Karim Meddah | Université des Sciences et Technologie Houari Boumediene (USTHB) (original) (raw)

Uploads

Conference Presentations by Karim Meddah

The continuous monitoring of cardiac patients requires an ambulatory system that can automaticall... more The continuous monitoring of cardiac patients requires an ambulatory system that can automatically detect heart diseases. This study presents a new field programmable gate array (FPGA)-based hardware implementation of the QRS complex detection. The proposed detection system is mainly based on the Pan and Tompkins algorithm, but applying a new, simple, and efficient technique in the detection stage. The new method is based on the centred derivative and the intermediate value theorem, to locate the QRS peaks. The proposed architecture has been implemented on FPGA using the Xilinx System Generator for digital signal processor and the Nexys-4 FPGA evaluation kit. To evaluate the effectiveness of the proposed system, a comparative study has been performed between the resulting performances and those obtained with existing QRS detection systems, in terms of reliability, execution time, and FPGA resources estimation. The proposed architecture has been validated using the 48 half-hours of records obtained from the Massachusetts Institute of Technology -Beth Israel Hospital (MIT-BIH) arrhythmia database. It has also been validated in real time via the analogue discovery device.

Le complexe QRS du signal ECG est l’élément essentiel pour détecter des Arythmies cardiaques. Dan... more Le complexe QRS du signal ECG est l’élément essentiel pour détecter des Arythmies cardiaques. Dans ce papier nous présenterons la conception et l’implémentation sous FPGA d’un algorithme de détection du complexe QRS en temps réel. Pour une implémentation optimale sous FPGA , Nous avons adapté l’algorithme de PAN et TOMPKINS. Notre adaptations touche deux phases principales de ce dernier, tout en apportant notre contribution personnelle dans la technique de la détection du QRS. Moyennant la carte Analog Discovery et l’outil de conception XSG, nous avons pu réaliser un système de détection d’arythmie cardiaque en temps réel. Grâce a une étude statistique sur la base de donnée MIT BIH, nous avons obtenu un taux de
96% de précision avec l’utilisation de 56% des ressources de la carte FPGA vertex cx5vlx50t.

The QRS complex of ECG signal is the essential element to detect cardiac arrhythmias. In this pap... more The QRS complex of ECG signal is the essential element to detect cardiac arrhythmias. In this paper, a real time design implementated on FPGA to present the QRS complex algorithm detection. For optimal implementation on FPGA, we have adapted the PAN and TOMPKINS algorithm. Our adaptation affects two main phases of this latter, while bringing our own contribution in the art of the QRS detection. By means of the Analog Discovery and the XSG design tool, we have achieved a system of arrhythmia detection in real time. A statistical study on the database MIT BIH, gives a good accuracy rate, using a 56 % of the resources in the FPGA virtex cx5vlx50t card.

Papers by Karim Meddah

Neural Computing and Applications, 2019

The automatic detection and cardiac classification are essential tasks for real-time cardiac dise... more The automatic detection and cardiac classification are essential tasks for real-time cardiac diseases diagnosis. In this context, this paper describes a field programmable gates array (FPGA) implementation of arrhythmia recognition system, based on artificial neural network. Firstly, we have developed an optimized software-based medical diagnostic approach, capable of defining the best electrocardiogram (ECG) signal classes. The main advantage of this approach is the significant features minimization, compared to the existing researches, which leads to minimize the FPGA prototype size and saving energy consumption. Secondly, to provide a continuous and mobile arrhythmia monitoring system for patients, we have performed a hardware implementation. The FPGA has been referred due to their easy testing and quick implementation. The optimized approach implementation has been designed on the Nexys4 Artix7 evaluation kit using the Xilinx System Generator for DSP. In order to evaluate the performance of our proposal system, the classification performances of proposed FPGA fixed point have been compared to those obtained from the MATLAB floating point. The proposed architecture is validated on FPGA to be a customized mobile ECG classifier for long-term real-time monitoring of patients.

 Abstract—By exploiting a database of 109 persons including two states to detect: sleepy or not,... more  Abstract—By exploiting a database of 109 persons including two states to detect: sleepy or not, we have designed a system for automatically detecting drowsiness of a driver at the wheel. By filtering the alpha wave and by using the power spectral density of that same wave, our data were analyzed using the percentiles as measures of dispersion. A threshold discriminating the two states was found, which helped to highlight the area of the brain responsible for the state of drowsiness for driver. Thus, number of EEG signals to be analyzed will reduce and processing time of this system will be decreased. With cross validation technique, data are trained and tested, to get result with accuracy of 80% or higher. It shows that the EEG could be used helping experts in the development of an intelligent system for detecting state of drowsy driving with only ten signals by person.

Neural Computing and Applications, 2019