Communications Internationales

Permanent URI for this collectionhttps://dspace.univ-boumerdes.dz/handle/123456789/11

Browse

Search Results

Now showing 1 - 10 of 847
  • No Thumbnail Available
    Item
    DotWise: A deep Learning-Powered Application for Efficient Black-To-Braille Text Conversion
    (Institute of Electrical and Electronics Engineers Inc., 2025) Zemouri, ET-Tahir; Zerrouki, Nabil; Harrou, Fouzi; Sun, Ying; Sayah, Djamel Eddine
    Access to information and reading materials is crucial for the empowerment and education of visually impaired individuals, and Braille serves as a vital medium for this purpose. However, the production of Braille texts is often time-consuming and expensive, limiting the availability of resources. This paper presents an innovative automatic Braille recognition and conversion system, designed to significantly reduce both the time and cost involved in producing Braille texts. By automating the conversion of standard printed text into electronic Braille, the system addresses the challenges faced in Braille production, enhancing accessibility for the visually impaired. The core of the proposed system leverages deep learning techniques, specifically the Long Short-Term Memory (LSTM) algorithm, to recognize printed characters and convert them into Braille. Experimental results demonstrate a drastic reduction in conversion time, highlighting the efficiency of the approach. This system promises to expand the availability of reading materials for visually impaired individuals, making a meaningful impact on their knowledge acquisition and overall welfare
  • No Thumbnail Available
    Item
    Robust Trajectory Tracking Control of a Robotic Manipulator Using Fractional Order PID Controller
    (2025) Maouche, Malak; Garma, Abdelkader; Guesmi, Kamel
    This paper investigates the efficiency of FractionalOrder Proportional-Integral-Derivative (FOPID) control of a 2-degree-of-freedom (2-DOF) robotic manipulator for highprecision trajectory tracking. Although the standard PID controller offers a performance baseline, its integer-order structure often fails to adequately compensate for the inherent nonlinearities and dynamic coupling in multi-joint manipulators under real-time operation. By incorporating fractional-order calculus, the proposed FOPID controller provides additional tuning parameters that substantially expand the optimization space. Additionally, we present a comparative study of both controllers under various dynamic tracking scenarios of a disturbed system. Our findings indicate that the enhanced flexibility of the FOPID structure facilitates a more robust and optimized control performance, resulting in superior tracking accuracy and improved disturbance rejection. The obtained results highlight the practical value of advanced control strategies in meeting the high-performance requirements of the next generation of autonomous systems.
  • No Thumbnail Available
    Item
    Finite-horizon optimal LQ control design using artificial bee colony programming
    (Institute of Electrical and Electronics Engineers, 2025) Boudouaoui, Yassine; Habbi, Hacene; Maidi, Ahmed; Belharet, Karim
    Designing optimal control laws in closed analytical form is still showing challenging computational issues. This may even hold for moderately complex problems like the linear quadratic (LQ) control problem with finite horizon. This paper introduces a novel approach to LQ controller design based on artificial bee colony programming (ABCP). Solution to the matrix Riccati differential equation (MRDE) derived for the optimal control problem subject to linear dynamical system model is determined by means of ABCP method. Aiming at this, preparatory steps have been set and analyzed as essential part of the ABCP-based MRDE solver. The effectiveness of the proposed solver is investigated on a typical LQ control problem and compared to existing methods in literature. Evidence of superiority is shown through numerical evaluation of the method convergence and solution accuracy
  • Thumbnail Image
    Item
    Synthesis, Characterization, and in Silico ADMET Evaluation of Transition Metal Complexes Based on Ortho-Phenylenediamine and Its Derivatives
    (ISRES, 2025) Kichou, Noura; Guechtouli, Nabila; Taferguennit, Manel; Ighilahriz, Karima
