Browsing by Author "Acheli, Dalila"

Now showing 1 - 20 of 23

Advances in coyote optimization algorithm : variants and applications
(Springer, 2023) Meraihi, Yassine; Gabis, Asma Benmessaoud; Ramdane-Cherif, Amar; Acheli, Dalila
Coyote Optimization Algorithm (COA) is a recent population-based technique inspired by the attitude of coyotes in nature. COA has been widely applied to tackle different optimization issues in several areas and has proved its successfulness compared to several methods found in the literature. In this paper, we describe a brief overview of COA and its variants including adjusted and hybridized versions. Additionally, we present COA applications in various fields such as image segmentation, wireless mesh networks, economic dispatch, electric power systems, distributed generation, and other engineering issues. Finally, we recommend some interesting future research areas directions for COA
Analysis of the human behavior from video with covariance matrix
(2016) Chebi, Hocine; Acheli, Dalila
Comparison of different wind farm layouts for a 25 MW project in the south west of Algeria
(2011) Kesraoui, M.; Harfouche, A.; Acheli, Dalila
The object of this work is to evaluate and compute the power potential of the KABERTEN site and to make the rigorous choice among different placements of wind turbines in order to decrease the wake effect and improve the power efficiency. Three proposals of wind farm layouts where all the turbines are faced to the prevailing wind have been used in the simulations. The results for individual and global energy yield as well as wake loss have been obtained and plotted. The wind Atlas Application Program (WASP) software of the Danish RISO laboratory is used in the study as a simulation tool to evaluate potential of the chosen site and to determine the best wind farm layout for a 25 MW project
Detection method without crowd behavior modeling by fuzzy logic
(2017) Chebi, Hocine; Acheli, Dalila; Kesraoui, Mohamed
Dragonfly algorithm: a comprehensive review and applications
(Springer, 2020) Meraihi, Yassine; Ramdane-Cherif, Amar; Acheli, Dalila; Mahseur, Mohammed
Dragonfly algorithm (DA) is a novel swarm intelligence meta-heuristic optimization algorithm inspired by the dynamic andstatic swarming behaviors of artificial dragonflies in nature. It has proved its effectiveness and superiority compared toseveral well-known meta-heuristics available in the literature. This paper presents a comprehensive review of DA and itsnew variants classified into modified and hybrid versions. It also describes the main diverse applications of DA in severalfields and areas such as machine learning, neural network, image processing, robotics, and engineering. Finally, the papersuggests some possible interesting research on the applications and hybridizations of DA for future works
Dynamic detection of anomalies in crowd's behavior analysis
(IEEE, 2015) Chebi, Hocine; Acheli, Dalila
The analysis of the human behavior from video is a wide field of the vision by computer. In this work we are interested in the analysis of the crowd behavior and its entities in a dense scene. These scenes are characterized by the presence of a great number of people in the camera's field of vision. A major problem is the development of an autonomous approach for the management of a great number of anomalies which is almost impossible to carry out by operators. We present in this paper a new approach for the anomalies detection very dense scenes relaying on the speed of both the individuals and the whole group. The various anomalies are detected by switching in a dynamic way between two approaches: the artificial neurons networks "ANN" for the management of group anomalies of people, and the Density Based Spatial Clustering of Application with Noise "DBSCAN" in the case of entities. For more robustness and effectiveness, we introduced two routines that serve to eliminate the shades and the management of occlusions.
