The X-GWO-SVM algorithm for ECG-based emotion recognition achieved a mean accuracy of 93.37% on the iRealcare dataset and 95.93% on the WESAD dataset, outperforming standard SVM (82.78%).
Does the X-GWO-SVM algorithm improve the accuracy of ECG-based emotion recognition compared to existing machine learning methods?
The proposed X-GWO-SVM algorithm achieves high accuracy for ECG-based emotion recognition and can be efficiently implemented in lightweight embedded systems.
Absolute Event Rate: 95.93% vs 82.78%
Emotion recognition or detection is broadly utilized in patient–doctor interactions for diseases, such as schizophrenia and autism and the most typical techniques are speech detection and facial recognition. However, features extracted from these behavior-based emotion recognitions are not reliable since humans can disguise their emotions. Recording voices or tracking facial expressions for a long term is also not efficient. Therefore, our aim is to find a reliable and efficient emotion recognition scheme, which can be used for nonbehavior-based emotion recognition in real time. This can be solved by implementing a single-channel electrocardiogram (ECG)-based emotion recognition scheme in a lightweight embedded system. However, existing schemes have relatively low accuracy. For instance, the accuracy is about 82.78% by using a least squares support vector machine (SVM). Therefore, we propose a reliable and efficient emotion recognition scheme—exploitative and explorative gray wolf optimizer-based SVM (X-GWO-SVM) for ECG-based emotion recognition. Two data sets, one raw self-collected iRealcare data set, and the widely used benchmark WESAD data set are used in the X-GWO-SVM algorithm for emotion recognition. Leave-single-subject-out cross-validation yields a mean accuracy of 93.37% for the iRealcare data set and a mean accuracy of 95.93% for the WESAD data set. This work demonstrates that the X-GWO-SVM algorithm can be used for emotion recognition and the algorithm exhibits superior performance in reliability compared to the use of other supervised machine learning methods in earlier works. It can be implemented in a lightweight embedded system, which is much more efficient than existing solutions based on deep neural networks.
Yan et al. (Mon,) conducted a other in Emotion recognition. Exploitative and explorative gray wolf optimizer-based SVM (X-GWO-SVM) algorithm vs. Least squares support vector machine (SVM) and other supervised machine learning methods was evaluated on Mean accuracy of emotion recognition. The X-GWO-SVM algorithm for ECG-based emotion recognition achieved a mean accuracy of 93.37% on the iRealcare dataset and 95.93% on the WESAD dataset, outperforming standard SVM (82.78%).