In this paper a full approach of modeling and intelligent control of a four rotor unmanned air ve... more In this paper a full approach of modeling and intelligent control of a four rotor unmanned air vehicle (UAV) known as quad-rotor aircraft is presented. In fact, a PID on-line optimized Neural Networks Approach (PID-NN) is developed to be applied to angular trajectories control of a quad-rotor. Whereas, PID classical controllers are dedicated for the positions, altitude and speed control. The goal of this work is to concept a smart Self-Tuning PID controller, for attitude angles control, based on neural networks able to supervise the quad-rotor for an optimized behavior while tracking a desired trajectory. Many challenges could arise if the quad-rotor is navigating in hostile environments presenting irregular disturbances in the form of wind modeled and applied to the overall system. The quad-rotor has to quickly perform tasks while ensuring stability and accuracy and must behave rapidly with regards to decision making facing disturbances. This technique offers some advantages over c...
2017 14th International Multi-Conference on Systems, Signals & Devices (SSD), 2017
Prostate cancer is becoming a threat to humanity. Today, the diagnosis of diseases is still be re... more Prostate cancer is becoming a threat to humanity. Today, the diagnosis of diseases is still be realized mostly by manual methods. Nevertheless, this traditional process is inefficient and not accurate. Its precision depends on the operator's expertise. Thus, applying machine learning algorithms for malignant cells detection and counting remains a significant purpose in medical image analysis research. In this paper, we apply a modified ACO algorithm to measure the rate of cell growth of cancer's patient automatically due to segmentation and counting process. The proposed method was applied on several medical images obtained from MRI-guided prostate biopsies. The robustness of this idea was showed by comparison with hand-labeled obtained segmentation results.
2013 International Conference on Electrical Engineering and Software Applications, 2013
Images are often corrupted by random variations in intensity ,illumination or have poor contrast ... more Images are often corrupted by random variations in intensity ,illumination or have poor contrast and can't be used directly .Several studies have expressed the need to reduce noise and to improve the visual quality of the image. For this purpose, several mathematical tools have been developed such as image filtering by a convolution filter, such as the kernel with compact support (KCS) which has been recently proposed by Remaki and Cheriet [1] and it's version separable (SKCS) [10].The effectiveness of the SKCS filter in the smoothing operation depends on the value of the scale parameter. Moreover, if the scale parameter is increased, the image is blurred and details and borders are removed. This disadvantage is related to the static nature of the KCS kernel. In this paper we propose a dynamic and adaptive SKCS filter based on neural networks. The scale parameters involved in the filtering process are calculated in real time and supervised by the neural network. The filter scale varies continuously in order to detect and clean noisy areas of the image. To assess the developed theory, an application of filtering noisy images is presented, including a qualitative comparison between the result obtained by the static SKCS and the adaptive SKCS kernel proposed.
International Review of Applied Sciences and Engineering
In this paper a complete methodology of modeling and control of quad-rotor aircraft is exposed. I... more In this paper a complete methodology of modeling and control of quad-rotor aircraft is exposed. In fact, a PD on-line optimized Neural Networks Approach (PD-NN) is developed and applied to control the attitude of a quad-rotor that is evolving in hostile environment with wind gust disturbances and should maintain its position despite of these troubles. Whereas PD classical controllers are dedicated for the positions, altitude and speed control. The main objective of this work is to develop a smart Self-Tuning PD controller for attitude angles control, based on neural networks capable of controlling the quad-rotor for an optimized performance thus following a desired trajectory. Many problems could arise if the quad-rotor is evolving in hostile environments presenting irregular troubles such as wind gusts modeled and applied to the overall system. The quad-rotor has to rapidly achieve tasks while guaranteeing stability and precision and must behave quickly with regards to decision mak...
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
of the accuracy of the contents or up to date. It (includes-instructions, formulae and drug doses... more of the accuracy of the contents or up to date. It (includes-instructions, formulae and drug doses) should be independently verified with all available primary sources. The publisher shall not be legally responsible for any types of loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material.
