Conference on Electrical Engineering

Machine learning applications for prognosis and health management usually face data unavailability, complexity, and drift due to the massive and rapid evolution of data volume, velocity, and variety (3V). Advances in deep learning have brought many improvements in this area, providing generative modeling, nonlinear abstractions, and adaptive learning to meet these challenges. Deep learning aims to learn from representations that provide a coherent abstraction of the original feature space, enabling it to be more meaningful and less complex. However, the data complexity associated with various distortions, such as higher noise levels, remains challenging to overcome. In this context, recurrent expansion algorithms have recently been introduced to explore deeper representations than ordinary deep networks, enabling even better feature mapping. In contrast to traditional deep learning, where abstracting inputs extract meaningful representations, recurrent expansion merges entire deep networks into one, allowing inputs, maps, and estimated targets to be explored as primary sources of learning. These three sources of information provide additional knowledge about their interactions in a deep network. Furthermore, recurrent expansion provides the ability to investigate the estimated targets of multiple networks and learn significant features, improving its accuracy with each round.

This keynote will provide a general overview of recurrent expansion, its main learning rules, variants, and prospective developments in this context. Case studies on electromechanical systems will be provided to illustrate the effectiveness of recurrent expansion prognosis.

1. P1-157: Study of U-shaped slot loaded patch antenna with COMSOL Multiphysics: Ibtissem Adoui; Mohammed Titaouine
2. P1-172: Adaptive observer for systems with nonlinear parameterization: Application to induction motor parameters estimation: Abdelaziz Maouche; Bachir Bensaker
3. P1-37: Sensorless PQ Control for Grid Connected Modular Multilevel Power Converter: Benhamimid Lakhdar; Abdeldjabar Benrabah; Bekheira Tabbache; Haroun Bensiali; Farid Khoucha
4. P1-18: A High-efficiency dipole antenna with carbon nanotubes and kapton II for terahertz applications using photonic band gap structures: Reguig Mustapha; Mohammed Belkheir; Allel Mokadem
5. P1-145: A Statistical Approach to Change Detection in Evolving Data Clouds for Leakage Monitoring in Thermal Exchanger: Meryem Mouhoun; Hacene Habbi
6. P1-166: Fooling the Watchers: Metaheuristic-Based Adversarial Attacks for Bypassing IoT Fingerprinting: Ramzi Boucherikha; Islam Debicha; Tayeb Kenaza
7. P1-154: Dynamic Modeling of a Tailed Bird-Inspired Flapping-Wing Vehicle: Brahim Bouksani; Hakim Bouadi; Housseyn Zamoum
8. P1-42: A Proposed Approach For Discrimination Between Eccentricity and Demagnetization Faults in PMSM Drives: Mohamed Boudiaf Koura; salah Marih; Rabeh Chehda
9. P1-69: Experimental Evaluation of EMI in DC/DC Converters: Focus on Switching Frequency and Supply Voltage: Amara Mohcine; Houcine Miloudi; Abdelber Bendaoud; Mohamed Miloudi; Mohammed Hamza Bermaki
10. P1-109: Numerical analysis of dual-core microstructured optical fiber (DC-MOF) based on tellurium dioxide (TeO2): Hamida Djelti; Fayza Bousalah
11. P1-46: A Comparative Analysis of Three Modulation Strategies for a 13-Level Inverter: Abdelfettah Kerboua; Sidi Mohamed Abdi; Mehdi Bouallou; Nihel Brikci; Ahmed Lemrabout
12. P1-49: Polarimetric SAR Image Simulation Using HFSS and Backprojection Algorithm: Azzeddine Chabane; Azzedine Bouaraba

To resist to the threat of the quantum computer, symmetric encryption algorithms are relatively easy to modify. Cryptologists' efforts have focused on public-key cryptography, namely digital signatures and key exchange mechanisms. In December 2016, NIST launched a standardization process by announcing a call for proposals. The goal is to submit to the community classical encryption algorithms that are resistant to attacks from quantum algorithms. Several proposals were submitted by academic-industrial research teams, they can be classified into five groups depending on the mathematical nature of the problem on which they are based. At the end of the fourth round in 2022, Lattice-based cryptography seems to present the best compromise for the future standard of public key cryptography.

