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

arXiv:2403.15422v1 Announce Type: cross
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 …

abstract arxiv assumptions challenges computing cs.ai cs.hc cs.lg data datasets distribution eess.sp human machine machine learning machine learning techniques nature progress recognition research review sensor studies through type uniform