2022 2nd International Conference on Computing and Information Technology (ICCIT), 2022
This study revisits the global mean pooling layer (GAP) proposed, and sheds light on how it allow... more This study revisits the global mean pooling layer (GAP) proposed, and sheds light on how it allows Deep Residual Neural Network to have a remarkable localization capacity, work with the same technique, but in three different forms, with the change of the type of network ResNet50, because it also works by the system (GAP) which is used to obtain the final convolutional layer representing the characteristics of the human face. In our experiment, we used “yalefaces” dataset with the addition of many blurry images to have the efficiency rate of this technique to detect the face. The experimental results from the proposed methods and the face recognition rate for the “yalefaces” dataset are validated, and we compared with recent techniques. The face recognition rate of the used dataset based on this network is 99%, which shows the effectiveness.
2017 14th International Multi-Conference on Systems, Signals & Devices (SSD), 2017
Regarding to the problems that can be encountered in the analysis step of medical images, removin... more Regarding to the problems that can be encountered in the analysis step of medical images, removing noise is an important processing for better diagnosis. This work deals with a new anisotropic method for medical image filtering. This method is based on an innovative conduction function. We show that the new algorithm offers an efficient noise removal while protecting edges without any blur of the image details.
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
This paper proposes a new fast diffusion function with an accelerator coefficient for image resto... more This paper proposes a new fast diffusion function with an accelerator coefficient for image restoration task. The suggested algorithm is carried out based on gradient magnitude and suitably filter the image while preserving edge and texture. Several comparisons with recent works is given to show the efficiency of the new conduction function. This performance is demonstrated using quantitative (PSNR, MSSIM) and qualitive metrics (visual evaluation).
2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2016
This paper proposes a new four-dimensional hyperchaotic map based on the lorenz system to realize... more This paper proposes a new four-dimensional hyperchaotic map based on the lorenz system to realize hyper-chaotic encryption in higher dimension and improve the security. The hyper-chaotic sequences generated by the new method used to generate key sequences. The key sequences are used for image encryption. The security test results indicate that the new hyperchaotic system has high security and complexity. The comparison between the new hyperchaotic system and the several low-dimensional chaotic systems shows that the proposed system performs more efficiently.
2018 International Conference on Smart Communications in Network Technologies (SaCoNeT), 2018
The field of autonomous navigation of mobile robot is advancing so fast especially with the devel... more The field of autonomous navigation of mobile robot is advancing so fast especially with the development of machine learning algorithms.This study aims to introduce a neural network controller that controls the trajectory and the obstacle avoidance of a non-holonomic mobile robot.We train the robot in environment containing multiple obstacles with different places.This paper includes both a kinematic and a dynamic study of a mobile robot.Different training schemes have been studied that tackle the learning objectives differently. The trained controller is producing the Pulse Width Modulation (PWM) signals that could be implemented in a microprocessor and validated by simulations.Unlike some other recent approaches, this work was validated by a 3D simulation which is similar to the real model.
2019 International Conference on Control, Automation and Diagnosis (ICCAD), 2019
In this paper a new Smart PID optimized Neural Networks Approach (SNNPID) is applied to a two-whe... more In this paper a new Smart PID optimized Neural Networks Approach (SNNPID) is applied to a two-wheeled differential mobile robot. The aim of this work is to optimize the parameters of a PID controller operating with the neural networks which supervise learning in order to teach the robot a desired behavior while tracking a desired trajectory. Many challenges could arise if the robot is moving in a hostile environment full of disturbances such as holes and stones. Yet, the engines that drive the robot should in no way be damaged. In fact, in the case of insurmountable disturbances, the robot must stop. The smart robot has to quickly perform tasks while ensuring stability and accuracy and must be autonomous with regards to decision making. Simulation results are obtained with the Matlab/Simulink environment and are given based on the application of load torques disturbances on the mobile robot behavior. These simulation results are satisfactory and have demonstrated the effectiveness o...