    A series of cobalt (II), nickel (II), and zinc(II) complexes were synthesized using orthophenylenediamine and its two substituted derivatives (methyl- and nitro-ortho-phenylenediamine) as ligands. These complexes were isolated and characterized using various analytical techniques, including Elemental analysis, infrared (IR) and UV-Visible spectroscopy, gravimetry, and conductimetry. Conductimetric analysis revealed that all the complexes exhibit a non-electrolytic behavior in solution, indicating the absence of free ions in the medium. IR spectroscopic studies allowed the identification of the coordination modes of the ligands to the metal centers. Comparison of the IR spectra of the complexes with those of the free ligands highlighted the involvement of the amine (-NH₂) groups in coordination with the metal, confirming their role as the primary coordination sites. UV-Visible spectroscopic analysis was used to determine the geometry of the complexes. The observed absorption bands are characteristic of an octahedral coordination around the metal ions, which is consistent with the expected electronic transitions for these systems. In recent years, the integration of computational methodologies has considerably enhanced the ability to predict the toxicity and pharmacokinetic behavior of bioactive compounds, thereby streamlining the early stages of drug discovery. Within this framework, the present study investigates the ADMET profiles - Absorption, Distribution, Metabolism, Excretion, and Toxicity as well as the drug-likeness properties of the synthesized ligands and their corresponding transition metal complexes.
  • Thumbnail Image
    Item
    Verified Path Indexing
    (pringer Science and Business Media Deutschland GmbH, 2025) Chaabani, Mohamed; Robillard, Simon
    The indexing of syntactic terms is a key component for the efficient implementation of automated theorem provers. This paper presents the first verified implementation of a term indexing data structure, namely a formalization of path indexing in the proof assistant Isabelle/HOL. We define the data structure, maintenance operations, and retrieval operations, including retrieval of unifiable terms, instances, generalizations and variants. We prove that maintenance operations preserve the invariants of the structure, and that retrieval operations are sound and complete
  • Thumbnail Image
    Item
    Diagnosis of a Leaky Pipeline Carrying Multiphase Flow under Plug Flow Conditions
    (Avestia Publishing, 2025) Ferroudji, Hicham; Al-Ammari, Wahib A.; Barooah, Abinash; Hassan, Ibrahim; Hassan, Rashid; Hassan, Rashid; Gomari, Sina Rezaei; Rahman, Mohammad Azizur
    Multiphase flows are crucial to the oil and gas industry since most petroleum companies produce and transport both gas and oil simultaneously. Pipeline leaks are frequently caused by corrosion, aging, and metal deterioration. After an incident, the energy sector not only loses money but also raises environmental and safety concerns. Therefore, developing a successful tool for instantaneous leakage identification in pipelines becomes crucial. In the current work, a leaky pipeline carrying multiphase flow is numerically simulated using Ansys-Fluent under plug flow conditions. The obtained numerical results were validated against experimental data collected from an experimental setup. After that, Probability Density Function (PDF), Wavelet Transform (WT), and Empirical Mode Decomposition (EMD) methods were applied to the obtained time series signals. On the other hand, the analysis is complemented by the application of several machine learning models like Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN). For instance, it is observed that the Empirical Mode Decomposition exhibits better performance in leakage identification
  • Thumbnail Image
    Item
    Interpreting NAS-Optimized Transformer Models for Remaining Useful Life Prediction Using Gradient Explainer
    (Warszawa: Polskie Towarzystwo Informatyczne, 2025) Nekkaa, Messaouda; Abdouni, Mohamed; Boughaci, Dalila
    Remaining Useful Life (RUL) estimation of complex machinery is critical for optimizing maintenance schedules and preventing unexpected failures in safety-critical systems. While Transformer architecture has recently achieved state-of-the-art performance on RUL benchmarks, their design often relies on expert tuning or costly Neural Architecture Search (NAS), and their predictions remain opaque to end users. In this work, we integrate a Transformer whose hyperparameters were discovered via evolutionary NAS with a gradient-based explainability method to deliver both high accuracy and transparent, perprediction insights. Specifically, we adapt the Gradient Explainer algorithm to produce global and local importance scores for each sensor in the C-MAPSS FD001 turbofan dataset. Our analysis shows that the sensors identified as most influential, such as key temperature and pressure measurements, match domain-expert expectations. By illuminating the int ernal decision process of a complex, NAS-derived model, this study paves the way for trustworthy adoption of advanced deep-learning prognostics in industrial settings.
