The latest experiences hint that the QoS (Quality of Service) approaches adopted by IMS (IP Multi... more The latest experiences hint that the QoS (Quality of Service) approaches adopted by IMS (IP Multimedia Subsystem) technologies are still suffering from a primary containment factor due to the nondifferentiation between IPTV (Internet Protocol Television) video components. IMS system also cannot ensure high IPTV data transfer due to the limitation of available cellular bandwidth. In this paper, we try to merge the advantage of high bandwidth assigned to LTE (Long Term Evolution) and a new PHB (Per-Hop Behavior) that classify and differentiate between IPTV sub traffics by using IPv6 Flow Label. This new architecture permits high-quality IPTV video components with the capability to prioritize the sub traffic according to the network administrator policy. The proposed architecture is implemented using OPNET software. The results show that IPTV users receive high-quality video data with a change in quantity according to data priority.
21st European Signal Processing Conference (EUSIPCO 2013), 2013
In this paper, we investigate how data embedding capacity and extraction fidelity can be enhanced... more In this paper, we investigate how data embedding capacity and extraction fidelity can be enhanced keeping imperceptibility of the host audio unaltered. To meet this end, we propose a new blind watermarking system for two-channel audio signals which is based on Code Division Multiple Access (CDMA) and Independent Components Analysis (ICA) techniques. At the emitter, CDMA is used to increase the watermark bit rate by inserting multiple parallel data. At the receiver, ICA algorithm is applied to recover the embedded information. In order to demonstrate the effectiveness of the proposed scheme, simulations under various conditions are conducted. The new system provides an embedding rate up to 60Kbits/s, while ensuring a compromise between inaudibility and extraction reliability.
A Brain‐Computer Interface (BCI) is an instrument capa‐ ble of commanding machine with brain sign... more A Brain‐Computer Interface (BCI) is an instrument capa‐ ble of commanding machine with brain signal. The mul‐ tiple types of signals allow designing many applications like the Oddball Paradigms with P300 signal. We propose an EEG classification system applied to BCI using the con‐ volutional neural network (ConvNet) for P300 problem. The system consists of three stages. The first stage is a Spatiotemporal convolutional layer which is a succession of temporal and spatial convolutions. The second stage contains 5 standard convolutional layers. Finally, a lo‐ gistic regression is applied to classify the input EEG sig‐ nal. The model includes Batch Normalization, Dropout, and Pooling. Also, It uses Exponential Linear Unit (ELU) function and L1‐L2 regularization to improve the lear‐ ning. For experiments, we use the database Dataset II of the BCI Competition III. As a result, we get an F1‐score of 53.26% which is higher than the BN model.
The Electrocardiography is a graphical representation of the heart’s electrical activity. In this... more The Electrocardiography is a graphical representation of the heart’s electrical activity. In this paper, we present an efficient algorithm for QRS complex detection in the Electrocardiogram (ECG) signal. The proposed algorithm is based on a combination of the Shift Invariant Wavelet Transform (ShIWT), a Nonlinear transform called Nonlinear Energy Operator (NEO) and a simple thresholding function followed by some decision rules for accurate R peak detection. In our scheme, ShIWT was used to filter out the raw ECG signal and the NEO was applied to highlight the QRS complex patterns. Finally, after simple thresholding stage, R peak time positions on the filtered ECG signal can be detected accurately with the help of efficient decision rules. The experimental results and tests carried over real ECG signals taken from the MIT-BIH Arrhythmia Database (MITDB) show that our proposed approach gives a comparable or higher detection performances against the state of the art techniques with an ...
