mohamed fezari - Academia.edu (original) (raw)

Papers by mohamed fezari

Wseas Transactions On Environment And Development, May 26, 2023

Forest fires are one of the most devastating natural disasters that can have a significant impact... more Forest fires are one of the most devastating natural disasters that can have a significant impact on the environment, economy, and human lives. Early detection and prompt response are crucial to minimize the damage caused by forest fires. In recent years, Wireless Sensor Networks (WSN) and Internet of Things (IoT) technologies have emerged as promising solutions for forest fire detection due to their low-cost and efficient monitoring capabilities. This paper proposes a low-cost forest fire detection system based on WSN and IoT. The system uses a network of sensor nodes that are strategically placed in the forest to monitor environmental conditions such as temperature, humidity, and smoke. The sensor data is transmitted to a central server, where advanced algorithms are used to detect and predict the occurrence of forest fires. The system provides real-time alerts to forest authorities and users using a mobile application that shows the fire maps and the current updates. The proposed system has been evaluated using based on experiments, and the results show that it can effectively detect forest fires with high accuracy, low false alarms, and low cost. This system has the potential to provide an efficient and cost-effective solution for forest fire detection and can play a vital role in protecting the environment and saving lives.

During the diagnosis of pulmonary diseases, the doctor listens to the lung sounds on the patient’... more During the diagnosis of pulmonary diseases, the doctor listens to the lung sounds on the patient’s chest using a traditional stethoscope for the earlier detection of abnormal respiratory sounds. Currently, due to developments in the digital technology domain, an electronic stethoscope can instead be used to acquire respiratory sounds and save these as data for further processing and analysing. Many algorithms for automatic classification have been implemented to distinguish between several lung diseases. In this study, we implemented a deep residual network (ResNet) model with three different architectures based on different numbers of layers (ResNet-50/101/152) for the classification of pulmonary pathologies. To evaluate this method, we used it for the analysis of gammatonegrams, which transform lung sounds from onedimensional to two-dimensional representations. The image outputs obtained with the gammatonegram are fed as inputs to the Three-ResNet architecture. The ICBHI database was used to classify three types of pulmonary conditions, namely, healthy, chronic obstructive pulmonary disease (COPD) and pneumonia conditions. The results showed that, ResNet-50, ResNet-101 and ResNet-152 presented accuracies of 90.37%, 89.79% and 67.57%, respectively. Therefore, our results demonstrate that the residual networks can achieve significant accuracy for the classification of these three types of pulmonary conditions.

IEEE Conference Proceedings, 2016

The aim of this paper is to investigate the development of a navigation aid for blind and visuall... more The aim of this paper is to investigate the development of a navigation aid for blind and visually impaired people. It is based on a microcontroller with synthetic speech output. This aid is portable and gives information to the user about urban walking routes to point out what decisions to make. On the other hand, and in order to reduce

Nucleation and Atmospheric Aerosols, 2008

ABSTRACT Automatic speech recognition (ASR) is the process of automatically recognizing the speec... more ABSTRACT Automatic speech recognition (ASR) is the process of automatically recognizing the speech on the basis of information obtained by acoustic features extracted from the speech signal. Because features extraction is the first component in ASR systems, the quality of the later component depends from the quality of feature extractor. The goal of this work is to study and implement features (representations) extraction, which are robust to the differences between the acoustic conditions of training and evolution. These features will be evaluated in an Automatic Arab digits recognition system. A particular attention will be taken to the robust features extraction methods (CMS, CGN, RASTAPLP, MBLPCC, and LPC MFCC).

