Wavelet-based Feature Extraction Research Articles

Early detection of arc faults in DC microgrids using wavelet-based feature extraction and deep learning

Early detection of arc faults in DC microgrids using wavelet-based feature extraction and deep learning

WALDATA: Wavelet transform based adversarial learning for the detection of anomalous trading activities

Detecting manipulative activities in stock market trading poses a significant challenge due to the complex temporal correlations inherent to the dynamically changing stock price data. This challenge is further exacerbated by the limited availability of labelled anomalous trading data instances. Stock price manipulations, which consist of infrequent anomalies in stock price trading data, are challenging to capture due to their sporadic occurrence and dynamically evolving nature. This scarcity and inherent complexity significantly complicate the creation of labelled datasets hence hinders the development of robust detection of different stock price manipulation schemes through supervised learning methods. Overcoming these challenges is crucial for enhancing our understanding of market dynamics and implementing robust market surveillance systems. To address these challenges, we introduce a novel stock price manipulation detection approach called WALDATA (Wavelet Transform based Adversarial Learning for the Detection of Anomalous Trading Activities). We leverage the Wavelet Transform (WT) to decompose non-stationary stock price time series into informative features and capture multi-scale dynamics within the data. We encode stock price data by transforming it into scalogram images through the Continuous Wavelet Transform, effectively converting stock price time series data into a 2D image representation. Subsequently, we employ a Generative Adversarial Network (GAN) architecture, originally applied to computer vision, to learn the underlying distribution of normal trading behaviour from the encoded images. We then train the discriminator as an anomaly detector for identifying manipulative trading activities in the stock market. The efficacy of WALDATA is rigorously evaluated on diverse real-world stock datasets using 1-level tick data from the LOBSTER project and the experimental results demonstrate the significant performance of our approach achieving an average AUC of 0.99 while maintaining low false alarm rates across various market conditions. These findings not only validate the effectiveness of the proposed WALDATA approach in accurately identifying stock price manipulations but also provide investors and regulators alike with valuable insights for the development of advanced market surveillance systems. This research demonstrates the promising potential of combining wavelet-based feature extraction and stock price time series to image representation with generative adversarial learning frameworks for anomaly detection in financial time series data. The successful implementation of WALDATA contributes to the development of advanced market surveillance systems and paves the way for further advancements in market surveillance, contributing towards a more efficient and robust financial system and a fair market environment.

The Impact of Feature Extraction on Classification Accuracy Examined by Employing a Signal Transformer to Classify Hand Gestures Using Surface Electromyography Signals.

Interest in developing techniques for acquiring and decoding biological signals is on the rise in the research community. This interest spans various applications, with a particular focus on prosthetic control and rehabilitation, where achieving precise hand gesture recognition using surface electromyography signals is crucial due to the complexity and variability of surface electromyography data. Advanced signal processing and data analysis techniques are required to effectively extract meaningful information from these signals. In our study, we utilized three datasets: NinaPro Database 1, CapgMyo Database A, and CapgMyo Database B. These datasets were chosen for their open-source availability and established role in evaluating surface electromyography classifiers. Hand gesture recognition using surface electromyography signals draws inspiration from image classification algorithms, leading to the introduction and development of the Novel Signal Transformer. We systematically investigated two feature extraction techniques for surface electromyography signals: the Fast Fourier Transform and wavelet-based feature extraction. Our study demonstrated significant advancements in surface electromyography signal classification, particularly in the Ninapro database 1 and CapgMyo dataset A, surpassing existing results in the literature. The newly introduced Signal Transformer outperformed traditional Convolutional Neural Networks by excelling in capturing structural details and incorporating global information from image-like signals through robust basis functions. Additionally, the inclusion of an attention mechanism within the Signal Transformer highlighted the significance of electrode readings, improving classification accuracy. These findings underscore the potential of the Signal Transformer as a powerful tool for precise and effective surface electromyography signal classification, promising applications in prosthetic control and rehabilitation.

