information monitoring practices such as poor real-time performance and low efficiency. Besides, it aims to realize the dynamic monitoring of forest fires in wild environment. In this paper, a forest fire monitoring method based on active analysis of UAV-acquired video image features is proposed to automatically detect and identify the occurrence of forest fires. The motion detection method based on dense optical flow and background modeling method were used to extract the motion regions for eliminating the influence of image background. By using wavelet energy feature and texture feature, 9 video images acquired by multi-rotor UAV on forest fire monitoring were selected as sample images (8 images for experiment and 1 image for contrast purpose). The mean values and standard deviations of the gray level co-occurrence matrix eigen values (angular second moment, entropy moment and reciprocal differential moment) were calculated as the discriminate basis for identifying forest fires. The experimental results showed that the proposed algorithm can effectively identify the forest fire, which provides a theoretical guarantee for the forest resources protection.

Laser ultrasonics and machine learning for automatic defect detection in metallic components

This paper develops an automatic and reliable nondestructive evaluation (NDE) technique that enables quantification of the width and depth of subsurface defects of metallic components simultaneously by using non-contact laser ultrasonic technique and identified machine learning (ML) algorithm. Twenty-two specimens with various subsurface defect dimensions are designed and fabricated for laser ultrasonic experiments, and a total of 220 labeled laser ultrasonic signals are obtained for training and verifying ML models. Twelve features, including four time-domain features (maximum, minimum, peak-to-peak, and |Neg|/Pos value of the laser generated Rayleigh ultrasonic waves) and eight wavelet energy features, are identified and extracted as sensitive feature vectors for establishing the dataset. The principal component analysis (PCA) is implemented as dimensionality reduction method of feature vectors to optimize the recognition algorithm and improve the detection accuracy. Three widely used ML models in NDE, adaptive boosting (Adaboost), extreme gradient boosting (XGBboost), and support vector machine (SVM), combined with the PCA are proposed and compared for detecting both the width and depth of subsurface defects. The PCA-XGBoost achieves the highest recognition rate of 98.48%, and is therefore identified as the most effective approach for analyzing laser-ultrasonic signals. Unlike published reports, the proposed model is trained and evaluated with experimental data covered various classification labels, which is more adaptive and reliable in practical application than the models established using simulated data or limited experimental data. In other applications, as long as sufficient laser ultrasonic data with regards to various defect properties (dimensions, orientations, locations, shapes, etc.) can be acquired, the developed approach can realize accurate detection of corresponding defects.

On the Minimal Amount of EEG Data Required for Learning Distinctive Human Features for Task-Dependent Biometric Applications.

Biometrics is the process of measuring and analyzing human characteristics to verify a given person's identity. Most real-world applications rely on unique human traits such as fingerprints or iris. However, among these unique human characteristics for biometrics, the use of Electroencephalogram (EEG) stands out given its high inter-subject variability. Recent advances in Deep Learning and a deeper understanding of EEG processing methods have led to the development of models that accurately discriminate unique individuals. However, it is still uncertain how much EEG data is required to train such models. This work aims at determining the minimal amount of training data required to develop a robust EEG-based biometric model (+95% and +99% testing accuracies) from a subject for a task-dependent task. This goal is achieved by performing and analyzing 11,780 combinations of training sizes, by employing various neural network-based learning techniques of increasing complexity, and feature extraction methods on the affective EEG-based DEAP dataset. Findings suggest that if Power Spectral Density or Wavelet Energy features are extracted from the artifact-free EEG signal, 1 and 3 s of data per subject is enough to achieve +95% and +99% accuracy, respectively. These findings contributes to the body of knowledge by paving a way for the application of EEG to real-world ecological biometric applications and by demonstrating methods to learn the minimal amount of data required for such applications.

Elevator Running Fault Monitoring Method Based on Vibration Signal

According to the one-dimensional characteristics of the vibration signal, this paper proposes an elevator operation fault monitoring method based on one-dimensional convolutional neural network (1-DCNN). It can solve the problems of traditional elevator fault monitoring methods that require complex feature extraction processes and a large amount of diagnostic experience. Because the elevator fault monitoring field has less fault information, it is different from the large sample situation in the field of face recognition. Aiming at the problem of small samples, this paper first preprocesses elevator vibration signals through singular value decomposition (SVD) and wavelet transform, then uses wavelet transform to extract wavelet energy features of the original vibration signals, and then use PCA to reduce the feature data to the dimension with a cumulative contribution rate of greater than 85%. When reducing the dimensionality, the original characteristics of the features are preserved as much as possible. When designing the 1-CNN, the K-fold cross-validation method is added to obtain as many abnormalities from the sample set as possible. The information is finally trained using the 1-CNN and classified by softmax regression. In order to verify the performance of the algorithm, the original vibration signal was used as the input of the 1-CNN, and the wavelet energy feature without PCA dimensionality reduction was used as the input of the 1-CNN. The experimental results showed that the 1-DCNN model with PCA dimension-reduced feature data as input can effectively extract and identify the features of normal and abnormal states and has high fault identification accuracy, and good results have been obtained.