Synthese, 2019

In this paper, we present a static hand gestures recognition system of Arabic Sign Language alpha... more In this paper, we present a static hand gestures recognition system of Arabic Sign Language alphabets. The proposed method uses Histogram Of visual Words (HOW) descriptor and Support Vector Machine (SVM). First, the images of static hand gestures are converted into HOW features and grouped using k-means clustering to create histograms. Then they are converted from non linear space into linear space using Chi-squared kernel. The result is fed into One-vs-All SVM classifier to build signs models. Training and test stages of this technique are implemented on hand postures images using cluttered backgrounds for different lighting conditions, scales and rotations. The proposed method shows a satisfactory recognition rate and achieves good real-time performance regardless of the image resolution. RESUME Dans cet article, nous présentons un système de reconnaissance des gestes statique de la main du Langage des Signes Arabe. La méthode proposée utilise un descripteur des histogrammes en mots visuels (HOW), et la classification en utilisant séparateur à vaste marges (SVM) avec un noyau homogène. Tout d'abord, les images des gestes statiques de la main sont converties en paramètres HOW et groupées en utilisant la classification k-means pour créer des histogrammes. Ensuite, ils sont convertis à partir d'un espace non linéaire en espace linéaire en utilisant le noyau Chi-carré (X 2). Le résultat est introduit dans le classificateur SVM pour créer des modèles de signes. Les étapes d'apprentissage et de test de cette technique sont implémentées sur des postures d'images en utilisant des fonds complexes pour différentes conditions d'éclairage, échelles et rotations. La méthode proposée montre un taux de reconnaissance satisfaisant et obtient de bonnes performances en temps réel quelle que soit la résolution de l'image. Keywords arabic sign language-static hand gesture-how-one-vs-all support vector machine (svm). Mots clés langue des signes arabe-geste de la main statique-howséparateur à Vaste Marges (svm).

Abstract:--The aim of this work is to implement on real-time a speech recognition module in order... more Abstract:--The aim of this work is to implement on real-time a speech recognition module in order to control the movements of a five degree of freedom manipulator arm using a Kalman filter as a selector in noisy environment and HHM model to recognise 12 Arabic spotted words. ...

Volume 4: ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications and the 19th Reliability, Stress Analysis, and Failure Prevention Conference, 2007

In this paper, a voice command system for autonomous robots is proposed as a project. The methodo... more In this paper, a voice command system for autonomous robots is proposed as a project. The methodology adopted is based on hybrid techniques used in speech recognition which are zero crossing and extremes with dynamic time warping followed by a decision system based on independent methods test results. To implement the approach on a real time application, a Personal Computer interface was designed to control the movement of a set of robots by voice commands. The voice command system for four autonomous robots is designed. The main parts of the robots are a microcontroller from Microchip PIC16F876, a set of ultrasonic modules and a radio frequency receiver module.

Industrial control systems (ICSs) integrates supervisory control and data acquisition (SCADA), di... more Industrial control systems (ICSs) integrates supervisory control and data acquisition (SCADA), distributed control system (DCS) and programmable logic controllers (PLC) operating on critical infrastructures. Both ICS and SCADA present an attractive target for attackers due to their increasing interconnectivity to the internet. So, it is so essential to develop a security mechanism appropriate to the context of industrial systems to avoid or reduce the identified risks. This paper is concerned with the modeling of SCADA cyber-attacks that change sensor measurements (such as deception attacks) and system behavior using a bond graph (BG) tool. The objective is to model the effect of the attack on the system. Then, to facilitate the detection and the isolation of the attack from the system.

Automatic Control and Computer Sciences, Feb 1, 2007

Communications in computer and information science, 2012

This paper details the simulation and design of a voice tele-operating system for a robot arm (ma... more This paper details the simulation and design of a voice tele-operating system for a robot arm (manipulator). The methodology adopted is based on hybrid technique that combines classical patterns used in automatic speech recognition system such as Crossing Zero, energy, Mel frequency cepstral derivative MFCC coefficients as features and Dynamic time warping as classifier. To implement the approach on a real-time application, a Personal Computer interface was designed to control the movements of a six degree of freedom (DOF) robot arm by transmitting the orders via radio frequency circuits. A simulation GUI was developed in order to guide the user in his commands. The speech recognition agent is tested and results of hybrid and classical techniques were compared. The hardware of the slave part (the robot arm) is composed from: a microcontroller from Microchip PIC16F628, a radio frequency wireless module and the power circuits.

