Towards the development of a new wavelet for ECG classification

In this paper an attempt has been made to determine the number of Premature Ventricular Contraction (PVC) cycles accurately from a given Electrocardiogram (ECG) using a wavelet constructed from multiple Gaussian functions. It is difficult to assess the ECGs of patients who are continuously monitored over a long period of time. Hence the proposed method of classification will be helpful to doctors to determine the severity of PVC in a patient. Principal Component Analysis (PCA) and a simple classifier have been used in addition to the specially developed wavelet transform. The proposed wavelet has been designed using multiple Gaussian functions which when summed up looks similar to that of a normal ECG. The number of Gaussians used depends on the number of peaks present in a normal ECG. The developed wavelet satisfied all the properties of a traditional continuous wavelet. The new wavelet was optimized using genetic algorithm (GA). ECG records from Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database have been used for validation. Out of the 8694 ECG cycles used for evaluation, the classification algorithm responded with an accuracy of 97.77%. In order to compare the performance of the new wavelet, classification was also performed using the standard wavelets like morlet, meyer, bior3.9, db5, db3, sym3 and haar. The new wavelet outperforms the rest

Smart-phone based electrocardiogram wavelet decomposition and neural network classification

This paper discusses ECG classification after parametrizing the ECG waveforms in the wavelet domain. The aim of the work is to develop an accurate classification algorithm that can be used to diagnose cardiac beat abnormalities detected using a mobile platform such as smart-phones. Continuous time recurrent neural network classifiers are considered for this task. Records from the European ST-T Database are decomposed in the wavelet domain using discrete wavelet transform (DWT) filter banks and the resulting DWT coefficients are filtered and used as inputs for training the neural network classifier. Advantages of the proposed methodology are the reduced memory requirement for the signals which is of relevance to mobile applications as well as an improvement in the ability of the neural network in its generalization ability due to the more parsimonious representation of the signal to its inputs.

Dysfunctional and compensatory duality in mild cognitive impairment during a continuous recognition memory task

One of the current issues of debate in the study of mild cognitive impairment (MCI) is deviations of oscillatory brain responses from normal brain states and its dynamics. This work aims to characterize the differences of power in brain oscillations during the execution of a recognition memory task in MCI subjects in comparison with elderly controls. Magnetoencephalographic (MEG) signals were recorded during a continuous recognition memory task performance. Oscillatory brain activity during the recognition phase of the task was analyzed by wavelet transform in the source space by means of minimum norm algorithm. Both groups obtained a 77% hit ratio. In comparison with healthy controls, MCI subjects showed increased theta (p < 0.001), lower beta reduction (p < 0.001) and decreased alpha and gamma power (p < 0.002 and p < 0.001 respectively) in frontal, temporal and parietal areas during early and late latencies. Our results point towards a dual pattern of activity (increase and decrease) which is indicative of MCI and specific to certain time windows, frequency bands and brain regions. These results could represent two neurophysiological sides of MCI. Characterizing these opposing processes may contribute to the understanding of the disorder.

Proteção diferencial de transformadores de potência utilizando a transformada Wavelet

About 10% of faults involving the electrical system occurs in power transformers. Therefore, the protection applied to the power transformers is essential to ensure the continuous operation of this device and the efficiency of the electrical system. Among the protection functions applied to power transformers, the differential protection appears as one of the main schemes, presenting reliable discrimination between internal faults and external faults or inrush currents. However, when using the low frequency components of the differential currents flowing through the transformer, the main difficulty of the conventional methods of differential protection is the delay for detection of the events. However, internal faults, external faults and other disturbances related to the transformer operation present transient and can be appropriately detected by the wavelet transform. In this paper is proposed the development of a wavelet-based differential protection for detection and identification of external faults to the transformer, internal faults, and transformer energizing by using the wavelet coefficient energy of the differential currents. The obtained results reveal the advantages of using of the wavelet transform in the differential protection compared to conventional protection, since it provides reliability and speed in detection of these events.

