Motif Difference Field: A Simple and Effective Image Representation of Time Series for Classification

TL;DR

This paper introduces the Motif Difference Field (MDF), a simple image-based representation of time series data that, when used with CNNs, achieves superior classification performance and highlights significant motifs.

Contribution

The paper proposes MDF as an easy-to-construct image representation for time series, demonstrating its effectiveness with CNNs and motif detection techniques.

Findings

MDF outperforms other image representations in time series classification.

Triadic motifs yield the best classification results.

Grad-CAM effectively identifies significant motifs in MDF.

Abstract

Time series motifs play an important role in the time series analysis. The motif-based time series clustering is used for the discovery of higher-order patterns or structures in time series data. Inspired by the convolutional neural network (CNN) classifier based on the image representations of time series, motif difference field (MDF) is proposed. Compared to other image representations of time series, MDF is simple and easy to construct. With the Fully Convolution Network (FCN) as the classifier, MDF demonstrates the superior performance on the UCR time series dataset in benchmark with other time series classification methods. It is interesting to find that the triadic time series motifs give the best result in the test. Due to the motif clustering reflected in MDF, the significant motifs are detected with the help of the Gradient-weighted Class Activation Mapping (Grad-CAM). The areas in MDF with high weight in Grad-CAM have a high contribution from the significant motifs with the desired ordinal patterns associated with the signature patterns in time series. However, the signature patterns cannot be identified with the neural network classifiers directly based on the time series.