Quantum Hybrid Support Vector Machines for Stress Detection in Older Adults

TL;DR

This paper tackles stress detection in older adults by framing it as an anomaly-detection problem and implementing a Quantum Hybrid SVM (QHSVM) with a fidelity-based kernel. The approach fuses classical feature extraction and a quantum kernel mapped via Dense angle encoding to train a One-Class SVM, using cortisol measurements during TSST as ground truth. Experimental results on a wearable-enabled dataset show that the quantum approach generally outperforms classical SVMs, achieving higher recall and up to 79% accuracy with optimized feature-qubit configurations (e.g., 12 features and 6 qubits). The findings suggest significant potential for quantum-enhanced stress monitoring in smart healthcare, while highlighting practical challenges on current quantum hardware and directions for reducing computational overhead and improving robustness.

Abstract

Stress can increase the possibility of cognitive impairment and decrease the quality of life in older adults. Smart healthcare can deploy quantum machine learning to enable preventive and diagnostic support. This work introduces a unique technique to address stress detection as an anomaly detection problem that uses quantum hybrid support vector machines. With the help of a wearable smartwatch, we mapped baseline sensor reading as normal data and stressed sensor reading as anomaly data using cortisol concentration as the ground truth. We have used quantum computing techniques to explore the complex feature spaces with kernel-based preprocessing. We illustrate the usefulness of our method by doing experimental validation on 40 older adults with the help of the TSST protocol. Our findings highlight that using a limited number of features, quantum machine learning provides improved accuracy compared to classical methods. We also observed that the recall value using quantum machine learning is higher compared to the classical method. The higher recall value illustrates the potential of quantum machine learning in healthcare, as missing anomalies could result in delayed diagnostics or treatment.

Figures (4)

• Figure 1: Pipeline of the hybrid-quantum SVM anomaly detection
• Figure 2: TSST Protocol
• Figure 3: Quantum Circuit for Feature Mapping with 8 qubits
• Figure 4: 2D Projection of test kernel matrix with classical and Quantum dot product kernel blue represents Baseline or Normal class and orange represents Anomaly or Stress class