Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity

TL;DR

This paper proposes combining multiple public human activity recognition datasets to create a generalized model that reduces the need for extensive labeled data and improves adaptation to new, unseen domains.

Contribution

It introduces a novel strategy for merging public datasets to develop pre-trained HAR models that require less labeled data for customization.

Findings

Combining datasets improves model generalization.

Significant reduction in labeled data needed for target domain.

Effective across various neural network architectures.

Abstract

The use of supervised learning for Human Activity Recognition (HAR) on mobile devices leads to strong classification performances. Such an approach, however, requires large amounts of labeled data, both for the initial training of the models and for their customization on specific clients (whose data often differ greatly from the training data). This is actually impractical to obtain due to the costs, intrusiveness, and time-consuming nature of data annotation. Moreover, even with the help of a significant amount of labeled data, model deployment on heterogeneous clients faces difficulties in generalizing well on unseen data. Other domains, like Computer Vision or Natural Language Processing, have proposed the notion of pre-trained models, leveraging large corpora, to reduce the need for annotated data and better manage heterogeneity. This promising approach has not been implemented in the HAR domain so far because of the lack of public datasets of sufficient size. In this paper, we propose a novel strategy to combine publicly available datasets with the goal of learning a generalized HAR model that can be fine-tuned using a limited amount of labeled data on an unseen target domain. Our experimental evaluation, which includes experimenting with different state-of-the-art neural network architectures, shows that combining public datasets can significantly reduce the number of labeled samples required to achieve satisfactory performance on an unseen target domain.