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.本仓库包含论文《时序分类中事后可解释性方法评估》（Evaluation of post-hoc interpretability methods in time-series classification）的配套数据集、训练模型与实验结果。复现论文中所述实验结果的代码已托管至GitHub，更多关于数据集与实验结果的细节可参阅该论文。<strong>文件说明：</strong><br><strong>datasets.zip</strong>：包含论文中使用的三类数据集：<br>&nbsp;&nbsp;<strong>ECG数据集</strong>：源自论文《12导联心电图分类：2020年PhysioNet计算心脏病学挑战赛》（Classification of 12-lead ECGs: the PhysioNet - Computing in Cardiology Challenge 2020）的CPSC数据集处理版本。<br>&nbsp;&nbsp;<strong>fordA数据集</strong>：源自UCR时序分类归档（UCR Time Series Classification Archive）的数据集。<br>&nbsp;&nbsp;<strong>synthetic数据集</strong>：专为本文研究定制开发的合成数据集。<br><strong>trained_models.zip</strong>：包含在上述三类数据集上训练得到的卷积神经网络（Convolutional Neural Network, CNN）、Transformer以及双向长短期记忆网络（Bidirectional Long Short-Term Memory, Bi-LSTM）。<br><strong>results_paper.zip</strong>：包含各训练模型的相关性计算结果与评估指标。<br><strong>model_interpretability文件夹</strong>：包含使用不同可解释性方法得到的相关性计算结果，以及各方法对应的评估指标。<br><strong>summary_results文件夹</strong>：包含各数据集下所有可解释性方法的评估指标汇总，以及一份跨所有数据集的指标汇总Excel文件。