Rania Loukil | Deep Learning | Best Scholar Award

Mr. Rania Loukil | Deep Learning | Best Scholar Award

Maitre Assistant at Ecole Nationale d’Ingenieurs de Tunis, Tunisia

Dr. Rania Loukil is a Tunisian researcher and academic specializing in Artificial Intelligence, Embedded Systems, and Control Engineering. Currently serving as a Maître Assistant (Assistant Professor) at the Higher Institute of Technology and Computer Science (ISTIC), University of Carthage, she has over a decade of experience in teaching, research, and interdisciplinary collaboration. Her research merges deep learning with practical domains like IoT, smart grids, and fault diagnosis, reflecting a strong commitment to innovation and applied AI solutions.

🔹Professional Profile:

Scopus Profile

Orcid Profile

🎓Education Background

  • Ph.D. in Electrical Engineering, National Engineering School of Sfax (ENIS), University of Sfax, Tunisia | 2010–2014

  • Master Project, INRIA Paris / ENIS | 2008–2009

  • Engineering Degree in Electrical Engineering, ENIS, Sfax | 2005–2008

  • Preparatory Classes (MP), IPEIS, Sfax | 2003–2005

  • Baccalaureate in Mathematics, Tunisia | 2002–2003 – Mention Bien

💼 Professional Development

  • Maître Assistant in Artificial Intelligence, ISTIC, University of Carthage | Jan 2018–Present

  • Coach Junior, BIAT Foundation | Nov 2018–Present

  • Maître Assistant in AI, ISI Gabes | Sep 2015–Dec 2017

  • Head of Electrical Engineering Department, Ecole Polytechnique Centrale Privée de Tunis | Feb 2015–Aug 2015

  • Permanent Faculty, Ecole Polytechnique Centrale Privée de Tunis | Oct 2014–Jan 2015

🔬Research Focus

  • Artificial Intelligence & Deep Learning (RNNs, Transformers, Bayesian Networks)

  • Fault Diagnosis and Nonlinear Control (Sliding Mode, Observers)

  • IoT and Embedded Systems

  • Smart Grids and Microgrid Energy Management

  • Nanocomposite Classification and Materials Informatics

📈Author Metrics:

  • Published in leading journals including Expert Systems with Applications and Scientific Reports

  • Recent works involve hybrid deep learning approaches for nanocomposite classification and smart energy systems

  • Selected publications:

    • Classification of Nanocomposites using RNN Transformer & Bayesian Network, ESWA, 2025

    • Probabilistic and Deep Learning Approaches for Conductivity-Driven Nanocomposite Classification, Scientific Reports, 2025

    • IoT Solution for Energy Management, IREC 2023

🏆Awards and Honors:

  • Recognized contributor to interdisciplinary AI projects

  • Regular presenter at international conferences on AI, control systems, and energy informatics

  • Acknowledged for excellence in education and mentorship through BIAT Foundation coaching initiatives

📝Publication Top Notes

1. Classification of a Nanocomposite Using a Combination Between Recurrent Neural Network Based on Transformer and Bayesian Network for Testing the Conductivity Property

Journal: Expert Systems with Applications
Publication Date: April 2025
DOI: 10.1016/j.eswa.2025.126518
ISSN: 0957-4174
Authors: Wejden Gazehi, Rania Loukil, Mongi Besbes
Abstract: This study presents a hybrid AI model combining Transformer-based RNN and Bayesian Networks to classify nanocomposites based on conductivity, demonstrating improved interpretability and predictive accuracy.

2. Probabilistic and Deep Learning Approaches for Conductivity-Driven Nanocomposite Classification

Journal: Scientific Reports
Publication Date: March 7, 2025
DOI: 10.1038/s41598-025-91057-1
ISSN: 2045-2322
Authors: Wejden Gazehi, Rania Loukil, Mongi Besbes
Abstract: This paper explores probabilistic learning and deep learning methods for classifying nanocomposites with a focus on electrical conductivity, emphasizing model generalizability.

3. Enhanced Nanoparticle Classification Through Optimized Artificial Neural Networks

Conference: 2024 International Conference on Decision Aid Sciences and Applications (DASA)
Presentation Date: December 11, 2024
DOI: 10.1109/dasa63652.2024.10836425
Authors: Wejden Gazehi, Rania Loukil, Mongi Besbes
Abstract: The paper demonstrates how optimized ANN architectures can significantly improve nanoparticle classification in terms of conductivity profiling, offering an efficient pipeline for smart material characterization.

