On Handling Catastrophic Forgetting for Incremental Learning of Human Physical Activity on the Edge

TL;DR

This paper introduces PILOTE, a novel incremental learning method that enables human activity recognition directly on edge devices with limited resources, addressing privacy concerns and catastrophic forgetting.

Contribution

PILOTE is a new incremental learning approach designed for edge devices, handling catastrophic forgetting with limited data and resources, enhancing privacy and personalization.

Findings

PILOTE achieves reliable activity recognition on resource-constrained edge devices.

The method effectively mitigates catastrophic forgetting in incremental learning.

Experiments demonstrate low latency and high accuracy in real-world scenarios.

Abstract

Human activity recognition (HAR) has been a classic research problem. In particular, with recent machine learning (ML) techniques, the recognition task has been largely investigated by companies and integrated into their products for customers. However, most of them apply a predefined activity set and conduct the learning process on the cloud, hindering specific personalizations from end users (i.e., edge devices). Even though recent progress in Incremental Learning allows learning new-class data on the fly, the learning process is generally conducted on the cloud, requiring constant data exchange between cloud and edge devices, thus leading to data privacy issues. In this paper, we propose PILOTE, which pushes the incremental learning process to the extreme edge, while providing reliable data privacy and practical utility, e.g., low processing latency, personalization, etc. In particular, we consider the practical challenge of extremely limited data during the incremental learning process on edge, where catastrophic forgetting is required to be handled in a practical way. We validate PILOTE with extensive experiments on human activity data collected from mobile sensors. The results show PILOTE can work on edge devices with extremely limited resources while providing reliable performance.