Wavelet-based feature extraction with hidden Markov model classification of Antarctic blue whale sounds

An approach for analyzing blue whale vocalizations in continuous acoustic recordings using wavelet transform (WT) algorithm as a feature extraction method is proposed in this study. The WT-based feature extraction technique offers a unique perspective on the frequency-time properties of whale vocalizations, enabling a comprehensive understanding of the complexity of non-stationary signals. The WT-based features are seamlessly adopted with a Hidden Markov Model (HMM) for efficient and accurate classification. Through extensive theoretical evaluation and comparison with conventional methods such as Principal Component Analysis (PCA) and Dynamic Mode Decomposition (DMD), the proposed approach demonstrates superior performance in accurately detecting and classifying blue whale calls from background noise. Furthermore, when benchmarked against state-of-the-art machine learning techniques such as Artificial Neural Network (ANN), Support Vector Machine (SVM), and Spectrogram Correlation Detector (SCD), the proposed WT-HMM detector exhibits the highest average accuracy, affirming its applicability for real-time scenarios. This study presents a valuable contribution to the field of marine bioacoustics, offering an effective solution for robust blue whale vocalization analysis.

TIFd-FR: Trends, Issues and Future directions of feature extraction in Face Recognition

Today, face recognition is the most prevalent and effective mechanism among various biometric technologies as it is non-invasive method. It helps in identifying or verifying the identity of a person by utilizing its face. But face recognition (FR) can be prone to high error rate. Therefore, efficient feature extraction methods are required for extracting robust facial features to develop efficient FR system. A FR system comprises of mainly three phases, that is, face detection and orientation, extracting facial features and classification of features. The most vital part of an efficient recognition system is extraction of robust features. Hence, extracting facial features is active research area of image processing. Although algorithms have been developed for extracting features, efficient and robust feature extraction still offers great challenge to researchers. Hence, a thorough analysis of feature extraction techniques presented in this work will enable the researchers to select the best suited technique for developing efficient system for recognition of face images. The performance of different feature extraction methods varies under variations in illumination, occlusion and pose etc. It is observed that deep-learning based feature extraction methods outperform wavelet-based methods. After rigorous analysis of various state-of-art techniques it is found that highest accuracy rate of 99.5% is achieved on AR database using wavelet based feature extraction whereas 99.78% is attained using convolutional neural network accuracy and various results achieved till now are stated.

Evaluation of wavelet-based feature extraction methods for detection and classification of power quality disturbances

The appearance of Power Quality Disturbances can cause serious damage to the utility grid. Their detection and identification are two of the major problems related to the improvement of Power Quality. This paper presents an evaluation of different combinations of wavelet-based features for the detection and classification of eight types of Single Power Quality Disturbances. A set of disturbances was generated in MATLAB through their mathematical models. The detection stage was performed using Multiresolution Analysis. The extracted features were normalized by Z-score to serve as input to four different classifiers: Multilayer Perceptron, K-Nearest Neighbors, Probabilistic Neural Network, and Decision Tree. The combination of Shannon Entropy and Log-Energy Entropy was found the best with the highest accuracy in all cases. Furthermore, the normalization stage has an impact on classification as it improves accuracy regardless of the classifier used. This fact makes it possible to reduce the computational expense by using only two types of features without compromising the accuracy.

A Novel Computer-Vision Approach Assisted by 2D-Wavelet Transform and Locality Sensitive Discriminant Analysis for Concrete Crack Detection.

This study proposes FastCrackNet, a computationally efficient crack-detection approach. Instead of a computationally costly convolutional neural network (CNN), this technique uses an effective, fully connected network, which is coupled with a 2D-wavelet image transform for analyzing and a locality sensitive discriminant analysis (LSDA) for reducing the number of features. The algorithm described here is used to detect tiny concrete cracks in two noisy adverse conditions and image shadows. By combining wavelet-based feature extraction, feature reduction, and a rapid classifier based on deep learning, this technique surpasses other image classifiers in terms of speed, performance, and resilience. In order to evaluate the accuracy and speed of FastCrackNet, two prominent pre-trained CNN architectures, namely GoogleNet and Xception, are employed. Findings reveal that FastCrackNet has better speed and accuracy than the other models. This study establishes performance and computational thresholds for classifying photos in difficult conditions. In terms of classification efficiency, FastCrackNet outperformed GoogleNet and the Xception model by more than 60 and 80 times, respectively. Furthermore, FastCrackNet's dependability was proved by its robustness and stability in the presence of uncertainties produced by network characteristics and input images, such as input image size, batch size, and input image dimensions.