The latest experiences hint that IMS (IP Multimedia Subsystem) technologies cannot perform its hi... more The latest experiences hint that IMS (IP Multimedia Subsystem) technologies cannot perform its highest QoS (Quality of Service) approaches as they aren’t able to distinguish between the priorities of IPTV (Internet Protocol Television) video components. IMS system also cannot ensure high IPTV data transfer due to the limitation of available cellular bandwidth. Success of IPTV services depends on how the customer perceives QoS related to the provided stream. The satisfaction of this factor is crucial to the success of IMS services. This need constitutes a major challenge for the IMS-based IPTV on the horizon of overcoming the failure of existing QoS models namely IntServ (Integrated Services) and DiffServ (Differentiated Services). In this paper, we try to merge the advantage of high bandwidth assigned to LTE (Long Term Evolution) and a new PHB (Per-Hop Behavior) that classify and differentiate between IPTV sub traffics by using IPv6 Flow Label. This new architecture permits high-qua...
2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
Electrocardiogram (ECG) signal is a non-invasive technique that is currently used to diagnose var... more Electrocardiogram (ECG) signal is a non-invasive technique that is currently used to diagnose various types of cardiovascular diseases. However, ECG recording is vulnerable to different types of noises and artifacts that make it very difficult to obtain an accurate diagnosis. In this context, we propose a novel ECG denoising algorithm based on the deep Convolutional Denoising Auto-Encoder (CDAE) which requires minimal preprocessing steps, and conserves the important ECG features. In this study, the proposed CDAE algorithm is specifically implemented to remove the Additive White Gaussian noise (AWGN) from the recorded ECG signal. The CDAE was trained, validated and tested on a set of real ECG signals acquired from the well-known MIT-BIH-Arrythmia (MITDB) database with artificially generated AWGN. The experimental results demonstrate that the proposed method shows better Signal to Noise Ratio (SNR) and lower Root Mean Square Error (RMSE) compared to some of the state-of-the-art methods. The promising results indicate also that the proposed CDAE technique is an effective solution for denoising the ECG signal, by providing ECG waves accentuation for other ECG processing applications like diseases diagnosis.
The electrocardiogram is an important tool that is widely used for diagnosis of many cardiovascul... more The electrocardiogram is an important tool that is widely used for diagnosis of many cardiovascular diseases. In this context, QRS complex detection is a very crucial step in the ECG diagnosis system. The major aim of this work is to develop a novel method for QRS complex detection under various ECG signal morphologies as well as under different ECG recording conditions, including numerous noise sources and varying QRS waveforms. The proposed algorithm is based principally on the stationary wavelet transform (SWT) and Teager energy operator (TEO). In our scheme, SWT is first used for ECG signal preprocessing and QRS complex frequency content localization. Subsequently, a novel process for R peak detection based on TEO and a moving average (MA) filter is introduced. More precisely, SWT is coupled with TEO and the MA filter to construct a smoothed detection mask. Then, after the mask segmentation and adaptive thresholding steps, R peak times are identified using the maxima detected on the created mask and employing a reference ECG signal. At this stage, efficient decision rules are applied for reducing the number of false alarms. In the experiments, we validate the proposed method on the well-known annotated MIT-BIH arrhythmia database (MITDB). The experimental results show that the newly proposed algorithm provides satisfactory detection performances compared to the recent state-of-the-art methods, with an average sensitivity of 99.84%, average positive predictivity (P+) of $$99.87\%$$ 99.87 % , detection error rate of 0.30% and an overall detection accuracy of 99.70%. Also, the proposed method presents a low computational time complexity with an average processing time of 12 s on each ECG record from MITDB.
The Brain-Computer Interface (BCI) is a system able to serve as a mean of communication between m... more The Brain-Computer Interface (BCI) is a system able to serve as a mean of communication between machine and human where the brainwaves are the control signals acquired by electroencephalography (EEG). One of the most used brainwaves is the sensorimotor rhythm (SMR) which appears for real or imagined motor movement. In general, EEG signals need feature extraction methods and classification algorithms to interpret the raw signals. Deep learning approaches; however, permit the processing of the raw data without any transformation. In this paper, we present a deep learning neural network architecture to classify SMR signals due to its success for some previous works and to visualize the learned features. The architecture is composed of three parts. The first part contains a temporal convolution operation followed by a spatial convolution one. The second part contains recurrent layers. Finally, we use a dense layer to assign the signal to its class. The model is trained with Adam optimizer algorithm. Also, we use various regularization techniques such as dropout to prevent learning problem like overfitting. To evaluate the performance of the proposed architecture, the well known Dataset IIa of the BCI Competition IV is used. As a result, we get equivalent results to those ones of EEGNet.
