- By:
- Onim, Md. Saif Hassan; Humble, Travis S; Thapliyal, Himanshu
- Page Number:
- 589-593
- Book Title:
- GLSVLSI '26: Proceedings of the Great Lakes Symposium on VLSI 2026
- Publication Date:
- July 2, 2026
- Publisher Location:
- Association for Computing Machinery, New York, New York, United States of America
- Conference Name:
- Great Lakes Symposium on VLSI (GLSVLSI)
- Conference Location:
- Canandaigua, New York, United States of America
- Conference Sponsor:
- ACM
- View DOI Listing:
- https://doi.org/10.1145/3787109.3816382
Abstract
Stress and emotion detection from high-dimensional physiological signals is a challenging task, particularly when aiming for accurate classification across diverse behavioral states. Quantum machine learning (QML) is promising for modeling such high-dimensional data, but scalability is limited by qubit resources and the exponential cost of classical statevector simulation. This work studies the scalability of quantum support vector machines (QSVMs) for binary stress detection and three-class emotion recognition (Negative/Neutral/Positive) under varying qubit counts and angle-encoding strategies. We also present a comparison study with one-feature-per-qubit (1:1) and two-features-per-qubit (2:1) mappings. Experiments are executed on HPC infrastructure using NVIDIA CUDA-Q to evaluate performance, variance, and class-dependent separability at higher-qubit setups. Results show that larger Hilbert spaces can improve peak accuracy but may increase instability. At the same time, dense 2:1 encoding yields more consistent stress detection performance. For emotion recognition, scaling improves discrimination for classes like Negative and Positive more than Neutral. We find that effective QML scaling is task-dependent and benefits more from encoding design than simply increasing qubit count.
