Oussama El B'charri - Academia.edu (original) (raw)
Uploads
Papers by Oussama El B'charri
International Journal of Engineering and Technology Innovation, 2018
Electrocardiography is considered as a powerful technique for assessing heart condition. To study... more Electrocardiography is considered as a powerful technique for assessing heart condition. To study cardiac disorders, it is essential to localize and extract the QRS complex: the prominent region within the electrocardiogram signal. Since the QRS complex has various morphologies and is usually contaminated by severe overlapping spectral noise, accurate detection is a complicated task. This paper proposes a reliable method based on the Dual-Tree Wavelet Transform, which uses a threshold process to select the QRS frequency components and reduce the overlapping noise. The QRS deflections are then emphasized using squaring and moving average operators. The chosen decision rule is simple and based on the variance of the signal. The proposed method was tested on the MIT-BIH Arrhythmia database, and the algorithm showed high accuracy detection results compared to those of other recently published works.
Biomedical engineering online, Jan 7, 2017
Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, it is sensitiv... more Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, it is sensitive to miscellaneous mixed noises, which may reduce the diagnostic accuracy and hinder the physician's correct decision on patients. The dual tree wavelet transform (DT-WT) is one of the most recent enhanced versions of discrete wavelet transform. However, threshold tuning on this method for noise removal from ECG signal has not been investigated yet. In this work, we shall provide a comprehensive study on the impact of the choice of threshold algorithm, threshold value, and the appropriate wavelet decomposition level to evaluate the ECG signal de-noising performance. A set of simulations is performed on both synthetic and real ECG signals to achieve the promised results. First, the synthetic ECG signal is used to observe the algorithm response. The evaluation results of synthetic ECG signal corrupted by various types of noise has showed that the modified unified threshold and wavelet ...
International Review on Computers and Software (IRECOS), 2016
This paper proposes an efficient method of QRS extraction from the ECG signal using wavelet coeff... more This paper proposes an efficient method of QRS extraction from the ECG signal using wavelet coefficients. This method is composed of three parts. The extraction of QRS regions from details decompositions using an enhanced algorithm, the QRS detection by the elimination of falsely detected peaks and the extraction of higher peaks from the QRS complex. The proposed method has been tested on the 48 records of the MIT-BIH Arrhythmia database signals. The results obtained from this method are promising, compared to recently published techniques where the positive predictivity (Pp) is 99.91 %, and sensitivity (Se) is 99.77 %.
Biocybernetics and Biomedical Engineering, 2016
This paper proposes an efficient method of ECG signal denoising using the adaptive dual threshold... more This paper proposes an efficient method of ECG signal denoising using the adaptive dual threshold filter (ADTF) and the discrete wavelet transform (DWT). The aim of this method is to bring together the advantages of these methods in order to improve the filtering of the ECG signal. The aim of the proposed method is to deal with the EMG noises, the power line interferences and the high frequency noises that could perturb the ECG signal. This algorithm is based on three steps of denoising, namely, the DWT decomposition, the ADTF step and the highest peaks correction step. This paper presents certain applications of this algorithm on some of the MIT-BIH Arrhythmia database's signals. The results of these applications allow observing the high performance of the proposed method comparing to some other techniques recently published.
International Journal of Advanced Computer Science and Applications, 2016
The storage capacity of the ECG records presents an important issue in the medical practices. The... more The storage capacity of the ECG records presents an important issue in the medical practices. These data could contain hours of recording, which needs a large space for storage to save these records. The compression of the ECG signal is widely used to deal with this issue. The problem with this process is the possibility of losing some important features of the ECG signal. This loss could influence negatively the analyzing of the heart condition. In this paper, we shall propose an efficient method of the ECG signal compression using the discrete wavelet transform and the run length encoding. This method is based on the decomposition of the ECG signal, the thresholding stage and the encoding of the final data. This method is tested on some of the MIT-BIH arrhythmia signals from the international database Physionet. This method shows high performances comparing to other methods recently published.
International Journal of Advanced Computer Science and Applications, 2016
Cardiac diseases constitute the main cause of mortality around the globe. For detection and ident... more Cardiac diseases constitute the main cause of mortality around the globe. For detection and identification of cardiac problems, it is very important to monitor the patient's heart activities for long periods during his normal daily life. The recorded signal that contains information about the condition of the heart called electrocardiogram (ECG). As a result, long recording of ECG signal amounts to huge data sizes. In this work, a robust lossless ECG data compression scheme for realtime applications is proposed. The developed algorithm has the advantages of lossy compression without introducing any distortion to the reconstructed signal. The ECG signals under test were taken from the PTB Diagnostic ECG Database. The compression procedure is simple and provides a high compression ratio compared to other lossless ECG compression methods. The compressed ECG data is generated as a text file. The decompression scheme has also been developed using the reverse logic and it is observed that there is no difference between original and reconstructed ECG signal.
Telemedicine is experiencing a great growth in recent years, is a technology allowing remote heal... more Telemedicine is experiencing a great growth in recent years, is a technology allowing remote health services and exchange of medical information, among these areas we find telecardiology. In telecardiology the ECG requires a long recording. For this purpose the data are high, the reason that an effective compression method is required for biomedical signals. The electrocardiogram (ECG) or (EKG) is an important tool for assessing the heart condition of a patient, and is very sensitive to noise. For that several methods are proposed to denoising the ECG signal include: EMD, EEMD, DWT, and adaptive filter ADTF. After the transfer phase it is necessary to compress the signal. Among the algorithms that can be found, low complexity compression based on ASCII coding, DWT and DCT based compression. In this work we propose an embedded system based on the CUDA architecture of the lossless ECG data compression.
International Review on Computers and Software (IRECOS), 2015
This paper is proposing an efficient denoising method of baseline wandering and high frequency no... more This paper is proposing an efficient denoising method of baseline wandering and high frequency noise for ECG signals. The proposed method starts by extracting baseline wandering from ECG signal. This technique has been developed using an adaptive algorithm based on mean filter. Next, an adaptive dual threshold filter is proposed to deal with high frequency noises. This filter is inspired from an adaptive dual threshold median filter recently developed in image processing. This paper presents certain applications of this algorithm on some of the MIT-BIH Arrhythmia database’s signals. Interestingly, results of this method are very promising compared to recently published methods. In the case of an input SNR level of 5dB to 20dB, the values of the PRD parameter are varied between 25 % and 7 %. For the same input SNR level, the obtained values of the MSE parameter are varied between 0.0087 and 0.00062. The aim of this work, in addition to improving denosing, is to implement this method in real-time systems, which is the next step of this work.
2014 Second World Conference on Complex Systems (WCCS), 2014
Background: Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, i... more Background:
Since the electrocardiogram (ECG) signal has a low frequency and a
weak amplitude, it is sensitive to miscellaneous mixed noises, which may reduce the diagnostic accuracy and hinder the physician’s correct decision on patients.
Methods:
The dual tree wavelet transform (DT-WT) is one of the most recent
enhanced versions of discrete wavelet transform. However, threshold tuning on this method for noise removal from ECG signal has not been investigated yet. In this work, we shall provide a comprehensive study on the impact of the choice of threshold algorithm, threshold value, and the appropriate wavelet decomposition level to evaluate the ECG signal de-noising performance.
Results:
A set of simulations is performed on both synthetic and real ECG signals
to achieve the promised results. First, the synthetic ECG signal is used to observe the algorithm response. The evaluation results of synthetic ECG signal corrupted by various types of noise has showed that the modified unified threshold and wavelet hyperbolic threshold de-noising method is better in realistic and colored noises. The tuned threshold is then used on real ECG signals from the MIT-BIH database. The results has shown
that the proposed method achieves higher performance than the ordinary dual tree wavelet transform into all kinds of noise removal from ECG signal.
Conclusion:
The simulation results indicate that the algorithm is robust for all kinds
of noises with varying degrees of input noise, providing a high quality clean signal. Moreover, the algorithm is quite simple and can be used in real time ECG monitoring.
The storage capacity of the ECG records presents an important issue in the medical practices. The... more The storage capacity of the ECG records presents an important issue in the medical practices. These data could contain hours of recording, which needs a large space for storage to save these records. The compression of the ECG signal is widely used to deal with this issue. The problem with this process is the possibility of losing some important features of the ECG signal. This loss could influence negatively the analyzing of the heart condition. In this paper, we shall propose an efficient method of the ECG signal compression using the discrete wavelet transform and the run length encoding. This method is based on the decomposition of the ECG signal, the thresholding stage and the encoding of the final data. This method is tested on some of the MIT-BIH arrhythmia signals from the international database Physionet. This method shows high performances comparing to other methods recently published.
Cardiac diseases constitute the main cause of mortality around the globe. For detection and ident... more Cardiac diseases constitute the main cause of mortality around the globe. For detection and identification of cardiac problems, it is very important to monitor the patient's heart activities for long periods during his normal daily life. The recorded signal that contains information about the condition of the heart called electrocardiogram (ECG). As a result, long recording of ECG signal amounts to huge data sizes. In this work, a robust lossless ECG data compression scheme for real-time applications is proposed. The developed algorithm has the advantages of lossy compression without introducing any distortion to the reconstructed signal. The ECG signals under test were taken from the PTB Diagnostic ECG Database. The compression procedure is simple and provides a high compression ratio compared to other lossless ECG compression methods. The compressed ECG data is generated as a text file. The decompression scheme has also been developed using the reverse logic and it is observed that there is no difference between original and reconstructed ECG signal.
