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

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