Wavelet analysis of MODIS time series to detect expansion and intensification of row-crop agriculture in Brazil

Since 2000, the southwestern Brazilian Amazon has undergone a rapid transformation from natural vegetation and pastures to row-crop agricultural with the potential to affect regional biogeochemistry. The goals of this research are to assess wavelet algorithms applied to MODIS time series to determine expansion of row-crops and intensification of the number of crops grown. MODIS provides data from February 2000 to present, a period of agricultural expansion and intensification in the southwestern Brazilian Amazon. We have selected a study area near Comodoro, Mato Grosso because of the rapid growth of row-crop agriculture and availability of ground truth data of agricultural land-use history. We used a 90% power wavelet transform to create a wavelet-smoothed time series for five years of MODIS EVI data. From this wavelet-smoothed time series we determine characteristic phenology of single and double crops. We estimate that over 3200 km(2) were converted from native vegetation and pasture to row-crop agriculture from 2000 to 2005 in our study area encompassing 40,000 km(2). We observe an increase of 2000 km(2) of agricultural intensification, where areas of single crops were converted to double crops during the study period. (C) 2007 Elsevier Inc. All rights reserved.

Power quality analysis applying a hybrid methodology with wavelet transforms and neural networks

A hybrid system to automatically detect, locate and classify disturbances affecting power quality in an electrical power system is presented in this paper. The disturbances characterized are events from an actual power distribution system simulated by the ATP (Alternative Transients Program) software. The hybrid approach introduced consists of two stages. In the first stage, the wavelet transform (WT) is used to detect disturbances in the system and to locate the time of their occurrence. When such an event is flagged, the second stage is triggered and various artificial neural networks (ANNs) are applied to classify the data measured during the disturbance(s). A computational logic using WTs and ANNs together with a graphical user interface (GU) between the algorithm and its end user is then implemented. The results obtained so far are promising and suggest that this approach could lead to a useful application in an actual distribution system. (C) 2009 Elsevier Ltd. All rights reserved.

Classification of normal swallowing and oropharyngeal dysphagia using wavelet

Oropharyngeal dysphagia is characterized by any alteration in swallowing dynamics which may lead to malnutrition and aspiration pneumonia. Early diagnosis is crucial for the prognosis of patients with dysphagia, and the best method for swallowing dynamics assessment is swallowing videofluoroscopy, an exam performed with X-rays. Because it exposes patients to radiation, videofluoroscopy should not be performed frequently nor should it be prolonged. This study presents a non-invasive method for the pre-diagnosis of dysphagia based on the analysis of the swallowing acoustics, where the discrete wavelet transform plays an important role to increase sensitivity and specificity in the identification of dysphagic patients. (C) 2008 Elsevier Inc. All rights reserved.

A wavelet visible difference predictor

In this paper, we describe a model of the human visual system (HVS) based on the wavelet transform. This model is largely based on a previously proposed model, but has a number of modifications that make it more amenable to potential integration into a wavelet based image compression scheme. These modifications include the use of a separable wavelet transform instead of the cortex transform, the application of a wavelet contrast sensitivity function (CSP), and a simplified definition of subband contrast that allows us to predict noise visibility directly from wavelet coefficients. Initially, we outline the luminance, frequency, and masking sensitivities of the HVS and discuss how these can be incorporated into the wavelet transform. We then outline a number of limitations of the wavelet transform as a model of the HVS, namely the lack of translational invariance and poor orientation sensitivity. In order to investigate the efficacy of this wavelet based model, a wavelet visible difference predictor (WVDP) is described. The WVDP is then used to predict visible differences between an original and compressed (or noisy) image. Results are presented to emphasize the limitations of commonly used measures of image quality and to demonstrate the performance of the WVDP, The paper concludes with suggestions on bow the WVDP can be used to determine a visually optimal quantization strategy for wavelet coefficients and produce a quantitative measure of image quality.

