Sara Tehsin | Deep learning | Best Researcher Award

Ms. Sara Tehsin | Deep learning | Best Researcher Award

PhD Student, National University of Sciences and Technology, Islamabad, Pakistan

Sara Tehsin is a motivated and results-driven professional with over ten years of experience in Image Processing and Machine Learning. As an Engineering Lecturer at HITEC University in Taxila, Pakistan, she excels in delivering high-quality educational experiences and has a proven track record of producing outstanding results through her strong work ethic, adaptability, and effective communication skills. She is passionate about academic development and seeks opportunities to contribute her expertise while furthering her professional growth. 📚💻

Publication Profile

Google Scholar

Education

Sara Tehsin is currently pursuing a PhD in Computer Engineering at the National University of Sciences and Technology (NUST), Islamabad, where she has achieved a remarkable GPA of 3.83/4.00. Her research focuses on Digital Forensics, Deep Learning, and Digital Image Processing. She holds a Master’s degree in Computer Engineering from NUST, where she graduated with a GPA of 3.7/4.0, and a Bachelor’s degree from The Islamia University of Bahawalpur, with a GPA of 3.36/4.00. 🎓🌟

Experience

Sara has extensive teaching experience, currently serving as an Engineering Lecturer at HITEC University since September 2019, where she develops engaging curriculum and delivers lectures aligned with international standards. Previously, she was a Computer Science Lecturer at Sharif College of Engineering and Technology, and she also served as a Teaching Assistant at NUST and a Lab Engineer at Foundation University. Her roles have encompassed curriculum development, practical instruction, and student support in various computer science subjects. 👩‍🏫🔧

Research Interests

Sara’s research interests encompass Digital Forensics, Deep Learning, Digital Image Processing, and Machine Learning. She focuses on developing innovative solutions for image recognition and forgery detection, contributing significantly to the fields of computer vision and machine learning. Her work aims to enhance the accuracy and efficiency of image processing systems. 🧠🔍

Publications

Self-organizing hierarchical particle swarm optimization of correlation filters for object recognition
S. Tehsin, S. Rehman, M.O.B. Saeed, F. Riaz, A. Hassan, M. Abbas, R. Young, …
IEEE Access, 5, 24495-24502 (2017)
Cited by: 21

Improved maximum average correlation height filter with adaptive log base selection for object recognition
S. Tehsin, S. Rehman, A.B. Awan, Q. Chaudry, M. Abbas, R. Young, A. Asif
Optical Pattern Recognition XXVII, 9845, 29-41 (2016)
Cited by: 18

Fully invariant wavelet enhanced minimum average correlation energy filter for object recognition in cluttered and occluded environments
S. Tehsin, S. Rehman, F. Riaz, O. Saeed, A. Hassan, M. Khan, M.S. Alam
Pattern Recognition and Tracking XXVIII, 10203, 28-39 (2017)
Cited by: 12

Comparative analysis of zero aliasing logarithmic mapped optimal trade-off correlation filter
S. Tehsin, S. Rehman, A. Bilal, Q. Chaudry, O. Saeed, M. Abbas, R. Young
Pattern Recognition and Tracking XXVIII, 10203, 22-37 (2017)
Cited by: N/A

slimane arbaoui | Artificial Intelligence | Young Scientist Award

Mr. slimane arbaoui | Artificial intellegence | Young Scientist Award

Cube-SDC team, INSA Strasbourg, University of Strasbourg , 24 Bd de la Victoire, Strasbourg, 67000, France, insa strasbourg, France

Slimane Arbaoui is a dedicated final-year Computer Science student at École Supérieure en Informatique (ESI) in Sidi Bel Abbess, Algeria, specializing in Android application development and machine learning. 🎓 His skills span Java-based Android development, data integration, and advanced problem-solving in software, alongside a versatile understanding of multiple programming languages, including Python and Kotlin. Slimane has applied his AI knowledge to impactful projects, even authoring a research paper. 📚 Known for his innovation and strong analytical skills, Slimane is passionate about tackling real-world challenges with technology.

Publication Profile

Scopus

Education

Slimane completed his State Engineering and Master’s degrees in Computer Science at ESI SBA in 2023. 🎓 His academic journey has strengthened his technical expertise and provided a foundation in both theoretical and applied computing, with a focus on machine learning, mobile app development, and web technologies.

Experience

During his internship at INSA-Strasbourg, France 🇫🇷, Slimane applied machine learning to improve battery health prediction, developing models that track and identify factors contributing to battery degradation. At CNAS in Algeria, he gained practical insights into network database applications and web app development. 💻 As a freelancer on Upwork, Slimane developed Android applications and managed web back-end services, demonstrating his versatility in real-world projects.

Research Focus

Slimane’s research interests center on artificial intelligence and machine learning, with a special focus on NLP applications, sentiment analysis, and health data prediction. 🧠 His projects include sentiment analysis and fake news detection in Arabic language datasets, alongside health management applications that leverage data-driven insights to enhance service quality. His work in battery health prediction highlights his proficiency in machine learning model development and evaluation.

Awards and Honours

Slimane holds several certifications, including Microsoft Certified: Azure Fundamentals and the Android Basics Nanodegree. 🏅 His achievements in AI include completing courses on deep learning and machine learning through Kaggle and Coursera, which demonstrate his commitment to continuous learning and professional development.

Publication Top Notes

Dual-model approach for one-shot lithium-ion battery state of health sequence prediction

SOCXAI: Leveraging CNN and SHAP Analysis for Battery SOC Estimation and Anomaly Detection

Data-driven strategy for state of health prediction and anomaly detection in lithium-ion batteries