.png){kind=icon}
.png){kind=icon}
Return
Exploring Regularization Methods for Domain Generalization in Accelerometer-Based Human Activity Recognition
.png){kind=icon}
OA
AI
DOI：10.3390/s23146511.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The study of Domain Generalization (DG) has gained considerable momentum in the Machine Learning (ML) field. Human Activity Recognition (HAR) inherently encompasses diverse domains (e.g., users, devices, or datasets), rendering it an ideal testbed for exploring Domain Generalization. Building upon recent work, this paper investigates the application of regularization methods to bridge the generalization gap between traditional models based on handcrafted features and deep neural networks. We apply various regularizers, including sparse training, Mixup, Distributionally Robust Optimization (DRO), and Sharpness-Aware Minimization (SAM), to deep learning models and assess their performance in Out-of-Distribution (OOD) settings across multiple domains using homogenized public datasets. Our results show that Mixup and SAM are the best-performing regularizers. However, they are unable to match the performance of models based on handcrafted features. This suggests that while regularization techniques can improve OOD robustness to some extent, handcrafted features remain superior for domain generalization in HAR tasks.
Keywords:
Human Activity Recognition
deep learning
Domain Generalization
regularization
accelerometer
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.