Nucleation and Atmospheric Aerosols, 2008

In this paper, we propose an efficient direct method that estimates pure translation motion param... more In this paper, we propose an efficient direct method that estimates pure translation motion parameters in dynamic scenes. We develop an algorithm that computes, directly, phase information in Fourier domain. The computations are locally performed and limited to small patches of the image. The local measurement of motion parameters are then combined in a more global interpretation by using parametric

2021 29th Telecommunications Forum (TELFOR), Nov 23, 2021

This paper aims to develop an automatic1 cleaning system for Photovoltaic (PV) solar panels insta... more This paper aims to develop an automatic1 cleaning system for Photovoltaic (PV) solar panels installed on the roof of University Al-Zaytoonah faculty of IT in Jordan. The experiments were done at University Badji Mokhtar Annaba Algeria. We designed a dust detector and perform tests on it for calibration. The brain of the system is an Arduino Uno microcontroller, which gets data from the dust sensor then makes treatment and sends instructions to the system to perform the cleaning process. The cleaning process is based on-power circuit that controls the speed and direction of a motor to scan all surface of the PV panel. GUI was developed to monitor the system and sensor status. The collected data is transmitted to the central unit. Finally, the primary results obtained to meet our expatiations for optimizing the efficiency of the solar panels.

International Conference on Systems, Apr 29, 2014

Wireless sensor networks (WSN) have been involved in different applications including monitoring ... more Wireless sensor networks (WSN) have been involved in different applications including monitoring many environmental phenomena such as air quality assessment, forest fire monitoring, flood rivers control.. In this paper, a WSN architecture where nodes are equipped with gas , temperature and dust sensors and Arduino-uno as microcontroller have been designed for air quality monitoring for some sensible area in Annaba City East of Algeria. The previous design included several units mainly: MSP430 Microcontroller, Gas and dust sensors, and the current regulator circuit. The new design is based on Arduino-Uno as micro-system. Comparing of normal gas levels for the clean air, the obtained results indicate that there is a big difference in the gas levels of both gases (LPG , NO2 and CO) which obtained from the several tests. However, the acquired results for the air quality control in some areas in Annaba city show no risky situation to be considered for further actions. In this work we cover the field of Air quality monitoring electronic Nodes design and wireless transmission of fusion data. Then A GUI has been designed for simulation of the WSN in controlling the environment air Quality. Tests are encouraging; the flexibility off the shelf components and the ease of design facilitates the implementation of this system.

Procedia Computer Science, 2015

In this paper, we propose an improvement of our previous work in this field by developing a heart... more In this paper, we propose an improvement of our previous work in this field by developing a heart rate , body temperature and blood pressure monitor system based on new Arduino Mega micro-system device. It offers the advantage of portability over old embedded system (tape-based recording systems). The paper focus on: how we implemented algorithms to analyze heart beat rate signals in real-time, how to fusion data of different sensors mainly here temperature and blood pressure and to transmit the data via radio frequency (Xbee module). Then explain a web server application for healthcare givers to access the data. In addition, it allows doctors to get the heart beat rate file of the patient by email every twenty four hours. It can also be used to control patients or athletic person over a long period. The system reads, stores and analyses the heart beat rate signals, body temperature repetitively in real-time. The hardware and software design are oriented towards a single-chip microcontroller-based system, hence minimizing the size. The important features of this paper are the implementation of extremums and energy in the algorithm to compute patient heart rate and detect any anomaly within the P wav in ECG signal. The first tests were encouraging.

Improving pre-installed monitoring system for a set of Photovoltaic (PV) panels, using wireless s... more Improving pre-installed monitoring system for a set of Photovoltaic (PV) panels, using wireless sensor network (WNS) with embedded fuzzy controller, is our contribution in this work in order to control and detect faults within solar panels that affect considerably the energy produced by the solar panels. The new solution is to integrate the detection and classification of faults within the sensors node. The proposed classifier based on Fuzzy logic controller is integrated within the Node. The WSN nodes are implemented with appropriate sensors for more often occurred faults on the solar power panels. A simulation has been done on nodes distribution and a study for the design of a node with appropriate sensors taking into account the priorities of the processing faults. The primary results of simulation are very encouraging in point of fast detection of faults with minimum computation and minimum data transmission.

