Institut de Génie Electrique et d'Electronique

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/2344

Browse

Now showing 1 - 20 of 613

3D antenna array optimization using firefly algorithm
(Université M’Hamed BOUGARA de Boumerdes : Institut de génie electrique et electronique (IGEE), 2019) Laouar, Abdelali; Recioui, A. (Supervisor)
The design of antenna arrays in a cubic geometry is presented in this project. The decision variables considered for this synthesis problem is the amplitude excitations. The synthesis process is carried out by the technique of a new type of nature-inspired global optimization methodology in the design of an optimized cubic antenna array which ensures minimum side lobes and high directivity, this new optimization method is based on the reaction of a firefly to the light of other fireflies and it is known as Firefly Algorithm (FA) a population based iterative heuristic global optimization algorithm technique, developed by Xin-She Yang, for multi-dimensional and multi-modal problems, with the potential to implement constraints on the search domain. Simulation results, detailed by using an antenna array with isotropic elements and with cubic antenna optimized by Firefly algorithm, show that side lobe level is reduced significantly in non-uniform case. Besides, the directivity is not worse than that of the uniform one.
3D statistical shape modeling
(2016) Omari, Sabrina; Soual, Imene; Cherifi, Dalila (supervisor)
Statistical shape models (SSMs) have been firmly established as a robust tool for segmentation of images. Widespread utilization of three-dimensional models appeared only in recent years, primarily made possible by breakthroughs in automatic detection of shape correspondences; while 2D models have been in use since the early 1990s. The objective of this project is to build a 3D statistical shape modeling for a given data; the implemented process goes through those basic steps, first collect the given data then apply the alignment algorithm based on the ICP (iterative closest point) method which in turn relies on Procrustes analysis result as a starting point, next we apply fitting algorithm which is also based on ICP. Finally we obtain the model using PCA (principle component analysis). To achieve this work, we have implemented the above process on two different shape models, one tested with the Basel Face Model (BSF) and the other is the femur model data samples from the SICAS (Swiss Institute for Computer Assissted Surgery) Medical Image Repository which is used by the Basel University (Switzerland) for both samples, where these models allow the generation and the exploration of the possible shape variation.
Action detection using deep learning shoplifting detection framework
(Université M’hamed Bougara de Boumerdes : Institut de Genie Electrique et Electronique, 2024) Bettahar, Mohammed Nadir; Touzout, Walid ( Supervisor)
This project delves into the application of deep learning for action detection, with a specifi cfocu so nidentifyin gshopliftin gbehavior si nretai lenvironments. Th egrowing need for automated surveillance systems that can efficient lya ndaccurate lydetect suspicious activities has motivated this work. Shoplifting action detection is the process of identifying and localizing shoplifting activities in a video by findin gbot hwhere and when an action occurs within a video clip and determining what action is being performed. A key challenge lies in preparing a dataset that reflect sth ecomplexity of real-world scenarios, which was addressed by employing semi-supervised learning techniques. The use of You Only Watch Once version 9 (YOLOv9) object detection model,its tracking function, was instrumental in the automation of labeling and tracking objects within the shoplifting video dataset, ensuring a reliable foundation for action detection. To evaluate the effectivenes so fth esystem ,th eYo uOnl yWatc hOnc eversio n2 (YOWOv2) model was used, conducting comprehensive training and testing across a variety of shoplifting situations. This allowed for a detailed assessment of the model’s ability to recognize and generalize diverse shoplifting actions, even in challenging environments. The results show that the models can detect suspicious behavior, offerin ga promising tool for improving retail security. This work contributes to the broader field of shoplifting detection by providing insights into how deep learning techniques can enhance real-time surveillance and reduce theft in retail settings, with potential applications in other domains of anomaly detection. The YOWOv2-Medium-16-frames model gave the best performance with 54.74% frame mean average precision and 42.67% in video mean average precision.
