Accurate sleep stage identification through machine learning

  • This study compared different biosignals, biosignal length, and window length to evaluate the performance of machine learning algorithms in sleep stage classification.
  • The combination of electroencephalogram, electromyogram, and electrocardiogram with a 40 s window and 120 s signal length resulted in the best classification performance (precision: 0.853, recall: 0.855, F1-score: 0.853, and accuracy: 0.853).
  • Authors concluded that electroencephalogram signals showed a relatively higher importance for classification.