Proposed ECG features achieved higher average accuracies for emotion recognition in valence (55.8% vs 42.6%) and arousal (59.7% vs 47.7%) compared to standard heart rate variability analysis.
The proposed ECG features based on bivariate empirical mode decomposition and spectrogram analysis improve emotion recognition accuracy compared to standard HRV features.
Absolute Event Rate: 55.8% vs 42.6%
We propose new features for emotion recognition from short ECG signals. The features represent the statistical distribution of dominant frequencies, calculated using spectrogram analysis of intrinsic mode function after applying the bivariate empirical mode decomposition to ECG. KNN was used to classify emotions in valence and arousal for a 3-class problem (low-medium-high). Using ECG from the Mahnob-HCI database, the average accuracies for valence and arousal were 55.8% and 59.7% respectively with 10-fold cross validation. The accuracies using features from standard Heart Rate Variability analysis were 42.6% and 47.7% for valence and arousal respectively for the 3-class problem. These features were also tested using subject-independent validation, achieving an accuracy of 59.2% for valence and 58.7% for arousal. The proposed features also showed better performance compared to features based on statistical distribution of instantaneous frequency, calculated using Hilbert transform of intrinsic mode function after applying standard empirical mode decomposition and bivariate empirical mode decomposition to ECG. We conclude that the proposed features offer a promising approach to emotion recognition based on short ECG signals. The proposed features could be potentially used also in applications in which it is important to detect quickly any changes in emotional state.
Ferdinando et al. (Sat,) conducted a other in Emotion recognition. Proposed features (statistical distribution of dominant frequencies from ECG) vs. Standard Heart Rate Variability (HRV) analysis features was evaluated on Accuracy for valence and arousal (3-class problem). Proposed ECG features achieved higher average accuracies for emotion recognition in valence (55.8% vs 42.6%) and arousal (59.7% vs 47.7%) compared to standard heart rate variability analysis.