In this paper a full approach of modeling and intelligent control of a four rotor unmanned air ve... more In this paper a full approach of modeling and intelligent control of a four rotor unmanned air vehicle (UAV) known as quad-rotor aircraft is presented. In fact, a PID on-line optimized Neural Networks Approach (PID-NN) is developed to be applied to angular trajectories control of a quad-rotor. Whereas, PID classical controllers are dedicated for the positions, altitude and speed control. The goal of this work is to concept a smart Self-Tuning PID controller, for attitude angles control, based on neural networks able to supervise the quad-rotor for an optimized behavior while tracking a desired trajectory. Many challenges could arise if the quad-rotor is navigating in hostile environments presenting irregular disturbances in the form of wind modeled and applied to the overall system. The quad-rotor has to quickly perform tasks while ensuring stability and accuracy and must behave rapidly with regards to decision making facing disturbances. This technique offers some advantages over c...
2017 14th International Multi-Conference on Systems, Signals & Devices (SSD), 2017
Prostate cancer is becoming a threat to humanity. Today, the diagnosis of diseases is still be re... more Prostate cancer is becoming a threat to humanity. Today, the diagnosis of diseases is still be realized mostly by manual methods. Nevertheless, this traditional process is inefficient and not accurate. Its precision depends on the operator's expertise. Thus, applying machine learning algorithms for malignant cells detection and counting remains a significant purpose in medical image analysis research. In this paper, we apply a modified ACO algorithm to measure the rate of cell growth of cancer's patient automatically due to segmentation and counting process. The proposed method was applied on several medical images obtained from MRI-guided prostate biopsies. The robustness of this idea was showed by comparison with hand-labeled obtained segmentation results.
2013 International Conference on Electrical Engineering and Software Applications, 2013
Images are often corrupted by random variations in intensity ,illumination or have poor contrast ... more Images are often corrupted by random variations in intensity ,illumination or have poor contrast and can't be used directly .Several studies have expressed the need to reduce noise and to improve the visual quality of the image. For this purpose, several mathematical tools have been developed such as image filtering by a convolution filter, such as the kernel with compact support (KCS) which has been recently proposed by Remaki and Cheriet [1] and it's version separable (SKCS) [10].The effectiveness of the SKCS filter in the smoothing operation depends on the value of the scale parameter. Moreover, if the scale parameter is increased, the image is blurred and details and borders are removed. This disadvantage is related to the static nature of the KCS kernel. In this paper we propose a dynamic and adaptive SKCS filter based on neural networks. The scale parameters involved in the filtering process are calculated in real time and supervised by the neural network. The filter scale varies continuously in order to detect and clean noisy areas of the image. To assess the developed theory, an application of filtering noisy images is presented, including a qualitative comparison between the result obtained by the static SKCS and the adaptive SKCS kernel proposed.
International Review of Applied Sciences and Engineering
In this paper a complete methodology of modeling and control of quad-rotor aircraft is exposed. I... more In this paper a complete methodology of modeling and control of quad-rotor aircraft is exposed. In fact, a PD on-line optimized Neural Networks Approach (PD-NN) is developed and applied to control the attitude of a quad-rotor that is evolving in hostile environment with wind gust disturbances and should maintain its position despite of these troubles. Whereas PD classical controllers are dedicated for the positions, altitude and speed control. The main objective of this work is to develop a smart Self-Tuning PD controller for attitude angles control, based on neural networks capable of controlling the quad-rotor for an optimized performance thus following a desired trajectory. Many problems could arise if the quad-rotor is evolving in hostile environments presenting irregular troubles such as wind gusts modeled and applied to the overall system. The quad-rotor has to rapidly achieve tasks while guaranteeing stability and precision and must behave quickly with regards to decision mak...
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
of the accuracy of the contents or up to date. It (includes-instructions, formulae and drug doses... more of the accuracy of the contents or up to date. It (includes-instructions, formulae and drug doses) should be independently verified with all available primary sources. The publisher shall not be legally responsible for any types of loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material.