A progressive deep wavelet cascade classification model for epilepsy detection

Automatic epileptic seizure detection according to EEG recordings is helpful for neurologists to identify an epilepsy occurrence in the initial anti-epileptic treatment. To quickly and accurately detect epilepsy, we proposed a progressive deep wavelet cascade classification model (PDWC) based on the discrete wavelet transform (DWT) and Random Forest (RF). Different from current deep networks, the PDWC mimics the progressive object identification process of human beings with recognition cycles. In every cycle, enhanced wavelet energy features at a specific scale were extracted by DWT and input into a set of cascade RF classifiers to realize one recognition. The recognition accuracy of PDWC is gradually improved by the fusion of classification results produced by multiple recognition cycles. Moreover, the cascade structure of PDWC can be automatically determined by the classification accuracy increment between layers. To verify the performance of the PDWC, we respectively applied five traditional schemes and four deep learning schemes to four public datasets. The results show that the PDWC is not only superior than five traditional schemes, including KNN, Bayes, DT, SVM, and RF, but also better than deep learning methods, i.e. convolutional neural network (CNN), Long Short-Term Memory (LSTM), multi-Grained Cascade Forest (gcForest) and wavelet cascade model (WCM). The mean accuracy of PDWC for all subjects of all datasets reaches to 0.9914. With a flexible structure and less parameters, the PDWC is more suitable for the epilepsy detection of diverse EEG signals.

Pixel Prediction-Based Image Steganography Using Crow Search Algorithm-Based Deep Belief Network Approach

Securing the confidentiality of patient information using the image steganography process has gained more attention in the research community. However, embedding the patient information is a major task in the steganography process due to the complexity in identifying the pixel features. Thus, an effective Crow Search Algorithm-based deep belief network (CSA-DBN) is proposed for embedding the information in the medical image. Initially, the appropriate pixels and the features, like pixel coverage, wavelet energy, edge information, and texture features, such as local binary pattern (LBP) and local directional pattern (LDP), are extracted from each pixel. The proposed CSA-DBN utilizes the feature vector and identifies the suitable pixels used for embedding. The patient information is embedded into the image by using the embedding strength and the DWT coefficient. Finally, the embedded information is extracted using the DWT coefficient. The analysis of the proposed CSA-DBN approach is done based on the performance metrics, such as correlation coefficient, peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) that acquired the average values as 0.9471, 24.836[Formula: see text]dB, and 0.4916 in the presence of salt and pepper noise and 0.9741, 57.832[Formula: see text]dB, and 0.9766 in the absence of noise.

A Fault Diagnosis Method of Rolling Bearing Integrated with Cooperative Energy Feature Extraction and Improved Least-Squares Support Vector Machine

To solve the problem that the bearing fault of variable working conditions is challenging to identify and classify in the industrial field, this paper proposes a new method based on optimization of multidimension fault energy characteristics and integrates with an improved least-squares support vector machine (LSSVM). First, because the traditional wavelet energy feature is difficult to effectively reflect the characteristics of rolling bearing under different working conditions, based on analyzing the wavelet energy feature extraction in detail, a collaborative method of multidimension fault energy feature extraction combined with the method of Transfer Component Analysis (TCA) is constructed, which improves the discrimination between the different features and the compactness between the same features of rolling bearing faults. Then, for solving the problem of the local optimal of particle swarm optimization (PSO) in fault diagnosis and recognition of rolling bearing, an improved LSSVM based on particle swarm optimization and wavelet mutation optimization is established to realize the collaborative optimization and adjustment of LSSVM dynamic parameters. Based on the improved LSSVM and optimization of multidimensional energy characteristics, a new method for fault diagnosis of rolling bearing is designed. Finally, the simulation and analysis of the proposed algorithm are verified by the experimental data of different working conditions. The experimental results show that this method can effectively extract the multidimensional fault characteristics under variable working conditions and has a high fault recognition rate.

