Wavelet Feature Extraction Research Articles

A mode shape sensitivity-based wavelet feature extraction method for interface debonding detection in concrete-filled steel tubes

A mode shape sensitivity-based wavelet feature extraction method for interface debonding detection in concrete-filled steel tubes

A Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery

Pupillary instability is a known risk factor for complications in cataract surgery. This study aims to develop and validate an innovative and reliable computational framework for the automated assessment of pupil morphologic changes during the various phases of cataract surgery. Retrospective surgical video analysis. Two hundred forty complete surgical video recordings, among which 190 surgeries were conducted without the use of pupil expansion devices (PEDs) and 50 were performed with the use of a PED. The proposed framework consists of 3 stages: feature extraction, deep learning (DL)-based anatomy recognition, and obstruction (OB) detection/compensation. In the first stage, surgical video frames undergo noise reduction using a tensor-based wavelet feature extraction method. In the second stage, DL-based segmentation models are trained and employed to segment the pupil, limbus, and palpebral fissure. In the third stage, obstructed visualization of the pupil is detected and compensated for using a DL-based algorithm. A dataset of 5700 intraoperative video frames across 190 cataract surgeries in the BigCat database was collected for validating algorithm performance. The pupil analysis framework was assessed on the basis of segmentation performance for both obstructed and unobstructed pupils. Classification performance of models utilizing the segmented pupil time series to predict surgeon use of a PED was also assessed. An architecture based on the Feature Pyramid Network model with Visual Geometry Group 16 backbone integrated with the adaptive wavelet tensor feature extraction feature extraction method demonstrated the highest performance in anatomy segmentation, with Dice coefficient of 96.52%. Incorporation of an OB compensation algorithm improved performance further (Dice 96.82%). Downstream analysis of framework output enabled the development of a Support Vector Machine-based classifier that could predict surgeon usage of a PED prior to its placement with 96.67% accuracy and area under the curve of 99.44%. The experimental results demonstrate that the proposed framework (1) provides high accuracy in pupil analysis compared with human-annotated ground truth, (2) substantially outperforms isolated use of a DL segmentation model, and (3) can enable downstream analytics with clinically valuable predictive capacity. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Performance Analysis of Machine Learning Algorithms for MRI Using Wavelet Feature Extraction

Performance Analysis of Machine Learning Algorithms for MRI Using Wavelet Feature Extraction

Violent crowd flow detection from surveillance cameras using deep transfer learning–gated recurrent unit

AbstractViolence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short‐term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1‐score. The use of ResNet50V2 for feature extraction can improve model performance.

A Physics-Guided Wavelet Feature Extraction Method for Fault Diagnosis of Thruster Blades

A Physics-Guided Wavelet Feature Extraction Method for Fault Diagnosis of Thruster Blades

The performance of DST-Wavelet feature extraction for guitar chord recognition

Small systems can be designed to be more energy-efficient compared to larger systems. On small systems, the need for data processing with small data sizes becomes a necessity. In the context of small systems for guitar chord recognition, there are indications that further efforts can be made to reduce the size of feature extraction data. This paper introduces DST (Discrete Sine Transform)-Wavelet feature extraction to achieve this reduction. Basically, this work evaluated the frame blocking length, the number of DST cutting factors, and the type of wavelet filters (Daubechies and biorthogonal families) to obtain the optimal number of feature extraction data. Based on the evaluation, the optimal result obtained was a number of four feature extraction data. This optimal result was obtained by using a frame blocking length of 512 points, a DST cutting factor of 0.5, and a biorthogonal 3.3 wavelet filter. Testing with 140 test chords using these four feature extraction data could give an accuracy of up to 92.86%.