4. Improving the Classification of a Nanocomposite Using Nanoparticles Based on a Meta-Analysis Study, Recurrent Neural Network and Recurrent Neural Network Monte-Carlo Algorithms

Journal: Nanocomposites
Publication Date: July 8, 2024
DOI: 10.1080/20550324.2024.2367181
ISSN: 2055-0324, 2055-0332
Authors: Rania Loukil, Wejden Gazehi, Mongi Besbes
Abstract: Through a comparative analysis using RNN and Monte-Carlo RNN algorithms, this work proposes a robust framework for classifying nanocomposites, supported by meta-analytical insights.

5. Design and Implementation of an IoT Solution for Energy Management\

Conference: 14th International Renewable Energy Congress (IREC 2023)
Presentation Date: December 16, 2023
Authors: Rania Loukil, Neila Bediou, Hatem Oueslati, Majdi Hazami
Abstract: This contribution introduces a practical IoT-based architecture for optimizing energy consumption and monitoring within renewable energy systems, aligning with smart grid principles.

.Conclusion:

Dr. Rania Loukil stands out as an exemplary scholar combining deep learning, embedded systems, and energy informatics. Her cross-disciplinary work addresses both academic challenges and societal needs, aligning well with the objectives of a Best Scholar Award. Given her solid track record, thematic relevance, and academic leadership, she is highly deserving of this recognition.

➡️ Recommendation: Strongly endorse her nomination for the Best Scholar Award, with suggestions to highlight international collaborations, quantitative metrics, and applied impacts during the award presentation or application.

Xin Liu | Deep Learning | Best Researcher Award

Dr. Xin Liu | Deep Learning | Best Researcher Award

Associate Professor at Wenzhou Business College, China📖

Dr. Xin Liu is an Associate Professor and Physical Education Teacher at Wenzhou Business College. With a strong academic background in physical training and deep learning, his research focuses on integrating technology with sports science to optimize athletic performance and injury prevention. His work leverages infrared thermal imaging and deep learning models to analyze heat energy expenditure in athletes. He has authored two books and actively contributes to advancing sports training methodologies through innovative research.

Profile

Orcid Profile

Education Background🎓

  • Ph.D. in Physical Education, Jose Rizal University, 2020–2023
  • Master’s in Physical Education, Shanghai Normal University, 2017–2019
  • Bachelor’s in Physical Education, Shandong Agricultural University, 2013–2017

Professional Experience🌱

  • Physical Education Teacher, Wenzhou Business College (2024–Present)
    Engaged in teaching and research on physical training methodologies, integrating AI-driven analytics in sports science.
  • Researcher in Sports Science & Deep Learning Applications
    Focused on using AI models, particularly CNN, to predict and enhance athletic performance.
Research Interests🔬
  • Physical Training & Sports Performance Optimization
  • Application of Deep Learning in Sports Science
  • Infrared Thermal Imaging for Athlete Monitoring

Author Metrics

Dr. Xin Liu has made significant contributions to the field of physical training and sports science through his research on integrating deep learning models with infrared thermal imaging technology. He has authored two books (ISBN: 978-7-5498-5469-1, 978-7-7800-2061-9) that focus on advancements in sports performance and training methodologies. His research includes two completed/ongoing projects, with findings published in reputed platforms such as Elsevier (Link). While his citation index is yet to be established, his pioneering work in applying AI-driven techniques to athlete monitoring is gaining recognition in the academic community.

Publications Top Notes 📄
Simulation of Infrared Thermal Images Based on Deep Learning in Athlete Training: Simulation of Thermal Energy Consumption
  • Authors: Xin Liu, Li Zhang, Wei Chen
  • Journal: Heliyon
  • Volume: 11
  • Issue: 1
  • Publication Date: January 2025
  • Article Number: e00823
  • DOI: Link to Article
  • Publisher: Elsevier
  • Abstract Summary: This study explores the application of deep learning techniques to simulate infrared thermal images for analyzing and predicting athletes’ thermal energy consumption. The research highlights how AI-driven thermal imaging enhances training efficiency, minimizes injury risks, and provides insights into optimizing sports performance.

Conclusion

Dr. Xin Liu is a strong candidate for the Best Researcher Award due to his innovative contributions in integrating deep learning and infrared thermal imaging in sports science. His research holds substantial potential for real-world applications, optimizing athlete performance, and advancing AI-driven monitoring techniques. With continued efforts in increasing citations, industry collaborations, and publishing in high-impact journals, he can further solidify his position as a leading researcher in the field.