Non-invasive fetal electrocardiography (fECG) monitoring is crucial for prenatal care, enabling early detection of fetal cardiac anomalies. However, extracting the weak fECG signal from composite abdominal ECG (aECG) recordings is challenging due to maternal ECG dominance and noise interferences. This paper proposes W-NET, a novel deep learning architecture inspired by one-dimensional U-Net and Transformer models, designed for simultaneous extraction of maternal (mECG) and fetal (fECG) ECG signals from a singlechannel aECG. The model employs a dual-branch structure with adaptive maternal feature suppression in the fetal branch to enhance separation fidelity. Trained on synthetic and real datasets, W_Net outperforms baselines in QRS detection, achieving F1-score 1.000 on synthetic data and 0.824 on real data. To enable practical deployment, we integrate W-NET with a secure Flask-based web interface for real-time signal analysis, visualization, and fetal heart rate classification, thereby facilitating accessible and continuous prenatal monitoring.

Despite advances in modern medicine, restoring autonomy for individuals with severe motor impairments remains a major challenge. This work proposes an SSVEP-SLAM hybrid framework that integrates Steady-State Visual Evoked Potentials (SSVEPs) with simultaneous localization and mapping (SLAM) for autonomous robotics in a ROS2-simulated domestic environment. EEG signals were preprocessed and classified using two deep learning models: EEGNet and CCNN. Experimental results on a 12-class SSVEP dataset show that CCNN outperforms the other, achieving 90.28% accuracy versus 88,56% for EEGNet. The decoded intentions were integrated into ROS2 through a graphical interface, enabling real-time control of a TurtleBot3 platform acting as a simulated intelligent wheelchair. Using the Nav2 stack, the robot successfully navigated toward predefined targets in Gazebo with obstacle avoidance and trajectory visualization in RViz. This study demonstrates the feasibility of SSVEP-SLAM hybrid frameworks for autonomous wheelchair navigation, paving the way toward practical assistive mobility solutions.

Interictal epileptiform discharges (IEDs) play a crucial role in the diagnosis and assessment of seizure risk in epilepsy. Their frequency, amplitude, and morphological characteristics serve as consistent markers of epileptogenesis. Currently, the clinical evaluation of IEDs heavily relies on visual detection by specialized experts, which is a subjective and time-consuming task. To address this, there is a need for an automated IEDs detection system that can provide faster and more reliable epilepsy diagnosis. In this paper, we propose a novel method for automatic identification of IEDs by inspecting the fulfillment of specific criteria. The decisions made by our method were compared with the combined decisions of three neurologists, serving as a benchmark for evaluation. The results and performance metrics obtained from this comparison demonstrate the effectiveness and potential of our automated IEDs identification method.

The presence of artifacts in the EEG signals can cause a misunderstanding of the sought neurophysiological phenomena. In particular, the eye blink artifacts frequently contaminate the EEG and deteriorate its quality. Unfortunately, removing this artifact can lose useful information. The most popular approach in this field uses the independent component analysis to decompose the signal into different independent components and then eliminate those that are related to the artifact. Despite its reputation, this approach is computationally intensive, requires an acquisition from large number of channels and can alter the original EEG signal. In this paper, we propose a new method for blink artifact reduction. Several reference signals representing the eye blink are created then used in an orthogonal projection in order to cancel the artifact. The results of experiments, using 54 datasets from 27 subjects, show that the proposed method significantly outperformed the standard ADJUST, MARA and SASICA methods in removing the artifacts while preserving the pure EEG signals.

The new developments of medicine and information technology can help severely paralyzed people to restore the link with their environment through the Brain Computer Interface (BCI). In fact, a BCI can replace the movements of human organs by actions of a machine controlled by thoughts. Several studies on BCIs show that systems based on the steady state visual evoked potential (SSVEP) signal allow to reach the best performances. In the present work, we aim to evaluate and compare signal processing methods used in the conception of SSVEP based BCIs. Three methods from the literature were examined which are the Minimum Energy Combination (MEC), the Canonical Correlation Analysis (CCA) and the Multivariate synchronization index (MSI). Results show that the most efficient method is CCA.

The demand for system level flexibility and scalability in system-on-chip (SoC) designs is growing. Network-onchip (NoC) constitutes a functional solution to the SoC challenges without overly reducing the system level performances.In this paper, we describe the architecture and the implementation of a NoC with mesh 2D topological structure and an open core protocol (OCP) compliant network interface (NI). We used this architecture to create a 2D multiprocessor system. Results show that our system can reach an acceptable value of saturation point especially with the appropriate value of maximum burst size.

