Current wavelet thresholding methods for cardiogram signals captured by flexible wearable sensors face a challenge in achieving both accurate thresholding and real-time signal denoising. This paper proposes a real-time accurate thresholding method based on signal estimation, specifically the normalized ACF, as an alternative to traditional noise estimation without the need for parameter fine-tuning and extensive data training. This method is experimentally validated using a variety of electrocardiogram (ECG) signals from different databases, each containing specific types of noise such as additive white Gaussian (AWG) noise, baseline wander noise, electrode motion noise, and muscle artifact noise. Although this method only slightly outperforms other methods in removing AWG noise in ECG signals, it far outperforms conventional methods in removing other real noise. This is attributed to the method's ability to accurately distinguish not only AWG noise that is significantly different spectrum of the ECG signal, but also real noise with similar spectra. In contrast, the conventional methods are effective only for AWG noise. In additional, this method improves the denoising visualization of the measured ECG signals and can be used to optimize other parameters of other wavelet methods to enhancing the denoised periodic signals, thereby improving diagnostic accuracy.
Stock market, is one of the most important financial market which has a close relationship with a country's economy, due to which it is often called the barometer of the economy. Over the past 25 years, the stock markets have been affected by different global economic shocks. Various researchers have analyzed different aspects of these effects one by one, however, this study is an assessment of stock market interrelationship of emeriging Asian economies which include most of the East Asian, and Southeast Asian emerging economies with special focus on China for past decades during which different crisis occurred. We used Morgan Stanley capital international (MSCI) daily indices data for each stock market and compared Chinese stock market with the stock markets of India, Pakistan, Malaysia, Singapore, and Indonesia. We analyzed the data through the individual wavelet power spectrum, cross-wavelet transform and wavelet coherence, to determine the correlation and volatility among the selected stock markets. These model have the power to analyze co-movements among these countries with respect to both frequency and time spaces. Our findings show that there are co-movement patterns of higher frequencies during the crises periods of 1997, 2008 and 2015. The dependency strength among the considered economies is noted to increase in the crisis periods, which implies increased short- and long-term benefits for the investors. From a financial point of view, it has been determined that the co-movement strength among the emerging economies of Asia may have an effect on the VaR (Value at Risk) levels of a multi-country portfolio. Furthermore, the stock market of China shows a high correlation with the other six Asian stock emerging markets in both high and low-frequency spectrums. The association of the south and east Asian stock market with Chinese stock markets show the interconnection of these economies with the economy of China since past two decades. These findings are useful for investors, portfolio managers and the policymaker around the globe.
This study presents the use of a wavelet-based time series model to forecast the daily average particulate matter with an aerodynamic diameter of less than 10 μm (PM10) in Peninsular Malaysia. The highlight of this study is the use of a discrete wavelet transform (DWT) in order to improve the forecast accuracy. The DWT was applied to convert the highly variable PM10 series into more stable approximations and details sub-series, and the ARIMA-GARCH time series models were developed for each sub-series. Two different forecast periods, one was during normal days, while the other was during haze episodes, were designed to justify the usefulness of DWT. The models' performance was evaluated by four indices, namely root mean square error, mean absolute percentage error, probability of detection and false alarm rate. The results showed that the model incorporated with DWT yielded more accurate forecasts than the conventional method without DWT for both the forecast periods, and the improvement was more prominent for the period during the haze episodes.
Image processing is introduced to remove or reduce the noise and unwanted signal that deteriorate the quality of an image. Here, a single level two-dimensional wavelet transform is applied to the image in order to obtain the wavelet transform sub-band signal of an image. An estimation technique to predict the noise variance in an image is proposed, which is then fed into a Wiener filter to filter away the noise from the sub-band of the image. The proposed filter is called adaptive tuning piecewise cubic Hermite interpolation with Wiener filter in the wavelet domain. The performance of this filter is compared with four existing filters: median filter, Gaussian smoothing filter, two level wavelet transform with Wiener filter and adaptive noise Wiener filter. Based on the results, the adaptive tuning piecewise cubic Hermite interpolation with Wiener filter in wavelet domain has better performance than the other four methods.