Although a lot of research has been done on speaker identification in the presence of noise and c... more Although a lot of research has been done on speaker identification in the presence of noise and channel variation, to the best of our knowledge, no work has been reported for aeronautical applications. In this paper, we aim to fulfill this goal by developing a Speaker Identification System (SIS) for future aeronautical communications systems. Furthermore, we present a novel feature extraction scheme based on multi-resolution analysis. The proposed features called SMFCC use Mel Frequency Cepstral Coefficients (MFCCs) features of stationary wavelet transform sub-bands. The extracted features are modeled using the i-vector approach, and support-vector machines are adopted as a back-end classifier. The performance of the proposed SIS is evaluated using two publicly available databases. Comparison of the proposed approach with the baseline MFCC feature extraction shows the feasibility and the robustness of the proposed method. Besides the noise reduction, the identification accuracy is improved by about 12% at higher signal-to-noise ratios and reaches 97.33% as compared to 88.33% using MFCC for ATCOSIM database.
2016 11th International Conference on Intelligent Systems: Theories and Applications (SITA), 2016
In this paper, the performance of an automatic aircraft identification system is investigated in ... more In this paper, the performance of an automatic aircraft identification system is investigated in aeronautical flat fading channels. The automatic aircraft identification is achieved by means of spread-spectrum watermarking techniques. Due to its better resistance to fading environments, Orthogonal Frequency Division Multiplexing (OFDM) is used to transmit the watermarked signal through an aeronautical channel. Several stochastic reference models will be considered to characterize the aeronautical channel. Based on a scenario in air/ground communication, we compare the performance in term of Bit Error Rate (BER) of both transmission and robustness of the watermark signal in several fading channels. It has been observed that the performance of the proposed system is related to different factors affecting the signal propagation.
Because one of the key issues in improving the performance of Speech Emotion Recognition (SER) sy... more Because one of the key issues in improving the performance of Speech Emotion Recognition (SER) systems is the choice of an effective feature representation, most of the research has focused on developing a feature level fusion using a large set of features. In our study, we propose a relatively low-dimensional feature set that combines three features: baseline Mel Frequency Cepstral Coefficients (MFCCs), MFCCs derived from Discrete Wavelet Transform (DWT) sub-band coefficients that are denoted as DMFCC, and pitch based features. Moreover, the performance of the proposed feature extraction method is evaluated in clean conditions and in the presence of several real-world noises. Furthermore, conventional Machine Learning (ML) and Deep Learning (DL) classifiers are employed for comparison. The proposal is tested using speech utterances of both of the Berlin German Emotional Database (EMO-DB) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) speech databases through speaker inde...
