Evaluation of electrocardiogram: numerical vs. image data for emotion recognition system [version 2; peer review: 2 approved, 1 approved with reservations]

• Published in: F1000 research 2022, Vol.10, p.1114-1114
• Main Authors: Sayed Ismail, Sharifah Noor Masidayu, Ab. Aziz, Nor Azlina, Ibrahim, Siti Zainab, Nawawi, Sophan Wahyudi, Alelyani, Salem, Mohana, Mohamed, Chia Chun, Lee
• Format: Article
• Language: English
• Subjects: Accuracy; Arousal; Cardiac arrhythmia; Cardiovascular diseases; Classification; Datasets; Discriminant analysis; Disease; EKG; Electrocardiography; Emotions; Heart rate; Medical equipment; Physiology; Support vector machines
• ISSN: 2046-1402; 2046-1402
• DOI: 10.12688/f1000research.73255.2

Background: The electrocardiogram (ECG) is a physiological signal used to diagnose and monitor cardiovascular disease, usually using 2- D ECG. Numerous studies have proven that ECG can be used to detect human emotions using 1-D ECG; however, ECG is typically captured as 2-D images rather than as 1-D data. There is still no consensus on the effect of the ECG input format on the accuracy of the emotion recognition system (ERS). The ERS using 2-D ECG is still inadequately studied. Therefore, this study compared ERS performance using 1-D and 2-D ECG data to investigate the effect of the ECG input format on the ERS. Methods: This study employed the DREAMER dataset, which contains 23 ECG recordings obtained during audio-visual emotional elicitation. Numerical data was converted to ECG images for the comparison. Numerous approaches were used to obtain ECG features. The Augsburg BioSignal Toolbox (AUBT) and the Toolbox for Emotional feature extraction from Physiological signals (TEAP) extracted features from numerical data. Meanwhile, features were extracted from image data using Oriented FAST and rotated BRIEF (ORB), Scale Invariant Feature Transform (SIFT), KAZE, Accelerated-KAZE (AKAZE), Binary Robust Invariant Scalable Keypoints (BRISK), and Histogram of Oriented Gradients (HOG). Dimension reduction was accomplished using linear discriminant analysis (LDA), and valence and arousal were classified using the Support Vector Machine (SVM). Results: The experimental results show 1-D ECG-based ERS achieved 65.06% of accuracy and 75.63% of F1 score for valence, and 57.83% of accuracy and 44.44% of F1-score for arousal. For 2-D ECG-based ERS, the highest accuracy and F1-score for valence were 62.35% and 49.57%; whereas, the arousal was 59.64% and 59.71%. Conclusions: The results indicate that both inputs work comparably well in classifying emotions, which demonstrates the potential of 1-D and 2-D as input modalities for the ERS.