Comparison Analysis of Different Time-Scale Heart Rate Variability Signals for Mental Workload Assessment in Human-Robot Interaction

Algorithm 2

Mental workload assessment after preprocessing.

Input:Multiple time-scale HRV segments for all subjects.

Output:Per-subject and cross-subject probability of mental workload.

1: For each time scale , .

2:  For each such that do

3:   Extract linear and nonlinear features for each signal at task-performing state.

4:   Extract linear and nonlinear features for each signal at relaxation state.

5:  End for

6:    If per-subject mental workload assessment

7:    For each such that do

8:     Train classifiers (SVM, KNN, LDA, GB, NB, and DT) based on the training set randomly selected from

   .

9:     Obtain the probability of mental workload based on the testing set , which is defined as .

10:   End for

11:  End if

12:  If cross-subject mental workload assessment

13:   Merge matrices , ,…, into one matrix .

14:   Merge matrices , ,…, into one matrix .

15:    Train machine learning method (SVM, KNN, LDA, GB, NB, and DT) based on the training set and

     randomly selected from and , respectively.

16:    Obtain probability of mental workload based on the testing set and , which are defined as and

    , respectively.

17:  End if

18: End for