Multivariate Time Series Classification using Dilated Convolutional Neural Network

TL;DR

This paper introduces a dilated convolutional neural network approach for multivariate time series classification, transforming data into an image-like format to automatically extract features and achieve competitive results.

Contribution

The paper presents a novel dilated CNN architecture that automatically extracts features from multivariate time series by transforming data into an image-like format, eliminating the need for hand-crafted features.

Findings

Automatic features are as effective as hand-crafted features.

The model performs well on human activity recognition datasets.

Dilated convolutions capture both within-variates and between-variates features.

Abstract

Multivariate time series classification is a high value and well-known problem in machine learning community. Feature extraction is a main step in classification tasks. Traditional approaches employ hand-crafted features for classification while convolutional neural networks (CNN) are able to extract features automatically. In this paper, we use dilated convolutional neural network for multivariate time series classification. To deploy dilated CNN, a multivariate time series is transformed into an image-like style and stacks of dilated and strided convolutions are applied to extract in and between features of variates in time series simultaneously. We evaluate our model on two human activity recognition time series, finding that the automatic features extracted for the time series can be as effective as hand-crafted features.