Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity -- A Review
It addresses data heterogeneity challenges in HAR for ubiquitous computing, but as a review, it is incremental in summarizing existing work rather than presenting new research.
This review tackles the problem of data heterogeneity in sensor-based Human Activity Recognition (HAR), which arises from varied sensor data distributions in practical applications, and it investigates how machine learning methods can address this issue to improve performance and reduce computational costs.
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.