In this work, an algorithm for the classification of six motor functions from an electroencephalogram (EEG) signal that combines a common spatial pattern (CSP) filter and a continuous wavelet transform (CWT), is investigated. The EEG data comprise six grasp-and-lift events, which are used to investigate the potential of using EEG as input signals with brain computer interface devices for controlling prosthetic devices for upper limb movement. Selected EEG channels are the ones located over the motor cortex, C3, Cz and C4, as well as at the parietal region, P3, Pz and P4. In general, the proposed algorithm includes three main stages, band pass filtering, CSP filtering, and wavelet transform and training on GoogLeNet for feature extraction, feature learning and classification. The band pass filtering is performed to select the EEG signal in the band of 7 Hz to 30 Hz while eliminating artifacts related to eye blink, heartbeat and muscle movement. The CSP filtering is applied on two-class EEG signals that will result in maximizing the power difference between the two-class dataset. Since CSP is mathematically developed for two-class events, the extension to the multiclass paradigm is achieved by using the approach of one class versus all other classes. Subsequently, continuous wavelet transform is used to convert the band pass and CSP filtered signals from selected electrodes to scalograms which are then converted to images in grayscale format. The three scalograms from the motor cortex regions and the parietal region are then combined to form two sets of RGB images. Next, these RGB images become the input to GoogLeNet for classification of the motor EEG signals. The performance of the proposed classification algorithm is evaluated in terms of precision, sensitivity, specificity, accuracy with average values of 94.8%, 93.5%, 94.7%, 94.1%, respectively, and average area under the receiver operating characteristic (ROC) curve equal to 0.985. These results indicate a good performance of the proposed algorithm in classifying grasp-and-lift events from EEG signals.
To reduce undesirable charging effects in scanning electron microscope images, Rayleigh contrast stretching is developed and employed. First, re-scaling is performed on the input image histograms with Rayleigh algorithm. Then, contrast stretching or contrast adjustment is implemented to improve the images while reducing the contrast charging artifacts. This technique has been compared to some existing histogram equalization (HE) extension techniques: recursive sub-image HE, contrast stretching dynamic HE, multipeak HE and recursive mean separate HE. Other post processing methods, such as wavelet approach, spatial filtering, and exponential contrast stretching, are compared as well. Overall, the proposed method produces better image compensation in reducing charging artifacts.
This study presents a wavelet analysis of resultant velocity features belonging to genuine and forged groups of signature sample. Signatures of individuals were initially classified based on visual human perceptions of their relative sizes, complexities, and legibilities of the genuine counterparts. Then, the resultant velocity was extracted and modeled through wavelet analysis from each sample. The wavelet signal was decomposed into several layers based on maximum overlap discrete wavelet transform (MODWT). Next, the zero crossing rate features were calculated from all the high wavelet sub-bands. A total of seven hypotheses were then tested using a two-way ANOVA testing methodology. Of these, four hypotheses were conducted to test for significance differences between distributions. In addition, three hypotheses were run to provide test for interaction between two factors of signature authentication versus perceived classification. The results demonstrated that both feature distributions belonging to genuine and forged groups of samples cannot be distinguished by themselves. Instead, they were significantly different under the influence of two other inherent factors, namely perceived size and legibility. Such new findings are useful information particularly in providing bases for forensic justifications in establishing the authenticity of handwritten signature specimens.
Ultrasound is an important and low cost imaging modality used to study the internal organs of human body and blood flow through blood vessels. It uses high frequency sound waves to acquire images of internal organs. It is used to screen normal, benign and malignant tissues of various organs. Healthy and malignant tissues generate different echoes for ultrasound. Hence, it provides useful information about the potential tumor tissues that can be analyzed for diagnostic purposes before therapeutic procedures. Ultrasound images are affected with speckle noise due to an air gap between the transducer probe and the body. The challenge is to design and develop robust image preprocessing, segmentation and feature extraction algorithms to locate the tumor region and to extract subtle information from isolated tumor region for diagnosis. This information can be revealed using a scale space technique such as the Discrete Wavelet Transform (DWT). It decomposes an image into images at different scales using low pass and high pass filters. These filters help to identify the detail or sudden changes in intensity in the image. These changes are reflected in the wavelet coefficients. Various texture, statistical and image based features can be extracted from these coefficients. The extracted features are subjected to statistical analysis to identify the significant features to discriminate normal and malignant ultrasound images using supervised classifiers. This paper presents a review of wavelet techniques used for preprocessing, segmentation and feature extraction of breast, thyroid, ovarian and prostate cancer using ultrasound images.
Identification of alarming features in the electrocardiogram (ECG) signal is extremely significant for the prediction of congestive heart failure (CHF). ECG signal analysis carried out using computer-aided techniques can speed up the diagnosis process and aid in the proper management of CHF patients. Therefore, in this work, dual tree complex wavelets transform (DTCWT)-based methodology is proposed for an automated identification of ECG signals exhibiting CHF from normal. In the experiment, we have performed a DTCWT on ECG segments of 2s duration up to six levels to obtain the coefficients. From these DTCWT coefficients, statistical features are extracted and ranked using Bhattacharyya, entropy, minimum redundancy maximum relevance (mRMR), receiver-operating characteristics (ROC), Wilcoxon, t-test and reliefF methods. Ranked features are subjected to k-nearest neighbor (KNN) and decision tree (DT) classifiers for automated differentiation of CHF and normal ECG signals. We have achieved 99.86% accuracy, 99.78% sensitivity and 99.94% specificity in the identification of CHF affected ECG signals using 45 features. The proposed method is able to detect CHF patients accurately using only 2s of ECG signal length and hence providing sufficient time for the clinicians to further investigate on the severity of CHF and treatments.
Ambulatory EEGs began emerging in the healthcare industry over the years, setting a new norm for long-term monitoring services. The present devices in the market are neither meant for remote monitoring due to their technical complexity nor for meeting clinical setting needs in epilepsy patient monitoring. In this paper, we propose an ambulatory EEG device, OptiEEG, that has low setup complexity, for the remote EEG monitoring of epilepsy patients. OptiEEG's signal quality was compared with a gold standard clinical device, Natus. The experiment between OptiEEG and Natus included three different tests: eye open/close (EOC); hyperventilation (HV); and photic stimulation (PS). Statistical and wavelet analysis of retrieved data were presented when evaluating the performance of OptiEEG. The SNR and PSNR of OptiEEG were slightly lower than Natus, but within an acceptable bound. The standard deviations of MSE for both devices were almost in a similar range for the three tests. The frequency band energy analysis is consistent between the two devices. A rhythmic slowdown of theta and delta was observed in HV, whereas photic driving was observed during PS in both devices. The results validated the performance of OptiEEG as an acceptable EEG device for remote monitoring away from clinical environments.
Content-based image retrieval techniques have been extensively studied for the past few years. With the growth of digital medical image databases, the demand for content-based analysis and retrieval tools has been increasing remarkably. Blood cell image is a key diagnostic tool for hematologists. An automated system that can retrieved relevant blood cell images correctly and efficiently would save the effort and time of hematologists. The purpose of this work is to develop such a content-based image retrieval system. Global color histogram and wavelet-based methods are used in the prototype. The system allows users to search by providing a query image and select one of four implemented methods. The obtained results demonstrate the proposed extended query refinement has the potential to capture a user's high level query and perception subjectivity by dynamically giving better query combinations. Color-based methods performed better than wavelet-based methods with regard to precision, recall rate and retrieval time. Shape and density of blood cells are suggested as measurements for future improvement. The system developed is useful for undergraduate education.
Wavelet theory is emerging as one of the prevalent tool in signal and image processing applications. However, the most suitable mother wavelet for these applications is still a relative question mark amongst researchers. Selection of best mother wavelet through parameterization leads to better findings for the analysis in comparison to random selection. The objective of this article is to compare the performance of the existing members of mother wavelets and to select the most suitable mother wavelet for accurate infant cry classification. Optimal wavelet is found using three different criteria namely the degree of similarity of mother wavelets, regularity of mother wavelets and accuracy of correct recognition during classification processes. Recorded normal and pathological infant cry signals are decomposed into five levels using wavelet packet transform. Energy and entropy features are extracted at different sub bands of cry signals and their effectiveness are tested with four supervised neural network architectures. Findings of this study expound that, the Finite impulse response based approximation of Meyer is the best wavelet candidate for accurate infant cry classification analysis.
This paper reports on a two-step approach for optimally determining the location and severity of damage in beam structures under flexural vibration. The first step focuses on damage location detection. This is done by defining the damage index called relative wavelet packet entropy (RWPE). The damage severities of the model in terms of loss of stiffness are assessed in the second step using the inverse solution of equations of motion of a structural system in the wavelet domain. For this purpose, the connection coefficient of the scaling function to convert the equations of motion in the time domain into the wavelet domain is applied. Subsequently, the dominant components based on the relative energies of the wavelet packet transform (WPT) components of the acceleration responses are defined. To obtain the best estimation of the stiffness parameters of the model, the least squares error minimization is used iteratively over the dominant components. Then, the severity of the damage is evaluated by comparing the stiffness parameters of the identified model before and after the occurrence of damage. The numerical and experimental results demonstrate that the proposed method is robust and effective for the determination of damage location and accurate estimation of the loss in stiffness due to damage.
Parkinson's disease (PD) is a type of progressive neurodegenerative disorder that has affected a large part of the population till now. Several symptoms of PD include tremor, rigidity, slowness of movements and vocal impairments. In order to develop an effective diagnostic system, a number of algorithms were proposed mainly to distinguish healthy individuals from the ones with PD. However, most of the previous works were conducted based on a binary classification, with the early PD stage and the advanced ones being treated equally. Therefore, in this work, we propose a multiclass classification with three classes of PD severity level (mild, moderate, severe) and healthy control. The focus is to detect and classify PD using signals from wearable motion and audio sensors based on both empirical wavelet transform (EWT) and empirical wavelet packet transform (EWPT) respectively. The EWT/EWPT was applied to decompose both speech and motion data signals up to five levels. Next, several features are extracted after obtaining the instantaneous amplitudes and frequencies from the coefficients of the decomposed signals by applying the Hilbert transform. The performance of the algorithm was analysed using three classifiers - K-nearest neighbour (KNN), probabilistic neural network (PNN) and extreme learning machine (ELM). Experimental results demonstrated that our proposed approach had the ability to differentiate PD from non-PD subjects, including their severity level - with classification accuracies of more than 90% using EWT/EWPT-ELM based on signals from motion and audio sensors respectively. Additionally, classification accuracy of more than 95% was achieved when EWT/EWPT-ELM is applied to signals from integration of both signal's information.
Combining Mel Frequency Cepstral Coefficient with wavelet transform for feature extraction is not new. This paper proposes a new architecture to help in increasing the accuracy of speaker recognition compared with conventional architecture. In conventional speaker model, the voice will undergo noise elimination first before feature extraction. The proposed architecture however, will extract the features and eliminate noise simultaneously. The MFCC is used to extract the voice features while wavelet de-noising technique is used to eliminate the noise contained in the speech signals. Thus, the new architecture achieves two outcomes in one single process: ex-tracting voice feature and elimination of noise.
This paper proposes an approach to accurately estimate the impedance value of a high impedance fault (HIF) and the distance from its fault location for a distribution system. Based on the three-phase voltage and current waveforms which are monitored through a single measurement in the network, several features are extracted using discrete wavelet transform (DWT). The extracted features are then fed into the optimized artificial neural network (ANN) to estimate the HIF impedance and its distance. The particle swarm optimization (PSO) technique is employed to optimize the parameters of the ANN to enhance the performance of fault impedance and distance estimations. Based on the simulation results, the proposed method records encouraging results compared to other methods of similar complexity for both HIF impedance values and estimated distances.
Developing tools to assist physically disabled and immobilized people through facial expression is a challenging area of research and has attracted many researchers recently. In this paper, luminance stickers based facial expression recognition is proposed. Recognition of facial expression is carried out by employing Discrete Wavelet Transform (DWT) as a feature extraction method. Different wavelet families with their different orders (db1 to db20, Coif1 to Coif 5 and Sym2 to Sym8) are utilized to investigate their performance in recognizing facial expression and to evaluate their computational time. Standard deviation is computed for the coefficients of first level of wavelet decomposition for every order of wavelet family. This standard deviation is used to form a set of feature vectors for classification. In this study, conventional validation and cross validation are performed to evaluate the efficiency of the suggested feature vectors. Three different classifiers namely Artificial Neural Network (ANN), k-Nearest Neighborhood (kNN) and Linear Discriminant Analysis (LDA) are used to classify a set of eight facial expressions. The experimental results demonstrate that the proposed method gives very promising classification accuracies.