Active surge control of the compressor recycle system using feedback linearization
(2016) Hemchi, Oussama; Tebba, Assam; Boushaki, Razika (Supervisor)
Surge control in the centrifugal compressor recycle system is our main focus in this project. Surge is a term that is used for instability or oscillation through a compressor and is highly unwanted. The recycle system feeds compressed gas back to the intake via the recycle valve to ensure the safety of the system. A mathematical model of the recycle system which contains the compressor characteristic is extended and simulated in SIMULINK. The recycle system is proven to be stable as long as the slope of the compressor characteristic is negative. Two control techniques were used: The first is Surge Avoidance in which a PID controller keeps the operating point far from the unstable region and ensure the total safety of the system. The second method is Active Surge Control in which feedback linearization method is used to linearize the system then linear controllers were used to stabilize the system near the unstable region where efficiency is high.
Adaptability of applications according to the visibility offered SDN controller
(2021) Alioua, Nabil; Griche, Abdelghani; Belaidi, H. (Supervisor)
The volume of video traffic has grown considerably in recent years. This increase is pushing back the capabilities of the traditional networks of Internet Service Providers (ISPs), which results in their overuse and, consequently, the degradation of the video‘s Quality of Experience (QoE) perceived by users. In traditional networks Quality of Service (QoS) is one of the proposed solutions to overcome this problem, but it has many drawbacks because it is built on top of a fully distributed architecture that lacks broader visibility into the overall network resources. This work tries to solve this problem in the case of video streaming. To do this, we have used the great visibility provided by the SDN controller to develop a telemetry service in order to collect information about the state of the network and then provide it to the video streaming application to permit it to adapt its diffusion parameters accordingly. Finally, we moved on to the testing part where we demonstrated the effectiveness of our solution and its impact on the user‘s quality of experience. Keywords : SDN, QoS, QoE, Telemetry, Streaming.
Adaptive co-existence of OFDM and OTFS for Multi-Mobility scenarios in wireless communications
(Université M’Hamed Bougara de Boumerdes : Institut de génie electrique et electronique (IGEE), 2024) Zegrar, Hadj Mebarek; Smaili, Nesrine (Supervisor)
The rapid evolution of technology necessitates the development of new waveforms capable of handling the increasing demands of high-mobility scenarios. Orthogonal Frequency Di-vision Multiplexing (OFDM), although extensively used in current wireless communication systems, experiences significant performance degradation in highmobility environments due to large Doppler shifts and Doppler spread effects .To address these challenges, a novel waveform called Orthogonal Time Frequency Space (OTFS) has been developed, offer ingsuperior performance in highmobility scenarios by exploiting delay-Doppler diversity. However, OTFS introduces high processing complexity and does not exhibit obvious performance advantages for low-mobility users, where OFDM remains efficient and effective. There fore, there is a critical need to develop a co-existence method that leverages the strengths of both waveforms. we proposed a method to check the user’s velocity and dynamically switch between OFDM and OTFS based on user mobility. By doing so, the communication system can achieve optimal performance of Bit Error Rate (BER) versus Signal-to-Noise Ratio (SNR), maintaining robust and efficient data transmission across diverse mobility conditions.
Adaptive control for disturbance rejection in quadrotors.
(2021) Recham, Zine Eddine; Amrouche, Hafid; Boushaki, Razika (supervisor);
In order to fix the issue of precise trajectory tracking control for a quadrotor in the influence of environmental disturbance and system model parameter uncertainty, three control techniques were developed to control the quadrotor’s altitude, heading and position in space; the Proportional-Integral-Derivative or PID controller, the sliding mode controller and the backstepping controller. Simulation based experiments have been performed using MATLAB/SIMULINK to evaluate and compare between the three developed techniques in terms of dynamic performances, stability and disturbance effects.
Adaptive impedance control for unknown environment
(2022) Benbouali, Mohamed Amine; Derragui, N.(supervisor)
This report presents a simulation, design, build and evaluation of a 2 degree of freedom robotic arm guided by an adaptive impedance control algorithm governed by a neural network. This neural network is trained and evaluated by an adaptive genetic algorithm, the implementation of the robot arm consists of a 3D printed interconnected body controlled by Python and Arduino equipped with high torque servo motors. Interaction force sensors are installed around the end effector of the robotic arm as feedback to the neural network to exert manipulative decisions.
