Papers
10
Total Citations
72
H-Index
6
About
Rania Bouzid is an emerging robotics and artificial intelligence researcher whose work focuses on applying machine learning techniques — particularly Artificial Neural Networks — to solve fundamental challenges in robotic kinematics. Her research addresses both forward and inverse kinematics problems for robotic manipulators, including 2-DoF systems and the widely used SCARA robot, systems central to modern industrial automation. Bouzid's major contributions lie in systematically exploring how ANN architectures, hyperparameter configurations, training optimizers, and dataset diversity affect the accuracy of kinematic solutions. Rather than relying on traditional analytical methods, which can be computationally demanding and struggle with nonlinearity, her work demonstrates that neural networks offer flexible, high-performing alternatives. Her more recent investigations push further still, developing innovative hybrid approaches that combine ANNs with metaheuristic algorithms such as Particle Swarm Optimization, yielding enhanced precision in complex environments. With a publication record concentrated in 2023–2024, Bouzid has already accumulated over 70 citations across her ten most-cited works, with her top paper garnering 17 citations — a notable achievement for such recent output. Her comparative studies serve as valuable benchmarks for researchers designing learning-based control systems. Students and engineers working at the intersection of robotics, automation, and deep learning will find her work an accessible and rigorous entry point into data-driven kinematic modeling.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10