Energy harvesting based on SLIPT in I2V-VLC system
(IEEE, 2023) Refas, Souad; Acheli, Dalila; Yahia, Selma; Meraihi, Yassine
Vehicular connectivity is mostly based on wireless access. The vehicular applications may be limited due to the limited battery life of the equipment involved. To address this issue, a method based on simultaneous light wave information and power transfer (SLIPT) is proposed for harvesting the energy in the Infrastructure-to-Vehicle Visible Light Communication (I2VVLC) system. The purpose of SLIPT is to harvest energy using light sources while decoding information. This article studies the effect of SLIPT in an I2V-VLC system. In this method, the received light from the traffic light source at the vehicle is harvested while decoding the information signal. First, for I2VVLC channel modeling, a recent realistic channel model using the ray-tracing method is utilized. Then, we propose the energy harvesting analysis based on the SLIPT strategy. After that, we investigate the impact of both the longitudinal and lateral distance between the vehicle and the traffic light on the amount of harvested energy. Furthermore, we investigate the relationship between the achievable information rate and the harvested energy amount. The obtained results demonstrate the significant impact of the communication distance and the required information rate on the quantity of harvested energy
Energy harvesting based on SLIPT in V2V-VLC system under atmospheric weather conditions
(2022) Refas, Souad Ikram; Acheli, Dalila; Yahia, Selma; Meraihi, Yassine; Ramdane-Cherif, Amar; Benmessaoud Gabis, Asma
Enhanced Whale Optimization Algorithm for mesh routers placement problem in wireless mesh networks
(IEEE, 2022) Mekhmoukh Taleb, Sylia; Meraihi, Yassine; Yahia, Selma; Benmessaoud Gabis, Asma; Ramdane-Cherif, Amar; Acheli, Dalila
In order to address the placement issue for mesh routers in wireless mesh networks, this study suggests an enhanced variant of the Whale optimization Algorithm (WOA), called ELG-WOA. The Generalized Opposition Based-Learning (GOBL) and the Levy Flight Distribution (LFD) are two methods that were incorporated into the original WOA to form the foundation of the ELG-WOA. Four performance indicators, including coverage, connectivity, load balancing, and fitness value, are used to validate the performance of ELG-WOA. The simulation results showed that ELG-WOA outperformed WOA and Bat Algorithm (BA)
Extraction de motif de mouvement de la foule par le flot optique
(2015) Chebi, Hocine; Acheli, Dalila
Dans ce travail, nous nous intéressons à l’analyse d'extraction de motifs de mouvement par la technique de flot optique, dans le but d’analysé le comportement de la foule. Ces scènes se caractérisent par la présence d’un grand nombre de personnes dans le champ de vision des caméras. Le problème majeur est l’élaboration et d’utilisation d’une technique sans modélisation de l’arrière-plan pour détecter les mouvements de la foule. Par la suite une étape de détection d’anomalies par la technique des réseaux de neurones artificiels (RNA). Nous présentons dans cet article une comparaison de l’approche proposée pour la détection des mouvements dans des scènes très denses et celle d'utilisation de modèle social de force. Pour plus de robustesse et d’efficacité, nous avons introduit la routine permettant d’élimination des ombres.
Heuristic and learning method for obstacle avoidance with mobile robot
(IEEE, 2020) Lachekhab, Fadhila; Acheli, Dalila; Tadjine, Mohamed; Meraihi, Yassine
In this paper, a fuzzy controller obstacle avoidance of the mobile robot Pioneer II is proposed. The fuzzy inference system FIS of this controller is performed by two methods: heuristic and reinforcement learning. the manual tuning of the fuzzy control system can be long and difficult. In contrast, reinforcement learning has proven theoretically and practically its ability to automatically optimize some parameters of the FIS. For that, the Fuzzy Actor-Critic Learning algorithm allows the determination of the parameters of the conclusions among of an available set fixed by the operator. The proposed algorithm allows the automatic determination of the parameters of the conclusions of the fuzzy rules. The simulations show that the two controllers (heuristic, RL controller) are able to avoid the different shapes of obstacles contained in known environments, and they show exceptionally good robustness when changing the environment (shape of obstacles, location of obstacles in the environment
Hybrid whale optimization algorithm with simulated annealing for the UAV placement problem
(Springer Nature, 2024) Taleb, Sylia Mekhmoukh; Meraihi, Yassine; Yahia, Selma; Ramdane-Cherif, Amar; Gabis, Asma Benmessaoud; Acheli, Dalila
This chapter suggests a hybrid algorithm based on the combination of whale optimization algorithm (WOA) with simulated annealing (SA), called WOA-SA, for solving the unmanned aerial vehicle (UAV) placement problem. WOA-SA combines WOA’s global search functionality with SA’s local search functionality. The main objective of our work is to determine the optimal position of the UAV in order to maximize the total throughput, depending on a given set of user locations and traffic demands. The WOA-SA algorithm is validated in terms of the total throughput using 18 distinct instances with various numbers of users, taking into account the effect of the distribution of user positions. The results of simulation using Matlab demonstrated that the WOA-SA algorithm obtains better results than WOA, SA, Particle Swam Optimization (PSO), Genetic Algorithm (GA), and Bat Algorithm (BA).
