Toward the enhancement of affective brain-computer interfaces using dependence within EEG series.

In recent years, electroencephalogram (EEG)-based emotion recognition technology has made remarkable advances. 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 the emotion recognition systems. We name this mismatch as quantity-independence imbalance (Q/I imbalance) and propose the weak independence hypothesis to explain it. 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. Furthermore, inspired by the redundancy of the short-term EEG samples, we propose an inference correction (IC), which uses the majority of the classifier's outputs to correct the prediction. The proposed IC is tested in the two datasets, including 60 subjects, using the intra- and inter-subject validations. Our IC achieves a significant improvement of 14.97% in classification accuracy. This study promotes the understanding of the time-dependent nature of EEG signals.