ECG-based emotion recognition using random convolutional kernel method

Ancheng Fang

doi:10.1016/j.bspc.2023.105907

2024-05-01

PRE

DOI：10.1016/j.bspc.2023.105907

原文链接

原文求助

摘要

En 中文

The recognition of human emotions based on physiological signals has garnered significant attention from various fields such as human-computer interaction, cognitive-behavioral science, and the treatment of emotionrelated diseases. Using the easily accessible ECG signal for emotion recognition presents a viable approach. However, method relying on hand-crafted features necessitate task-specific domain knowledge and consume substantial time to design suitable features, and studies employing deep learning technologies incur greater computational complexity and extended training durations. To address these problems, we proposed an emotion recognition method that employs random convolutional kernels on ECG signals. Following ECG signal preprocessing, a large number of random convolutional kernels were used to transform the signals, and the resulting features are utilized to classify the various emotion states. In addition to accurately and automatically extracting the multi-scale features from ECG signals, combining the random convolutional kernels with ECG signal alone also reduces the computational complexity and training time compared to methods using multiple physiological signals or deep neural networks. Validation on three publicly available datasets revealed that the proposed method achieved recognition accuracies of 91.5%, 96% and 92.5% for valence, arousal and dominance in AMIGOS dataset, and 95.1%, 98.8% and 90.2% for same labels in DREAMER dataset. The accuracy for valence, arousal and affective states in WESAD dataset are 94.5%, 91.8% and 91.8%. The results show that the proposed method outperforms previous researches in multi-class emotion recognition, thus offering a new and promising approach for swift and precise emotion recognition.

Keyword:

Emotion recognition

Electrocardiogram (ECG)

Signal processing

Random Convolutional Kernel Transforms

(ROCKET)