Fig 1.
The block diagram of proposed method, showing the key processing stages used in this study.
Fig 2.
ECG signal examples in 60-second segments: (a) normal; (b) apnea class A.
Fig 3.
The employed wavelet decomposition scheme.
Fig 4.
The selected sub-bands coefficients respectively for ECG normal (left-column) and ECG apnea (right-column).
Fig 5.
The first five IMFs of d2s from Fig 3.
For the ECG normal (left-column) and for ECG apnea (right-column).
Table 1.
Performance of the apnea classification scheme using various evaluation measures for the class A verses class B problem.
Table 2.
Performance of the apnea classification scheme using various evaluation measures for the class A versus class C problem.
Table 3.
Performance of the apnea classification scheme using various evaluation measures for the class B versus class C problem.
Table 4.
Performance of the apnea classification scheme using various evaluation measures for the class apnea verses class normal problem.
Table 5.
Comparison with state of the art counter parts.