Brain-computer interface (BCI) systems translate the human neurophysiological activities into commands through EEG analysis. Improving the BCI performances leads to faster and easier use and less fatigue. In this study, we proposed a new prepossessing approach to increase the robustness of a steady-state visual evoked potential (SSVEP) based BCI. Inspiring from the known properties of the SSVEP frequency components, the goal was to enhance the signal quality by making it more convenient to be interpreted by the decision-making step. We first investigated the potential to detect the deteriorating periods based on the physiological properties of the SSVEP. The proposed system localizes the intervals which can obscure the SSVEP frequencies by a new algorithm founded on the processing and the analysis of the instantaneous phase. The piecewise linear regression allows a sampler comprehension of the phase signal. Then, these intervals are filtered by the moving average filter to enhance the SSVEP quality. Finally, the decision making is made by the canonical correlation analysis (CCA) algorithm. The results of experiments, using real EEG signals from five subjects, show that the proposed approach significantly increases the performances in terms of accuracy and information transfer rate by about 7.3% and 3.85 bits/min, respectively, in case of 2 s segment length. On the other hand, the spatial filtering methods of the literature weaken the system performances.

Brain-Computer Interface (BCI) systems are widely based on steady-state visual evoked potentials (SSVEP) detection using electroencephalography (EEG) signals. SSVEP-based BCIs are becoming attractive due to their higher signal-to-noise ratio (SNR) as well as faster information transfer rate (ITR). However, their performances are largely affected by the interference coming from the spontaneous EEG activities which intrinsically restrict their efficiency in distinguishing between SSVEPs and background EEG activities. In this paper, we introduce a new approach for the detection of SSVEP based on bispectral analysis to palliate the frequency-dependent bias. A COMB filter associated with a wavelet denoising filter is firstly used to minimize the noise while improving the SNR of phase signals. Next, the complementary orthogonal projections and the principle component analysis (PCA) are used to decompose the components related to SSVEPs and components related to brain activities. Finally, the bispectrum, a powerful tool for the analysis and the characterization of nonlinear properties of stochastic signals, is used to extract the features of the EEG signal benefiting from the information about the phase coupling of the signal components. The results of experiments, using two databases on five (or ten) subjects, show that the proposed approach significantly outperformed the standard CCA approach in distinguishing the target frequency and in average information transfer rate.

The automatic seizure detection system is designed to aid the physician's decision-making process with recognizing the sought EEG segments. Increasing the system sensitivity is the goal of several studies. In fact, ameliorating this criterion allows to find the same interpretations as found with a visual scanning. A patient-specific system is able to set its optimal parameters according to the patient which makes it more accurate than non-patient-specific system. This paper introduces a new patient-specific system with genetic and practical swarm optimisation algorithms. The results show that the proposed system is able to reach acceptable performances. Moreover, the use of the genetic algorithm improves the system sensitivity (95%) more than the practical swarm optimization (91%) which makes it a better method for the system parameter optimisation.

The typical question-answering system is facing many challenges related to the processing of questions and information resources in the extraction and generation of adequate answers.These challenges increase when the requested answer is cooperative and its language is Arabic.In this paper, we propose an original approach to generate cooperative answers for user-definitional questions designed to be integrated in a question-answering system.This approach is mainly based on the exploitation of the semi-structured Web knowledge which consists in using features derived from Wikipedia article infoboxes to generate cooperative answers.It is globally independent of a particular language, which gives it the ability to be integrated in any definitional question-answering system.We have chosen to integrate and experiment it in a definitional question-answering system dealing with the Arabic language entitled DefArabicQA.The results showed that this system has a significant impact on the approach efficiency regarding the improvement of the quality of the answer.

This paper presents a novel fully generic automated patient-specific seizures detection system. The aim is the detection of the seizure epochs with a high precision. For this end, the empirical mode decomposition is used to overcome the system limitations caused by the non-linear and non-stationary characteristics of the electroencephalography (EEG) signal. The genetic algorithm allows selecting the best parameters combination of each patient without the need of any prior information. For instance, it can estimate the relevant features for each subject from the list of 14 features extracted from the intrinsic mode functions. Thus, the proposed system is able to automatically self-adapt to increase its accuracy rate. The experimental results found using the benchmark CHB-MIT scalp long-term EEG database prove the effectiveness and the reliability of the proposed system with an average sensitivity of about 93.4% and an average specificity of about 99.9%.

The features extraction is the main step in a Brain-Computer Interface (BCI) design. Its goal is to create features easy to be interpreted in order to produce the most accurate control commands. For this end, these features must include all the original signal characteristics. The generated brain's signals' non-stationary and nonlinearity constitute a limitation to the improvement of the performances of systems based on traditional signal processing such as Fourier Transform. This work deals with the comparison of features extraction between Hilbert-Huang Transform (HHT) and Welch's method for Power Spectral Density estimation (PSD) then on the creation of an adaptive method combining the two. The parameters optimization of each method is firstly performed to reach the best classification accuracy rate. The study shows that the PSD estimation is sensitive to the parametric variation whereas the HHT method is mainly robust. The classification results show that an adaptive joint method can reach 90% of accuracy rate for a mental activity period of 1s.

