Asmarani Ahmad Puzi
Papers
5
Total Citations
85
H-Index
3
About
Dr. Asmarani Ahmad Puzi is a leading researcher in the field of rehabilitation robotics and human-robot interaction, with a primary focus on decoding human motor intention to enhance assistive technologies. Her work centers on using electromyography (EMG) signals to predict movement intention, a critical component for developing intelligent, responsive robotic training platforms. Dr. Puzi’s most impactful contribution, her 2021 paper on classifying movement intention via machine learning models, has garnered 57 citations and identifies key time-domain EMG features for accurate prediction. She has also advanced the field by applying k-NN classifiers to motion intention detection and by modeling human arm mechanical impedance to better understand upper limb dynamics. Notably, Dr. Puzi pioneered the integration of the Modified Ashworth Scale (MAS) with adaptive impedance control frameworks, creating a system that dynamically adjusts robotic assistance based on a patient’s spasticity level. Her development of a clasp-knife model for muscle spasticity further enables realistic simulation of robot-human interaction. Through these contributions, Dr. Puzi is helping to move rehabilitation robotics beyond monotonous, one-size-fits-all therapy toward personalized, intention-driven training that adapts to each patient’s unique needs.
Research Focus
Key Achievements
Top Papers
- 1
- 2Classifying Motion Intention from EMG signal: A k-NN Approach14 citations · 2019
- 3Mechanical Impedance Modeling of Human Arm:<i>A survey</i>9 citations · 2017
- 4
- 5