An inference correction method leveraging the majority of classifier outputs improved classification accuracy by 14.97% in EEG-based affective brain-computer interfaces.
An inference correction method addressing the quantity-independence imbalance in short-term EEG frames significantly improves classification accuracy in affective brain-computer interfaces.
Effect estimate: 14.97% improvement
Abstract In recent years, electroencephalogram (EEG)-based affective brain–computer interfaces (aBCI) has made remarkable advances. Objective . However, a subtle but crucial problem caused by the sliding window method has long been overlooked, which is the serious quantity mismatch between stimuli and short-term EEG frames. This may be an important factor limiting the performance of aBCIs. Approach . We refer to this mismatch as the quantity-independence imbalance (Q/I imbalance) and we propose the weak independence hypothesis to explain the mismatch. To validate this hypothesis and explore the effects of the Q/I imbalance on short-term EEG frames, we design four experiments from four perspectives, which are visualization, cross-validation, randomness test, and redundancy test. Main results . Inspired by validation experiments, we propose an inference correction (IC) method to enhancing the emotional predictions by leveraging the majority of the classifier’s outputs. The proposed IC method is evaluated on two datasets involving 60 subjects using both intra-subject and inter-subject validation protocols. Our IC achieves a significant improvement of 14.97% in classification accuracy. Significance . This study promotes the understanding of the time-dependent nature of EEG signals in aBCI.
Pei et al. (Wed,) conducted a other in Affective brain-computer interfaces (n=60). Inference correction (IC) method vs. Standard sliding window method was evaluated on Classification accuracy (14.97% improvement). An inference correction method leveraging the majority of classifier outputs improved classification accuracy by 14.97% in EEG-based affective brain-computer interfaces.