Master Thesis: Meta-Learning for Personalized Human Activity Recognition

Background

Human Activity Recognition (HAR) using data from wearable or smartphone sensors (e.g., accelerometers, gyroscopes) is an increasingly active research area with broad applications in healthcare, sports, mobile computing, and human-computer interaction.

Most HAR systems are built on generalized models trained across diverse populations. However, human actions vary greatly between individuals due to factors such as age, gender, and lifestyle. This variability often leads to reduced performance when generalized models are applied to new subjects, especially when only limited personal data is available.

To overcome this limitation, personalization methods have been explored. While transfer learning and few-shot learning approaches provide some adaptation capability, they remain constrained in flexibility and data efficiency. A promising solution is meta-learning, which trains models to quickly adapt to new tasks (in this case new subjects) with minimal data.

This thesis aims to develop a data-efficient meta-learning appraoch for personalized HAR and comparing it against existing approaches in terms of adaptability, classification performance, and computational efficiency.

Tasks

• Review literature on personalization strategies for HAR, including transfer learning, few-shot learning, and meta-learning.
• Design, implement, and train a meta-learning approach for personalized HAR.
• Evaluate the approach in terms of classification performance, adaptability to new subjects, and computational efficiency.
• Benchmark results against generalized models and transfer learning baselines.

Requirements

• Solid understanding of deep learning concepts.
• Proficient programming skills in Python and PyTorch.
• Experience in working with time series data is a plus but can be acquired during the thesis.

If you are interested in this topic, please contact Max Burzer (burzer@teco.edu)