International Journal of Engineering and Technology Innovation, 2018
Electrocardiography is considered as a powerful technique for assessing heart condition. To study... more Electrocardiography is considered as a powerful technique for assessing heart condition. To study cardiac disorders, it is essential to localize and extract the QRS complex: the prominent region within the electrocardiogram signal. Since the QRS complex has various morphologies and is usually contaminated by severe overlapping spectral noise, accurate detection is a complicated task. This paper proposes a reliable method based on the Dual-Tree Wavelet Transform, which uses a threshold process to select the QRS frequency components and reduce the overlapping noise. The QRS deflections are then emphasized using squaring and moving average operators. The chosen decision rule is simple and based on the variance of the signal. The proposed method was tested on the MIT-BIH Arrhythmia database, and the algorithm showed high accuracy detection results compared to those of other recently published works.
Biomedical engineering online, Jan 7, 2017
Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, it is sensitiv... more Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, it is sensitive to miscellaneous mixed noises, which may reduce the diagnostic accuracy and hinder the physician's correct decision on patients. The dual tree wavelet transform (DT-WT) is one of the most recent enhanced versions of discrete wavelet transform. However, threshold tuning on this method for noise removal from ECG signal has not been investigated yet. In this work, we shall provide a comprehensive study on the impact of the choice of threshold algorithm, threshold value, and the appropriate wavelet decomposition level to evaluate the ECG signal de-noising performance. A set of simulations is performed on both synthetic and real ECG signals to achieve the promised results. First, the synthetic ECG signal is used to observe the algorithm response. The evaluation results of synthetic ECG signal corrupted by various types of noise has showed that the modified unified threshold and wavelet ...
International Review on Computers and Software (IRECOS), 2016
This paper proposes an efficient method of QRS extraction from the ECG signal using wavelet coeff... more This paper proposes an efficient method of QRS extraction from the ECG signal using wavelet coefficients. This method is composed of three parts. The extraction of QRS regions from details decompositions using an enhanced algorithm, the QRS detection by the elimination of falsely detected peaks and the extraction of higher peaks from the QRS complex. The proposed method has been tested on the 48 records of the MIT-BIH Arrhythmia database signals. The results obtained from this method are promising, compared to recently published techniques where the positive predictivity (Pp) is 99.91 %, and sensitivity (Se) is 99.77 %.
Biocybernetics and Biomedical Engineering, 2016
This paper proposes an efficient method of ECG signal denoising using the adaptive dual threshold... more This paper proposes an efficient method of ECG signal denoising using the adaptive dual threshold filter (ADTF) and the discrete wavelet transform (DWT). The aim of this method is to bring together the advantages of these methods in order to improve the filtering of the ECG signal. The aim of the proposed method is to deal with the EMG noises, the power line interferences and the high frequency noises that could perturb the ECG signal. This algorithm is based on three steps of denoising, namely, the DWT decomposition, the ADTF step and the highest peaks correction step. This paper presents certain applications of this algorithm on some of the MIT-BIH Arrhythmia database's signals. The results of these applications allow observing the high performance of the proposed method comparing to some other techniques recently published.
International Journal of Advanced Computer Science and Applications, 2016
The storage capacity of the ECG records presents an important issue in the medical practices. The... more The storage capacity of the ECG records presents an important issue in the medical practices. These data could contain hours of recording, which needs a large space for storage to save these records. The compression of the ECG signal is widely used to deal with this issue. The problem with this process is the possibility of losing some important features of the ECG signal. This loss could influence negatively the analyzing of the heart condition. In this paper, we shall propose an efficient method of the ECG signal compression using the discrete wavelet transform and the run length encoding. This method is based on the decomposition of the ECG signal, the thresholding stage and the encoding of the final data. This method is tested on some of the MIT-BIH arrhythmia signals from the international database Physionet. This method shows high performances comparing to other methods recently published.
International Journal of Advanced Computer Science and Applications, 2016
Cardiac diseases constitute the main cause of mortality around the globe. For detection and ident... more Cardiac diseases constitute the main cause of mortality around the globe. For detection and identification of cardiac problems, it is very important to monitor the patient's heart activities for long periods during his normal daily life. The recorded signal that contains information about the condition of the heart called electrocardiogram (ECG). As a result, long recording of ECG signal amounts to huge data sizes. In this work, a robust lossless ECG data compression scheme for realtime applications is proposed. The developed algorithm has the advantages of lossy compression without introducing any distortion to the reconstructed signal. The ECG signals under test were taken from the PTB Diagnostic ECG Database. The compression procedure is simple and provides a high compression ratio compared to other lossless ECG compression methods. The compressed ECG data is generated as a text file. The decompression scheme has also been developed using the reverse logic and it is observed that there is no difference between original and reconstructed ECG signal.