Wseas Transactions On Environment And Development, May 26, 2023

Forest fires are one of the most devastating natural disasters that can have a significant impact... more Forest fires are one of the most devastating natural disasters that can have a significant impact on the environment, economy, and human lives. Early detection and prompt response are crucial to minimize the damage caused by forest fires. In recent years, Wireless Sensor Networks (WSN) and Internet of Things (IoT) technologies have emerged as promising solutions for forest fire detection due to their low-cost and efficient monitoring capabilities. This paper proposes a low-cost forest fire detection system based on WSN and IoT. The system uses a network of sensor nodes that are strategically placed in the forest to monitor environmental conditions such as temperature, humidity, and smoke. The sensor data is transmitted to a central server, where advanced algorithms are used to detect and predict the occurrence of forest fires. The system provides real-time alerts to forest authorities and users using a mobile application that shows the fire maps and the current updates. The proposed system has been evaluated using based on experiments, and the results show that it can effectively detect forest fires with high accuracy, low false alarms, and low cost. This system has the potential to provide an efficient and cost-effective solution for forest fire detection and can play a vital role in protecting the environment and saving lives.

During the diagnosis of pulmonary diseases, the doctor listens to the lung sounds on the patient’... more During the diagnosis of pulmonary diseases, the doctor listens to the lung sounds on the patient’s chest using a traditional stethoscope for the earlier detection of abnormal respiratory sounds. Currently, due to developments in the digital technology domain, an electronic stethoscope can instead be used to acquire respiratory sounds and save these as data for further processing and analysing. Many algorithms for automatic classification have been implemented to distinguish between several lung diseases. In this study, we implemented a deep residual network (ResNet) model with three different architectures based on different numbers of layers (ResNet-50/101/152) for the classification of pulmonary pathologies. To evaluate this method, we used it for the analysis of gammatonegrams, which transform lung sounds from onedimensional to two-dimensional representations. The image outputs obtained with the gammatonegram are fed as inputs to the Three-ResNet architecture. The ICBHI database was used to classify three types of pulmonary conditions, namely, healthy, chronic obstructive pulmonary disease (COPD) and pneumonia conditions. The results showed that, ResNet-50, ResNet-101 and ResNet-152 presented accuracies of 90.37%, 89.79% and 67.57%, respectively. Therefore, our results demonstrate that the residual networks can achieve significant accuracy for the classification of these three types of pulmonary conditions.

IEEE Conference Proceedings, 2016

The aim of this paper is to investigate the development of a navigation aid for blind and visuall... more The aim of this paper is to investigate the development of a navigation aid for blind and visually impaired people. It is based on a microcontroller with synthetic speech output. This aid is portable and gives information to the user about urban walking routes to point out what decisions to make. On the other hand, and in order to reduce

Nucleation and Atmospheric Aerosols, 2008

ABSTRACT Automatic speech recognition (ASR) is the process of automatically recognizing the speec... more ABSTRACT Automatic speech recognition (ASR) is the process of automatically recognizing the speech on the basis of information obtained by acoustic features extracted from the speech signal. Because features extraction is the first component in ASR systems, the quality of the later component depends from the quality of feature extractor. The goal of this work is to study and implement features (representations) extraction, which are robust to the differences between the acoustic conditions of training and evolution. These features will be evaluated in an Automatic Arab digits recognition system. A particular attention will be taken to the robust features extraction methods (CMS, CGN, RASTAPLP, MBLPCC, and LPC MFCC).

