Human-inspired time-series health evaluation with an adaptive multimodal electronic skin
TL;DR
This work presents a multimodal electronic skin that captures diverse physiological signs with an adaptive learning framework that rapidly generalizes to unseen tasks with minimal labeled data and demonstrates robust adaptation with 94.7% accuracy in activity recognition and 90.2% precision in fatigue assessment.
Abstract
Electronic skin powered with artificial intelligence could enable next-generation robotic and medical devices, yet integrating multimodal sensors and analyzing heterogeneous, multifrequency time series remain challenging. Most wearable machine learning architectures are time-invariant and trained for a specific task, limiting transfer across modalities and users. We present a multimodal electronic skin that captures diverse physiological signs with an adaptive learning framework that rapidly generalizes to unseen tasks with minimal labeled data. Our streamlined end-to-end framework uses a spectral variational autoencoder to denoise and compress multifrequency biosignals into a shared, unified second-wise latent space that preserves the spectral-temporal structure, followed by a transformer to capture temporal dependencies to support diverse downstream tasks with data-efficient learning. We demonstrate robust adaptation with 94.7% accuracy in activity recognition and 90.2% precision in fatigue assessment across various users and daily activities regardless of device and user variations, highlighting a scalable route to generalized physiological time-series analytics and human performance assessments.