Related Experiment Video
Updated: Jul 15, 2026
06:22
Stochastic Noise Application for the Assessment of Medial Vestibular Nucleus Neuron Sensitivity In Vitro
Published on: August 28, 2019
Visual evoked potential estimation by adaptive noise cancellation with neural-network-based fuzzy inference system
1Biomedical Information Institute, Beijing University of Technology, Beijing, PR, 100022, China. yjzeng@bjpu.edu.cn
Journal of Medical Engineering & Technology
|April 25, 2007
Summary
This study introduces a novel adaptive noise cancellation method using a neural network-based fuzzy inference system (NNFIS) to effectively isolate visual evoked potentials (VEPs) from background electroencephalogram (EEG) noise. The NNFIS method demonstrates superior performance in tracking dynamic VEP signals.
Area of Science:
- Neuroscience
- Signal Processing
- Biomedical Engineering
Background:
- Visual evoked potentials (VEPs) are crucial neurophysiological signals.
- VEPs are often obscured by significant background electroencephalogram (EEG) noise.
- Accurate VEP estimation is vital for neurological diagnostics.
Purpose of the Study:
- To develop an adaptive noise cancellation technique for VEP signal extraction.
- To model VEP signals using a neural network-based fuzzy inference system (NNFIS).
- To demonstrate the NNFIS method's ability to track non-stationary VEP characteristics.
Main Methods:
- Implemented an adaptive noise cancellation system utilizing NNFIS.
- Designed NNFIS with membership functions distributed over time.
- Employed the least mean squares (LMS) algorithm to adapt NNFIS weights by minimizing error variance.
- Validated the method with simulated data and 150 trials.
Main Results:
- The proposed NNFIS method effectively models VEP signals.
- The adaptive nature of NNFIS allows tracking of dynamic VEP changes.
- Simulated data confirmed the method's appropriateness for VEP estimation.
- Demonstrated superior performance compared to existing methods through extensive trials.
Conclusions:
- The NNFIS-based adaptive noise cancellation is a robust technique for VEP signal estimation.
- This method accurately extracts VEPs from noisy EEG data.
- The NNFIS approach offers a promising tool for analyzing non-stationary VEP signals in real-world applications.