Skip to main content

Advertisement

Table 2 The average performances of kNN, QDA, and SVM classification methods in sleep stage classification on healthy subjects

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

Classification Sleep Stages Total
Method Wake NREM1 NREM2 NREM3 NREM4 REM Accuracy
kNN 322/350 105/109 2159/3773 352/390 775/943 655/836 4414/6407
  = 92% = 97% = 58.2% = 90.3% = 82.2% = 78.4% = 68.9%
  CKI = 0.95 CKI = 0.98 CKI = 0.55 CKI = 0.95 CKI = 0.90 CKI = 0.91  
QDA 332/350 106/109 2253/3773 366/390 821/943 695/836 4581/6407
  = 94.9% = 97.9% = 59.7% = 93.8% = 87.1% = 83.2% = 71.5%
  CKI = 0.97 CKI = 0.98 CKI = 0.56 CKI = 0.96 CKI = 0.94 CKI = 0.95  
SVM 334/350 107/109 2328/3773 368/390 824/943 709/836 4684/6407
  = 95.6% = 98.5% = 61.8% = 94.3% = 87.4% = 84.9% = 73.1%
  CKI = 0.98 CKI = 0.99 CKI = 0.59 CKI = 0.98 CKI = 0.95 CKI = 0.95  
  1. The value in each cell shows the number of epochs with accurate estimations divided by the total number of epochs of that specific stage and the corresponding percentage. Cohen's Kappa Index (CKI) is given for each stage and classification method. The last column indicates the total classification accuracy obtained throughout the night for each method.