MLWAVE: A novel algorithm to classify primary versus secondary asphyxia-associated ventricular fibrillation

Introduction/HypothesisThe outcome of cardiopulmonary resuscitation (CPR) depends on timely recognition of the underlying cause of cardiac arrest. Ventricular fibrillation (VF) waveform analysis to differentiate primary VF from secondary asphyxia-associated VF may allow tailoring of therapies to improve cardiac arrest outcomes. Therefore, the primary goal of this investigation was to develop a novel technique utilizing wavelet synchrosqueezed transform (WSST) and decision-tree classifier that was specifically adapted to discriminate between these two incidents of VF. MethodsSecondary analytical investigation of electrocardiography (ECG) data obtained from swine models of either primary VF (n=18) or secondary asphyxia-associated VF (7min of asphyxia prior to VF induction; n=12). In the primary analysis, WSST technique was applied to the first 35s of the VF ECG signal to identify the most differentiating characteristics of the signal for use as features to develop a machine learning algorithm to classify the arrest as either primary VF vs. secondary asphyxia-associated VF. The performance of this new interactive Machine Learning algorithm with Wavelet Energy features of ECG (MLWAVE) was assessed using both classification accuracy and area under the receiver operating characteristic curve (AUCROC). To evaluate the validity of the new technique, the amplitude spectrum area (AMSA)-based technique, a well-established defibrillation classification method, was also applied to the same ECG signals. The classification accuracy and AUCROC were then compared between the two techniques. ResultsFor the primary analysis evaluating the first 35s of the VF waveform, the MLWAVE technique classified the type of VF with high accuracy (28/28 [100%], AUCROC: 1.00). The MLWAVE technique performed better than the AMSA technique across all comparisons, but given the small sample sizes, differences were not statistically significant (accuracy: 100% vs. 85.7%; p=0.24; AUCROC: 1.00 vs. 0.82; p=0.24). ConclusionThis analytical investigation illustrates the advantages of the MLWAVE signal processing method which was associated with 100% accuracy in classifying the type of VF waveform: primary vs. asphyxia-associated. Such classification could lead to personalized tailoring of resuscitation (e.g., immediate defibrillation vs. continued CPR and treatment of reversible cardiac arrest causes before defibrillation) to improve outcomes for cardiac arrest.

Ultra-High Frequency Partial Discharge Signal Recognition in GIS based on Fisher Linear Discriminant Theory

In this paper, dual tree complex wavelet transform (DT-CWT) is used to decompose UHF partial discharge (PD) signal in multi-scale. The optimal decomposition level of complex wavelet is solved. The wavelet energy features of real part and imaginary part of UHF-PD signal under the optimal decomposition scale are extracted. Fisher linear discriminant method is used to select the features of energy features and to identify the PD types. The results show that the optimized real part and imaginary part high frequency wavelet energy features can effectively identify four kinds of typical insulation defects, and the recognition rate can reach to 92.5%. Meanwhile, the optimal complex wavelet energy (OCWEF) feature has better sensitivity and recognition effect in PD type identification.

A decision support system for automatic sleep staging from HRV using wavelet packet decomposition and energy features

Heart rate variability (HRV) can reflect the relationship between heart rhythm and sleep structure. In order to achieve long-term effective monitoring of sleep and to solve the generalization problem of sleep staging algorithms, HRV signals were used to identify the wake, non-rapid eye movement (NREM) and rapid eye movement (REM) stages of two databases with 11,597 epoches of 16 subjects (8 healthy subjects and 8 sleep disorder). Features were extracted from HRV using three different methods: Hilbert Huang Transform (HHT), Singular Value Decomposition (SVD), and Wavelet Packet Decomposition (WPD). The extracted features were reconstructed into a new sleep score table, classified using random forest (RF) classifier and the results were interpreted using basic statistical criteria. Among these methods, the WPD extraction feature is the most successful. For the sleep staging model trained in the first database, the accuracy of Wake, NREM and REM after WPD extraction features were 80.9%, 88.2% and 65.8% respectively. The second databases were tested using a trained model, in which the Avg.Acc, Avg.Precision, Avg.F and Kappa statistic for healthy subjects were 72.9%, 0.720, 0.716 and 0.439 ± 0.0346. The standard explanations for sleep disorder subjects were 77.8%, 0.780, 0.843 and 0.656 ± 0.0324. The experimental results show that the energy characteristics of WPD extraction are the best. In addition, there was a significant difference in Kappa values (p < 0.05) between healthy subjects and sleep disorder subjects by variance analysis of standard interpretation, and it can be used as a basis for judging whether a subject has a sleep disorder.