Synthese, 2019

In this paper, we present a static hand gestures recognition system of Arabic Sign Language alpha... more In this paper, we present a static hand gestures recognition system of Arabic Sign Language alphabets. The proposed method uses Histogram Of visual Words (HOW) descriptor and Support Vector Machine (SVM). First, the images of static hand gestures are converted into HOW features and grouped using k-means clustering to create histograms. Then they are converted from non linear space into linear space using Chi-squared kernel. The result is fed into One-vs-All SVM classifier to build signs models. Training and test stages of this technique are implemented on hand postures images using cluttered backgrounds for different lighting conditions, scales and rotations. The proposed method shows a satisfactory recognition rate and achieves good real-time performance regardless of the image resolution. RESUME Dans cet article, nous présentons un système de reconnaissance des gestes statique de la main du Langage des Signes Arabe. La méthode proposée utilise un descripteur des histogrammes en mots visuels (HOW), et la classification en utilisant séparateur à vaste marges (SVM) avec un noyau homogène. Tout d'abord, les images des gestes statiques de la main sont converties en paramètres HOW et groupées en utilisant la classification k-means pour créer des histogrammes. Ensuite, ils sont convertis à partir d'un espace non linéaire en espace linéaire en utilisant le noyau Chi-carré (X 2). Le résultat est introduit dans le classificateur SVM pour créer des modèles de signes. Les étapes d'apprentissage et de test de cette technique sont implémentées sur des postures d'images en utilisant des fonds complexes pour différentes conditions d'éclairage, échelles et rotations. La méthode proposée montre un taux de reconnaissance satisfaisant et obtient de bonnes performances en temps réel quelle que soit la résolution de l'image. Keywords arabic sign language-static hand gesture-how-one-vs-all support vector machine (svm). Mots clés langue des signes arabe-geste de la main statique-howséparateur à Vaste Marges (svm).

Abstract:--The aim of this work is to implement on real-time a speech recognition module in order... more Abstract:--The aim of this work is to implement on real-time a speech recognition module in order to control the movements of a five degree of freedom manipulator arm using a Kalman filter as a selector in noisy environment and HHM model to recognise 12 Arabic spotted words. ...

Volume 4: ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications and the 19th Reliability, Stress Analysis, and Failure Prevention Conference, 2007

In this paper, a voice command system for autonomous robots is proposed as a project. The methodo... more In this paper, a voice command system for autonomous robots is proposed as a project. The methodology adopted is based on hybrid techniques used in speech recognition which are zero crossing and extremes with dynamic time warping followed by a decision system based on independent methods test results. To implement the approach on a real time application, a Personal Computer interface was designed to control the movement of a set of robots by voice commands. The voice command system for four autonomous robots is designed. The main parts of the robots are a microcontroller from Microchip PIC16F876, a set of ultrasonic modules and a radio frequency receiver module.

Industrial control systems (ICSs) integrates supervisory control and data acquisition (SCADA), di... more Industrial control systems (ICSs) integrates supervisory control and data acquisition (SCADA), distributed control system (DCS) and programmable logic controllers (PLC) operating on critical infrastructures. Both ICS and SCADA present an attractive target for attackers due to their increasing interconnectivity to the internet. So, it is so essential to develop a security mechanism appropriate to the context of industrial systems to avoid or reduce the identified risks. This paper is concerned with the modeling of SCADA cyber-attacks that change sensor measurements (such as deception attacks) and system behavior using a bond graph (BG) tool. The objective is to model the effect of the attack on the system. Then, to facilitate the detection and the isolation of the attack from the system.

Automatic Control and Computer Sciences, Feb 1, 2007

Communications in computer and information science, 2012

This paper details the simulation and design of a voice tele-operating system for a robot arm (ma... more This paper details the simulation and design of a voice tele-operating system for a robot arm (manipulator). The methodology adopted is based on hybrid technique that combines classical patterns used in automatic speech recognition system such as Crossing Zero, energy, Mel frequency cepstral derivative MFCC coefficients as features and Dynamic time warping as classifier. To implement the approach on a real-time application, a Personal Computer interface was designed to control the movements of a six degree of freedom (DOF) robot arm by transmitting the orders via radio frequency circuits. A simulation GUI was developed in order to guide the user in his commands. The speech recognition agent is tested and results of hybrid and classical techniques were compared. The hardware of the slave part (the robot arm) is composed from: a microcontroller from Microchip PIC16F628, a radio frequency wireless module and the power circuits.