Intelligent detection without modeling of behavior unusual by fuzzy logic
(Springer, 2017) Chebi, Hocine; Acheli, Dalila; Kesraoui, Mohamed
Mesh router nodes placement for wireless mesh networks based on an enhanced Moth–Flame optimization algorithm
(Springer, 2023) Mekhmoukh Taleb, Sylia; Meraihi, Yassine; Mirjalili, Seyedali; Acheli, Dalila; Ramdane-Cherif, Amar; Benmessaoud Gabis, Asma
This paper proposes an enhanced version of Moth Flame Optimization (MFO) algorithm, called Enhanced Chaotic Lévy Opposition-based MFO (ECLO-MFO) for solving the mesh router nodes placement problem in wireless mesh network (WMN-MRNP). The proposed ECLO-MFO incorporates three strategies including the chaotic map concept, the Lévy flight strategy, and the Opposition-Based Learning (OBL) technique to enhance the optimization performance of MFO. Firstly, chaotic maps are used to increase the chaotic stochastic behavior of the MFO algorithm. Lévy flight distribution is adopted to increase the population diversity of MFO. Finally, OBL is introduced to improve the convergence speed of MFO and to explore the search space effectively. The effectiveness of the proposed ECLO-MFO is tested based on various scenarios under different settings, considering network connectivity and client coverage metrics. The results of simulation obtained using MATLAB 2020a demonstrate the accuracy and superiority of ECLO-MFO in determining the optimal positions of mesh routers when compared with the original MFO and ten other optimization algorithms such as Genetic Algorithm (GA), Simulated Annealing (SA), Harmony Search (HS), Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Cuckoo Search Algorithm (CS), Bat Algorithm (BA), Firefly optimization (FA), Grey Wolf Optimizer (GWO), and Whale Optimization Algorithm (WOA)
Orientation system of solar panels based on a robot manipulator
(2011) Chaib, Ahmed; Acheli, Dalila; Kesraoui, Mohamed
Solar energy is one of the most interesting renewable energies, as it is an inexhaustible natural accumulation. The electrical energy generated depends on the performance of photovoltaic panels that is based on the direction of sunlight. The position of the sun changes during the day, even during the year, which imposes a system of automatic orientation of solar panels for this purpose, several devices have been proposed and marketed. In our article, we focus on the adaptation of a robot manipulator for orientation and positioning of solar panels, applying for the control system, the model of the robot controller. First, we present the robotic system, which is a well-mastered, and his order was the subject of several studies and applications, and the model of the robot used for controlling the system. Finally, we give the simulation results in two modes: Mode fixed facing south with an inclination of 45° and the robot tracking mode following the elevation and azimuth movements with two decoupled movement. The results found show a gain in terms of solar energy collected measured about 51%
Performance analysis of bidirectional multi-hop vehicle-to-vehicle visible light communication
(Institute of Electrical and Electronics Engineers Inc, 2023) Refas, Souad; Acheli, Dalila; Yahia, Selma; Meraihi, Yassine; Ramdane-Cherif, Amar; Van, Nhan Vo; Ho, Tu Dac
Vehicular visible light communication (VVLC) has emerged as a promising field of research, garnering considerable attention from scientists and researchers. VVLC offers a potential solution to enable connectivity and communication between travelling vehicles along the road by using their existing headlights (HLs) and taillights (TLs) as wireless transmitters and integrating photodetectors (PDs) within the car front or car-back as wireless receivers. However, VVLC encounters more challenges than indoor VLC, particularly in vehicle-to-vehicle (V2V) communication, where vehicle mobility disrupts the establishment of direct communication links. To address this, we propose a multi-hop relay system wherein intermediate vehicles act as wireless relays to maintain a line-of-sight (LoS) link. In this paper, we investigate the performance of a bidirectional multi-hop relay V2V-VLC system that operates in both the forward and backward directions. Based on realistic ray tracing channel models, we derive a closed-form expression for the full bidirectional communication range. We also analyze how the transceiver's parameters and the number of relays affect the system performance. Our results show that the proposed bidirectional multi-hop relay system can extend the direct transmission range by more than 19 m with only a hop relay.
Solar tracking with photovoltaic panel
(Elsevier, 2013) Miloudi, Lalia; Acheli, Dalila; Chaib, Ahmed
Strategy of detecting abnormal behaviors by fuzzy logic
(IEEE, 2017) Chebi, Hocine; Acheli, Dalila; Kesraoui, Mohamed
This work falls within the framework of the video surveillance research axis. This work falls within the scope of video surveillance. It involves a link between automatic processing and problems related to video surveillance. The job is to analyze video streams coming from a network of surveillance cameras, deployed in an area of interest in order to detect abnormal behavior. Our approach in this article relies on the new application and the use of fuzzy logic in the case of division and fusion of the crowd. The detection of these behaviors will increase the speed of response of the security services in order to perform accurate analysis and detection of events in real time
Strategy of detections abnormal behavior by fuzzy logic
(IEEE, 2017) Chebi, Hocine; Acheli, Dalila; Kesraoui, Mohamed
Sun trajectory and PV module I–V characteristics estimation using neural networks
(IEEE, 2017) Miloudi, Lalia; Acheli, Dalila; Kesraoui, Mohamed