Ensemble Heterogeneous Feature Selection (EHFS) and Heterogeneous Ensemble Classifier with VOTE (HECV) for Automatic Detection of Snore Sounds

Obstructive Sleep Apnea (OSA) is generally considered as a sleep co-related breathing difficulty with some important well known disabling indication. This research work tends to differentiate the condition of OSA victims. The significant work is to propose an innovative Heterogeneous Ensemble Classifier with Velum Oropharyngeal Tongue Epiglottis (HECV) method with a high level of effectiveness. In the formulated study, data recording, features extraction, multifeature selection, classification and performance evaluation are the five stages of processing. At the initial stage, the noises represented in the audio signals which were eliminated through Adaptive Fuzzy Median Filter (AFMF) algorithm. After thatCrest Factor, original Frequency, Spectral Frequency Features, Subband Energy Ratio, Mel-Scale Frequency Cepstral Coefficients (MFCC), Empirical Mode Decomposition (EMD) Features, and Wavelet Energy Features are collected from the noise suppressed audio signals and inputs are fed into Ensemble Heterogeneous Feature Selection (EHFS) technique. EHFS algorithm fuses the outputs of filter and wrapper oriented feature selection methods. These identified features are classified using HECV technique which renders a good classification outputs by validation without the regard of subjects. The outputs show that the formulated HECV approach gives better performance in snore detection when co-related with other classifiers.

Wavelet energy feature based source camera identification for ear biometric images

In this paper a source camera identification algorithm for ear biometric images has been proposed based on tunable filter bank as a feature extractor. Maintaining the frequency selectivity property, distinct features are extracted by this filter bank, based on a half-band polynomial of 14th order. With the help of four ear databases, it is demonstrated that tunable filter bank based features correctly identify the sources of ear images with an average accuracy of 99.25% when there are limited number of camera sources available. It is also shown that accuracy would fall when significantly large number of cameras are introduced to acquire ear images. Depending on the experimental results, it can be well concluded that tunable filter bank based feature, apart from its recognition performance, is also a promising candidate to support forensic validation of camera source.

Neural correlates of action video game experience in a visuospatial working memory task

Studies have shown improved cognitive performance of action video game players (AVGPs); however, the corresponding neural correlates are still unclear. The present study aims to investigate whether the unsupervised training on action video games contributes to the visuomotor adaptation of working memory or not, considering neural measures. Twenty-seven-Channel electroencephalogram (EEG) signals from 35 participants are recorded while performing Corsi block-tapping task (CBTT), a working memory task incorporating recall of visual and sequential–spatial information, and are analyzed employing wavelet transform-based feature extraction techniques. For removing artifacts, we have used the wavelet denoising method. Different mother wavelet functions, with different thresholding algorithms, are compared. The dmeyer mother wavelet function along with Rigorous SURE soft thresholding emerged as the best combination for denoising. Comparison of wavelet energy features has revealed improved rhythmic activity in AVGPs. Also, two measures of engagement index β/(α + θ) and β/α are computed which has provided good classification accuracies with ANFIS classifier. Higher engagement indexes are found in the frontal, right parietal and occipital cortex of AVGPs. These results evidence the neurocortical modulation among the players that may attribute to the effective cognitive processes in AVGPs related to the task.

Black tea classification employing feature fusion of E-Nose and E-Tongue responses

In this article, wavelet energy feature (WEF) has been extracted from the responses of e-nose and e-tongue for the classification of different grades of Indian black tea. For WEF, different decomposition levels of wavelet packet transform have been tested for both the systems and performance is evaluated with K- Nearest Neighbors classifier. Energy features of the best-suited decomposition level for e-nose and e-tongue have been calculated and fused to get a combined sensor response. Results confirm that the clustering nature (PCA plot) and classification accuracy (10-fold cross-validated based on KNN) have improved (accuracy 99.75%) with the applied method on the combined data. Moreover, this method is compared with some benchmark classification methods namely PLS-DA and Sammon's projection method which exhibits the superiority of the WEF extraction method combining the responses of multi sensory system.