Telemedicine is experiencing a great growth in recent years, is a technology allowing remote heal... more Telemedicine is experiencing a great growth in recent years, is a technology allowing remote health services and exchange of medical information, among these areas we find telecardiology. In telecardiology the ECG requires a long recording. For this purpose the data are high, the reason that an effective compression method is required for biomedical signals. The electrocardiogram (ECG) or (EKG) is an important tool for assessing the heart condition of a patient, and is very sensitive to noise. For that several methods are proposed to denoising the ECG signal include: EMD, EEMD, DWT, and adaptive filter ADTF. After the transfer phase it is necessary to compress the signal. Among the algorithms that can be found, low complexity compression based on ASCII coding, DWT and DCT based compression. In this work we propose an embedded system based on the CUDA architecture of the lossless ECG data compression.
International Review on Computers and Software (IRECOS), 2015
This paper is proposing an efficient denoising method of baseline wandering and high frequency no... more This paper is proposing an efficient denoising method of baseline wandering and high frequency noise for ECG signals. The proposed method starts by extracting baseline wandering from ECG signal. This technique has been developed using an adaptive algorithm based on mean filter. Next, an adaptive dual threshold filter is proposed to deal with high frequency noises. This filter is inspired from an adaptive dual threshold median filter recently developed in image processing. This paper presents certain applications of this algorithm on some of the MIT-BIH Arrhythmia database’s signals. Interestingly, results of this method are very promising compared to recently published methods. In the case of an input SNR level of 5dB to 20dB, the values of the PRD parameter are varied between 25 % and 7 %. For the same input SNR level, the obtained values of the MSE parameter are varied between 0.0087 and 0.00062. The aim of this work, in addition to improving denosing, is to implement this method in real-time systems, which is the next step of this work.
2014 Second World Conference on Complex Systems (WCCS), 2014
Background: Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, i... more Background:
Since the electrocardiogram (ECG) signal has a low frequency and a
weak amplitude, it is sensitive to miscellaneous mixed noises, which may reduce the diagnostic accuracy and hinder the physician’s correct decision on patients.
Methods:
The dual tree wavelet transform (DT-WT) is one of the most recent
enhanced versions of discrete wavelet transform. However, threshold tuning on this method for noise removal from ECG signal has not been investigated yet. In this work, we shall provide a comprehensive study on the impact of the choice of threshold algorithm, threshold value, and the appropriate wavelet decomposition level to evaluate the ECG signal de-noising performance.
Results:
A set of simulations is performed on both synthetic and real ECG signals
to achieve the promised results. First, the synthetic ECG signal is used to observe the algorithm response. The evaluation results of synthetic ECG signal corrupted by various types of noise has showed that the modified unified threshold and wavelet hyperbolic threshold de-noising method is better in realistic and colored noises. The tuned threshold is then used on real ECG signals from the MIT-BIH database. The results has shown
that the proposed method achieves higher performance than the ordinary dual tree wavelet transform into all kinds of noise removal from ECG signal.
Conclusion:
The simulation results indicate that the algorithm is robust for all kinds
of noises with varying degrees of input noise, providing a high quality clean signal. Moreover, the algorithm is quite simple and can be used in real time ECG monitoring.
The storage capacity of the ECG records presents an important issue in the medical practices. The... more The storage capacity of the ECG records presents an important issue in the medical practices. These data could contain hours of recording, which needs a large space for storage to save these records. The compression of the ECG signal is widely used to deal with this issue. The problem with this process is the possibility of losing some important features of the ECG signal. This loss could influence negatively the analyzing of the heart condition. In this paper, we shall propose an efficient method of the ECG signal compression using the discrete wavelet transform and the run length encoding. This method is based on the decomposition of the ECG signal, the thresholding stage and the encoding of the final data. This method is tested on some of the MIT-BIH arrhythmia signals from the international database Physionet. This method shows high performances comparing to other methods recently published.
Cardiac diseases constitute the main cause of mortality around the globe. For detection and ident... more Cardiac diseases constitute the main cause of mortality around the globe. For detection and identification of cardiac problems, it is very important to monitor the patient's heart activities for long periods during his normal daily life. The recorded signal that contains information about the condition of the heart called electrocardiogram (ECG). As a result, long recording of ECG signal amounts to huge data sizes. In this work, a robust lossless ECG data compression scheme for real-time applications is proposed. The developed algorithm has the advantages of lossy compression without introducing any distortion to the reconstructed signal. The ECG signals under test were taken from the PTB Diagnostic ECG Database. The compression procedure is simple and provides a high compression ratio compared to other lossless ECG compression methods. The compressed ECG data is generated as a text file. The decompression scheme has also been developed using the reverse logic and it is observed that there is no difference between original and reconstructed ECG signal.