Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity -- A Review

Abstract

Sensor-based Human Activity Recognition (HAR) is crucial in ubiquitous computing, analysing behaviours through multi-dimensional observations. Despite research progress, HAR confronts challenges, particularly in data distribution assumptions. Most studies often assume uniform data distributions across datasets, contrasting with the varied nature of practical sensor data in human activities. Addressing data heterogeneity issues can improve performance, reduce computational costs, and aid in developing personalized, adaptive models with less annotated data. This review investigates how machine learning addresses data heterogeneity in HAR, by categorizing data heterogeneity types, applying corresponding suitable machine learning methods, summarizing available datasets, and discussing future challenges.

References in corpus (14)

• Deep Learning for Sensor-based Activity Recognition: A Survey
• A continual learning survey: Defying forgetting in classification tasks
• Recent Advances in Open Set Recognition: A Survey
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Federated Machine Learning: Concept and Applications
• Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
• Protecting Sensory Data against Sensitive Inferences
• Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis
• Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization
• Deep Generative Domain Adaptation with Temporal Attention for Cross-User Activity Recognition
• Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
• Wearable-based behaviour interpolation for semi-supervised human activity recognition
• SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
• Cross-user activity recognition via temporal relation optimal transport