Nucleation and Atmospheric Aerosols, 2008

In this paper, we propose an efficient direct method that estimates pure translation motion param... more In this paper, we propose an efficient direct method that estimates pure translation motion parameters in dynamic scenes. We develop an algorithm that computes, directly, phase information in Fourier domain. The computations are locally performed and limited to small patches of the image. The local measurement of motion parameters are then combined in a more global interpretation by using parametric

2021 29th Telecommunications Forum (TELFOR), Nov 23, 2021

This paper aims to develop an automatic1 cleaning system for Photovoltaic (PV) solar panels insta... more This paper aims to develop an automatic1 cleaning system for Photovoltaic (PV) solar panels installed on the roof of University Al-Zaytoonah faculty of IT in Jordan. The experiments were done at University Badji Mokhtar Annaba Algeria. We designed a dust detector and perform tests on it for calibration. The brain of the system is an Arduino Uno microcontroller, which gets data from the dust sensor then makes treatment and sends instructions to the system to perform the cleaning process. The cleaning process is based on-power circuit that controls the speed and direction of a motor to scan all surface of the PV panel. GUI was developed to monitor the system and sensor status. The collected data is transmitted to the central unit. Finally, the primary results obtained to meet our expatiations for optimizing the efficiency of the solar panels.

International Conference on Systems, Apr 29, 2014

Wireless sensor networks (WSN) have been involved in different applications including monitoring ... more Wireless sensor networks (WSN) have been involved in different applications including monitoring many environmental phenomena such as air quality assessment, forest fire monitoring, flood rivers control.. In this paper, a WSN architecture where nodes are equipped with gas , temperature and dust sensors and Arduino-uno as microcontroller have been designed for air quality monitoring for some sensible area in Annaba City East of Algeria. The previous design included several units mainly: MSP430 Microcontroller, Gas and dust sensors, and the current regulator circuit. The new design is based on Arduino-Uno as micro-system. Comparing of normal gas levels for the clean air, the obtained results indicate that there is a big difference in the gas levels of both gases (LPG , NO2 and CO) which obtained from the several tests. However, the acquired results for the air quality control in some areas in Annaba city show no risky situation to be considered for further actions. In this work we cover the field of Air quality monitoring electronic Nodes design and wireless transmission of fusion data. Then A GUI has been designed for simulation of the WSN in controlling the environment air Quality. Tests are encouraging; the flexibility off the shelf components and the ease of design facilitates the implementation of this system.

Procedia Computer Science, 2015

In this paper, we propose an improvement of our previous work in this field by developing a heart... more In this paper, we propose an improvement of our previous work in this field by developing a heart rate , body temperature and blood pressure monitor system based on new Arduino Mega micro-system device. It offers the advantage of portability over old embedded system (tape-based recording systems). The paper focus on: how we implemented algorithms to analyze heart beat rate signals in real-time, how to fusion data of different sensors mainly here temperature and blood pressure and to transmit the data via radio frequency (Xbee module). Then explain a web server application for healthcare givers to access the data. In addition, it allows doctors to get the heart beat rate file of the patient by email every twenty four hours. It can also be used to control patients or athletic person over a long period. The system reads, stores and analyses the heart beat rate signals, body temperature repetitively in real-time. The hardware and software design are oriented towards a single-chip microcontroller-based system, hence minimizing the size. The important features of this paper are the implementation of extremums and energy in the algorithm to compute patient heart rate and detect any anomaly within the P wav in ECG signal. The first tests were encouraging.

Improving pre-installed monitoring system for a set of Photovoltaic (PV) panels, using wireless s... more Improving pre-installed monitoring system for a set of Photovoltaic (PV) panels, using wireless sensor network (WNS) with embedded fuzzy controller, is our contribution in this work in order to control and detect faults within solar panels that affect considerably the energy produced by the solar panels. The new solution is to integrate the detection and classification of faults within the sensors node. The proposed classifier based on Fuzzy logic controller is integrated within the Node. The WSN nodes are implemented with appropriate sensors for more often occurred faults on the solar power panels. A simulation has been done on nodes distribution and a study for the design of a node with appropriate sensors taking into account the priorities of the processing faults. The primary results of simulation are very encouraging in point of fast detection of faults with minimum computation and minimum data transmission.