Wavelet Support Vector Machine Research Articles

Bearing Fault Diagnosis Using a Particle Swarm Optimization-Least Squares Wavelet Support Vector Machine Classifier.

Bearing is one of the key components of a rotating machine. Hence, monitoring health condition of the bearing is of paramount importace. This paper develops a novel particle swarm optimization (PSO)-least squares wavelet support vector machine (PSO-LSWSVM) classifier, which is designed based on a combination between a PSO, a least squares procedure, and a new wavelet kernel function-based support vector machine (SVM), for bearing fault diagnosis. In this work, bearing fault classification is transformed into a pattern recognition problem, which consists of three stages of data processing. Firstly, a rich information dataset is built by extracting the features from the signals, which are decomposed by the nonlocal means (NLM) and empirical mode decomposition (EMD). Secondly, a minimum-redundancy maximum-relevance (mRMR) method is employed to determine a subset of feature that can provide an optimal performance. Thirdly, a novel classifier, namely LSWSVM, is proposed with the aid of a PSO, to provide higher classification accuracy. The key innovative science of this work is to propropose a new classifier with the aid of an new wavelet kernel type to increase the classification precision of bearing fault diagnosis. The merit features of the proposed approach are demonstrated based on a benchmark bearing dataset and a comprehensive comparison procedure.

ICM-BTD: improved classification model for brain tumor diagnosis using discrete wavelet transform-based feature extraction and SVM classifier

In medical image processing, the detection, classification and segmentation of the tumor region from MRI scans accurately are very complicated, significant and time-consuming process. When there is a scenario occurs to handle with large amount of images for tumor diagnosis, there is need of an efficient and adaptive classification model to handle with the anomalous structures of human brains. The MRI brain images show the typical internal brain structure and hence help scholars and medical practitioners in accurate disease diagnosis. With that note, this paper develops a model called improved classification model for brain tumor diagnosis for appropriate classification of tumor images from input MRI images. Initially, filtering techniques are applied for preprocessing the acquired scan images and feature extraction is done with gray-level co-occurrence matrix and discrete wavelet transform equations, which produces more precise results. And, classification is done with the technique called support vector machine, in which the binary classifications are effectively done. The proposed model is evaluated under simulation, and the obtained results outperform the results of traditional brain tumor detection process based on precision, recall and processing time.

Classification of Refrigerant Flow Noise of Air Conditioners Based on Continuous Wavelet Transform and Support Vector Machine

This study proposes a classification method that uses the continuous wavelet transform and the support vector machine approach to classify refrigerant flow noises generated in an air conditioner. The air conditioning noise was identified as an abnormal signal by the use of the first- and second-order moments. The start and end times of refrigerant flow noises were identified by detecting the singularities of the continuous wavelet transform coefficient in the time domain and by means of listening to the measured sounds. Further, the time-frequency characteristics of refrigerant flow noise were analyzed with the continuous wavelet transform. For the support vector machine-based classification of refrigerant flow noise in an air conditioner, the grid search method was used to determine kernel hyperparameters. Five-fold cross validation was employed for the application of the support vector machine to the classification of air conditioner refrigerant noise. In addition, measured sound sources were modified based on classified refrigerant flow noise to compare the classification accuracy of a jury test with the results of the support vector machine.

Evolutionary intelligence for breast lesion detection in ultrasound images: A wavelet modulus maxima and SVM based approach

Intelligent lesion detection system for medical ultrasound images are aimed at reducing physicians’ effort during cancer diagnosis process. Automatic separation and classification of tumours in ultrasound images is challenging owing to the low contra

Identification of Disease Symptoms Using Taste Disorders in Electroencephalogram Signal

A Brain Computer Interface (BCI) is the one which converts the activity of the brain signals into useful and understandable signal. Brain computer interface is also called as Neural-Control Interface (NCI), Direct Neural Interface (DCI) or Brain Interface Machine (BMI). Electroencephalogram (EEG) based brain computer interfaces (BCI) is the technique used to measure the activity of the brain. Electroencephalography (EEG) is a brain wave monitoring and diagnosis. It is the measurement of electrical activity of the brain from the scalp. Taste sensations are important for our body to digest food. Identification of disease symptoms is based on the inhibition of different types of taste and by testing them to find the normality and abnormality of taste. The information is used in detection of disorder such as Parkinson’s disease etc. It is a source of reimbursement for better clinical diagnosis. Our brain continuously produces electrical signals when it operates. Those signals are measured with the equipment called Neurosky Mindwave Mobile headset. It is used to collect the real time brain signal samples. Neurosky is the equipment used in proposed work. Here the pre-processing technique is executed with median filtering. Feature extraction and classification is done with Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM). It increases the performance accuracy. The SVM classification accuracy achieved by this work is 90%. The sensitivity achieved is higher and the specificity is about 80%. We can able to predict the taste disorders using this methodology.

