Mohamad O. Diab

Classification performance of the frequency-related parameters derived from uterine EMG signals

Frequency-related parameters derived from the uterine electromyogram (EMG) signals are widely used in many pregnancy monitoring and preterm delivery prediction studies. Although they are classical parameters, they are well suited for quantifying uterine EMG signals and have many advantages over amplitude-related parameters. The present work aims to compare various frequency-related parameters according to their classification performances (pregnancy vs. labor) using the receiver operating characteristic (ROC) curve analysis. The comparison between the parameters indicates that median frequency is the best frequency-related parameter that can be used for distinguishing between pregnancy and labor contractions. We conclude that median frequency can be the representative frequency-related parameter for classification problems of uterine EMG.

Complexity analysis of the uterine electromyography

In respect to the main goal of our ongoing work for predicting preterm birth, we analyze in this paper the complexity of the uterine electromyography (EMG) by using the sample entropy (SampEn) algorithm. By considering recent methodological developments, we measure the SampEn over multiple scales using the wavelet packet decomposition method. The results obtained from the analyzed data indicate that SampEn decreases along pregnancy. Furthermore, we demonstrate that the computed SampEn parameter may discriminate between the two classes (pregnancy/labor). The results are supported by statistical analysis using t-test indicating good statistical significance with a confidence level of 95%. A surrogate data test is also performed to investigate the nature of the underlying dynamics of our experimental data. The results are very promising for monitoring pregnancy and detecting labor to help identify preterm labor.

Classification of multichannel uterine EMG signals

Classification of multichannel uterine electromyogram (EMG) signals is addressed. Signals were recorded by a matrix of 16 electrodes. First, signals corresponding to each channel were individually classified using an artificial neural network (ANN) based on radial basis functions (RBF). The results have shown that the classification performance varies from one channel to another. Then, a decision fusion method based on these classification performances was tested. After fusion, the network yielded better classification accuracy than any individual channel could provide. The high percentage of correctly classified labor/non-labor events proves the efficiency of multichannel recordings in detecting labor. These findings can be very useful for the aim of classifying antepartum versus labor patients.

A multisensor data fusion approach for improving the classification accuracy of uterine EMG signals

Multisensor data fusion is an important technique used for solving various pattern recognition problems. In this paper, we used data fusion for improving the classification of uterine electromyogram (EMG) signals recorded by 16 electrodes positioned on the abdominal wall of the pregnant women. First, we evaluated the classification performance of each channel. Then, we applied a decision-level fusion method based first on the majority voting (MV), then on the weighted majority voting (WMV) rules. The results were very promising. The fusion of data from multiple sensors improved the accuracy of uterine EMG classification. The high percentage of correctly classified events, compared with earlier results, proves the efficiency of this approach for detecting labor.

Combining data fusion with multiresolution analysis for improving the classification accuracy of uterine EMG signals

Multisensor data fusion is a powerful solution for solving difficult pattern recognition problems such as the classification of bioelectrical signals. It is the process of combining information from different sensors to provide a more stable and more robust classification decisions. We combine here data fusion with multiresolution analysis based on the wavelet packet transform (WPT) in order to classify real uterine electromyogram (EMG) signals recorded by 16 electrodes. Herein, the data fusion is done at the decision level by using a weighted majority voting (WMV) rule. On the other hand, the WPT is used to achieve significant enhancement in the classification performance of each channel by improving the discrimination power of the selected feature. We show that the proposed approach tested on our recorded data can improve the recognition accuracy in labor prediction and has a competitive and promising performance.

The smartphone accessory heart rate monitor

This paper describes a design for a smartphone accessory that aims to determine the human heart rate, especially for cardiac patients who need to monitor their heart rate, it being an important indicator for prognosis and diagnosis, and also share it with their physician anytime to seek medical advice when needed. The goal of this paper is to present our design of this compact sized and user friendly smartphone accessory that can be accounted in clinical care and practice.

An unsupervised classification method of uterine electromyography signals using wavelet decomposition

The purpose of this study is to classify the uterine contractions in the electromyography (EMG) signal. As the frequency content of the contraction changes from one woman to another and during the pregnancy, wavelet decomposition is used to extract the parameters of each contraction, and an unsupervised statistical classification method based on Fisher test is used to classify events. A principal component analysis projection is then used to evidence the groups resulting from this classification. Results show that uterine contractions may be classified into independent groups according to their frequency content.

Classification of uterine EMG signals by using Normalized Wavelet Packet Energy

The aim of this work is to detect labor by classifying uterine electromyogram (EMG) signals into 2 classes: pregnancy and labor. Based on the fact that the energy distribution of the uterine EMG signals varies throughout pregnancy, the recorded signals are first decomposed into a 3-level wavelet packet tree then the Normalized Wavelet Packets Energies (NWPEs) are calculated and used to classify the signals. The high percentage of correctly classified events indicates that the use of NWPE can be a suitable choice for solving classification problems of electrophysiological signals and proves the efficiency of this approach in detecting labor.

Combining multiple support vector machines for boosting the classification accuracy of uterine EMG signals

A defining feature of physiological systems is the complexity both in their structures and functions. As a result, classifying physiological data is a difficult task. In this paper, we propose the use of a committee machines with a Support Vector Machines (SVM) as the component classifier in order to boost the classification accuracy of multichannel uterine electromyogram (EMG) signals. The approach was applied on each channel and a majority voting rule was used in order to determine the final decision of the committee. The results indicate that a committee machines exhibits performance unobtainable by an individual committee member on its own. We conclude that this approach can improve the recognition accuracy and has a competitive and promising performance.

Classification of multichannel uterine EMG signals by using unsupervised competitive learning

Multichannel analysis is an innovative technique used for the analysis of bioelectrical signals. In this paper, we analyzed uterine Electromyogram (EMG) signals recorded by means of a 4×4 electrode matrix positioned on the womans abdomen by using a multichannel approach. Relevant features were extracted from each channel and fed to a competitive neural network (CNN). First, we evaluated the classification performance of each channel. Then, we compared these performances to see which channel ranks better than the others. Finally, a decision fusion method based on the weighted sum of the individual decision of each channel was tested. The results showed that data can be grouped into 2 different groups. Furthermore, they showed that the classification performance varies according to the position of the electrode. Therefore, when a decision fusion rule was applied, the network yielded better classification accuracy than any individual channel could provide. These encouraging results prove that multichannel analysis can improve the classification of uterine EMG signals.