Explainability of time series missing data techniques
Dive into an experimental study to discover how filling missing values for time series data affects the explainability of a downstream classification task. Potential applications are health care, sport analysis or lifelogging (the application of your choice).
The aim of the project is to discover how filling missing values for time series data affects the explainability of downstream classification tasks, with application in health care, sport analysis, or lifelogging. Delve into the nuanced relationship between missing data imputation and the interpretability of classification outcomes in diverse domains. In health care, it is becoming a requirement to have explainable diagnostics and transparent decision-making. In sports analysis, insights from performance data must be comprehensible/understandable. In the context of lifelogging, the interpretability of classification outcomes will shed light on the significance of personal analytics. In all these applications, exploring the impact of various imputation techniques on the explainability of results will contribute to a more trustworthy way of handling missing values. This multifaceted study aims to elucidate the complex interplay between missing data handling and the explainability of classification tasks, offering valuable insights across diverse applications.
Goal
Discover how filling missing values for time series data affects the explainability of downstream classification tasks, with application in health care, sport analysis, or lifelogging.
Learning outcome
- Missing data analysis and how to apply it to e.g. sport and lifelogging data
- Machine learning and deep learning
- Building proper research methodology to handle missing data and evaluate the performance of different techniques
- Writing a scientific paper and how to publish it
Qualifications
- Hard working, motivated
- Fluent in Python programming
- Interested in learning
- The rest can be learned during the thesis work
Supervisors
- Thu Thi Nguyen
- Luis Lopez Ramos
- Hugo Hammer
