Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis

TL;DR

This paper evaluates the applicability of continual learning techniques to sensor-based human activity recognition (HAR), providing a comprehensive benchmark analysis of their effectiveness, computational cost, and challenges like sensor noise and label scarcity.

Contribution

It introduces a general framework for benchmarking continual learning methods in HAR and offers an empirical analysis of their performance and limitations.

Findings

Continual learning techniques vary in effectiveness for HAR tasks.

Sensor noise and label scarcity significantly impact continual learning performance.

The study provides insights and future directions for HAR systems using continual learning.

Abstract

Sensor-based human activity recognition (HAR), i.e., the ability to discover human daily activity patterns from wearable or embedded sensors, is a key enabler for many real-world applications in smart homes, personal healthcare, and urban planning. However, with an increasing number of applications being deployed, an important question arises: how can a HAR system autonomously learn new activities over a long period of time without being re-engineered from scratch? This problem is known as continual learning and has been particularly popular in the domain of computer vision, where several techniques to attack it have been developed. This paper aims to assess to what extent such continual learning techniques can be applied to the HAR domain. To this end, we propose a general framework to evaluate the performance of such techniques on various types of commonly used HAR datasets. We then present a comprehensive empirical analysis of their computational cost and effectiveness of tackling HAR-specific challenges (i.e., sensor noise and labels' scarcity). The presented results uncover useful insights on their applicability and suggest future research directions for HAR systems. Our code, models and data are available at https://github.com/srvCodes/continual-learning-benchmark.