. Author manuscript; available in PMC: 2020 Aug 21.

Published in final edited form as: ACM Trans Comput Healthc. 2020 Apr;1(2):8. doi: 10.1145/3361562

Table 18.

LOSO Cross-Validation Results from the Different Datasets for HR-GSR Using SVM and RF, and Considering Only the Last 4 Minutes of the Rest Baseline as Not Stressed

Prediction Metrics	trim_zscore		trim_minmax		wins_zscore		wins_minmax
Prediction Metrics	SVM	RF	SVM	RF	SVM	RF	SVM	RF
Precision	0.86	0.92	0.83	0.86	0.85	0.87	0.79	0.77
Recall	0.89	0.91	0.86	0.84	0.82	0.88	0.82	0.79
F1-score	0.87	0.91	0.84	0.85	0.83	0.87	0.80	0.78