IMPROVED ECG SIGNAL CLASSIFICATION USING EFFICIENT MACHINE LEARNING METHOD FOR OBSTRUCTIVE SLEEP APNEA DETECTION AT MULTIPLE SCALES

An electrocardiogram (ECG) is a crucial tool for the prognosis of many disorders that affect people. To conduct out automatic ECG diagnostics by categorising patient ECGs into relevant cardiac diseases, we deploy a machine learning for the classification framework in this procedure. This framework was previously trained on a broad signal data set. The main goal of this approach, however, is to forecast anomalous signals using a straightforward, broadly applicable machine learning technique for the categorization of the chosen signals from the dataset. In light of these findings, it can be concluded that the suggested approach is successful in obtaining very high performance rates. The primary goal of this research is to anticipate the ECG signal using an effective classification approach, as well as to increase classification accuracy and decrease miss classes