Semi-supervised Multivariate Time Series Classification by Subsample Correlation Prediction

• Published in: Proceedings - IEEE Symposium on Computers and Communications pp. 1177 - 1180
• Main Author: Su, Yun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.07.2023
• Subjects: Computers; Correlation; Feature extraction; Fluctuations; Multivariate Time Series Classification; Self-Supervised; Semi-Supervised Learning; Semisupervised learning; Subsample Correlation; Time series analysis; Training
• ISSN: 2642-7389
• DOI: 10.1109/ISCC58397.2023.10217939

This paper introduces a novel Semi-supervised learning (SSL) model based on subsample correlation (SSC) to address the challenge of Multivariate Time Series (MTS) classification tasks due to the scarcity of labeled data. The proposed method utilizes the coherence property of subsamples from identical subjects to devise the pretext task. For labeled time series, SSC conducts supervised classification under the supervision of annotated class labels. For unlabeled time series, SSC uses two subsampling techniques and considers subsamples from the same time series candidate as having a positive relationship and subsamples from different candidates as having a negative relationship. By jointly classifying labeled data and predicting the subsample correlation of unlabeled data, SSC captures useful representations of unlabeled time series. The experimental results on several Multivariate Time Series classification (TSC) datasets demonstrate the effectiveness of the proposed algorithm.