Age-related Macular Degeneration (AMD) is one of the major causes of vision loss and blindness in ageing population. Currently, there is no cure for AMD, however early detection and subsequent treatment may prevent the severe vision loss or slow the progression of the disease. AMD can be classified into two types: dry and wet AMDs. The people with macular degeneration are mostly affected by dry AMD. Early symptoms of AMD are formation of drusen and yellow pigmentation. These lesions are identified by manual inspection of fundus images by the ophthalmologists. It is a time consuming, tiresome process, and hence an automated diagnosis of AMD screening tool can aid clinicians in their diagnosis significantly. This study proposes an automated dry AMD detection system using various entropies (Shannon, Kapur, Renyi and Yager), Higher Order Spectra (HOS) bispectra features, Fractional Dimension (FD), and Gabor wavelet features extracted from greyscale fundus images. The features are ranked using t-test, Kullback-Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance (CBBD), Receiver Operating Characteristics (ROC) curve-based and Wilcoxon ranking methods in order to select optimum features and classified into normal and AMD classes using Naive Bayes (NB), k-Nearest Neighbour (k-NN), Probabilistic Neural Network (PNN), Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The performance of the proposed system is evaluated using private (Kasturba Medical Hospital, Manipal, India), Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) datasets. The proposed system yielded the highest average classification accuracies of 90.19%, 95.07% and 95% with 42, 54 and 38 optimal ranked features using SVM classifier for private, ARIA and STARE datasets respectively. This automated AMD detection system can be used for mass fundus image screening and aid clinicians by making better use of their expertise on selected images that require further examination.
Medical image fusion is the procedure of combining several images from one or multiple imaging modalities. In spite of numerous attempts in direction of automation ventricle segmentation and tracking in echocardiography, due to low quality images with missing anatomical details or speckle noises and restricted field of view, this problem is a challenging task. This paper presents a fusion method which particularly intends to increase the segment-ability of echocardiography features such as endocardial and improving the image contrast. In addition, it tries to expand the field of view, decreasing impact of noise and artifacts and enhancing the signal to noise ratio of the echo images. The proposed algorithm weights the image information regarding an integration feature between all the overlapping images, by using a combination of principal component analysis and discrete wavelet transform. For evaluation, a comparison has been done between results of some well-known techniques and the proposed method. Also, different metrics are implemented to evaluate the performance of proposed algorithm. It has been concluded that the presented pixel-based method based on the integration of PCA and DWT has the best result for the segment-ability of cardiac ultrasound images and better performance in all metrics.
Corrosion in carbon-steel pipelines leads to failure, which is a major cause of breakdown maintenance in the oil and gas industries. The acoustic emission (AE) signal is a reliable method for corrosion detection and classification in the modern Structural Health Monitoring (SHM) system. The efficiency of this system in detection and classification mainly depends on the suitable AE features. Therefore, many feature extraction and classification methods have been developed for corrosion detection and severity assessment. However, the extraction of appropriate AE features and classification of various levels of corrosion utilizing these extracted features are still challenging issues. To overcome these issues, this article proposes a hybrid machine learning approach that combines Wavelet Packet Transform (WPT) integrated with Fast Fourier Transform (FFT) for multiresolution feature extraction and Linear Support Vector Classifier (L-SVC) for predicting corrosion severity levels. A Laboratory-based Linear Polarization Resistance (LPR) test was performed on carbon-steel samples for AE data acquisition over a different time span. AE signals were collected at a high sampling rate with a sound well AE sensor using AEWin software. Simulation results show a linear relationship between the proposed approach-based extracted AE features and the corrosion process. For multi-class problems, three corrosion severity stages have been made based on the corrosion rate over time and AE activity. The ANOVA test results indicate the significance within and between the feature-groups where F-values (F-value>1) rejects the null hypothesis and P-values (P-value<0.05) are less than the significance level. The utilized L-SVC classifier achieves higher prediction accuracy of 99.0% than the accuracy of other benchmarked classifiers. Findings of our proposed machine learning approach confirm that it can be effectively utilized for corrosion detection and severity assessment in SHM applications.