Skip to main content

Table 3 Model performance measurements estimated on the test set (Folder 2) on 5 min excerpts

From: Ultra-short term HRV features as surrogates of short term HRV: a case study on mental stress detection in real life

Method Parameters AUC SEN SPE ACC
MLP LR = 0.3; ML = 0.2; NE = 500 98% 100% 88% 94%
SVM PolyKernel, E = 1.0 88% 88% 88% 88%
C4.5 CF = 0.25; ML = 2 94% 88% 100% 94%
IBK K = 3 99% 88% 100% 94%
LDA 98% 88% 100% 94%
  1. MLP Multilayer Perceptron, SVM Support Vector Machine, C4.5 decision trees, IBK Neighbor Search, LDA Linear Discriminate Analysis, AUC area under the curve, SEN sensitivity, SPE specificity, ACC accuracy