Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild
This work addresses stress detection in real-world settings for health monitoring applications, but it is incremental as it builds on existing semi-supervised and data augmentation techniques.
The paper tackled the problem of limited labeled data for stress detection using wearable sensors by developing a semi-supervised learning framework with data augmentation, improving stress classification performance by 7.7% to 13.8% over baseline supervised models.
Physiological and behavioral data collected from wearable or mobile sensors have been used to estimate self-reported stress levels. Since the stress annotation usually relies on self-reports during the study, a limited amount of labeled data can be an obstacle in developing accurate and generalized stress predicting models. On the other hand, the sensors can continuously capture signals without annotations. This work investigates leveraging unlabeled wearable sensor data for stress detection in the wild. We first applied data augmentation techniques on the physiological and behavioral data to improve the robustness of supervised stress detection models. Using an auto-encoder with actively selected unlabeled sequences, we pre-trained the supervised model structure to leverage the information learned from unlabeled samples. Then, we developed a semi-supervised learning framework to leverage the unlabeled data sequences. We combined data augmentation techniques with consistency regularization, which enforces the consistency of prediction output based on augmented and original unlabeled data. We validated these methods using three wearable/mobile sensor datasets collected in the wild. Our results showed that combining the proposed methods improved stress classification performance by 7.7% to 13.8% on the evaluated datasets, compared to the baseline supervised learning models.