Time Series Self-Supervised Representation Learning

• Grant number: 24/07016-4
• Support Opportunities: Scholarships in Brazil - Doctorate
• Effective date (Start): June 01, 2024
• Effective date (End): October 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Furtado Silva
• Grantee: Rafael da Costa Silva
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 22/03176-1 - Machine learning for time series obtained in mHealth applications, AP.PNGP.PI

Abstract

The monitoring of physiological signals, vital signs, and other parameters collected over time is essential in various tasks in the healthcare field, such as estimating heart rate and identifying anomalous heartbeats. However, these time series are typically obtained through costly and non-portable equipment. On the other hand, with the improvement and miniaturization of sensors capable of transmitting various types of data, mobile and wearable devices have increasingly shown promise in supporting medical decisions. Smartphones and smartwatches are equipped with increasingly precise and diverse sensors, leading the World Health Organization to consider mobile health (mHealth) as potentially revolutionary in how populations interact with public health systems. However, several scientific and technological challenges need to be overcome for mHealth applications to be viable in practice. Among these challenges are the need for low-cost methods, the heterogeneity and multimodality of data, and the difficulty in obtaining annotated data.In this scenario, this project proposes to investigate the use of Self-Supervised Machine Learning for time series in mHealth applications. By the end of this research, we aim to establish a new state-of-the-art for these applications and make the generated models available, along with any other resources necessary for advancing research in the same line of focus.