The Role of Artificial Intelligence in Decoding Speech from EEG Signals: A Scoping Review.

Background: Brain traumas, mental disorders, and vocal abuse can result in permanent or temporary speech impairment, significantly impairing one’s quality of life and occasionally resulting in social isolation. Brain–computer interfaces (BCI) can support people who have issues with their speech or who have been paralyzed to communicate with their surroundings via brain signals. Therefore, EEG signal-based BCI has received significant attention in the last two decades for multiple reasons: (i) clinical research has capitulated detailed knowledge of EEG signals, (ii) inexpensive EEG devices, and (iii) its application in medical and social fields. Objective: This study explores the existing literature and summarizes EEG data acquisition, feature extraction, and artificial intelligence (AI) techniques for decoding speech from brain signals. Method: We followed the PRISMA-ScR guidelines to conduct this scoping review. We searched six electronic databases: PubMed, IEEE Xplore, the ACM Digital Library, Scopus, arXiv, and Google Scholar. We carefully selected search terms based on target intervention (i.e., imagined speech and AI) and target data (EEG signals), and some of the search terms were derived from previous reviews. The study selection process was carried out in three phases: study identification, study selection, and data extraction. Two reviewers independently carried out study selection and data extraction. A narrative approach was adopted to synthesize the extracted data. Results: A total of 263 studies were evaluated; however, 34 met the eligibility criteria for inclusion in this review. We found 64-electrode EEG signal devices to be the most widely used in the included studies. The most common signal normalization and feature extractions in the included studies were the bandpass filter and wavelet-based feature extraction. We categorized the studies based on AI techniques, such as machine learning and deep learning. The most prominent ML algorithm was a support vector machine, and the DL algorithm was a convolutional neural network. Conclusions: EEG signal-based BCI is a viable technology that can enable people with severe or temporal voice impairment to communicate to the world directly from their brain. However, the development of BCI technology is still in its infancy.

A Novel Unsupervised Data-Driven Method for Electricity Theft Detection in AMI Using Observer Meters

The smart meter data of the Advanced Metering Infrastructure (AMI) can be tampered by electricity thieves with advanced digital instruments or cyber attacks to reduce their electricity bills, which causes devastating financial losses to utilities. A novel unsupervised data-driven method for electricity theft detection in AMI is proposed in this paper. The method incorporates observer meter data, wavelet-based feature extraction, and fuzzy c-means (FCM) clustering. A new anomaly score is developed based on the degree of cluster membership information produced by FCM clustering to differentiate normal and fraudulent users.We perform an ablation study to investigate the impact of key components of the proposed method on the performance by using a publicly available smart meter dataset. The results show that all key components of the proposed method contribute significantly to the performance improvement. The proposed method is compared with a set of baselines including state-of-the-art methods by using smart meter data of both business users and residential users. The comparison results indicate that the proposed method achieves significantly better detection performance than all baseline methods. We also show that the proposed method maintains a good performance when the detection time frame is reduced from 30 days to 20 days.

Two-Step Approach to Processing Raw Strain Monitoring Data for Damage Detection of Structures under Operational Conditions.

Strain data of structural health monitoring is a prospective to be made full use of, because it reflects the stress peak and fatigue, especially sensitive to local stress redistribution, which is the probably damage in the vicinity of the sensor. For decoupling structural damage and masking effects caused by operational conditions to eliminate the adverse impacts on strain-based damage detection, small time-scale structural events, i.e., the short-term dynamic strain responses, are analyzed in this paper by employing unsupervised modeling. A two-step approach to successively processing the raw strain monitoring data in the sliding time window is presented, consisting of the wavelet-based initial feature extraction step and the decoupling step to draw damage indicators. The principal component analysis and a low-rank property-based subspace projection method are adopted as two alternative decoupling methodologies. The approach’s feasibility and robustness are substantiated by analyzing the strain monitoring data from a customized truss experiment to successfully remove the masking effects of operating loads and identify local damages even concerning accommodating situations of missing data and limited measuring points. This work also sheds light on the merit of a low-rank property to separate structural damages from masking effects by comparing the performances of the two optional decoupling methods of the distinct rationales.

A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling.

