Skip to main content

Table 4 The average performances of kNN, QDA, and SVM classification methods in apnea detection.

From: Sleep stage and obstructive apneaic epoch classification using single-lead ECG

Classification Method

Mean

Worst

Best

kNN

718/904 = 79.5%

615/904 = 68%

808/904 = 89.4%

 

CKI = 0.94

CKI = 0.91

CKI = 0.95

QDA

788/904 = 87.2%

687/904 = 76%

854/904 = 94.5%

 

CKI = 0.97

CKI = 0.95

CKI = 0.98

SVM

789/904 = 87.3%

683/904 = 75.6%

854/904 = 94.5%

 

CKI = 0.98

CKI = 0.95

CKI = 0.98

  1. The values on the "Mean" column are the average percentages of accurate estimations. The "Worst" and "Best" classification accuracies across OSA subjects are also included.