IMPROVED ECG SIGNAL CLASSIFICATION USING EFFICIENT MACHINE LEARNING METHOD FOR OBSTRUCTIVE SLEEP APNEA DETECTION AT MULTIPLE SCALES
Journal: International Journal of Mechanical Engineering and Technology(IJMET) (Vol.9, No. 1)Publication Date: 2018-01-28
Authors : Aditya Harbola;
Page : 1224-1233
Keywords : Electrocardiogram (ECG); Automatic ECG diagnostics; Classification; Cardiac Diseases; Machine Learning; Prognosis; Signal Data Set; Anomalous Signals; Forecasting;
Abstract
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
Other Latest Articles
- EXPLORING ENGINEERING STUDENT SUCCESS: A CLUSTER ANALYSIS OF ACADEMIC PERFORMANCE AND DEMOGRAPHIC FACTORS
- ENHANCING SPECTRAL EFFICIENCY AND ERROR RATE PERFORMANCE OF LAYERED ACO-OFDM WITH SINGLE-FFT RECEIVER AND PAIRWISE MAXIMUM LIKELIHOOD TECHNIQUE
- ENHANCED FINGER VEIN VERIFICATION WITH DEEP REPRESENTATION-BASED FEATURE EXTRACTION AND RECOVERY USING LOCAL LINE BINARY PATTERN DESCRIPTOR
- SELECTION OF POSSIBLE SCENARIOS FOR IMPROVING THE QUALITY OF PUBLIC TRANSPORT SERVICES THROUGH THE USE OF HYBRID FUZZY-MCDM MODELS
- DESIGN AND CONTROL OF A MECHATRONIC ROBOTIC ARM FOR INDUSTRIAL APPLICATIONS
Last modified: 2023-06-09 15:44:59