Adaptive PID fuzzy logic control of the recycle compression systems
(2016) Lahbiben, Yasmine; Ouacif, Hadjer; Boushaki, Razika (Supervisor)
Centrifugal compressors play an integral role in the oil and gas industry, helping power the multiple processes that convert oil and gas into thousands of practical products. These types of compressors can encounter a very dangerous and detrimental problem called surge. This work deals with the study of Centrifugal compressor surge and its prevention. In order to avoid the surge occurrence and ensure compressor’s operation in the stable region with maximum efficiency, appropriate techniques are considered based on PID regulator. Classical PID controllers remain one of the simplest, most effective, robust, and easily certifiable control strategies. However, this simplicity comes with a price. Design tradeoffs between integral and derivative gain in a linear PID controller often make it difficult to achieve optimal performance. To solve this problem, the design of a multistage fuzzy PID controller is proposed in this thesis. The simulation results show the effectiveness of the multistage fuzzy PID controller in maintaining the speed and stability of the system.
Algeria licence plate recognition system using faster-RCNN and YOLO models
(2020) Boudissa, Mehieddine; Kissoum, Malik; Khouas, Abdelhakim (supervisor)
In some institutions, of?ce buildings, or government facilities the ?ow of incoming and outgoing traf?c of people and cars needs to be monitored and recorded for security purposes as well as practicality and automation of entry pass for vehicles. Over the last years, many techniques have been proposed in an attempt to solve the Automatic License Plate Recognition System (ALPRS) problem. These techniques rely mainly on hand-crafted approaches and basic computer vision algorithms such as edge detection with Sobel ?lter. These approaches are not accurate enough for real-world applications, nor are they robust enough to changes in size, shape, and rotation of the license plates. Recently, deep learning techniques have been shown to be a strong tool for solving computer vision and object detection problems, such as ALPRS. In this project, we propose a solution based on convolutional neural networks (CNN). A data set containing 1000 car images has been collected, labeled, and then split into a training set and testing set. The size of this data set would allow for a transfer learning approach and ?ne-tuning of models. In the next step, various models belonging to the “You Only Look Once” (YOLO) CNN and “Faster Region-based CNN” (Faster RCNN) families are trained to perform plate detection task only. Once the models are trained and optimized, they are used to crop images of plates from the original car images. These cropped images are used to train models to perform the digit recognition task, similar to those trained for plate detection. The training process was repeated for different structures and parameters of the models to obtain the best performance possible. Evaluating these models relies on the use of the mean average precision (mAP) used in the original papers of YOLO and Faster-RCNN. The evaluation of the ?nal model (plate detection and digit recognition) relies on the accuracy of performing the identi?cation of the license plate numbers. The end result is an application that achieved an accuracy of 81.36% with real-time video processing capabilities and robust to changes in size, shape, color, and rotation of the license plates. This project provides users of the application with a reliable and practical security tool. It would also supply Algerian academics and software developers with a benchmark data set for further research on the topic and evaluation of future models.
Altitude backstepping control of quadcopter
(2018) Hamza, Younes; Boushaki, Razika (Supervisor)
This work deals with the study of the stabilization process of a nonlinear control system taking a certain model and derive state space equations through implementation of kinetic and dynamic equations where we present a challenging tool known as backstepping controllers based on Energy functions concept as presented by the famous Russian mathematician Lyaponuv. Simulation of the obtained results is done with Simulink.
Altitude backstepping control of quadcopter
(Université M’Hamed BOUGARA de Boumerdes : Institut de génie electrique et electronique (IGEE), 2018) Younes, Hamza; Boushaki, Razika (supervisor)
This work deals with the study of the stabilization process of a nonlinear control system taking a certain model and derive state space equations through implementation of kinetic and dynamic equations where we present a challenging tool known as backstepping controllers based on Energy functions concept as presented by the famous Russian mathematician Lyaponuv. Simulation of the obtained results is done with Simulink.
