ECG 2D

<p>The original version of this dataset was formatted by R. Olszewski as part of his thesis <em>Generalized feature extraction for structural pattern recognition in time-series data</em> at Carnegie Mellon University, 2001. Each series traces the electrical activity recorded during one heartbeat. The two classes are a normal heartbeat and a Myocardial Infarction.</p> <p>This is a modified multivariate version of the dataset saved in numpy format. The original dataset was obtained from <a href="https://www.cs.ucr.edu/%7Eeamonn/time_series_data_2018/">here</a>.</p> <p>The data are 3-dimensional arrays of shape [n_samples, time_steps, n_variables]. The data can be loaded as follows:</p> <pre><code>loaded_data = np.load("ECG_2D.npz") Xtr = loaded_data['Xtr'] # Training data of shape (100, 152, 2) Ytr = loaded_data['Ytr'] # Training labels of shape (100, 1) Xte = loaded_data['Xte'] # Test data of shape (100, 152, 2) Yte = loaded_data['Yte'] # Test labels of shape (100, 1)</code></pre>