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.

This educational paper presents a modular workshop framework for teaching quantum programming and hardware-oriented reasoning within microelectronics education. The framework integrates five connected instructional elements. They are Qiskit foundations laboratory on gates, measurement, and Bell-state entanglement; a noise-aware quantum arithmetic module featuring GHZ circuits, ripple-carry addition, and quantum carry-lookahead addition; a structured adder-analysis exercise focused on depth, ancilla, and reversible cleanup; a capstone project on noise-resilient and security-aware 4-bit quantum adders; and a bridge from classical machine learning workflows to quantum machine learning. The paper redefines these activities explicitly as learning modules with student learning outcomes, module learning outcomes, assessment options, and discussion prompts. The resulting sequence helps learners bridge from syntax and circuit building to architecture-level trade-offs, noise interpretation, approximate design, and research-oriented thinking, all of which are well-suited for the quantum workforce.

Emotion detection in older adults is crucial for understanding their cognitive and emotional well-being, especially in hospital and assisted living environments. In this work, we investigate an edge-based, non-obtrusive approach to emotion identification that uses only physiological signals obtained via wearable sensors. Our dataset includes data from 40 older individuals. Emotional states were obtained using physiological signals from the Empatica E4 and Shimmer3 GSR+ wristband and facial expressions were recorded using camera-based emotion recognition with the iMotion's Facial Expression Analysis (FEA) module. The dataset also contains twelve emotion categories in terms of relative intensities. We aim to study how well emotion recognition can be accomplished using simply physiological sensor data, without the requirement for cameras or intrusive facial analysis. By leveraging classical machine learning models, we predict the intensity of emotional responses based on physiological signals. We achieved the highest 0.782 r2 score with the lowest 0.0006 MSE on the regression task. This method has significant implications for individuals with Alzheimer's Disease and Related Dementia (ADRD), as well as veterans coping with Post-Traumatic Stress Disorder (PTSD) or other cognitive impairments. Our results across multiple classical regression models validate the feasibility of this method, paving the way for privacy-preserving and efficient emotion recognition systems in real-world settings.

The widespread use of cloud-based medical devices and wearable sensors has made physiological data susceptible to tampering. These attacks can compromise the reliability of healthcare systems which can be critical and life-threatening. Detection of such data tampering is of immediate need. Machine learning has been used to detect anomalies in datasets but the performance of Quantum Machine Learning (QML) is still yet to be evaluated for physiological sensor data. Thus, our study compares the effectiveness of QML for detecting physiological data tampering, focusing on two types of white-box attacks: data poisoning and adversarial perturbation. The results show that QML models are better at identifying label-flipping attacks, achieving accuracy rates of 75% − 95% depending on the data and attack severity. This superior performance is due to the ability of quantum algorithms to handle complex and high-dimensional data. However, both QML and classical models struggle to detect more sophisticated adversarial perturbation attacks, which subtly alter data without changing its statistical properties. Although QML performed poorly against this attack with around 45% − 65% accuracy, it still outperformed classical algorithms in some cases.

Stress can aggravate age-related diseases that can lead to significant clinical impairment and decrease the quality of life in older adults. To mitigate the harmful effects of stress and aging, it is important to monitor and manage stress. In this paper, we have developed context-aware stress detection for older adults with machine learning and cortisol biomarker. The Trier Social Stress Test (TSST), a well-known experimental protocol that consistently inflicts stress on people in a social context, was used as the stress protocol for this study. We have used salivary cortisol as a stress biomarker for ground truth estimation. The proposed machine learning model classifies stress into three different levels (no-stress, low-stress, and high-stress) based on data collected from Electro-Dermal Activity (EDA), Blood Volume Pressure (BVP), and Inter Beat Interval (IBI) sensors. To develop a context-aware machine learning model, we have used context features captured from the TSST protocol. Using sensor fusion, our proposed context-aware machine learning model achieved a macro-average F1-score of 0.937 and an accuracy of 92.48% in distinguishing among the three stress levels. We have also illustrated that using context improves the macro-average F1-score by 0.20 and accuracy by over 20% compared to the machine learning model without context.