Presentation
Classify Mental Stress Level with Privacy-preserving Machine Learning
DescriptionThe growing need for mental stress detection in the workplace has prompted the exploration of machine-learning solutions. Nevertheless, traditional centralized machine-learning methods encounter critical data privacy issues, especially with sensitive physiological signals. To address this challenge, we introduced a privacy-preserving mental stress detection framework utilizing federated learning, focusing on human-robot collaboration scenarios. We first developed classifiers employing traditional centralized algorithms including support vector machine (SVM), multilayer perceptron, random forest, and naïve Bayes, followed by implementing a federated SVM classifier. These classifiers utilize multimodal physiological signal features to distinguish between relaxed, low-level stressed, and high-level stressed states. Comparative analysis in terms of precision, recall, and F1-score was conducted to evaluate the performance. The results demonstrate that federated learning not only offers comparable accuracy to centralized methods but also ensures the protection of sensitive data, making it a valuable approach in scenarios where data privacy is of the most importance.
Event Type
Lecture
TimeWednesday, September 11th2:10pm - 2:30pm MST
LocationFlagstaff
Human AI Robot Teaming (AI)