Human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. In this paper, we present a hierarchical classification framework based on wavelets and adaptive pooling for activity recognition and fall detection predicting fall direction and severity. To accomplish this, windowed segments were extracted from each recording of inertial measurements from the SisFall dataset. A combination of wavelet based feature extraction and adaptive pooling was used before a classification framework was applied to determine the output class. Furthermore, tests were performed to determine the best observation window size and the sensor modality to use. Based on the experiments the best window size was found to be 3 s and the best sensor modality was found to be a combination of accelerometer and gyroscope measurements. These were used to perform activity recognition and fall detection with a resulting weighted F1 score of 94.67%. This framework is novel in terms of the approach to the human activity recognition and fall detection problem as it provides a scheme that is computationally less intensive while providing promising results and therefore can contribute to edge deployment of such systems.

Paroxysmal atrial fibrillation prediction based on morphological variant P-wave analysis with wideband ECG and deep learning

Background and objectiveAtrial fibrillation (AF) is one of the most frequent asymptomatic arrhythmias associated with significant morbidity and mortality. Identifying the susceptibility to AF based on routine or continuous ECG recording is of considerable interest. Despite several P-wave characteristics and skin sympathetic nerve activity (SKNA) linked to AF onset, neither factor has offered accurate predictability. We propose a deep learning enabled method for AF risk prediction. MethodsWe develop a novel MVPNet to predict the upcoming onset of paroxysmal AF. MVPNet combines wavelet-based feature extraction and a deep learning classifier. MVPNet detect the approaching of AF onset by analyzing the template and frequency in P-wave segments. The morphological variant P-wave (MVP) analysis includes P-wave and SKNA features cross temporal-spectral domain. Subsequently, we designed an optimized lightweight convolutional neural network model to detect the MVP features of pre-AF episodes during sinus rhythm segments. Wideband ECG data obtained through the neuECG protocol from eight PAF patients with 177 times AF occurrence in this study. We compared the accuracy of AF prediction between ordinary ECG and neuECG. ResultsThe MVPNet effectively predicted the onset of AF episodes. 89% of ECG recorded at 5 min before the AF onset can be identified using neuECG. The proposed deep learning model, MVPNet, obtained a better precision and inference speed with less computing resources than existing models. The gradient activation map showed that neuECG recording may be a superior AF risk predictor. ConclusionsMVP analysis combined SKNA and P-wave parameters to improve predictive accuracy. The proposed MVPNet based on neuECG is superior to existing AF risk assessment with improved reliability and effectiveness. The method can be potentially applied in clinical scenarios for real-time, continuous AF prediction.

Designed orthogonal wavelet based feature extraction and classification of underlying causes of power quality disturbance using probabilistic neural network

ABSTRACT – Finding the reasons responsible behind PQ disturbances is as much important as detection of various inconspicuous PQ disturbances to have timely and accurate mitigation. Therefore, this paper proposes a robust solution for detection and classification of different voltage sag causes. For efficient feature extraction, a novel method is proposed for designing of wavelet using vector-quantised signal information to instil signal information into the wavelet. Multiresolution analysis of voltage signals is carried out to decompose voltage signals to multiple scales. In this way, sag-related information is more effectively captured and utilised in classification of voltage sag signals into one of the classes of sag causes. Probabilistic neural network is trained and tested using five-fold cross-validation on the data simulated in MATLAB/Simulink. Another challenge in PQ analysis, i.e. noisy data, is also addressed here by considering noise of 30dB in voltage sag signals. Quantitative evaluation of classifier performance using two measures, such as classification rate and false alarm rate, proves the proposed method efficient for voltage sag detection and classification.

An Empiric Analysis of Wavelet-Based Feature Extraction on Deep Learning and Machine Learning Algorithms for Arrhythmia Classification

An Empiric Analysis of Wavelet-Based Feature Extraction on Deep Learning and Machine Learning Algorithms for Arrhythmia Classification

Vision machine learning for detection of ocular pathologies from iris images

Detection of eye pathologies from the database of iris images is taken into deliberation. The images of disease affected and normal eyes are collected from High-Resolution Fundus (HRF) Image Database is analyzed and the influence of ocular diseases on iris using a reliable Fuzzy recognition scheme is proposed here. These eye images are then subjected to various image processing techniques like pre-processing for de-noising using Blind de-convolution, wavelet based feature extraction, Principal Component Analysis (PCA) for dimension reductionality, followed by fuzzy C-means clustering inference scheme to categorize the normal and diseased eyes. It is inferred that the proposed method takes only 2 minutes with an accuracy, specificity and sensitivity varying in the range of 94% to 98% respectively.

