2024/01/01 by Younis, Raneen, Hakmeh, Abdul, Ahmadi, Zahra
Computer Science · Neuroscience · #000 #150 #Classification #EEG and Brain-Computer Interfaces #Interpretability #Machine Learning in Healthcare #Multivariate time series #Neural networks #Time Series Analysis and Forecasting
paper · doi:10.15488/20237
openalex publication_date 2024/01/01 · openalex created_date 2025/12/19 · openalex updated_date 2026/07/01
Conventional time series classification approaches based on bags of patterns or shapelets face significant challenges in dealing with a vast amount of feature candidates from high-dimensional multivariate data. In contrast, deep neural networks can learn low-dimensional features efficiently, and in particular, convolutional neural networks have shown promising results in classifying multivariate time series data. A key factor in the success of deep neural networks is this astonishing expressive power. However, this power comes at the cost of complex, black-boxed models, conflicting with the goals of building reliable and human-understandable models. In this work1, we introduce a new interpretable framework for multivariate time series data that by extracting and clustering the input quantifies the contribution of time-varying input variables and each signal’s role to the classification. We construct a graph that captures the temporal relationship between the extracted patterns for each layer and propose an effective merging strategy to aggregate those graphs into one. Finally, a graph embedding algorithm generates new representations of the created interpretable time-series features. Our extensive experiments indicate the benefit of our time-aware graph-based representation in multivariate time series classification while enriching them with more interpretability.