Dataset: Evaluation of post-hoc interpretability methods in time-series classification

<p>This repository contains the dataset, trained models as well as results for the article&nbsp;<em>Evaluation of post-hoc interpretability&nbsp;methods in time-series classification.</em></p> <p>The code to reproduce the results presented in the article is available on <a href="https://github.com/hturbe/InterpretTime">GitHub</a>. More details on the data and results can be found in the article.</p> <p><strong>Files:</strong></p> <ul> <li><strong>datasets.zip:&nbsp;</strong>Include the three datasets used in the article: <ul> <li><strong>ECG:&nbsp;</strong>Processed version of the CPSC dataset from&nbsp;<em>Classification of 12-lead ECGs: the PhysioNet - Computing in Cardiology Challenge 2020.</em></li> <li><strong>fordA:&nbsp;</strong>Dataset from the&nbsp;<a href="https://www.cs.ucr.edu/~eamonn/time_series_data_2018/">UCR Time Series Classification Archive</a></li> <li><strong>synthetic: </strong>Synthetic dataset developed specifically for the purpose of the article</li> </ul> </li> <li><strong>trained_models.zip:&nbsp;</strong>Include&nbsp;CNN, transformer and bi-lstm trained on the three datasets</li> <li><strong>results_paper.zip:&nbsp;</strong>Computed relevance and evaluation metrics for the trained models <ul> <li><strong>model_interpretability:&nbsp;</strong>Include the relevance computed using the different interpretability methods as well as the computed metrics for each method&nbsp;</li> <li><strong>summary_results:&nbsp;</strong>Summary of&nbsp;the evaluation metrics across all interpretability methods for each dataset as well as an excel file summarising the metrics across all datasets.</li> </ul> </li> </ul>