Proceedings International Symposium on Computers and Communications, 2008
ABSTRACT This paper is concerned with blind separation of convolutive mixtures of spatially indep... more ABSTRACT This paper is concerned with blind separation of convolutive mixtures of spatially independent, and temporally possible non linear processes. We consider the MIMO extraction based on the maximization of a contrast function. A new self-styled referenced contrast (RC) function is proposed, which is based on cross-trispectra between the estimated output and a reference signal. Using Parsevals formula, the former criterion yields a new class of time-domain contrast. It presents two main advantages over other more traditional contrasts. Firstly, it concerns the computational cost, and secondly the extension takes into consideration the extraction of the independent sources in the presence of Gaussian sources by making some constraints on the reference signals. There is no comparison with other methods because this is the first technique that deals with this kind of signals in the convolutif mixtures
The latest experiences hint that the QoS (Quality of Service) approaches adopted by IMS (IP Multi... more The latest experiences hint that the QoS (Quality of Service) approaches adopted by IMS (IP Multimedia Subsystem) technologies are still suffering from a primary containment factor due to the nondifferentiation between IPTV (Internet Protocol Television) video components. IMS system also cannot ensure high IPTV data transfer due to the limitation of available cellular bandwidth. In this paper, we try to merge the advantage of high bandwidth assigned to LTE (Long Term Evolution) and a new PHB (Per-Hop Behavior) that classify and differentiate between IPTV sub traffics by using IPv6 Flow Label. This new architecture permits high-quality IPTV video components with the capability to prioritize the sub traffic according to the network administrator policy. The proposed architecture is implemented using OPNET software. The results show that IPTV users receive high-quality video data with a change in quantity according to data priority.
21st European Signal Processing Conference (EUSIPCO 2013), 2013
In this paper, we investigate how data embedding capacity and extraction fidelity can be enhanced... more In this paper, we investigate how data embedding capacity and extraction fidelity can be enhanced keeping imperceptibility of the host audio unaltered. To meet this end, we propose a new blind watermarking system for two-channel audio signals which is based on Code Division Multiple Access (CDMA) and Independent Components Analysis (ICA) techniques. At the emitter, CDMA is used to increase the watermark bit rate by inserting multiple parallel data. At the receiver, ICA algorithm is applied to recover the embedded information. In order to demonstrate the effectiveness of the proposed scheme, simulations under various conditions are conducted. The new system provides an embedding rate up to 60Kbits/s, while ensuring a compromise between inaudibility and extraction reliability.
A Brain‐Computer Interface (BCI) is an instrument capa‐ ble of commanding machine with brain sign... more A Brain‐Computer Interface (BCI) is an instrument capa‐ ble of commanding machine with brain signal. The mul‐ tiple types of signals allow designing many applications like the Oddball Paradigms with P300 signal. We propose an EEG classification system applied to BCI using the con‐ volutional neural network (ConvNet) for P300 problem. The system consists of three stages. The first stage is a Spatiotemporal convolutional layer which is a succession of temporal and spatial convolutions. The second stage contains 5 standard convolutional layers. Finally, a lo‐ gistic regression is applied to classify the input EEG sig‐ nal. The model includes Batch Normalization, Dropout, and Pooling. Also, It uses Exponential Linear Unit (ELU) function and L1‐L2 regularization to improve the lear‐ ning. For experiments, we use the database Dataset II of the BCI Competition III. As a result, we get an F1‐score of 53.26% which is higher than the BN model.
The Electrocardiography is a graphical representation of the heart’s electrical activity. In this... more The Electrocardiography is a graphical representation of the heart’s electrical activity. In this paper, we present an efficient algorithm for QRS complex detection in the Electrocardiogram (ECG) signal. The proposed algorithm is based on a combination of the Shift Invariant Wavelet Transform (ShIWT), a Nonlinear transform called Nonlinear Energy Operator (NEO) and a simple thresholding function followed by some decision rules for accurate R peak detection. In our scheme, ShIWT was used to filter out the raw ECG signal and the NEO was applied to highlight the QRS complex patterns. Finally, after simple thresholding stage, R peak time positions on the filtered ECG signal can be detected accurately with the help of efficient decision rules. The experimental results and tests carried over real ECG signals taken from the MIT-BIH Arrhythmia Database (MITDB) show that our proposed approach gives a comparable or higher detection performances against the state of the art techniques with an ...