Extending Capture Range for Piston Error in Segmented Primary Mirror Telescopes Based on Wavelet Support Vector Machine With Improved Particle Swarm Optimization

In the co-phasing techniques applied to the segmented telescope, a Shack-Hartmann wavefront sensor cannot accurately detect the piston error of the segment. Although the phase diversity (PD) algorithm can detect the piston error of each segment, it fails to reconstruct the wavefront quickly, and its dynamic range is small. Other technologies, such as prisms or micro-lens arrays, will significantly increase the complexity and construction cost of the optical system. Moreover, they may also introduce non-common path errors. In this study, we propose an approach to address this challenging problem via curvature sensing. This method uses multi-wavelength to eliminate the influence of $2\pi $ ambiguity and improve the capture range of co-phasing detection. However, curvature sensing is easily influenced by atmospheric seeing. We propose a wavelet support vector machine optimized via particle swarm optimization (PSO-WSVM) method to deal with this problem, and to improve the application scope of curvature sensing. We reshape SVM with a wavelet kernel function, and improve the PSO algorithm. We train the SVM to build a prediction model to distinguish the piston error range of each pair of adjacent segments and surpass $2\pi $ ambiguity. First, we obtain defocused images by means of the convolution technique. Second, we propose a prediction model based on SVM. We select the correlation coefficient between the sampling signal and the template signal at different wavelengths as the input vector, and we choose a wavelet basis function as the kernel function of SVM. Third, we improve the PSO algorithm with the exponential decreasing inertia weight (EDIW) to tune the parameters of SVM. Finally, we perform a simulation experiment on a real optical system model based on the Keck telescope. The results indicate that the performance of this method is better than that of other state-of-the-art SVM-based classifiers, and it works rapidly during the observation.

OP Performance Prediction for Complex Mobile Multiuser Networks Based on Extreme Learning Machine

Due to the complex and variable environments of mobile communication, the mobile multiuser networks become a hot topic. To process active complex event in mobile multiuser networks, it is important to predict the system performance. In this work, the authors consider the multiuser networks which utilizes transmit antenna selection (TAS). We derive novel closed-form expressions for the outage probability (OP) in terms of the Meijer's G-function. Then, a extreme learning machine (ELM)-based OP performance prediction algorithm is proposed. We use the theoretical results to generate training data. We test back-propagation (BP) neural network, locally weighted linear regression (LWLR), wavelet neural network, ELM, and support vector machine (SVM) methods. Compared with wavelet neural network, SVM, BP neural network, and LWLR methods, the Monte-Carlo results shows that the proposed prediction algorithm can consistently achieve higher OP performance prediction results.

Forecasting ASEAN Tourist Arrivals in Malaysia Using Different Time Series Models

In this study three time series models are used for forecasting monthly ASEAN tourist arrivals in Malaysia from January 1999 to December 2015. Brunei, Thailand and Vietnam of ASEAN country selected as case study. This paper compares the forecasting accuracy of seasonal autoregressive integrated moving average (SARIMA), Support Vector Machine (SVM) and Wavelet Support Vector Machine (WSVM) and Empirical Mode Decomposition with Wavelet Support Vector Machine (EMD_WSVM) using root mean square error (RMSE) and mean absolute percentage error (MAPE) criterion. Moreover, correlation test has also been carried out to strengthen decisions, and to check accuracy of various forecasting models. Based on the forecasting performance of all four models, hybrid model SARIMA and EMD_WSVM are found to be best models as compare to single model SVM and hybrid model WSVM.