For the deployment of the PQC, a hybrid approach seems the most advantageous. A hybrid key or signature establishment mechanism combines the calculations of an algorithm with recognized pre-quantum public key and an additional post-quantum algorithm. This allows to benefit from both the strong assurance on the resistance of the first against traditional attackers and of the second's conjectured resistance against quantum attackers.

In recent years, legged robotics—encompassing both animal-like and humanoid robots—has seen significant progress, driven by rapid advancements in embedded hardware and software systems, as well as growing capabilities in artificial intelligence. Initially deployed in areas such as entertainment and disaster response, legged robots are now making notable strides in large-scale manufacturing, social services, and defense forces. These developments position legged robots as potential game-changers across multiple industries and as transformative agents in social services. In this presentation, I will discuss the current state of the field, with a particular focus on humanoid robots, and share our research exploring the feasibility and effectiveness of legged robots in such applications while identifying the key challenges that must be addressed. Specifically, I will highlight the existing research and development gaps that must be overcome to fully harness the potential of humanoid robots in real-world scenarios. By examining these challenges, my aim is to provide a comprehensive overview of the technical, ethical, and practical considerations involved in advancing humanoid robotics toward real-world deployment.

1. P2-118: Design and Optimization of a Dual-Band Microstrip Patch Antenna Using Binary Grey Wolf Optimization for Millimeter-Wave Applications: Tarek Salah Eddine Mohammedi; Djelloul Aissaoui; Abdelhalim Chaabane; Mustafa Mosbah
2. P2-129: Finite elements modeling of equivalent neuronal currents signals with smart sensor: Mohamed Hider; Sara Sahraoui; Hassane Mohellebi;
3. P2-153: Optimization of Electric Field Reduction in HVXLPE Cable Terminations Using Conductive Wire Arrays Embedded in a Semiconductive Matrix: Zoubida Azaizia, Madijd Teguar, Abdellah Hedir
4. P2-08: Electrical Equivalence between Plan-Plane and Multi Points-Points Systems InThe Development of Parallel Discharges on Insulating: Satta Samia; Abdelhafid Bayadi
5. P2-147: Evaluating the Influence of Spectral Bands on Land Cover Classification Performance: Abderrahim Belkenniche; Toufik Ababsa; Atmane Khellal; Billel Nebili; Mehrez Boulahmar; Rabah Louali
6. P2-156: Finite-Difference Time-Domain vs. Finite Element Method: Analyzing Lightning EM fields Propagation in Heterogeneous Medium: Omari Mohamed, Abdenbi Mimouni, Imane Ghlib
7. P2-32: Modeling and simulation of intermodal interference in multimode optical fibers for sensing applications: Aya Malek Belhis; Hocine Medjadba, Abderrahim Azzoune
8. P2-99: A New Analytical Dynamic Model Based on the Critical State Model for the representation of Minor Hysteresis Loops in the Magnetization of Hard Type II Superconductor: Azzouza Asma; H. Allag, J-P Yonnet; P. Tixador
9. P2-10: Waveform Optimization Techniques for Energy Transfer Systems: A Novel Approach to Improving Performance: Abderrahim Benhamou; Mohamed Tellache
10. P2-108: Multi-Objective Optimal Load Shedding Strategy Using Equilibrium Optimizer for Smart Grid Applications: Aoumeur Ouyaba; Salem Arif; Mustapha mosbah; Ridha-djamel Mohammedi
11. P2-28: SDR-Based TWRI with UWB SFCW Signals and Compressive Sensing: An Experimental Approach: Ahcene Bellabas; Tahar Ziani; Belaid Ghezali; Ammar Mesloub; Djamel Teguig; Abdelmadjid Maali
12. P2-48: Impact of Windowing Functions on TomoSAR Reconstruction: A Comparative Analysis: Majd Eddine Bensmaine; Nabil Haddad; Osama Mahfoudia; Azzedine Bouaraba

Electric discharges are the main cause of insulation degradation in electrical equipment and disconnections in power networks. Their detection must be carried out as early as possible, and the evolution of their characteristics (intensity, frequency of occurrence, etc.) must be monitored over time. Electric discharges are characterized by voltage, current, and emission of a magnetic field, light waves, and acoustic waves. Diagnosis based on each of these parameters has its advantages and disadvantages. In this presentation, the various setups implemented and the measurement techniques will be presented for direct current, alternating current, and pulsed current. The Faraday cage, shielding, and signal protection measures against strong surrounding fields will also be discussed