Hybrid ML-MDKL feature subset selection and classification technique accompanied with rat swarm optimizer to classify the multidimensional breast cancer mammogram image

Breast cancer is a pathological condition characterized by the abnormal proliferation of cells inside the breast tissue. The biggest challenge at the moment is determining the most optimal subset from large datasets. Numerous methodologies have been presented for the purpose of selecting the most suitable subset from datasets with high dimensions. However, the outcomes have proven to be insufficient in effectively addressing extensive quantities of multidimensional datasets. This publication presents a proposal for an efficient approach of selecting numerous feature subsets and performing classification on Multidimensional Datasets (MDD). In this study, the Moment Invariant Wavelet Feature Extraction (MI-WFE) approach is employed for the purpose of feature extraction. The New Adaptive Hybrid Levy Flight based Cuckoo Search Optimization Algorithm is employed to identify the most pertinent subset of features. This study presents a novel approach, referred to as H-RS-LVCSO, which aims to enhance the local search capability and optimization speed of the algorithm. This is achieved through the hybridization of the Rat Swarm Optimizer with the levy flight based cuckoo search optimization technique. In this study, it is suggested a hybridized approach for classifying breast cancer, utilizing a Multilayer Multiple Deep Kernel Learning (ML-MDKL) Classifier in conjunction with the standard Support Vector Machine (SVM) Classifier. The simulation of the suggested method is conducted using the MATLAB software. The approach under consideration is evaluated in comparison to two pre-existing methods. The suggested method demonstrates an accuracy improvement of 10.58% compared to existing methods. Furthermore, it outperforms these methods by 17.5% in terms of accuracy. The proposed method exhibits a precision improvement of 6.52% and 14.23% compared to the existing methods.

Comparison of KNN and SVM Algorithms in Facial Image Recognition Using Haar Wavelet Feature Extraction

To process all the pixels in the face image, feature extraction can be performed using the Haar Wavelet method so that it processes identifiers with lower dimensions. However, a classification algorithm must separate the distance between classes with minimal data to classify low-dimensional facial images. KNN and SVM algorithms are classifiers that can be used for facial image recognition. When classifying images, SVM creates a hyperplane, divides the input space between classes and classifies based on which side of the hyperplane the unclassified object is placed when it is placed in the input space. KNN uses a voting system to determine which class an unclassified object belongs to, taking into account the nearest neighbor class in the decision space. When classifying, KNN will generally classify accurately, resulting in some minor misclassifications that plagued the final classified image. This study aims to compare the two algorithms on image identifiers with low dimensions resulting from haar wavelet extraction. The research results obtained are facial image classification using the haar wavelet extraction method using the SVM algorithm to obtain an accuracy of 98.8%. Whereas when using the KNN algorithm, the accuracy obtained is 96.6%. The results of this study show that the SVM algorithm produces better accuracy in facial image recognition using haar wavelet feature extraction compared to the KNN algorithm. The SVM algorithm can recognize facial images even though it uses image training data with various face poses and sizes, resulting in higher accuracy.

Comparison of KNN and SVM Algorithms in Facial Image Recognition Using Haar Wavelet Feature Extraction

To process all the pixels in the face image, feature extraction can be performed using the Haar Wavelet method so that it processes identifiers with lower dimensions. However, a classification algorithm must separate the distance between classes with minimal data to classify low-dimensional facial images. KNN and SVM algorithms are classifiers that can be used for facial image recognition. When classifying images, SVM creates a hyperplane, divides the input space between classes and classifies based on which side of the hyperplane the unclassified object is placed when it is placed in the input space. KNN uses a voting system to determine which class an unclassified object belongs to, taking into account the nearest neighbor class in the decision space. When classifying, KNN will generally classify accurately, resulting in some minor misclassifications that plagued the final classified image. This study aims to compare the two algorithms on image identifiers with low dimensions resulting from haar wavelet extraction. The research results obtained are facial image classification using the haar wavelet extraction method using the SVM algorithm to obtain an accuracy of 98.8%. Whereas when using the KNN algorithm, the accuracy obtained is 96.6%. The results of this study show that the SVM algorithm produces better accuracy in facial image recognition using haar wavelet feature extraction compared to the KNN algorithm. The SVM algorithm can recognize facial images even though it uses image training data with various face poses and sizes, resulting in higher accuracy.

