Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns to Attend to Important Variables As Well As Time Intervals
Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns to Attend to Important Variables As Well As Time Intervals
复制标题
DOI：
10.1145/3437963.3441815
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Tsung-Yu Hsieh;Suhang Wang;Yiwei Sun
中科院分区：
文献类型：
--
作者：
Tsung-Yu Hsieh;Suhang Wang;Yiwei Sun
许多现实世界的应用，例如，医疗保健，提出多变量时间序列预测问题。在这种情况下，除了模型的预测准确性外，模型的透明度和可解释性也至关重要。我们考虑从多变量时间序列数据建立可解释的分类器的问题。理解这种预测模型的一个关键标准涉及阐明和量化时变输入变量对分类的贡献。因此，我们引入了一种新颖的，模块化的，基于卷积的特征提取和注意力机制，同时识别变量以及确定分类器输出的时间间隔。我们提出了广泛的实验结果与几个基准数据集，表明所提出的方法优于国家的最先进的基线方法对多变量时间序列分类任务。我们的案例研究的结果表明，所提出的方法确定的变量和时间间隔是有意义的，相对于现有的领域知识。
Many real-world applications, e.g., healthcare, present multi-variate time series prediction problems. In such settings, in addition to the predictive accuracy of the models, model transparency and explainability are paramount. We consider the problem of building explainable classifiers from multi-variate time series data. A key criterion to understand such predictive models involves elucidating and quantifying the contribution of time varying input variables to the classification. Hence, we introduce a novel, modular, convolution-based feature extraction and attention mechanism that simultaneously identifies the variables as well as time intervals which determine the classifier output. We present results of extensive experiments with several benchmark data sets that show that the proposed method outperforms the state-of-the-art baseline methods on multi-variate time series classification task. The results of our case studies demonstrate that the variables and time intervals identified by the proposed method make sense relative to available domain knowledge.