Alzheimer Disease Classification Using Convolution Neural Networks and Transfer Learning
(Université M’Hamed bougara : Institute de Ginie électric et électronic, 2023) Brahimi, Kahina; Slimi, Ounissa; Cherifi, Dalila (Supervisor)
Alzheimer’s Disease (AD) is a neurological disorder which causes brain cells to die, result-ing in memory loss, language diffi culties, and impulsive or erratic behavior. In recent years the number of individuals affected has seen a rapid increase, it is estimated that up to 107 million subjects will be affected by 2050 worldwide. Early diagnosis has become crucial to improve patients care and treatment. AD diagnosis is diffi cult due to the complexity of the brain struc-ture and its pixel intensity similarity especially at its early stage. A comprehensive diagnosis must be led including clinical assessment and medical imaging, which is a process that requires the expertise of professionals including neurologists and radiologists. One of the drawbacks of medical imaging approach is the inability to detect changes in very mild impairment also known as mild cognitive impairment (MCI). Deep learning has inspired a lot of interest in recent years in tackling challenges in a variety of fi elds, including medical imaging and detecting abnormal- ities beyond human capabilities. In this work we explored classifi cation approaches of AD through two different datasets which are respectively MRI dataset and tabular dataset. First, we dealt with the tabular data for bi- nary classifi cation of AD into demented and non demented using classical machine learning algorithms namely Support Vector Machine, K Nearest Neighbor, Decision Tree, Na¨ive Bayes Gaussian, Random Forest and Logistic Regressor. The fi ndings indicate that the models ef- fectively utilize the Clinical Dementia Rating feature for AD classifi cation. Second, we dealtwith MRI dataset for multiclassifi cation of AD into Non Demented, Very Mild Demented,Mild Demented, and Moderate Demented using transfer learning models namely VGG19, Res-Net50, Xception and MobileNet. The VGG19 model gave the best performance with 98.60%testing accuracy where the other models achieved 97.35%, 86.35% and 95.50% respectively.We also proposed a custom CNN model that outperformed the transfer learning models and achieved an accuracy of 99.00%.
Analysis and design of an analytical MPPT applied for different converter configurations
(2022) Djouider, Abderrazak Ziane; Tahir, Mustapha; Kheldoun, Aissa (Supervisor)
This project is intended to analyze the maximum power point tracking constraint conditions of the 12 PV systems under ideal conditions; The constraint conditions are necessary and sufficient conditions to guarantee the existence of the maximum power points of these PV systems. These constraint conditions are expressed by the modal parameters of the PV, therefore they show the inherent relationship between the load and the cell parameters when the maximum power point of the system always exist. In addition to apply them in practice, the maximum power point tracking constraint condition of the practical application are nvestigated. Furthermore, our work includes the variable weather parameter maximum power point tracking method based on equation solution (ES-VWP method). This equation consists of two analytic equations which represent two different operating points of the PV system. The simulation of this technique has shown a good effectiveness in terms of maximum power point and time response.
Analysis and design of MIMO microstrip antennas for smart grid applications
(2019) Lamri, Isam Eddine; Zeraib, Ahmed; Dehmas, M. (Supervisor)
In this work, an UWB and a Dual Band 2x2 element MIMO microstrip antennas are proposed for these applications. These antennas, printed on an FR-4 dielectric material, are fed by a microstrip line for the UWB and by a coplanar waveguide for the Dual Band structures. The structures radio electric properties including S-parameters, current distributions, radiation patterns, correlation coefficients and diversity gains were investigated using the CST electromagnetic simulator. Prototypes of the two final four-element MIMO structures have been fabricated and their S-parameters measured where an agreement is observed between simulated and measured results.
Analysis of a fractal Ultra Wide Band monopole antenna with reconfigurable notches
(2021) Abbad, Mohammed; Habtiche, Nabil; Dehmas, Mokrane
This work describes the design and analysis of a fractal Ultra-Wide Band (UWB) coplanar fractal antenna with triple reconfigurable notch rejection bands. The investigation considers three successive configurations: coplanar monopole circular UWB antenna – Fractal coplanar monopole UWB band antenna with improved bandwidth – Slotted UWB structurewith reconfigurable notches. Reconfigurability is achieved by opening / short-circuiting appropriate slots to select the rejected band(s). This study has ended with three reconfigurable notches bands covering the frequency bands: [4.50 ?????? , 5.35 ??????] , [6.30 ?????? , 7.15 ??????] and [8.15 ?????? , 8.60 ??????] including Wi-Max and WLAN applications and X band. The Developed structure was printed on a 21x25x1.63 mm 3 glass epoxy FR-4 substrate. The input reflection coefficient has been measured where an agreement was observed betweensimulated and experimental results. The simulations concerning the input reflection coefficients, current distributions and radiation patterns were carried out using the CST Microwave Studio.