Wavelet-based feature extraction technique for classification of different shoulder girdle motions for high-level upper limb amputees

Wavelet-based feature extraction technique for classification of different shoulder girdle motions for high-level upper limb amputees

Wavelet-based feature extraction technique for classification of different shoulder girdle motions for high-level upper limb amputees

The aim of this study is to suggest a system for classification of seven classes of shoulder girdle motions for high-level upper limb amputees using pattern recognition (PR) system. In the suggested system, the wavelet transform was utilised for feature extraction and extreme learning machine (ELM) and linear discriminant analysis (LDA) were used as classifiers. The data were recorded from six intact-limbed subjects, and four amputees, with eight channels involving five electromyography (EMG) channels and 3-axis accelerometer. The study shows that the suggested pattern recognition system has the ability to classify the shoulder girdle motions with 92.67% classification accuracy for intact-limbed subjects and 87.67% classification accuracy for amputees by combining EMG and accelerometer channels. The outcomes of this study show that non-invasive PR system can help to provide control signals to drive a prosthetic arm for high level upper limb amputees.

Motor Imagery Classification using Wavelet-Based Features and Tensorflow

This paper proposes a methodology for making a decision on left and right motor imagery using Tensorflow and wavelet-based feature extraction. Wavelet coefficients are extracted by the Haar wavelet transforms from electroencephalogram (EEG) signals in the first step. In the second step, 60 wavelet-based features are extracted by the frequency distribution and the amount of variability in frequency distribution. In the final step, this paper classified left or right motion imagery using these 60 features as inputs to the Tensorflow. The proposed methodology shows that the performance result is 82.14% with 60 features in accuracy rate.

Wavelet-Based Multicomponent Denoising Profile for the Classification of Hyperspectral Images

The high resolution of the hyperspectral remote sensing images available allows the detailed analysis of even small spatial structures. As a consequence, the study of techniques to efficiently extract spatial information is a very active realm. In this paper, we propose a novel denoising wavelet-based profile for the extraction of spatial information that does not require parameters fixed by the user. Over each band obtained by a wavelet-based feature extraction technique, a denoising profile (DP) is built through the recursive application of discrete wavelet transforms followed by a thresholding process. Each component of the DP consists of features reconstructed by recursively applying inverse wavelet transforms to the thresholded coefficients. Several thresholding methods are explored. In order to show the effectiveness of the extended DP (EDP), we propose a classification scheme based on the computation of the EDP and supervised classification by extreme learning machine. The obtained results are compared to other state-of-the-art methods based on profiles in the literature. An additional study of behavior in the presence of added noise is also performed showing the high reliability of the EDP proposed.

Classification of inter-ictal and ictal EEGs using multi-basis MODWPT, dimensionality reduction algorithms and LS-SVM: A comparative study

Abstract Wavelet-based feature extraction techniques are very promising for classifying epileptic electroencephalograph (EEG) but the determination of the optimal wavelet basis is intractable. To overcome this strait, maximal overlap discrete wavelet package transform (MODWPT) was introduced to characterize epileptic EEG for the first time and the multi-basis MODWPT-based feature extraction was further proposed in this study. Instead of merely using single wavelet basis, multiple bases were synchronously adopted in one-time implementation of multi-basis MODWPT. Six dimensionality reduction algorithms, namely principal component analysis (PCA), independent component analysis (ICA), kernel principal component analysis (KPCA), isometric feature mapping (ISOMAP), locally linear embedding (LLE) and Laplacian eigenmaps (LE), were then employed to map the extracted features into other domain in feature selection procedure. Finally, the mapped features were fed into a least squares support vector machine (LS-SVM) for classification and multiple kernel learning support vector machine (MKLSVM) was used as comparison. Experimental results show the combination of multi-basis MODWPT, ICA and LS-SVM with linear kernel provides the highest accuracy of 99.67% in classifying inter-ictal and ictal EEGs while MKLSVM in conjunction with multi-basis MODWPT-based PCA also leads to the maximal accuracy of 99.83%. Our presented scheme yields superior performance than the majority of newly-developed methods and is proven useful.