Classification of Time-Series Images Using Deep Convolutional Neural Networks

TL;DR

This paper proposes transforming time-series data into 2D images using Recurrence Plots and then applying deep CNNs for classification, achieving competitive accuracy on benchmark datasets.

Contribution

It introduces a novel approach combining Recurrence Plots with CNNs for time-series classification, leveraging image recognition techniques for improved performance.

Findings

Achieved competitive accuracy on UCR datasets.

Demonstrated the effectiveness of image-based representation for TSC.

Outperformed some existing deep learning and state-of-the-art algorithms.

Abstract

Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.