The Brain-Computer Interface is a system mainly designed to provide people suffering from severe neuromuscular disorder with a new mean of communication and control. Increasing the system accuracy rate is the goal of several studies. In fact, ameliorating this criterion allows to minimize the correction phase and makes the use of the system more natural. This is very important to develop Brain-Computer interface systems for everyday use outside the laboratory. This paper introduces a new Brain-Computer Interface based on the Inter-Battery Factor Analysis method. The results show that the proposed BCI system has a higher accuracy than systems based on Canonical Correlation Analysis or Multivariate Synchronization Index. The accuracy rate has reached 93.2% for the five participants using only the two electrodes O1 and O2 with data acquired over a period of 2.25s.

Minimum energy combination (MEC) is a widely used method for frequency recognition in steady state visual evoked potential based BCI systems. Although it can reach acceptable performances, this method remains sensitive to noise. This paper introduces a new technique for the improvement of the MEC method allowing ameliorating its Anti-noise capability. The Empirical mode decomposition (EMD) and the moving average filter were used to separate noise from relevant signals. The results show that the proposed BCI system has a higher accuracy than systems based on Canonical Correlation Analysis (CCA) or Multivariate Synchronization Index (MSI). In fact, the system achieves an average accuracy of about 99% using real data measured from five subjects by means of the EPOC EMOTIVE headset with three visual stimuli. Also by using four commands, the system accuracy reaches 91.78% with an information-transfer rate of about 27.18 bits/min.

This article constitutes an opening to think of the modeling and the analysis of Arabic texts within a question-answering system. It is a question of exceeding the traditional investigations focused on morpho-syntactic approaches. We present a new approach that analyzes a text, transforms it to logical predicates and extracts the accurate answer. In addition, we represent different levels of information within a text and choose an answer among several proposed. To do so, we transform the question and the text into logical forms. Then, recognize all entailments between them. So, the results of this recognizing are a set of text sentences that can implicate the user’s question. Now, our work is concentrated on an implementation step to develop a question-answering system in Arabic using the techniques of textual entailment recognition. Text features extraction (keywords, named entities, relationships that link them) is actually considered the first step in our text modeling process. The second one is the use of textual entailment techniques that relies on inference and logic representation to extract the candidate answer. The last step is the extraction and selection of this answer.

Recently, the low cost EEG acquisition systems such as the Emotiv Epoc give new tools to develop Brain-Computer interface systems for everyday use outside the laboratory.However, the low sampling rate and the low number of channels remain possible sources of failure. The Canonical Correlation Analysis and the Multivariate Synchronization Index ( MSI) methods are applied in a SSVEP- based BCI in order to compare their accuracies. The main goal of this research is to find the appropriate method allowing the control of an autonomous wheelchair by the severely handicapped people. The experimental results show that the MSI method reaches 96% of accuracy with optimal parameters.

Logical and inference approaches in Arabic question answering are in their first steps compared to other languages like English. This paper deals with the automatic Arabic text comprehension of question answering. Our goal is to understand a given text then answer a list of questions related to it. To do that, we have proposed an approach with which we can analyze a given text in an open domain and generate from them logical representations. Our approach is based on recognizing the textual entailment method. We have implemented this approach in a question answering system called NArQAS: New Arabic Question Answering System.

Brain-computer interface (BCI) offers solutions for those with severe neuromuscular disorder. Indeed, it provides new non-muscular channel to control external devices. The aim of this work is to increase the classification accuracy rate using the suitable system parameters and methods. In this present study Welch's method for power spectral density (PSD) estimation has been used for features extraction followed by two different classification methods (Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA)). The task was to think about right and left hand movement. A study of the influence of the flowing parameters was performed: frequency bands, predictive features, and classification method. The results show that the most significant increase takes place by improving the PSD estimation. Selecting the specific frequency bands of each cortical area provides also an important improvement. Finally the use of the suitable classifier is essential to attain optimal performances.

Brain controlled wheelchair system is a Brain-computer interface (BCI) allowing people with severe neuromuscular disorder to control the navigation by themselves. Indeed, it replaces muscular activities by neurophysiological ones. The advantages of the Steady State Visual Evoked Potential (SSVEP) make it a favorable choice to be used in the BCI. The aim of the present study is to design a brain controlled wheelchair system which is cheap and easy to use. Two signal processing methods for SSVEP frequencies detection are presented and discussed. The first method is based on the calculation of the normalized amplitude spectrum. The second method is based on the comparison between the signals' signal to noise ratio calculated on specific frequencies. A comparison of the accuracy of these methods with a frequency resolution of 0.1Hz allows the identification of the most precise method among them both. Results show that by using the second method, the system can reach for 97% of the four directions' navigation's accuracy.