Skip to main content

Table 1 Classification performance of the algorithm versus the ground truth events for Driving Data 1 for three data conditions: the full data without partitioning, the training data and the testing data, respectively

From: Detecting alpha spindle events in EEG time series using adaptive autoregressive models

 

Full data

Training data

Testing data

Sensitivity/Recall

.915

.895

.863

Specificity

.966

.966

.984

Precision

.536

.612

.581

Hit Rate

97.87% (138/141)

100% (96/96)

93.33% (42/45)

Spindle Temporal Error

~96 ms

~120 ms

~150 ms

Agreement

146.430 s

98.617 s

43.055 s

Null Agreement

3591.156 s

1762.414 s

1861.141 s

False Negative

13.586 s

11.531 s

6.813 s

False Positive

126.828 s

62.445 s

31.000 s

  1. A fuzzy window parameter of 0 s was used.