Predicting motor learning
stages using EEG
Context: Dancing, typing, and playing piano involve motor skill learning, which allows executing a sequence of actions based on a defined spatial or temporal sequence. A gradual change in mental representations and behavior is observed due to practice in such sequential learning tasks. This learning, mostly implicit in nature, makes processing quick and reliable like those of automatised skills.
​
Objective: To investigate event-related potential (ERPs) changes, particularly the error-related negativity (ERN) and P200 components, as participants learned a motor sequence using a serial reaction time task.
​
Method: EEG was recorded using 128 scalp electrodes as participants learned a motor sequence. Then, machine learning was to understand the significance of different scalps electrodes and their combinations.
Results: Our study demonstrates that ERN and P200 signals can serve as temporal neural markers for motor skill learning.
​
Presented at: 2nd international workshop on Machine Learning for EEG Signal Processing, IEEE International Conference on Bioinformatics and Biomedicine, Houston, USA.