Researchers at Walailak University in Thailand tested EEG-based emotion recognition under auditory stimulation, scoring valence and arousal. Discrete wavelet transform features reached 0.88 accuracy when classifiers were trained and tested on the same subject, but leave-one-subject-out evaluation fell to near chance, exposing how far EEG emotion signatures differ between people. Few-shot adaptation closed part of that gap: with 75% of a new subject's calibration data, functional connectivity features reached 0.77.
