Respiratory rate and heart rate variability (HRV) are studied as stress markers in a database of young healthy volunteers subjected to acute emotional stress, induced by a modification of the Trier Social Stress Test. First, instantaneous frequency domain HRV parameters are computed using time-frequency analysis in the classical bands. Then, the respiratory rate is estimated and this information is included in HRV analysis in two ways: 1) redefining the high-frequency (HF) band to be centered at respiratory frequency; 2) excluding from the analysis those instants where respiratory frequency falls within the low-frequency (LF) band. Classical frequency domain HRV indices scarcely show statistical differences during stress. However, when including respiratory frequency information in HRV analysis, the normalized LF power as well as the LF/HF ratio significantly increase during stress (p-value <; 0.05 according to the Wilcoxon test), revealing higher sympathetic dominance. The LF power increases during stress, only being significantly different in a stress anticipation stage, while the HF power decreases during stress, only being significantly different during the stress task demanding attention. Our results support that joint analysis of respiration and HRV obtains a more reliable characterization of autonomic nervous response to stress. In addition, the respiratory rate is observed to be higher and less stable during stress than during relax (p-value <; 0.05 according to the Wilcoxon test) being the most discriminative index for stress stratification (AUC = 88.2%).

Social and medical problems associated with stress are increasing globally and seriously affect mental health and well-being. However, an effective stress-level monitoring method is still not available. This paper presents a quantitative method for monitoring acute stress levels in healthy young people using biomarkers from physiological signals that can be unobtrusively monitored. Two states were induced to 40 volunteers, a basal state generated with a relaxation task and an acute stress state generated by applying a standard stress test that includes five different tasks. Standard psychological questionnaires and biochemical markers were utilized as ground truth of stress levels. A multivariable approach to comprehensively measure the physiological stress response is proposed using stress biomarkers derived from skin temperature, heart rate, and pulse wave signals. Acute physiological stress levels (total-range 0–100 au) were continuously estimated every 1 min showing medians of 29.06 au in the relaxation tasks, while rising from 34.58 to 47.55 au in the stress tasks. Moreover, using the proposed method, five statistically different stress levels induced by the performed tasks were also measured. Results obtained show that, in these experimental conditions, stress can be monitored from unobtrusive biomarkers. Thus, a more general stress monitoring method could be derived based on this approach.

Objective: Cognitive workload monitoring (CWM) can enhance human-machine interaction by supporting task execution assistance considering the operator's cognitive state. Therefore, we propose a machine learning design methodology and a data processing strategy to enable CWM on resource-constrained wearable devices. Methods: Our CWM solution is built upon edge computing on a simple wearable system, with only four peripheral channels of electroencephalography (EEG). We assess our solution on experimental data from 24 volunteers. Moreover, to overcome the system's memory constraints, we adopt an optimization strategy for model size reduction and a multi-batch data processing scheme for optimizing RAM memory footprint. Finally, we implement our data processing strategy on a state-of-the-art wearable platform and assess its execution and system battery life. Results: We achieve an accuracy of 74.5% and a 74.0% geometric mean between sensitivity and specificity for CWM classification on unseen data. Besides, the proposed model optimization strategy generates a 27.5x smaller model compared to the one generated with default parameters, and the multi-batch data processing scheme reduces RAM memory footprint by 14x compared to a single batch data processing. Finally, our algorithm uses only 1.28% of the available processing time, thus, allowing our system to achieve 28.5 hours of battery life. Conclusion: We provide a reliable and optimized CWM solution using wearable devices, enabling more than a day of operation on a single battery charge. Significance: The proposed methodology enables real-time data processing on resource-constrained devices and supports real-time wearable monitoring based on EEG for applications as CWM in human-machine interaction.

In search and rescue missions, drone operations are challenging and cognitively demanding. High levels of cognitive workload can affect rescuers’ performance, leading to failure with catastrophic outcomes. To face this problem, we propose a machine learning algorithm for real-time cognitive workload monitoring to understand if a search and rescue operator has to be replaced or if more resources are required. Our multimodal cognitive workload monitoring model combines the information of 25 features extracted from physiological signals, such as respiration, electrocardiogram, photoplethysmogram, and skin temperature, acquired in a noninvasive way. To reduce both subject and day inter-variability of the signals, we explore different feature normalization techniques, and introduce a novel weighted-learning method based on support vector machines suitable for subject-specific optimizations. On an unseen test set acquired from 34 volunteers, our proposed subject-specific model is able to distinguish between low and high cognitive workloads with an average accuracy of 87.3% and 91.2% while controlling a drone simulator using both a traditional controller and a new-generation controller, respectively.

Objective: Today, stress monitoring on wearable devices is challenged by the tension between high-detection accuracy and battery lifetime driven by multimodal data acquisition and processing. Limited research has addressed the classification cost on multimodal wearable sensors, particularly when the features are cost-dependent. Thus, we design a Cost-Aware Feature Selection (CAFS) methodology that trades-off between prediction-power and energy-cost for multimodal stress monitoring. Methods: CAFS selects the most important features under different energy-constraints, which allows us to obtain energy-scalable stress monitoring models. We further propose a self-aware stress monitoring method that intelligently switches among the energy-scalable models, reducing energy consumption. Results: Using CAFS methodology on experimental data and simulation, we reduce the energy-cost of the stress model designed without energy constraints up to 94.37%. We obtain 90.98% and 95.74% as the best accuracy and confidence values, respectively, on unseen data, outperforming state-of-the-art studies. Analyzing our interpretable and energy-scalable models, we showed that simple models using only heart rate (HR) or skin conductance level (SCL), confidently predict acute stress for $HR>93.30BPM$ and non-stress for $SCL< 6.42\; \mu S$ , but, outside these values, a multimodal model using respiration and pulse wave’s features is needed for confident classification. Our self-aware acute stress monitoring proposal saves $10\mathbf {x}$ energy and provides 88.72% of accuracy on unseen data. Conclusion: We propose a comprehensive solution for the cost-aware acute stress monitoring design addressing the problem of selecting an optimized feature subset considering their cost-dependency and cost-constraints. Significant: Our design framework enables long-term and confident acute stress monitoring on wearable devices.