A combined support vector machine-FCGS classification based on the wavelet transform for Helitrons recognition in C.elegans

The Helitrons, an important sub-class of the transposable elements (TEs) class II, have been revealed in diverse eukaryotic genomes. They are mobile elements with great impact on genomic evolution. Till today, there is no systematic classification model of helitrons; that’s why we thought of creating an efficient automatic model to identify these sequences. This paper focuses on the discrimination between helitrons and non-helitrons using the Support Vector Machine (SVM). In this study, we use all the SVM kernels and the higher accuracy rates are obtained by reaching the optimal kernels-parameters (d, c and σ). Further, we introduce two methods to represent the genomic sequences in the form of features to be considered later for the classification task: (i) the temporal and the spectral features extracted from the Frequency Chaos Game Signals order 2 (FCGS2) (ii) the features extracted from the Continuous Wavelet Transform (CWT) applied to the FCGS2 signals. The dataset we used regards two types DNA classes in C.elegans: the helitrons and the repetitive DNA sequences that contain microsatellites and do not form helitrons. The classification results prove that the wavelet energy feature is more effective than the FCGS2 features in the helitron’s recognition system. The performance of our system achieves a high recognition rate (Globally accuracy rate) reaching the value of 92.27%.

Wavelet Energy and Shape Features for Plants Recognition

This work presents plants recognition system with rotation invariant based on plant leaf. Wavelet energy features are extracted for sub-images (blocks) beside three of leaf shape features: [area, perimeter, circularity ratio]. (8) species of leaves are used in different size and color, (15) samples for each leaf are used. Leaves images are rotated at angles: 90?, 180?, 270?(counterclockwise,clockwise). Euclidean distance is used, the recognition rate was 98.2% with/without rotation.

Classification of tumor based on magnetic resonance (MR) brain images using wavelet energy feature and neuro-fuzzy model

The brain is the organ that coordinates all the activities that occur in our bodies. Small abnormalities in the brain will affect body activity. Tumor of the brain is a mass formed a result of cell growth not normal and unbridled in the brain. MRI is a non-invasive medical test that is useful for doctors in diagnosing and treating medical conditions. The process of classification of brain tumor can provide the right decision and correct treatment and right on the process of treatment of brain tumor. In this study, the classification process performed to determine the type of brain tumor disease, namely Alzheimer’s, Glioma, Carcinoma and normal, using energy coefficient and ANFIS. Process stages in the classification of images of MR brain are the extraction of a feature, reduction of a feature, and process of classification. The result of feature extraction is a vector approximation of each wavelet decomposition level. The feature reduction is a process of reducing the feature by using the energy coefficients of the vector approximation. The feature reduction result for energy coefficient of 100 per feature is 1 x 52 pixels. This vector will be the input on the classification using ANFIS with Fuzzy C-Means and FLVQ clustering process and LM back-propagation. Percentage of success rate of MR brain images recognition using ANFIS-FLVQ, ANFIS, and LM back-propagation was obtained at 100%.

A novel local wavelet energy mesh pattern (LWEMeP) for heterogeneous face recognition

This paper proposes a novel and accurate methodology for matching of heterogeneous faces, such as sketch–photo and near infrared (NIR)-visible (VIS) images. Inspired from mesh topology in computer networking, a new local binary pattern has been developed. We call it derived local mesh pattern (DLMeP). DLMeP is computed based on the relationship among each and every pixel present in a local window. For heterogeneous face recognition, more emphasis is given to the edge and texture features, because these features could be extracted invariant to different modalities. The wavelet transform is employed to capture the edge and texture features simultaneously. Then a local wavelet energy feature is calculated to enhance the local texture information and edges. Finally, DLMeP is used to measure the local variation or pattern of wavelet energy, and we call it local wavelet energy mesh pattern (LWEMeP). For refinement of LWEMeP, a model based weight value learning is suggested. We have tested the proposed methodology on different sketch–photo and NIR-VIS benchmark databases. In the case of viewed sketches, the rank-1 recognition accuracy of 99.37% is achieved on CUFSF database. LWEMeP gives the rank-1 accuracy of 65.31% on challenging e-PRIP composite sketch database. In the case of NIR-VIS matching, the rank-1 accuracy of 89.78% is achieved and which is superior to other state-of-the-art methods. Finally, proposed LWEMeP is also compared with state-of-the-art deep learning based methods in the case of composite sketch vs photo matching and NIR vs VIS matching. Superior results of the proposed feature after combining with deep learning suggest that handcrafted features combining with deep learning give excellent classification results.