Victoria Peterson

This study analyzes sex-related biases in deep learning models for motor imagery BCIs, finding that performance disparities are mainly due to EEG pattern discriminability, not the models themselves.

The paper develops a supervised spatial filter to remove speech artifacts from intracranial EEG recordings while preserving neural activity.

The paper presents an open-access EEG dataset for inner speech recognition to advance research on brain-computer interfaces.

The paper identifies speech-induced artifacts in intracranial recordings and shows they correlate with speech audio and vibration patterns.

This paper develops a movement decoding pipeline using spatio-spectral features from cortical and subcortical signals, showing improved decoding with spatial information.

This paper compares electrocorticography (ECoG) and subthalamic local field potentials (LFP) for movement decoding in Parkinson's disease, finding ECoG superior and demonstrating the impact of PD pathophysiology on decoding performance.