Cross-convolution for multivariate time series tasks

• Grant number: 23/11775-5
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: December 01, 2023
• End date: February 29, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Furtado Silva
• Grantee: José Gilberto Barbosa de Medeiros Júnior
• Supervisor: Germain Forestier
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Université de Haute-Alsace, France
• Associated to the scholarship: 23/02680-0 - Transfer of Learning to Deal with Devices Heterogeneity, BP.MS

Abstract

With the growing ubiquity of smartphones, smartwatches, and other devices capable of collecting data across time, applications that use time series as input, such as cardiac monitoring and activity recognition, have become increasingly popular. Several of these scenarios can be mapped naturally as tasks involving multivariate time series. Thus, various techniques for Machine Learning applied to time series have been developed. However, most of the developed techniques are adapted from univariate to multivariate problems, therefore, they are not fully adapted to multivariate series. Considering this scenario, this research will propose a cross-convolution mechanism adapted for time series problems capable of capturing the structural and temporal relationship of the data. (AU)