Efficient Detection of Ventricular Late Potentials on ECG Signals Based on Wavelet Denoising and SVM Classification

The analysis of cardiac signals is still regarded as attractive by both the academic community and industry because it helps physicians in detecting abnormalities and improving the diagnosis and therapy of diseases. Electrocardiographic signal processing for detecting irregularities related to the occurrence of low-amplitude waveforms inside the cardiac signal has a considerable workload as cardiac signals are heavily contaminated by noise and other artifacts. This paper presents an effective approach for the detection of ventricular late potential occurrences which are considered as markers of sudden cardiac death risk. Three stages characterize the implemented method which performs a beat-to-beat processing of high-resolution electrocardiograms (HR-ECG). Fifteen lead HR-ECG signals are filtered and denoised for the improvement of signal-to-noise ratio. Five features were then extracted and used as inputs of a classifier based on a machine learning approach. For the performance evaluation of the proposed method, a HR-ECG database consisting of real ventricular late potential (VLP)-negative and semi-simulated VLP-positive patterns was used. Experimental results show that the implemented system reaches satisfactory performance in terms of sensitivity, specificity accuracy, and positive predictivity; in fact, the respective values equal to 98.33%, 98.36%, 98.35%, and 98.52% were achieved.

RTDGPS Accuracy Improvement Using PSO-LSWSVM and Low-Cost GPS Receivers

The position of mobile devices is determined by Real Time Differential Global Positioning System (RTDGPS). This system is composed of fixed and mobile station. The accuracy of this system depends on the speed of updating the correction data. Yet, this system often faces the problem of the reference GPS receiver’s signal cut off and internal or non- internal delays which increase the latency time and decrease the updating speed. The prediction models are used to compensate these delays. In this paper, the Particle Swarm Optimization Least Square Wavelet Support Vector Machine (PSO-LSWSVM) is used for predicting the DGPS correction. An experimental setup is designed in order to carry out the operations of reference and user stations. Low-cost receivers were used in both stations. The accuracy of PSO-LSWSVM was evaluated through various simulations and experimental. The practical tests showed that the accuracy of the designed RTDGPS is 0.42 m with PSO-LSWSVM and is equal to 0.73 m without it. In comparing with other method that recently is introduced; it has a higher positioning accuracy.

Image classification towards transmission line fault detection via learning deep quality-aware fine-grained categorization

Object detection and image classification are basic tasks in computer vision. In this paper, we introduce fault detection towards transmission line. Traditional fault detection methods in the transmission line are prone to be affected by the noise and transient magnitude. To overcome these limitations, we propose a novel fault zone detection method, where quality-aware fine-grained categorization model is well encoded for category cues discovery. The goal of our approach is to recognize the most discriminative image patches for classification. The key techniques of our method include quality-based discriminative feature extraction and wavelet-support vector machine. We extract the features of the line currents by leveraging Fast R-CNN based image samples decomposition, where quality module is utilized to choose the most discriminative regions. Afterwards, the extracted features are fed into a SVM to recognize the fault. We conduct comprehensive experiment on transmission line fault identification to verify the availability and superiority of our proposed method.

Full-Waveform LiDAR Point Clouds Classification Based on Wavelet Support Vector Machine and Ensemble Learning.

Light Detection and Ranging (LiDAR) produces 3D point clouds that describe ground objects, and has been used to make object interpretation in many cases. However, traditional LiDAR only records discrete echo signals and provides limited feature parameters of point clouds, while full-waveform LiDAR (FWL) records the backscattered echo in the form of a waveform, which provides more echo information. With the development of machine learning, support vector machine (SVM) is one of the commonly used classifiers to deal with high dimensional data via small amount of samples. Ensemble learning, which combines a set of base classifiers to determine the output result, is presented and SVM ensemble is used to improve the discrimination ability, owing to small differences in features between different types of data. In addition, previous kernel functions of SVM usually cause under-fitting or over-fitting that decreases the generalization performance. Hence, a series of kernel functions based on wavelet analysis are used to construct different wavelet SVMs (WSVMs) that improve the heterogeneity of ensemble system. Meanwhile, the parameters of SVM have a significant influence on the classification result. Therefore, in this paper, FWL point clouds are classified by WSVM ensemble and particle swarm optimization is used to find the optimal parameters of WSVM. Experimental results illustrate that the proposed method is robust and effective, and it is applicable to some practical work.

Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network

Short-term passenger flow prediction and passenger flow control are essential for managing congestion in metros. This paper proposes a new dynamic radial basis function (RBF) neural network to forecast outbound passenger volumes and improve passenger flow control. First, we adopt a train timetable to model passenger flow propagation and identify potential stations that substantially impact the outbound volumes of the target stations. As a result, we incorporate inbound volume, outbound volume, and the train timetable to avoid overfitting. Second, passenger flow control is considered to improve the prediction accuracy by adding passenger flow control coefficients to our model, which then attempts to specify the true influence of these potential stations during crowded times. Finally, we construct a dynamic input radial basis function neural network whose performance is illustrated by the following three scenarios: large passenger flow under passenger flow control during morning peak hours, evening peak hours under passenger flow control, and normal passenger flow without passenger flow control. Compared with the backpropagation neural network, the wavelet support vector machine and the K-nearest neighbor, the proposed method achieves the best prediction performance at a half-hour prediction time lag. The proposed method can also identify crucial stations and time periods 30 min in advance, which contributes when considering proactive passenger flow control to alleviate congestion during peak hours in metro networks.

Wavelet-support vector machine for forecasting palm oil price

This study examines the feasibility of applying Wavelet-Support Vector Machine (W-SVM) model in forecasting palm oil price. The conjunction method wavelet-support vector machine (W-SVM) is obtained by the integration of discrete wavelet transform (DWT) method and support vector machine (SVM). In W-SVM model, wavelet transform is used to decompose data series into two parts; approximation series and details series. This decomposed series were then used as the input to the SVM model to forecast the palm oil price. This study also utilizes the application of partial correlation-based input variable selection as the preprocessing steps in determining the best input to the model. The performance of the W-SVM model was then compared with the classical SVM model and also artificial neural network (ANN) model. The empirical result shows that the addition of wavelet technique in W-SVM model enhances the forecasting performance of classical SVM and performs better than ANN.

Performance and predict the ball bearing faults using wavelet packet decomposition and ANFIS

Element bearings are widespread significant parts of rotary machinery in industries and their condition monitoring through fault detection and isolation methods are of superior interests to engineers. Condition monitoring could assist in attaining effective system maintenance and the automation processes. Nonetheless, despite the availability of diverse bearing fault detection methods, there is paucity of literature concerning the theoretical modelling of the bearing faults using mathematical representations. The principal goal of this communication is to build up an approach to predict ball bearing fault, including ball fault, outer race fault and inner race fault. The proposed method uses the vibration data collected from the rotating ball bearing and predicts the type of fault. The proposed method is based on wavelet decomposition method, PCA, ANFIS and SVM. The vibration data is decomposed into 3rd level wavelet components using wavelet packet decomposition; each wavelet component has been divided into several energy segments, these 3rd level wavelet components are reduced to lower level components using Principal Component Analysis (PCA). ANFIS algorithm is trained using the reduced feature set as input and the type of fault as output. The trained ANFIS algorithm is validated using another set of data. Support Vector Machine (SVM) has been used instead of ANFIS algorithm, the SVM based method gives more accurate prediction compared to that of ANFIS. The proposed method has been validated using the real-time data collected from the ball bearing setup. The validation results show that the proposed method exactly predicts the type of ball bearing fault. The real-time data validation results confirm the accuracy of the fault prediction method.Keywords: Principal component analysis, support vector machine; ANFIS; bearing

Estimating inelastic seismic response of reinforced concrete frame structures using a wavelet support vector machine and an artificial neural network

Modern building codes increasingly enforce evaluating the inelastic response of structures to ensure their safety in major seismic events. Although an inelastic dynamic analysis provides the most realistic and accurate measure for the seismic response, its application for large-scale structures is hampered by the excessive computational burden involved. This is particularly the case for the optimization of inelastic structures subjected to dynamic loads using metaheuristic algorithms where numerous analyses are required before the design converges to the optimum. In this regard, developing predictive models with sufficient accuracy will significantly help to reduce the computational demand, thus making the seismic analysis and optimization of large structures more feasible and common practice. Motivated by this need, this paper reports a study on the capabilities of a wavelet weighted least squares support vector machine (WWLSSVM) and a feedforward, backpropagation artificial neural network (ANN) to accurately predict the inelastic seismic responses of structures. The force- and displacement-based seismic responses of an 18-story reinforced concrete frame subjected to different earthquake ground motion records scaled to the design basis earthquake and maximum considered earthquake levels are used to train the models and examine their accuracies. The first three natural periods of the frame and combinations thereof are considered as the inputs for the model. The results indicate that both models exhibit satisfactory prediction performances, with the ANN model having a slight edge on accuracy in most of the cases studied, especially when a smaller number of samples are used for training. A parametric sensitivity analysis shows that the seismic responses predicted by the ANN model generally exhibit less sensitivity to the inputs than do those predicted by the WWLSSVM model. The results also indicate that force- and displacement-based responses exhibit the highest sensitivity to the first and second natural periods, respectively.

Resolution invariant wavelet features of melanoma studied by SVM classifiers.

This article refers to the Computer Aided Diagnosis of the melanoma skin cancer. We derive wavelet-based features of melanoma from the dermoscopic images of pigmental skin lesions and apply binary C-SVM classifiers to discriminate malignant melanoma from dysplastic nevus. The aim of this research is to select the most efficient model of the SVM classifier for various image resolutions and to search for the best resolution-invariant wavelet bases. We show AUC as a function of the wavelet number and SVM kernels optimized by the Bayesian search for two independent data sets. Our results are compatible with the previous experiments to discriminate melanoma in dermoscopy images with ensembling and feed-forward neural networks.

A Novel Approach for Prediction of Monthly Ground Water Level Using a Hybrid Wavelet and Non-Tuned Self-Adaptive Machine Learning Model

In recent decades, due to groundwater withdrawal in the Kabodarahang region, Iran, Hamadan, hazardous events such as sinkholes, droughts, water scarcity, etc., have occurred. This study models groundwater level (GWL) of the Kabodarahang region using two novel techniques including Self-Adaptive Extreme Learning Machine (SAELM) and Wavelet-Self-Adaptive Extreme Learning Machine (WA-SAELM). Using the stepwise selection as different lags along with different input combinations, ten different SAELM and WA-SAELM models were developed. First, the best activation function is chosen for numerical models. After that, GWL values were normalized to equalize the values and enhance speed and accuracy of modeling. Then, an optimized mother wavelet is selected in order to simulate GWLs. Next, the best model was introduced as the superior model in which values of the correlation coefficient (R), Root Mean Squared Error (RMSE) and Nash-Sutcliffe efficiency coefficient (NSC) were obtained 0.969, 0.358 and 0.939, respectively. In addition, the results of the superior model are compared with classical neural network models such as Artificial Neural Network (ANN), Wavelet-Artificial Neural Network (WA-ANN), Support Vector Machine (SVM) and Wavelet-Support Vector Machine (WA-SVM). Among all models, WA-SAELM approximated GWLs with higher accuracy. Furthermore, based on the results obtained from an uncertainty analysis, the superior model was identified as a model with an underestimated performance. Additionally, an explicit and practical matrix was proposed for computing GWLs. Finally, the matrix was validated for another piezometer.

Transient signal identification of HVDC transmission lines based on wavelet entropy and SVM

High-voltage DC (HVDC) transmission plays an important role in power transmission projects due to its advantages of large transmission power and good control performance. As the main protection of the DC transmission line, transient protection uses the high-frequency signal generated by fault transient to detect faults, having the characteristics of fast response and high accuracy. However, the HVDC transmission line has complex conditions along the route and is vulnerable to lightning strikes and other accidents, resulting in the occurrence of a variety of transients in the line, which increases the difficulty of fault identification. Being able to reveal signal time-frequency characteristic, wavelet entropy is an effective tool of signal recognition. This study proposes a method of transient signal identification based on the wavelet entropy and support vector machine (SVM). Firstly, the transient processes of three kinds of signals, including unipolar faults, lightning strike faults, and lightning disturbances, are briefly introduced. Then the time−frequency features of three kinds of transient signals under different scenes are analysed by wavelet entropy. Finally, the training set was used to train the SVM classification model with the signal wavelet entropy being taken as the eigenvector, and the test results validate the effectiveness of the proposed method.

A feature selection approach for hyperspectral image based on modified ant lion optimizer

Feature selection is one of the most important issues in hyperspectral image (HSI) classification to achieve high correlation between the adjacent bands. The main concern is selecting fewer bands with the highest accuracy as possible. Generally, it is a combinatorial optimization problem and cannot be fully solved by swarm intelligence algorithms. Ant lion optimizer (ALO) is a newly proposed swarm intelligence algorithm that mimics the swarming behaviour of antlions. In addition, wavelet support vector machine (WSVM) is able to enhance the stability of the classification result, and Lévy flight helps swarm intelligence algorithms jump out of the local optimum. Therefore, in this paper, a novel feature selection method based on a modified ALO (MALO) and WSVM is proposed to reduce the dimensionality of HSIs. The proposed method is compared with some state-of-the-art algorithms on some HSI datasets. Moreover, a new evaluating criteria is formulated to estimate the performance of feature selection, and the classification accuracy and selected number of bands are balanced as much as possible. Experimental results demonstrate that the proposed method outperforms other approaches, finds the optimal solution with a reasonable convergence orientation, and its classification accuracy is satisfied with fewer bands, it is robust, adaptive and might be applied for practical work of feature selection.