Application of Transfer Learning Approaches in Multimodal Wearable Human Activity Recognition

TL;DR

This paper explores transfer learning techniques applied to multimodal wearable human activity recognition, analyzing their advantages and limitations, and suggests ensemble methods for improved performance.

Contribution

It provides a comparative analysis of transfer learning methods in wearable activity recognition and proposes ensemble learning as a future direction.

Findings

Different transfer learning methods have unique strengths and limitations.

Applying transfer learning improves model performance in activity recognition.

Ensemble approaches may enhance accuracy in future work.

Abstract

Through this project, we researched on transfer learning methods and their applications on real world problems. By implementing and modifying various methods in transfer learning for our problem, we obtained an insight in the advantages and disadvantages of these methods, as well as experiences in developing neural network models for knowledge transfer. Due to time constraint, we only applied a representative method for each major approach in transfer learning. As pointed out in the literature review, each method has its own assumptions, strengths and shortcomings. Thus we believe that an ensemble-learning approach combining the different methods should yield a better performance, which can be our future research focus.