Wavelet correlation between subjects: A time-scale data driven analysis for brain mapping using fMRI

Functional magnetic resonance imaging (fMRI) based on BOLD signal has been used to indirectly measure the local neural activity induced by cognitive tasks or stimulation. Most fMRI data analysis is carried out using the general linear model (GLM), a statistical approach which predicts the changes in the observed BOLD response based on an expected hemodynamic response function (HRF). In cases when the task is cognitively complex or in cases of diseases, variations in shape and/or delay may reduce the reliability of results. A novel exploratory method using fMRI data, which attempts to discriminate between neurophysiological signals induced by the stimulation protocol from artifacts or other confounding factors, is introduced in this paper. This new method is based on the fusion between correlation analysis and the discrete wavelet transform, to identify similarities in the time course of the BOLD signal in a group of volunteers. We illustrate the usefulness of this approach by analyzing fMRI data from normal subjects presented with standardized human face pictures expressing different degrees of sadness. The results show that the proposed wavelet correlation analysis has greater statistical power than conventional GLM or time domain intersubject correlation analysis. (C) 2010 Elsevier B.V. All rights reserved.

A new wavelet-based adaptive method for solving population balance equations

A new wavelet-based adaptive framework for solving population balance equations (PBEs) is proposed in this work. The technique is general, powerful and efficient without the need for prior assumptions about the characteristics of the processes. Because there are steeply varying number densities across a size range, a new strategy is developed to select the optimal order of resolution and the collocation points based on an interpolating wavelet transform (IWT). The proposed technique has been tested for size-independent agglomeration, agglomeration with a linear summation kernel and agglomeration with a nonlinear kernel. In all cases, the predicted and analytical particle size distributions (PSDs) are in excellent agreement. Further work on the solution of the general population balance equations with nucleation, growth and agglomeration and the solution of steady-state population balance equations will be presented in this framework. (C) 2002 Elsevier Science B.V. All rights reserved.

Hybrid Wavelet-PSO-ANFIS Approach for Short-Term Electricity Prices Forecasting

A novel hybrid approach, combining wavelet transform, particle swarm optimization, and adaptive-network-based fuzzy inference system, is proposed in this paper for short-term electricity prices forecasting in a competitive market. Results from a case study based on the electricity market of mainland Spain are presented. A thorough comparison is carried out, taking into account the results of previous publications. Finally, conclusions are duly drawn.

Analysis of stock market indices with multidimensional scaling and wavelets

Stock market indices SMIs are important measures of financial and economical performance. Considerable research efforts during the last years demonstrated that these signals have a chaotic nature and require sophisticated mathematical tools for analyzing their characteristics. Classical methods, such as the Fourier transform, reveal considerable limitations in discriminating different periods of time. This paper studies the dynamics of SMI by combining the wavelet transform and the multidimensional scaling MDS . Six continuous wavelets are tested for analyzing the information content of the stock signals. In a first phase, the real Shannon wavelet is adopted for performing the evaluation of the SMI dynamics, while their comparison is visualized by means of the MDS. In a second phase, the other wavelets are also tested, and the corresponding MDS plots are analyzed.

Técnicas de deteção de dano estrutural com base na monitorização

Ao longo dos últimos anos, acompanhada da evolução tecnológica, da dificuldade da inspeção visual e da consciencialização dos efeitos de uma má inspeção, verificou-se uma maior sensibilidade para a importância da monitorização estrutural, principalmente nas grandes infra-estruturas de engenharia civil. Os sistemas de monitorização estrutural permitem o acompanhamento contínuo do comportamento de uma determinada estrutura de tal forma que com os dados obtidos, é possível avaliar alterações no comportamento da mesma. Com isso, tem-se desenvolvido e implementado estratégias de identificação de danos estruturais com o intuito de aumentar a fiabilidade estrutural e evitar precocemente que alterações na condição da estrutura possam evoluir para situações mais severas. Neste contexto, a primeira parte desta dissertação consiste numa introdução à monitorização estrutural e à deteção de dano estrutural. Relativamente à monitorização, são expostos os seus objetivos e os princípios da sua aplicação. Conjuntamente são apresentados e descritos os principais sensores e são explicadas as funcionalidades de um sistema de aquisição de dados. O segundo tema aborda a importância da deteção de dano introduzindo os métodos estudados neste trabalho. Destaca-se o método das linhas de influência, o método da curvatura dos modos de vibração e o método da transformada de wavelet. Na segunda parte desta dissertação são apresentados dois casos de estudo. O primeiro estudo apresenta uma componente numérica e uma componente experimental. Estuda-se um modelo de viga que se encontra submetida a vários cenários de dano e valida-se a capacidade do método das linhas de influência em detetar e localizar essas anomalias. O segundo estudo consiste na modelação numérica de uma ponte real, na posterior simulação de cenários de dano e na análise comparativa da eficácia de cada um dos três métodos de deteção de dano na identificação e localização dos danos simulados. Por último, são apresentadas as principais conclusões deste trabalho e são sugeridos alguns tópicos a explorar na elaboração de trabalhos futuros.

