Related Experiment Video
Updated: Jun 1, 2025
13:44
Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy
Published on: August 8, 2011
13.8K
Real-time isolation of physiological tremor using recursive singular spectrum analysis and random vector functional
Asad Rasheed1, Jeonghong Kim2, Wei Tech Ang3
1School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea.
ISA Transactions
|January 18, 2025
Summary
This study introduces RSSA-RVFL, a new method for tremor filtering in robotic microsurgery. It improves accuracy and reduces delays compared to existing techniques, enhancing surgical precision.
Area of Science:
- Robotics
- Biomedical Engineering
- Signal Processing
Background:
- Hand-held robotic instruments are crucial for microsurgery precision.
- Current tremor filtering methods cause phase distortion, reducing accuracy.
- Existing advanced methods like RSSA have limitations in generalization, delay, and computation.
Purpose of the Study:
- To develop an accurate and fast tremor filtering algorithm for robotic microsurgery.
- To overcome the limitations of phase distortion, generalization, delay, and computational cost in existing methods.
Main Methods:
- Integration of Recursive Singular Spectrum Analysis (RSSA) with Random Vector Functional Link (RVFL) networks, termed RSSA-RVFL.
- Utilizing RSSA for tremor estimation and RVFL for prediction.
- Development of two moving window variants of RSSA-RVFL for real-time implementation and reduced computational load.
Main Results:
- The proposed RSSA-RVFL approach achieved an average accuracy of 79.03% on real tremor data.
- This surpasses the benchmark accuracy of 70.40%.
- The method demonstrated a reduced delay of nine samples.
Conclusions:
- The RSSA-RVFL method effectively filters physiological tremor in robotic microsurgery.
- It offers improved accuracy and reduced delay compared to existing techniques.
- Real-time variants significantly decrease computational costs without performance compromise.