A DT-CWT and Data mining based approach for High Impedance Fault Diagnosis in Micro-grid System

The high impedance faults (HIFs) detection in the micro-grid is very difficult for over-current protection owing to the less fault magnitude. As this is a practical problem in the distribution feeder, the detection of HIFs plays a vital role in industry 4.0. A dual-tree complex wavelet transform(DT-CWT) and data mining approaches have been used for fault detection and fault classification. For the extraction of wavelet features by DT-CWT, the residual voltage is used as input and fed to various data mining approaches to separate the HIF events and the created confusion matrix gives the best results. The correctness of the method implemented is investigated with other data mining approaches like support vector machine(SVM), k-nearest neighbor(KNN), and ensemble classifiers. As correlated to further methods, the proposed technique is 100% accurate. To execute the proposed method, the interconnection of DG with a wind-integrated micro-grid system is designed using Power System Computer-Aided Design (PSCAD) software.

Coronavirus disease identification using Multi-subband feature analysis in DWT domain

Coronavirus disease early identification and differentiating it with other lung infections is a complex and time-consuming task. At present RT-PCR and Antigen tests are used for diagnosis, but the whole process is tedious, time exhausting and sometimes gives inaccurate results. Radiological scans like CT scan and X-rays are often considered for confirmation of infection, as it contains vital information about region of infection, disease state and severity, texture, size and opacity of infection. Automated machine learning techniques along with CXR (Chest X-ray) images can serve as alternative approach for Covid-19 diagnosis and differentiating it with other health conditions. In this work, Covid-19 disease identification is performed based on multi-subband feature extraction using 2D Discrete Wavelet Transform (DWT) on CX-Ray images. The CX-ray images are decomposed into multi-subbands of frequencies using DWT. The quarter-sized decomposed low and high frequency components are concatenated into single feature vector. In order to find suitable wavelet filter for extracting features from CX-ray images, a rigorous experimentation is carried out among various wavelet families such as Haar, Daubechies, Symlets, Biorthogonal and their respective members that have different vanishing moment and regularity properties. The feature vector is then used for training machine learning model based on support vector machine classifier. Experimental result shows that the classification model based on Haar wavelet feature extraction performs better as compared to other wavelet families with classification accuracy of 100%.

Automatic diagnosis of cardiovascular diseases using wavelet feature extraction and convolutional capsule network

Cardiovascular diseases (CVDs) are the primary cause of high mortality levels worldwide with coronary artery disease (CAD) being the largest contributor. Delay in diagnosis of CAD may progress and lead to myocardial infarction and congestive heart failure. Thus, timely diagnosis is a crucial key to prevent the development of serious complications and allow an optimum medication. This paper intends to design a diagnosis system to classify-eight different diseases using a capsule network with wavelet decomposed images of short ECG segments. It is noteworthy that in contrast to the previous studies that require large training data to efficiently predict unseen data, our designed models achieve high performance with less training data and training time. In the proposed system, firstlyECG signals are preprocessed and segmented into beats segments. Then, the continuous wavelet transform is used to transform the segments into2D scalograms. These latter are decomposed using discrete wavelet transform to obtain wavelet coefficient imageswhich are fed to the reformed capsule networks. The focal loss was applied to mitigate the class-imbalance issue. The proposed model was trained and tested using 5-fold cross-validation and train-test split techniques. The best performance parameters were achieved in the train-test split approach with an accuracy of 98.6%, sensitivity of 99.6%, specificity of 98.7%, precision of 99.1%, F1 score of 99.4% and area under the roc value of 0.99.Furthermore, experimental results demonstrated the superiority of our approach over state-of-the-art techniques using the same dataset.

Pulse coupled neural network optimized with chaotic grey wolf algorithm for breast cancer classification using mammogram images

