Skip to main content

Table 2 Classification performance of the algorithm versus the ground truth events for Driving Data 1 and Driving Data 2 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

 

Data 1

Data 2

Data 1

Data 2

Data 1

Data 2

Sensitivity/Recall

.957

.876

.959

.914

.952

.904

Specificity

.981

.964

.974

.958

.989

.934

Precision

.704

.620

.706

.660

.701

.400

Hit Rate

97.16% (137/141)

94.36% (184/195)

100% (96/96)

95.38% (124/130)

91.11% (41/45)

93.85% (61/65)

Spindle Temporal Error

~52 ms

~114 ms

~50 ms

~77 ms

~40 ms

~96 ms

Agreement

165.422 s

157.008 s

114.539 s

106.688 s

50.833 s

59.047 s

Null Agreement

3635.516 s

2584.453 s

1167.875 s

1257.414 s

1866.859 s

1275.273 s

False Negative

7.438 s

22.195 s

4.875 s

9.984 s

2.563 s

6.273 s

False Positive

69.625 s

96.344 s

47.720 s

54.922 s

21.703 s

89.414 s

  1. A fuzzy window parameter of 0.1 s was used.