Emotion Recognition in Older Adults with Quantum Machine Learning and Wearable Sensors

2025-07-10

AI Summary

To address privacy leakage and intrusive interference in emotion recognition for older adults, this work proposes a non-intrusive, privacy-preserving framework integrating wearable physiological sensing with quantum machine learning. Methodologically, we introduce the first application of Quantum Kernel Support Vector Machines (QKSVM) to multimodal wearable physiological signals—including heart rate variability and galvanic skin response—for emotion classification, augmented by classical preprocessing and feature fusion strategies to enable efficient modeling under small-sample conditions. Experimental results demonstrate that the quantum-enhanced model achieves F1-scores exceeding 80% across all classes in emotion recognition tasks related to Alzheimer’s disease, dementia, and PTSD; average recall improves by 36% over classical baselines, markedly enhancing robustness and generalization. This study validates the practical viability of quantum machine learning in resource-constrained edge settings and establishes a deployable, low-intrusion paradigm for clinical emotion monitoring.

Technology Category

• Machine Learning: Quantum Machine Learning
• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We investigate the feasibility of inferring emotional states exclusively from physiological signals, thereby presenting a privacy-preserving alternative to conventional facial recognition techniques. We conduct a performance comparison of classical machine learning algorithms and hybrid quantum machine learning (QML) methods with a quantum kernel-based model. Our results indicate that the quantum-enhanced SVM surpasses classical counterparts in classification performance across all emotion categories, even when trained on limited datasets. The F1 scores over all classes are over 80% with around a maximum of 36% improvement in the recall values. The integration of wearable sensor data with quantum machine learning not only enhances accuracy and robustness but also facilitates unobtrusive emotion recognition. This methodology holds promise for populations with impaired communication abilities, such as individuals with Alzheimer's Disease and Related Dementias (ADRD) and veterans with Post-Traumatic Stress Disorder (PTSD). The findings establish an early foundation for passive emotional monitoring in clinical and assisted living conditions.

Problem

• Emotion recognition in older adults using wearable sensors
• Comparing classical and quantum machine learning for emotion classification
• Enhancing accuracy for populations with communication impairments

Innovation

• Quantum-enhanced SVM improves emotion classification accuracy
• Wearable sensors enable privacy-preserving emotion recognition
• Hybrid QML enhances robustness with limited datasets