SummaryBreast cancer is a very hazardous disease that mainly affects women and leads to a high mortality rate. Early detection of this disease only can reduce the mortality rate. Previously, several methods were used to detect this cancer, but none of them provides sufficient accuracy. To deal this issue, a pulse coupled neural network optimized with chaotic grey wolf algorithm is proposed in this article for the classification of breast cancer using mammogram images. The breast cancer images are gathered from MAMMOSET dataset. The images are preprocessed and segmented with the help of Tsalli's entropy based multilevel 3D Otsu (TE‐3D‐Otsu) thresholding method. Then the parameters of the TE‐3D‐Otsu are optimized using the improved shuffled shepherd optimization algorithm. The features are extracted using moment invariant wavelet feature extraction technique. The images are classified using pulse coupled neural network (PCNN). Then, PCNN mass parameters are optimizes utilizing chaotic grey wolf optimization algorithm (chaotic‐GWOA) for categorizing the mammogram breast cancer imageries, such as malignant, benign, and normal. The proposed method is activated on MATLAB, its performance is analyzed with existing methods. The simulation results show that the proposed BC‐PCNN‐CGWOA attains the accuracy 57.86%, 85.94%, and 53.45% is greater than the existing methods.

Dental X-ray Identification System Based on Association Rules Extracted by k-Symbol Fractional Haar Functions

Several identification approaches have recently been employed in human identification systems for forensic purposes to decrease human efforts and to boost the accuracy of identification. Dental identification systems provide automated matching by searching photographic dental features to retrieve similar models. In this study, the problem of dental image identification was investigated by developing a novel dental identification scheme (DIS) utilizing a fractional wavelet feature extraction technique and rule mining with an Apriori procedure. The proposed approach extracts the most discriminating image features during the mining process to obtain strong association rules (ARs). The proposed approach is divided into two steps. The first stage is feature extraction using a wavelet transform based on a k-symbol fractional Haar filter (k-symbol FHF), while the second stage is the Apriori algorithm of AR mining, which is applied to find the frequent patterns in dental images. Each dental image’s created ARs are saved alongside the image in the rules database for use in the dental identification system’s recognition. The DIS method suggested in this study primarily enhances the Apriori-based dental identification system, which aims to address the drawbacks of dental rule mining.

Development of Feature Extraction Technique

A problem of personal verification and identification is an actively growing area of research in pattern recognition, computer vision, and digital image processing. A Face acknowledgment system is largely significant move toward in our life. Face acknowledgment method must be proficient to robotically identify images of face. This system mainly used to recognize a person and make available a protection during various features of our life. It is extremely complicated job for investigator to obtain mainly excellent face acknowledgment velocity in a variety of circumstances and benchmarks. Face recognition is grassland of computer visualization to uses faces to recognize or authenticate a human being. Principal Component Analysis (PCA) is accomplished and used for feature extraction and measurement lessening. The feature extraction is used to reduce the dimension of the face space by transforming it into feature representation. Features may be symbolic, numerical or both. The symbolic feature is color and numerical feature is weight. The combined feature extraction of PCA, LDA and Wavelet are used in proposed feature extraction algorithm for human face recognition system. The structure is tested and achieves high recognition rates. Information regarding individuals was stored in a database.

Braille Detection Application Using Gabor Wavelet and Support Vector Machine

Difference any exchanging of several kinds information such visual, printed or written form between impairments vision or blind with normal will cause problem especially in written form. For instance in the assistance of a blind child by family with normal vision. One of family role is education to help their children to study and understand about their learning development from home, particularly for blind children. In this study, braille letters can be identified through images obtained using a scanner to help parents and families of a blind child in learning assistance by implementing the Gabor Wavelet feature extraction method. The features used are standard deviation, mean, variance, and median with theta angles of 00,300,450,600,1200,1350,1800 and wavelengths 3,6,13,28, and 58. These features will be combined and used as input as test data and training data. at the Support Vector Machine (SVM) classification stage and generates words in the alphabet. The braille letters detected in this study were small braille letters, capital braille letters, punctuation marks, and numbers. The test is carried out using a multi-class confusion matrix scenario to determine the level of accuracy, precision, and recall. Based on the results of tests carried out using 758 braille data, the accuracy value is 98.15%, the precision value is 97.66% and the recall value is 98.28%. From these results it can be concluded that the Gabor Wavelet feature extraction method and the Support Vector Machine (SVM) can be used to identify braille letters.

Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review.

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of ‘3N’ biosignals—nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result.