Analysis of a reconfigurable multi-Band monopole antenna
(2021) Gharbi, Abdelhamid; Belgacem, Abdelmalek; Dehmas, Mokrane
This work deals with analysis of a monopole and frequency reconfigurable E-shape patch antenna using FR-4 substrate. The first step concerns modification of a published reconfigurable antenna due to difference in physical properties of the used substrate and the one at our disposal. These appropriate modifications have been performed on the antenna dimensions and on the stripline width so that the modified structure fits the original antenna band characteristics. In the second step, which concerns the main contribution of this work, a parametric analysis of the first structure focusing on the slot positions is achieved. The analysis ended up with nine (9) antenna geometrical configurations each one operating in four (4) reconfigurable modes. These antennas fulfill and satisfy various applications. One of these antenna configurations -operating in one single-band and three dual band reconfigurable modes- has been considered for further analysis. Prototypes of the modified original antenna as well as the one selected in the second part have been fabricated and their reflection coefficients in open switch positions mode measured where good agreements with simulated results have been obtained.
Analysis of frequency response of the Algerian power system
(Université M’Hamed BOUGARA de Boumerdes : Institut de génie electrique et electronique (IGEE), 2023) Hamam, Lyes; Ykhlef, Abdessemed Abdelwaheb; Kheldoun, Aissa (Supervisor)
The frequency response of a power system is a key parameter that reflects its stability and ability to maintain a consistent supply of power. This project presents an analysis of the frequency response characteristics of the Algerian power system, with a focus on frequency control techniques, reserve capacity, flywheel battery and battery energy storage system (BESS) integration. Furthermore, this analysis explores the role of reserve capacity in frequency regulation. Reserve capacity is spare generation capacity that stands by to deal with sudden frequency excursions or imbalances between supply and demand. The assessment focuses on the adequacy of reserve capacity in the Algerian grid and its impact on frequency stability. Finally, the project considers the integration of Battery Energy Storage Systems (BESS) and flywheel battery as a potential solution to improve frequency response capability.
Analytical studies of the modernization of the IGW (Internet Gateway) platform case : optimum telecom Algérie
(2019) Hachour, Abdelghani; Khene, Loukmane hakim; Khene, Loukmane hakim; Zitouni, Abdelkader (Supervisor); Zitouni, Abdelkader (Supervisor)
The internet is an indispensable service within the OTA company both in terms of the smooth running of the company and the quality of service provided to customers, unfortunately this service encounters an important problem that lies in availability that can affect the service continuity of one of the internet access sites of the company, to solve this problem and offer an optimal quality of service to the customer, the unification of the OTA network may leads to guarantee access to the internet to all the services of the company. An internet gateway can cope with many challenges in ubiquitous network systems such as efficiency, scalability, availability and reliability issues. The unification consists of three methods, single homing, double homing, triple homing. In this report we exploit by use of simulation, the strategic position of such methods to offer several higher-level services the obtained results will determine which of the three methods will be optimum in accordance with the technical and economic approval criteria.
Antenna selection in massive MIMO using machine learning
(Université M’hamed Bougara de Boumerdes : Institut de Genie Electrique et Electronique, 2024) Cherigui, Rahma; Bouazabia, Sarah; Boutellaa, Elhocine (Supervisor)
In massive MIMO (Multiple Input Multiple Output) systems the overall performance (bit/s/Hz/cell) is significantly improved by equipping the base stations with arrays of a hundred antennas; which becomes one of its most significant challenges; economically and technically due to the high power consumption. To solve this, Antenna selection (AS) is increasingly gaining more interest, as it strategically reduces the hardware complexity while maximizing efficiency and throughput by selecting a specific subset of antennas to activate in each transmission slot. In this report, we examine the application of multi-label learning (MLL) based algorithms in AS, such as problem transformation methods, including first order binary relevance; and high order chain classification. Additionally, we investigate the Deep neural networks (DNN) based algorithms, namely Multi-Label Convolutional Neural Networks (MLCNN) and Multi-Layer Perceptron (MLP) classifier, and multi-View based algorithm. These proposed methods are rigorously evaluated based on their maximum capacity, performance and the computation time across various scenarios. Our work concludes that, in comparison with the convex relaxation based method, the Multi-view MLL achieves comparable results.