HWI encoding/decoding of a non-invasive HWI-BCI paradigm based on temporal variation abundance scale

The performance of non-invasive Handwriting Imagery (HWI) input in Brain-computer interface (BCI) systems is highly dependent on the paradigms employed, yet there is limited research on interpretable scales to measure how HWI-BCI paradigms and neural encoding designs affect performance. This study introduces the "Temporal Variation Abundance" metric and utilizes it to design two classes of handwriting imagery paradigms: Low Temporal Variation Abundance (LTVA) and High Temporal Variation Abundance (HTVA). A dynamic time warping algorithm based on random templates (rt-DTW) is proposed to align HWI velocity fluctuations using EEG. Comprehensive comparisons of these experimental paradigms are conducted in terms of feature space distance, offline and online classification accuracy, and cognitive load assessment using functional near-infrared spectroscopy. Results indicate that HTVA-HWI exhibits lower velocity stability but demonstrates higher spatial distance, offline classification accuracy, online testing classification accuracy, and lower cognitive load. This study provides deep insights into paradigm design for non-invasive HWI-BCI and scales of neural encoding, offering new theoretical support and methodological insights for future advancements in brain-computer interaction.