Key result
Support Vector Machine (SVM) achieved a higher emotion classification accuracy of 98% and lower Hamming loss compared to Naive Bayes (96% accuracy) using real-time ECG data.
Why the study?
Emotion recognition is in high demand, but real-time hardware faces challenges with noise and hardware factors compared to simulations.
Comparison
Naive Bayes vs traditional KNN, SVM, and Random Forest methods
Authors
Loading...
May support ECG-based emotion monitoring in research; leaves open clinical validation before cardiovascular adoption.
Absolute Event Rate: 98% vs 96%
An AD8232 ECG sensor combined with machine learning algorithms, particularly SVM, can effectively classify human emotions in real-time with high accuracy.
Patil et al. (2023) studied Healthy volunteers (Emotion recognition) (n=10). Support Vector Machine (SVM) vs. Naive Bayes was evaluated on Emotion classification accuracy. Support Vector Machine (SVM) achieved a higher emotion classification accuracy of 98% and lower Hamming loss compared to Naive Bayes (96% accuracy) using real-time ECG data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: