Few-shot Learning using Data Augmentation and Time-Frequency Transformation for Time Series Classification

TL;DR

This paper introduces a novel few-shot learning framework for time series classification that combines data augmentation via time-frequency transformation and synthetic image generation, along with a specialized neural network architecture.

Contribution

The paper proposes a new few-shot learning approach using data augmentation and a dual-branch neural network for improved time series classification performance.

Findings

Achieved over 93% F1 score and accuracy on ALS dataset.

Achieved over 95% F1 score and accuracy on WTF dataset.

Demonstrated effectiveness of data augmentation in few-shot TSC tasks.

Abstract

Deep neural networks (DNNs) that tackle the time series classification (TSC) task have provided a promising framework in signal processing. In real-world applications, as a data-driven model, DNNs are suffered from insufficient data. Few-shot learning has been studied to deal with this limitation. In this paper, we propose a novel few-shot learning framework through data augmentation, which involves transformation through the time-frequency domain and the generation of synthetic images through random erasing. Additionally, we develop a sequence-spectrogram neural network (SSNN). This neural network model composes of two sub-networks: one utilizing 1D residual blocks to extract features from the input sequence while the other one employing 2D residual blocks to extract features from the spectrogram representation. In the experiments, comparison studies of different existing DNN models with/without data augmentation are conducted on an amyotrophic lateral sclerosis (ALS) dataset and a wind turbine fault (WTF) dataset. The experimental results manifest that our proposed method achieves 93.75% F1 score and 93.33% accuracy on the ALS datasets while 95.48% F1 score and 95.59% accuracy on the WTF datasets. Our methodology demonstrates its applicability of addressing the few-shot problems for time series classification.