Time-Series Based Machine Learning

The proposed project aims to enhance the interpretability of machine learning models, particularly in the context of time series data analysis. By extending the capabilities of the tsfresh library, a widely used tool for time series feature extraction, the project seeks to make complex models more transparent and understandable. This effort will improve confidence in the predictions and decisions made by these models, benefiting both research institutions (University of Toronto and University of Auckland) and industry partners. Additionally, the project addresses specific challenges in benchmark datasets like the UCR Time Series Classification Archive, aiming to enhance model robustness and reliability in real-world applications. Ultimately, the project aims to foster trust and usability in various domains by providing clearer insights into the workings of machine learning models.

Faculty Supervisor:

Arthur Chan

Student:

Partner:

University of Auckland

Discipline:

Engineering

Sector:

Artificial Intelligence; Technology; Other

University:

University of Toronto

Program: