Self-Supervised Representation Learning for Motion Time Series: A Case Study in Activity Recognition

Author

Luis Carlos Garza Perez, The University of Texas Rio Grande Valley

Date of Award

5-2023

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Dr. Yifeng Gao

Second Advisor

Dr. Dongchul Kim

Third Advisor

Dr. Bin Fu

Abstract

In this thesis we will learn about what contrastive learning and time series are and understand the differences between supervised and self-supervised frameworks in machine learning. In addition, we will describe how the newest and most efficient self-supervised learning framework for visual representations to this date works, called SimCLR, which was originally developed to obtain useful vector representations from static images. We will also explain what TS2Vec is, and how a combination of both approaches can be applied to the concept of a time series, and still be able to extract a vector representation of the subject described by the time series, our goal is to show that even when the input dataset does not contain visual representations, contrastive learning can still be applied successfully, including when the whole subject data is spread between multiple time series.

Comments

Copyright 2023 Luis Carlos Garza Perez. All Rights Reserved.

https://go.openathens.net/redirector/utrgv.edu?url=https://www.proquest.com/dissertations-theses/self-supervised-representation-learning-motion/docview/2842685007/se-2?accountid=7119

Recommended Citation

Garza Perez, Luis Carlos, "Self-Supervised Representation Learning for Motion Time Series: A Case Study in Activity Recognition" (2023). Theses and Dissertations. 1218.
https://scholarworks.utrgv.edu/etd/1218