# Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild

arXiv: https://arxiv.org/abs/2202.12935 · HTML: https://mlsanity.com/paper/2202.12935/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 52 references that are in the map.
- First posted on arXiv 22 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Semi-supervised Sequence Learning](https://mlsanity.com/paper/1511.01432/) (2015)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [Exploring Interpretable LSTM Neural Networks over Multi-Variable Data](https://mlsanity.com/paper/1905.12034/) (2019)
- [TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers](https://mlsanity.com/paper/2003.08474/) (2020)
- [DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction](https://mlsanity.com/paper/1802.02511/) (2018)

## Built on by (most cited first, 8 of 8)

- [A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism](https://mlsanity.com/paper/2303.03577/) (2023)
- [Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach](https://mlsanity.com/paper/2407.08215/) (2024)
- [Active Reinforcement Learning for Personalized Stress Monitoring in Everyday Settings](https://mlsanity.com/paper/2305.00111/) (2023)
- [Data Augmentation for Traffic Classification](https://mlsanity.com/paper/2401.10754/) (2024)
- [Context-Aware Stress Monitoring using Wearable and Mobile Technologies in Everyday Settings](https://mlsanity.com/paper/2401.05367/) (2023)
- [Human Heterogeneity Invariant Stress Sensing](https://mlsanity.com/paper/2506.02256/) (2025)
- [Classification of Stress via Ambulatory ECG and GSR Data](https://mlsanity.com/paper/2208.04705/) (2022)
- [PiRL: Participant-Invariant Representation Learning for Healthcare](https://mlsanity.com/paper/2211.12422/) (2022)

## Abstract (arXiv)

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.