COVID-19 Chest X-Ray Detection Performance Through Variations of Wavelets Basis Function

Our previous work regarding the X-Ray detection of COVID-19 using Haar wavelet feature extraction and the Support Vector Machines (SVM) classification machine has shown that the combination of the two methods can detect COVID-19 well but then the question arises whether the Haar wavelet is the best wavelet method. So that in this study we conducted experiments on several wavelet methods such as biorthogonal, coiflet, Daubechies, haar, and symlets for chest X-Ray feature extraction with the same dataset. The results of the feature extraction are then classified using SVM and measure the quality of the classification model with parameters of accuracy, error rate, recall, specification, and precision. The results showed that the Daubechies wavelet gave the best performance for all classification quality parameters. The Daubechies wavelet transformation gave 95.47% accuracy, 4.53% error rate, 98.75% recall, 92.19% specificity, and 93.45% precision.

Application of Wavelet Feature Extraction and Artificial Neural Networks for Improving the Performance of Gas-Liquid Two-Phase Flow Meters Used in Oil and Petrochemical Industries.

Measuring fluid characteristics is of high importance in various industries such as the polymer, petroleum, and petrochemical industries, etc. Flow regime classification and void fraction measurement are essential for predicting the performance of many systems. The efficiency of multiphase flow meters strongly depends on the flow parameters. In this study, MCNP (Monte Carlo N-Particle) code was employed to simulate annular, stratified, and homogeneous regimes. In this approach, two detectors (NaI) were utilized to detect the emitted photons from a cesium-137 source. The registered signals of both detectors were decomposed using a discrete wavelet transform (DWT). Following this, the low-frequency (approximation) and high-frequency (detail) components of the signals were calculated. Finally, various features of the approximation signals were extracted, using the average value, kurtosis, standard deviation (STD), and root mean square (RMS). The extracted features were thoroughly analyzed to find those features which could classify the flow regimes and be utilized as the inputs to a network for improving the efficiency of flow meters. Two different networks were implemented for flow regime classification and void fraction prediction. In the current study, using the wavelet transform and feature extraction approach, the considered flow regimes were classified correctly, and the void fraction percentages were calculated with a mean relative error (MRE) of 0.4%. Although the system presented in this study is proposed for measuring the characteristics of petroleum fluids, it can be easily used for other types of fluids such as polymeric fluids.

Microwave breast tumor localization using wavelet feature extraction and genetic algorithm-neural network.

Ultra-Wide Band (UWB) microwave breast cancer detection is a promising new technology for routine physical examination and home monitoring. The existing microwave imaging algorithms for breast tumor detection are complex and the effect is still not ideal, due to the heterogeneity of breast tissue, skin reflection, and fibroglandular tissue reflection in backscatter signals. This study aims to develop a machine learning method to accurately locate breast tumor. A microwave-based breast tumor localization method is proposed by time-frequency feature extraction and neural network technology. First, the received microwave array signals are converted into representative and compact features by 4-level Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA). Then, the Genetic Algorithm-Neural Network (GA-NN) is developed to tune hyper-parameters of the neural network adaptively. The neural network embedded in the GA-NN algorithm is a four-layer architecture and 10-fold cross-validation is performed. Through the trained neural network, the tumor localization performance is evaluated on four datasets that are created by FDTD simulation method from 2-D MRI-derived breast models with varying tissue density, shape, and size. Each dataset consists of 1000 backscatter signals with different tumor positions, in which the ratio of training set to test set is 9:1. In order to verify the generalizability and scalability of the proposed method, the tumor localization performance is also tested on a 3-D breast model. For these 2-D breast models with unknown tumor locations, the evaluation results show that the proposed method has small location errors, which are 0.6076mm, 3.0813mm, 2.0798mm, and 3.2988mm, respectively, and high accuracy, which is 99%, 80%, 94%, and 85%, respectively. Furthermore, the location error and the prediction accuracy of the 3-D breast model are 3.3896mm and 81%. These evaluation results demonstrate that the proposed machine learning method is effective and accurate for microwave breast tumor localization. The traditional microwave-based breast cancer detection method is to reconstruct the entire breast image to highlight the tumor. Compared with the traditional method, our proposed method can directly get the breast tumor location by applying neural network to the received microwave array signals, and circumvent any complicated image reconstruction processing.