The latest experiences hint that IMS (IP Multimedia Subsystem) technologies cannot perform its hi... more The latest experiences hint that IMS (IP Multimedia Subsystem) technologies cannot perform its highest QoS (Quality of Service) approaches as they aren’t able to distinguish between the priorities of IPTV (Internet Protocol Television) video components. IMS system also cannot ensure high IPTV data transfer due to the limitation of available cellular bandwidth. Success of IPTV services depends on how the customer perceives QoS related to the provided stream. The satisfaction of this factor is crucial to the success of IMS services. This need constitutes a major challenge for the IMS-based IPTV on the horizon of overcoming the failure of existing QoS models namely IntServ (Integrated Services) and DiffServ (Differentiated Services). In this paper, we try to merge the advantage of high bandwidth assigned to LTE (Long Term Evolution) and a new PHB (Per-Hop Behavior) that classify and differentiate between IPTV sub traffics by using IPv6 Flow Label. This new architecture permits high-qua...
2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
Electrocardiogram (ECG) signal is a non-invasive technique that is currently used to diagnose var... more Electrocardiogram (ECG) signal is a non-invasive technique that is currently used to diagnose various types of cardiovascular diseases. However, ECG recording is vulnerable to different types of noises and artifacts that make it very difficult to obtain an accurate diagnosis. In this context, we propose a novel ECG denoising algorithm based on the deep Convolutional Denoising Auto-Encoder (CDAE) which requires minimal preprocessing steps, and conserves the important ECG features. In this study, the proposed CDAE algorithm is specifically implemented to remove the Additive White Gaussian noise (AWGN) from the recorded ECG signal. The CDAE was trained, validated and tested on a set of real ECG signals acquired from the well-known MIT-BIH-Arrythmia (MITDB) database with artificially generated AWGN. The experimental results demonstrate that the proposed method shows better Signal to Noise Ratio (SNR) and lower Root Mean Square Error (RMSE) compared to some of the state-of-the-art methods. The promising results indicate also that the proposed CDAE technique is an effective solution for denoising the ECG signal, by providing ECG waves accentuation for other ECG processing applications like diseases diagnosis.
The electrocardiogram is an important tool that is widely used for diagnosis of many cardiovascul... more The electrocardiogram is an important tool that is widely used for diagnosis of many cardiovascular diseases. In this context, QRS complex detection is a very crucial step in the ECG diagnosis system. The major aim of this work is to develop a novel method for QRS complex detection under various ECG signal morphologies as well as under different ECG recording conditions, including numerous noise sources and varying QRS waveforms. The proposed algorithm is based principally on the stationary wavelet transform (SWT) and Teager energy operator (TEO). In our scheme, SWT is first used for ECG signal preprocessing and QRS complex frequency content localization. Subsequently, a novel process for R peak detection based on TEO and a moving average (MA) filter is introduced. More precisely, SWT is coupled with TEO and the MA filter to construct a smoothed detection mask. Then, after the mask segmentation and adaptive thresholding steps, R peak times are identified using the maxima detected on the created mask and employing a reference ECG signal. At this stage, efficient decision rules are applied for reducing the number of false alarms. In the experiments, we validate the proposed method on the well-known annotated MIT-BIH arrhythmia database (MITDB). The experimental results show that the newly proposed algorithm provides satisfactory detection performances compared to the recent state-of-the-art methods, with an average sensitivity of 99.84%, average positive predictivity (P+) of $$99.87\%$$ 99.87 % , detection error rate of 0.30% and an overall detection accuracy of 99.70%. Also, the proposed method presents a low computational time complexity with an average processing time of 12 s on each ECG record from MITDB.
The Brain-Computer Interface (BCI) is a system able to serve as a mean of communication between m... more The Brain-Computer Interface (BCI) is a system able to serve as a mean of communication between machine and human where the brainwaves are the control signals acquired by electroencephalography (EEG). One of the most used brainwaves is the sensorimotor rhythm (SMR) which appears for real or imagined motor movement. In general, EEG signals need feature extraction methods and classification algorithms to interpret the raw signals. Deep learning approaches; however, permit the processing of the raw data without any transformation. In this paper, we present a deep learning neural network architecture to classify SMR signals due to its success for some previous works and to visualize the learned features. The architecture is composed of three parts. The first part contains a temporal convolution operation followed by a spatial convolution one. The second part contains recurrent layers. Finally, we use a dense layer to assign the signal to its class. The model is trained with Adam optimizer algorithm. Also, we use various regularization techniques such as dropout to prevent learning problem like overfitting. To evaluate the performance of the proposed architecture, the well known Dataset IIa of the BCI Competition IV is used. As a result, we get equivalent results to those ones of EEGNet.
