Wavelet Based Feature Extraction Method Research Articles

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.

Subband entropy-based features for clothing invariant human gait recognition

This paper presents a wavelet-based feature extraction method for human gait recognition. The selection of features with most discriminative information is the key to improve recognition performance. The frequency domain representation of the gait image is obtained by using fast Fourier transforms. Next, a discrete wavelet transform is applied to the obtained spectrum. With single-level wavelet decomposition, four coefficients are generated. The sum of the entropy of these four wavelet coefficients is computed yielding the wavelet Entropy Image (wEnI) which is used here as the potential feature for human gait recognition. A template matching-based approach is used as the classification. The performance of the proposed wEnI feature is evaluated using whole-based and part-based methods. The experimental results show that the wEnI feature performs better compared to state-of-the-art gait features in common use.

Wavelet Based Method for Congestive Heart Failure Recognition by Three Confirmation Functions.

An investigation of the electrocardiogram (ECG) signals and arrhythmia characterization by wavelet energy is proposed. This study employs a wavelet based feature extraction method for congestive heart failure (CHF) obtained from the percentage energy (PE) of terminal wavelet packet transform (WPT) subsignals. In addition, the average framing percentage energy (AFE) technique is proposed, termed WAFE. A new classification method is introduced by three confirmation functions. The confirmation methods are based on three concepts: percentage root mean square difference error (PRD), logarithmic difference signal ratio (LDSR), and correlation coefficient (CC). The proposed method showed to be a potential effective discriminator in recognizing such clinical syndrome. ECG signals taken from MIT-BIH arrhythmia dataset and other databases are utilized to analyze different arrhythmias and normal ECGs. Several known methods were studied for comparison. The best recognition rate selection obtained was for WAFE. The recognition performance was accomplished as 92.60% accurate. The Receiver Operating Characteristic curve as a common tool for evaluating the diagnostic accuracy was illustrated, which indicated that the tests are reliable. The performance of the presented system was investigated in additive white Gaussian noise (AWGN) environment, where the recognition rate was 81.48% for 5 dB.

Identifying acquisition devices from recorded speech signals using wavelet-based features

Speech characteristics have played a critical role in media forensics, particularly in the investigation of evidence. This study proposes two wavelet-based feature extraction methods for the identification of acquisition devices from recorded speech. These methods are discrete wavelet-based coefficients (DWBCs) and wavelet packet-based coefficients, which are mainly based on a multiresolution analysis. These features' ability to capture characteristics of acquisition devices is compared to conventional mel frequency cepstral coefficients and subband-based coefficients. In the experiments, 14 different audio acquisition devices were trained and tested using support vector machines. Experimental results showed that DWBCs can effectively be used in source audio acquisition device identification problems.

Local energy-based shape histogram feature extraction technique for breast cancer diagnosis

This paper proposes a novel local energy-based shape histogram (LESH) as the feature set for recognition of abnormalities in mammograms. It investigates the implication of this technique on mammogram datasets of the Mammographic Image Analysis Society and INbreast. In the evaluation, regions of interest were extracted from the mammograms, their LESH features calculated, and fed to support vector machine (SVM) classifiers. In addition, the impact of selecting a subset of LESH features on classification performance was also observed and benchmarked against a state-of-the-art wavelet based feature extraction method. The proposed method achieved a higher classification accuracy of 99.00±0.50, as well as an Az value of 0.9900±0.0050 with multiple SVM kernels, where a linear kernel performed with 100% accuracy for distinguishing between the abnormalities (masses vs. microcalcifications). Hence, the general capability of the proposed method was established, in which it not only distinguishes between malignant and benign cases for any type of abnormality but also among different types of abnormalities. It is therefore concluded that LESH features are an excellent choice for extracting significant clinical information from mammogram images with significant potential for application to 3-D MRI images.

Face Recognition Using MLP and RBF Neural Network with Gabor and Discrete Wavelet Transform Characterization: A Comparative Study

Face recognition has received a great attention from a lot of researchers in computer vision, pattern recognition, and human machine computer interfaces in recent years. Designing a face recognition system is a complex task due to the wide variety of illumination, pose, and facial expression. A lot of approaches have been developed to find the optimal space in which face feature descriptors are well distinguished and separated. Face representation using Gabor features and discrete wavelet has attracted considerable attention in computer vision and image processing. We describe in this paper a face recognition system using artificial neural networks like multilayer perceptron (MLP) and radial basis function (RBF) where Gabor and discrete wavelet based feature extraction methods are proposed for the extraction of features from facial images using two facial databases: the ORL and computer vision. Good recognition rate was obtained using Gabor and DWT parameterization with MLP classifier applied for computer vision dataset.

