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

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.

arXiv commentAccepted in the Information Sciences journal

References in corpus (26)

• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Deep Learning for Sensor-based Activity Recognition: A Survey
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• A continual learning survey: Defying forgetting in classification tasks
• Progressive Neural Networks
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Efficient Lifelong Learning with A-GEM
• Three scenarios for continual learning
• Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
• Continual Learning with Deep Generative Replay
• Measuring Catastrophic Forgetting in Neural Networks
• Lifelong Learning with Dynamically Expandable Networks
• Towards Robust Evaluations of Continual Learning
• Net2Net: Accelerating Learning via Knowledge Transfer
• Compacting, Picking and Growing for Unforgetting Continual Learning
• On Quadratic Penalties in Elastic Weight Consolidation
• A comprehensive, application-oriented study of catastrophic forgetting in DNNs
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Orthogonal Gradient Descent for Continual Learning
• Optimal Continual Learning has Perfect Memory and is NP-hard
• Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
• Few-Shot Self Reminder to Overcome Catastrophic Forgetting
• Incremental Learning In Online Scenario
• Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
• Greedy Frank-Wolfe Algorithm for Exemplar Selection

Cited by in corpus (3)

• Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity -- A Review
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks
• Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning