# Ensemble Machine Learning Model Trained on a New Synthesized Dataset Generalizes Well for Stress Prediction Using Wearable Devices

arXiv: https://arxiv.org/abs/2209.15146 · HTML: https://mlsanity.com/paper/2209.15146/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 37 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 7 of 7)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning](https://mlsanity.com/paper/2203.06498/) (2022)
- [A multimodal sensor dataset for continuous stress detection of nurses in a hospital](https://mlsanity.com/paper/2108.07689/) (2021)
- [The Effect of Person-Specific Biometrics in Improving Generic Stress Predictive Models](https://mlsanity.com/paper/1910.01770/) (2019)
- [Analysing the Performance of Stress Detection Models on Consumer-Grade Wearable Devices](https://mlsanity.com/paper/2203.09669/) (2022)
- [Semi-Supervised Generative Adversarial Network for Stress Detection Using Partially Labeled Physiological Data](https://mlsanity.com/paper/2206.14976/) (2022)

## Built on by (most cited first, 6 of 6)

- [Stressor Type Matters! -- Exploring Factors Influencing Cross-Dataset Generalizability of Physiological Stress Detection](https://mlsanity.com/paper/2405.09563/) (2024)
- [Protecting Student Mental Health with a Context-Aware Machine Learning Framework for Stress Monitoring](https://mlsanity.com/paper/2508.01105/) (2025)
- [The Effect of Acute Stress on the Interpretability and Generalization of Schizophrenia Predictive Machine Learning Models](https://mlsanity.com/paper/2410.19739/) (2024)
- [Stabilizing Machine Learning for Reproducible and Explainable Results: A Novel Validation Approach to Subject-Specific Insights](https://mlsanity.com/paper/2412.16199/) (2024)
- [A Statistical Approach for Synthetic EEG Data Generation](https://mlsanity.com/paper/2504.16143/) (2025)
- [Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition](https://mlsanity.com/paper/2610.01692/) (2026)

## Abstract (arXiv)

Introduction. We investigate the generalization ability of models built on datasets containing a small number of subjects, recorded in single study protocols. Next, we propose and evaluate methods combining these datasets into a single, large dataset. Finally, we propose and evaluate the use of ensemble techniques by combining gradient boosting with an artificial neural network to measure predictive power on new, unseen data. Methods. Sensor biomarker data from six public datasets were utilized in this study. To test model generalization, we developed a gradient boosting model trained on one dataset (SWELL), and tested its predictive power on two datasets previously used in other studies (WESAD, NEURO). Next, we merged four small datasets, i.e. (SWELL, NEURO, WESAD, UBFC-Phys), to provide a combined total of 99 subjects,. In addition, we utilized random sampling combined with another dataset (EXAM) to build a larger training dataset consisting of 200 synthesized subjects,. Finally, we developed an ensemble model that combines our gradient boosting model with an artificial neural network, and tested it on two additional, unseen publicly available stress datasets (WESAD and Toadstool). Results. Our method delivers a robust stress measurement system capable of achieving 85% predictive accuracy on new, unseen validation data, achieving a 25% performance improvement over single models trained on small datasets. Conclusion. Models trained on small, single study protocol datasets do not generalize well for use on new, unseen data and lack statistical power. Ma-chine learning models trained on a dataset containing a larger number of varied study subjects capture physiological variance better, resulting in more robust stress detection.