BCI-sift: An automated feature selection toolbox for Brain Computer Interface applications
Researchers have developed BCI-sift, a new Python toolbox designed to automate feature selection for Brain-Computer Interface (BCI) applications. This tool integrates various optimization algorithms to identify the most relevant neural features from high-dimensional and noisy BCI data. Validation on electrocorticography data from participants speaking words showed that BCI-sift improved classification accuracy and provided interpretable results aligned with known sensorimotor cortex organization. AI
IMPACT Streamlines BCI research by automating feature selection, potentially leading to more accurate and interpretable neural decoding.