2022 2nd International Conference on Computing and Information Technology (ICCIT), 2022
This study revisits the global mean pooling layer (GAP) proposed, and sheds light on how it allow... more This study revisits the global mean pooling layer (GAP) proposed, and sheds light on how it allows Deep Residual Neural Network to have a remarkable localization capacity, work with the same technique, but in three different forms, with the change of the type of network ResNet50, because it also works by the system (GAP) which is used to obtain the final convolutional layer representing the characteristics of the human face. In our experiment, we used “yalefaces” dataset with the addition of many blurry images to have the efficiency rate of this technique to detect the face. The experimental results from the proposed methods and the face recognition rate for the “yalefaces” dataset are validated, and we compared with recent techniques. The face recognition rate of the used dataset based on this network is 99%, which shows the effectiveness.
2017 14th International Multi-Conference on Systems, Signals & Devices (SSD), 2017
Regarding to the problems that can be encountered in the analysis step of medical images, removin... more Regarding to the problems that can be encountered in the analysis step of medical images, removing noise is an important processing for better diagnosis. This work deals with a new anisotropic method for medical image filtering. This method is based on an innovative conduction function. We show that the new algorithm offers an efficient noise removal while protecting edges without any blur of the image details.
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
This paper proposes a new fast diffusion function with an accelerator coefficient for image resto... more This paper proposes a new fast diffusion function with an accelerator coefficient for image restoration task. The suggested algorithm is carried out based on gradient magnitude and suitably filter the image while preserving edge and texture. Several comparisons with recent works is given to show the efficiency of the new conduction function. This performance is demonstrated using quantitative (PSNR, MSSIM) and qualitive metrics (visual evaluation).
2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2016
This paper proposes a new four-dimensional hyperchaotic map based on the lorenz system to realize... more This paper proposes a new four-dimensional hyperchaotic map based on the lorenz system to realize hyper-chaotic encryption in higher dimension and improve the security. The hyper-chaotic sequences generated by the new method used to generate key sequences. The key sequences are used for image encryption. The security test results indicate that the new hyperchaotic system has high security and complexity. The comparison between the new hyperchaotic system and the several low-dimensional chaotic systems shows that the proposed system performs more efficiently.
2018 International Conference on Smart Communications in Network Technologies (SaCoNeT), 2018
The field of autonomous navigation of mobile robot is advancing so fast especially with the devel... more The field of autonomous navigation of mobile robot is advancing so fast especially with the development of machine learning algorithms.This study aims to introduce a neural network controller that controls the trajectory and the obstacle avoidance of a non-holonomic mobile robot.We train the robot in environment containing multiple obstacles with different places.This paper includes both a kinematic and a dynamic study of a mobile robot.Different training schemes have been studied that tackle the learning objectives differently. The trained controller is producing the Pulse Width Modulation (PWM) signals that could be implemented in a microprocessor and validated by simulations.Unlike some other recent approaches, this work was validated by a 3D simulation which is similar to the real model.
2019 International Conference on Control, Automation and Diagnosis (ICCAD), 2019
In this paper a new Smart PID optimized Neural Networks Approach (SNNPID) is applied to a two-whe... more In this paper a new Smart PID optimized Neural Networks Approach (SNNPID) is applied to a two-wheeled differential mobile robot. The aim of this work is to optimize the parameters of a PID controller operating with the neural networks which supervise learning in order to teach the robot a desired behavior while tracking a desired trajectory. Many challenges could arise if the robot is moving in a hostile environment full of disturbances such as holes and stones. Yet, the engines that drive the robot should in no way be damaged. In fact, in the case of insurmountable disturbances, the robot must stop. The smart robot has to quickly perform tasks while ensuring stability and accuracy and must be autonomous with regards to decision making. Simulation results are obtained with the Matlab/Simulink environment and are given based on the application of load torques disturbances on the mobile robot behavior. These simulation results are satisfactory and have demonstrated the effectiveness o...
Uploads
Papers by Hassene Seddik