  • No Thumbnail Available
    Item
    Numerical analysis of a new composite patch design effect for repairing a damaged steel structure with an inclined crack (mixed mode I+II)
    (Springer Science and Business Media Deutschland GmbH, 2025) Boussahra, S. M. N.; Madani, K.; Liamani, S.; Boukais M.; Houari A.; Campilho R.D.S.G.
    The available studies in the field of repair of damaged structures aim at reducing the high stress concentrations in the damaged area by optimizing the geometric and mechanical parameters of the composite patch. The geometric modifications are mainly performed on the repair patch based on standard geometric shapes (square, rectangle, triangle, or elliptical) intended for the repair of an aluminum structure. The present work highlights a non-standard geometric shape of the composite patch to repair a DH36 steel plate under mode I and mixed mode cracks using the finite element method (FEM). The composite patch performance regarding the damaged plate strength was validated by determining the J-integral in the plate and by evaluating the Von Mises stress in the adhesive and the principal stress in the patch to estimate the load transfer. The effect of the crack size, the patch material, and the geometric parameters of the patch were evaluated. The results of the numerical analysis show that the proposed patch shape, compared to the conventional shapes, provides an increased reduction of the J-integral in mode I and mixed mode, and that the patch ensures a good load transfer
  • No Thumbnail Available
    Item
    Vortex characteristics of two rotating immiscible fluids
    (2023) Brahma, Kenza; Saci, Rachid; Mansouri, Kacem
    Hydrodynamic and behavior of laminar confined axisymmetric flows driven by the rotating top disk in cylindrical cavity have been studied numerically. The vertical cavity, is filled with two superposed immiscible incompressible fluids. The top more viscous liquid drives the lower heavier fluid via the interface shear. The study, identified and highlighted a flow topology of types of axisymmetric recirculation regions; depending upon the effects of the disk rotation rate. This work confirms partly previous experimental observations and provides additional quantitative findings; particularly in the vicinity of the interface. The findings are in good accord with the experiments and show that vortex size increases with increasing rotation rate. The basic flow is made up of two clockwise circulation cells, separated by a thin layer of anticlockwise circulation (TCL). The gap thickness of TCL decreases with increasing rotation rate however, the interface high increases as rotation rate increases
  • No Thumbnail Available
    Item
    Grid-Connected and Grid-Islanded Energy Consumption Management
    (2023) Kaddour, Djillali; Hadjira, Belaidi; Belaidi, Dehia
    Ensuring microgrid continuity and improving system reliability in grid-connected and islanded modes is crucial for a reliable and sustainable power system. With intelligent EMS (Energy Management System), appropriate sizing, and resource optimization, the microgrid can handle the peak demand even under challenging weather conditions, in both (Connected/Islanded) modes without consuming any extra power from the grid facility or any external resources yet maintaining a reliable power supply. In this paper, a case study of load profile and power consumption estimation of some buildings in our institution IGEE (Institute of Electrical and Electronic Engineering) is used to test and illustrate our EMS performance via MATLAB Simulink. The DG-PV (Diesel Generator-Photovoltaic panel) synchronization technique is adopted to overcome the grid-tied PV system limitation and make it functional in off-grid mode. We used The same DERs (Distributed Energy Resources) sizing for (PV and BESS (Battery Energy Storage System)) in both modes, with advanced control algorithms and monitoring to ensure that our microgrid can have the ability to operate in both modes with a smooth transition from one to another. Hence, by improving the overall system reliability and continuity, we can benefit from all the microgrid mode's advantages to make our system work more efficiently and sustainably.