Parallel computing for efficient time‐frequency feature extraction of power quality disturbances

Fast signal processing implementation techniques for detection and classification of power quality (PQ) disturbances are the need of the hour. Hence in this work, a parallel computing approach has been proposed to speed up the feature extraction of PQ signals to facilitate rapid building of classifier models. Considering that the Fourier, the one-dimensional discrete wavelet, the time-time and the Stockwell transforms have been used extensively to extract pertinent time-frequency features from non-stationary and multi-frequency PQ signals, acceleration approaches using data and task parallelism have been employed for parallel implementation of the above time-frequency transforms. In the first approach, data parallelism was applied to the Stockwell transform and the time-time transform-based feature extraction methods separately to alleviate capability problems. Also, data parallelism was applied to Fourier and wavelet-based feature extraction methods independently to alleviate capacity problems. Secondly, a combination of task and data parallelism was applied to speed up S-transform based three-phase sag feature extraction. Experiments were conducted using shared-memory and distributed memory architectures to try out the effectiveness of the proposed parallel approaches. The performances of these parallel implementations were analysed in terms of computational speed and efficiency in comparison with the sequential approach.

COMPARISOM OF WAVELET-BASED AND HHT-BASED FEATURE EXTRACTION METHODS FOR HYPERSPECTRAL IMAGE CLASSIFICATION

Abstract. Hyperspectral images, which contain rich and fine spectral information, can be used to identify surface objects and improve land use/cover classification accuracy. Due to the property of high dimensionality of hyperspectral data, traditional statistics-based classifiers cannot be directly used on such images with limited training samples. This problem is referred as "curse of dimensionality". The commonly used method to solve this problem is dimensionality reduction, and feature extraction is used to reduce the dimensionality of hyperspectral images more frequently. There are two types of feature extraction methods. The first type is based on statistical property of data. The other type is based on time-frequency analysis. In this study, the time-frequency analysis methods are used to extract the features for hyperspectral image classification. Firstly, it has been proven that wavelet-based feature extraction provide an effective tool for spectral feature extraction. On the other hand, Hilbert-Huang transform (HHT), a relative new time-frequency analysis tool, has been widely used in nonlinear and nonstationary data analysis. In this study, wavelet transform and HHT are implemented on the hyperspectral data for physical spectral analysis. Therefore, we can get a small number of salient features, reduce the dimensionality of hyperspectral images and keep the accuracy of classification results. An AVIRIS data set is used to test the performance of the proposed HHT-based feature extraction methods; then, the results are compared with wavelet-based feature extraction. According to the experiment results, HHT-based feature extraction methods are effective tools and the results are similar with wavelet-based feature extraction methods.

Wavelets-Based Feature Extraction for Texture Classification

Texture classification is a necessary task in a wider variety of application areas such as manufacturing, textiles, and medicine. In this paper, we propose a novel wavelet-based feature extraction method for robust, scale invariant and rotation invariant texture classification. The method divides the 2-D wavelet coefficient matrices into 2-D clusters and then computes features from the energies inherent in these clusters. The features that contain the information effective for classifying texture images are computed from the energy content of the clusters, and these feature vectors are input to a neural network for texture classification. The results show that the discrimination performance obtained with the proposed cluster-based feature extraction method is superior to that obtained using conventional feature extraction methods, and robust to the rotation and scale invariant texture classification.

Content-based image classification with wavelet relevance vector machines

This paper introduces the use of relevance vector machines (RVMs) for content-based image classification and compares it with the conventional support vector machine (SVM) approach. Different wavelet kernels are included in the formulation of the RVM. We also propose a new wavelet-based feature extraction method that extracts lesser number of features as compared to other wavelet-based feature extraction methods. Experimental results confirm the superiority of RVM over SVM in terms of the trade-off between slightly reduced accuracy but substantially enhanced sparseness of the solution, and also the ease of free parameters tuning.