Alterações da Actividade Autonómica Durante o Teste de Inclinação em Doentes com Fibrilhação Auricular Paroxística: Análise com Wavelets

The autonomic nervous system (ANS) is known to be an important modulator in the pathogenesis of paroxysmal atrial fibrillation (PAF). Changes in ANS control of heart rate variability (HRV) occur during orthostatism to maintain cardiovascular homeostasis. Wavelet transform has emerged as a useful tool that provides time-frequency decomposition of the signal under investigation, enabling intermittent components of transient phenomena to be analyzed. AIM: To study HRV during head-up tilt (HUT) with wavelet transform analysis in PAF patients and healthy individuals (normals). METHODS: Twenty-one patients with PAF (8 men; age 58 +/- 14 yrs) were examined and compared with 21 normals (7 men, age 48 +/- 12 yrs). After a supine resting period, all subjects underwent passive HUT (60 degrees) while in sinus rhythm. Continuous monitoring of ECG and blood pressure was carried out (Task Force Monitor, CNSystems). Acute changes in RR-intervals were assessed by wavelet analysis and low-frequency power (LF: 0.04-0.15 Hz), high-frequency power (HF: 0.15-0.60 Hz) and LF/HF (sympathovagal) were calculated for 1) the last 2 min of the supine period; 2) the 15 sec of tilting movement (TM); and 3) the 1st (TT1) and 2nd (TT2) min of HUT. Data are expressed as means +/- SEM. RESULTS: Baseline and HUT RR-intervals were similar for the two groups. Supine basal blood pressure was also similar for the two groups, with a sustained increase in PAF patients, and a decrease followed by an increase and then recovery in normals. Basal LF, HF and LF/ HF values in PAF patients were 632 +/- 162 ms2, 534 +/- 231 ms2 and 1.95 +/- 0.39 respectively, and 1058 +/- 223 ms2, 789 +/- 244 ms2 and 2.4 +/- 0.36 respectively in normals (p = NS). During TM, LF, HF and LF/HF values for PAF patients were 747 +/- 277 ms2, 387 +/- 94 ms2 and 2.9 +/- 0.6 respectively, and 1316 +/- 315 ms2, 698 +/- 148 ms2 and 2.8 +/- 0.6 respectively in normals (p < 0.05 for LF and HF). During TF1, LF, HF and LF/ HF values for PAF patients were 1243 +/- 432 ms2, 302 +/- 88 ms2 and 7.7 +/- 2.4 respectively, and 1992 +/- 398 ms2, 333 +/- 76 ms2 and 7.8 +/- 0.98 respectively for normals (p < 0.05 for LF). During TF2, LF, HF and LF/HF values for PAF patients were 871 +/- 256 ms2, 242 +/- 51 ms2 and 4.7 +/- 0.9 respectively, and 1263 +/- 335 ms2, 317 +/- 108 ms2 and 8.6 +/- 0.68 respectively for normals (p < 0.05 for LF/HF). The dynamic profile of HRV showed that LF and HF values in PAF patients did not change significantly during TM or TT2, and LF/HF did not change during TM but increased in TT1 and TT2. CONCLUSION: Patients with PAF present alterations in HRV during orthostatism, with decreased LF and HF power during TM, without significant variations during the first minutes of HUT. These findings suggest that wavelet transform analysis may provide new insights when assessing autonomic heart regulation and highlight the presence of ANS disturbances in PAF.

Automatic Small Bowel Tumor Diagnosis by Using Multi-Scale Wavelet-Based Analysis in Wireless Capsule Endoscopy Images

BACKGROUND: Wireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity. METHOD: The set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis. RESULTS: The proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.