Obstructive sleep apnea | |
Electrocardiogram | |
ECG-Derived Respiration | |
Apnea-Hypopnea Index | |
Hidden Markov model | |
Random under-sampling Boost | |
Adaptive boost | |
Discrete wavelet transform | |
Tunable Q-factor wavelet transform | |
Linear/Quadratic Discriminant Analysis | |
Sequential forward feature selection | |
Spectral regression discriminant analysis | |
Deep/Convolutional neural network | |
Decision tree classifier | |
Radial basis function | |
Support vector machine | |
Recursive least squares | |
Gram-Schmidt | |
Short-time load forecasting | |
Dual-tree complex wavelet transform |
ACC% | Sens% | Spec% | |||
---|---|---|---|---|---|
DWT+SFFS | SVM (RBF kernel) | 92.98 | 91.74 | 93.75 | |
HMM | HMM+SVM | 86.2 | 82.6 | 88.4 | |
TQWT | RUSBoost | 88.88 | 87.58 | 91.49 | |
Cepstrum+ Filter bank | QDA | 84.76 | 81.45 | 86.82 | |
Statistical and spectral | Bootstrap aggregating | 85.97 | 84.14 | 86.83 | |
Normal invers Gaussian modeling | AdaBoost | 87.33 | 81.99 | 90.72 | |
QRS features | LS-SVM (RBF kernel) | 83.8 | 79.5 | 88.4 | |
Frequency features | Statistical analysis | 93 | 100 | 81 | |
Time domain feaures+PSD | SVM-KNN-NN-LD-QD | 90.9 | 89.6 | 91.8 | |
Statistical features | Statistical analysis | 87 | 89 | 79 | |
Tunable-Q wavelet transform features | Random Forest | 92.78 | 93.91 | 90.95 | |
RR-intervals | CNN (LeNet-5) | 92.3 | 90.9 | 100 | |
Time-frequency Scalogram features | CNN (AlexNet) | 86.22 | 90 | 100 | |
RR-intervals | CNN | 96 | 96 | 96 | |
RR-intervals | CNN | 97.8 | 100 | 93 | |
Fuzzy-entropy (FUEN) and the Log of signal-energy (LOEN) | KNN-DT-SVM | 90.87 | 92.43 | 88.33 | |
DWT+PCA | Random forest | 92–98 | - | - | |
DWT+PCA | SVM | 94.3 | 92.65 | 92.2 | |
DT-CWT+SRDA | Hybrid “k-means, RLS” RBF |
FE | Fuzzy Entropy |
ApEn | Approximate Entropy |
IQR | Interquartile Range |
RP | Recurrence Plot |
SD1, SD2, SD1/SD2 | Poincare Plot |