Special issue on pattern recognition and information processing using neural networks

Neural network techniques have proven to be flexible in pattern recognition and information processing in complex environments. They typically include BP networks, RBF networks, support vector machine (SVM) and other similar biologically motivated models. The neural network techniques are able to enhance recognition accuracy, and have found applications in real-world environments. This special issue addresses neural network techniques in pattern recognition and information processing problems. The first paper ‘‘Kernel based improved discriminant analysis and its application to face recognition,’’ coauthored by Dake Zhou and Zhenmin Tang, presents a variant of KDA called kernel-based improved discriminant analysis (KIDA). In the proposed framework, original samples are projected firstly into a feature space by an implicit nonlinear mapping. After reconstructing betweenclass scatter matrix in the feature space by weighted schemes, the kernel method is used to obtain a modified Fisher criterion. Finally, simultaneous diagonalization technique is employed to find lower dimensional nonlinear features with significant discriminant power. The second paper ‘‘A Novel Application of a Self-Organizing Network for Recognition of Facial Expressions from Contours,’’ coauthored by W.F. Gu, Y.V. Venkatesh, and C. Xiang, proposes a self-organizing network for recognizing facial expressions using biologically plausible features: contours of face and its components. Experimental results show that the recognition accuracy of the presented algorithm is superior to that of other algorithms in the literature on the Japanese Female Facial Expression (JAFFE) database. The third paper ‘‘An Automatic Fuzzy C-Means Algorithm for Image Segmentation,’’ co-authored by Yanling Li and Yi Shen, proposes a novel fuzzy clustering algorithm for automatically grouping the pixels of an image into different homogeneous regions when the number of clusters is not known a priori. The new algorithm initiates the first two centroids of clusters by a method based on hard c-means algorithm and automatically determines the appropriate cluster number for image segmentation. The fourth paper ‘‘Content Based Image Classification with Wavelet Relevance Vector Machines,’’ co-authored by Arvind Tolambiya, S. Venkataraman, and Prem K. Kalra, introduces the use of relevance vector machines (RVM) for content-based image classification and compares it with the conventional SVM approach. The authors also propose a new wavelet-based feature extraction method that extracts less number of features as compared to other wavelet-based feature extraction methods. The fifth paper ‘‘A Three-layer Back-propagation Neural Network for Spam Detection Using Artificial Immune Concentration,’’ co-authored by Guangchen Ruan and Ying Tan, uses a three-layer back-propagation neural network F.-C. Sun (&) State Key Lab of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, 100084 Beijing, China e-mail: fcsun@tsinghua.edu.cn

An effective wavelet-based feature extraction method for classification of power quality disturbance signals

This paper presents a wavelet norm entropy-based effective feature extraction method for power quality (PQ) disturbance classification problem. The disturbance classification schema is performed with wavelet-neural network (WNN). It performs a feature extraction and a classification algorithm composed of a wavelet feature extractor based on norm entropy and a classifier based on a multi-layer perceptron. The PQ signals used in this study are seven types. The performance of this classifier is evaluated by using total 2800 PQ disturbance signals which are generated the based model. The classification performance of different wavelet family for the proposed algorithm is tested. Sensitivity of WNN under different noise conditions which are different levels of noises with the signal to noise ratio is investigated. The rate of average correct classification is about 92.5% for the different PQ disturbance signals under noise conditions.

Vehicle classification in Sensor Networks using time-domain signal processing and Neural Networks

Vehicle classification is a demanding application of Wireless Sensor Networks. In many cases, sensor nodes detect and classify vehicles from their acoustic and/or seismic signature using spectral or wavelet based feature extraction methods. Such methods, while providing good results are quite demanding in computational power and energy and are difficult to implement on low-cost sensor nodes with limited resources. In this work, we investigate the use of a time-domain encoding and feature extraction method, to produce simple, fixed-size matrices from complex acoustic and seismic signatures of vehicles for classification purposes. Classification is accomplished using an Artificial Neural Network and a basic, L1 distance, archetype classifier. Hardware implementation issues on a prototype sensor node, based on an 8-bit microcontroller, are also discussed. For evaluation purposes we use real data from DARPA’s SensIt project, which contains various acoustic and seismic signatures from two different vehicle types, a tracked vehicle and a heavy truck.

Denoising and Wavelet-Based Feature Extraction of MODIS Multi-Temporal Vegetation Signatures

Temporal vegetation signatures (i.e., vegetation indices as functions of time) generated using the MODIS imagery poses many challenges, primarily due to signal-to-noise-related issues. This article describes the use of MODIS time-series data for the detection of specific tropical invasive species vegetation types. Due to challenges with the MODIS quality assurance data, a significant level of noise was present in the temporal signatures. This study investigated methods for denoising the vegetation temporal signatures, followed by a comparative analysis of three denoising methods to generate signatures for vegetation target detection. The analytical approach focused on the use of wavelet-based versus Fourier-based feature extraction methods. Methods included the development of a novel wavelet-based feature extraction method that quantifies the fundamental shape of the temporal signatures.