Jinhua Deng
Papers
2
Total Citations
18
H-Index
2
About
Jinhua Deng is a leading researcher in computational intelligence and robotics, specializing in advanced neural network architectures for real-time optimization and control. Their work focuses on solving critical challenges in redundant-robot manipulation and time-varying quadratic programming, with an emphasis on finite-time convergence and adaptive feedback mechanisms. Deng’s most-cited paper, “A Novel Variable-Parameter Variable-Activation-Function Finite-Time Neural Network for Solving Joint-Angle Drift Issues of Redundant-Robot Manipulators” (2024, 10 citations), introduces the VPA-FTNN, a groundbreaking model that eliminates joint-angle drift by leveraging error-based finite-time convergence—a significant improvement over traditional recurrent neural networks. Another key contribution, “A Novel Error-Based Adaptive Feedback Zeroing Neural Network for Solving Time-Varying Quadratic Programming Problems” (2024, 8 citations), presents the EAF-ZNN, which dynamically adjusts parameters to accelerate problem-solving without excessive computational overhead. These innovations have direct applications in robotics, automation, and real-time control systems. Deng’s work is notable for its practical impact, offering robust, efficient solutions to complex dynamic problems, and has quickly garnered attention in the field. Their research continues to push boundaries in neural network design and robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2