Although a lot of research has been done on speaker identification in the presence of noise and c... more Although a lot of research has been done on speaker identification in the presence of noise and channel variation, to the best of our knowledge, no work has been reported for aeronautical applications. In this paper, we aim to fulfill this goal by developing a Speaker Identification System (SIS) for future aeronautical communications systems. Furthermore, we present a novel feature extraction scheme based on multi-resolution analysis. The proposed features called SMFCC use Mel Frequency Cepstral Coefficients (MFCCs) features of stationary wavelet transform sub-bands. The extracted features are modeled using the i-vector approach, and support-vector machines are adopted as a back-end classifier. The performance of the proposed SIS is evaluated using two publicly available databases. Comparison of the proposed approach with the baseline MFCC feature extraction shows the feasibility and the robustness of the proposed method. Besides the noise reduction, the identification accuracy is improved by about 12% at higher signal-to-noise ratios and reaches 97.33% as compared to 88.33% using MFCC for ATCOSIM database.
2016 11th International Conference on Intelligent Systems: Theories and Applications (SITA), 2016
In this paper, the performance of an automatic aircraft identification system is investigated in ... more In this paper, the performance of an automatic aircraft identification system is investigated in aeronautical flat fading channels. The automatic aircraft identification is achieved by means of spread-spectrum watermarking techniques. Due to its better resistance to fading environments, Orthogonal Frequency Division Multiplexing (OFDM) is used to transmit the watermarked signal through an aeronautical channel. Several stochastic reference models will be considered to characterize the aeronautical channel. Based on a scenario in air/ground communication, we compare the performance in term of Bit Error Rate (BER) of both transmission and robustness of the watermark signal in several fading channels. It has been observed that the performance of the proposed system is related to different factors affecting the signal propagation.
Because one of the key issues in improving the performance of Speech Emotion Recognition (SER) sy... more Because one of the key issues in improving the performance of Speech Emotion Recognition (SER) systems is the choice of an effective feature representation, most of the research has focused on developing a feature level fusion using a large set of features. In our study, we propose a relatively low-dimensional feature set that combines three features: baseline Mel Frequency Cepstral Coefficients (MFCCs), MFCCs derived from Discrete Wavelet Transform (DWT) sub-band coefficients that are denoted as DMFCC, and pitch based features. Moreover, the performance of the proposed feature extraction method is evaluated in clean conditions and in the presence of several real-world noises. Furthermore, conventional Machine Learning (ML) and Deep Learning (DL) classifiers are employed for comparison. The proposal is tested using speech utterances of both of the Berlin German Emotional Database (EMO-DB) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) speech databases through speaker inde...
Proceedings International Symposium on Computers and Communications, 2008
ABSTRACT This paper is concerned with blind separation of convolutive mixtures of spatially indep... more ABSTRACT This paper is concerned with blind separation of convolutive mixtures of spatially independent, and temporally possible non linear processes. We consider the MIMO extraction based on the maximization of a contrast function. A new self-styled referenced contrast (RC) function is proposed, which is based on cross-trispectra between the estimated output and a reference signal. Using Parsevals formula, the former criterion yields a new class of time-domain contrast. It presents two main advantages over other more traditional contrasts. Firstly, it concerns the computational cost, and secondly the extension takes into consideration the extraction of the independent sources in the presence of Gaussian sources by making some constraints on the reference signals. There is no comparison with other methods because this is the first technique that deals with this kind of signals in the convolutif mixtures
Uploads