Human cognitive capabilities are under constant pressure in the modern information society. Cognitive load detection would be beneficial in several applications of human–computer interaction, including attention management and user interface adaptation. However, current research into accurate and real-time biosignal-based cognitive load detection lacks understanding of the optimal and minimal window length in data segmentation which would allow for more timely, continuous state detection. This study presents a comparative analysis of ultra-short (30 s or less) window lengths in cognitive load detection with a wearable device. Heart rate, heart rate variability, galvanic skin response, and skin temperature features are extracted at six different window lengths and used to train an Extreme Gradient Boosting classifier to detect between cognitive load and rest. A 25 s window showed the highest accury (67.6%), which is similar to earlier studies using the same dataset. Overall, model accuracy tended to decrease as the window length decreased, and lowest performance (60.0%) was observed with a 5 s window. The contribution of different physiological features to the classification performance and the most useful features that react in short windows are also discussed. The analysis provides a promising basis for future real-time applications with wearable sensors.

Prolonged work stress has an extensive negative impact on modern society. Recently, it has become an increasing issue, specifically in cognitively demanding knowledge-intensive professions. To address the global necessity of timely detection and reduction of work stress, sensor-based automated methods for measuring stress are emerging. Physiological and behavioral sensor data enable the potential for continuous stress detection, but challenges still exist concerning the effort required from the user and the sufficiency of available information, especially for models that want to adapt to personal traits and stress perceptions. This survey paper focuses on sensor-based stress recognition enabling continuous unobtrusive stress monitoring in the knowledge work environment, with a user acceptance and load suitable for sustainable long-term adoption. We provide an overview of the theoretical background of work stress and review the recent developments of sensor-based stress assessment, emphasizing real-world studies using physiological, behavioral, and environmental data. In addition, we discuss the applicability and challenges of different monitoring methods, including user acceptance. The presented survey provides insights into automating the assessment of work stress and related factors to advance the development of personalized well-being solutions based on pervasive data.

Introduction: Current stress detection methods concentrate on identification of stress and non-stress states despite the existence of various stress types. The present study performs a more specific, explainable stress classification, which could provide valuable information on the physiological stress reactions.Methods: Physiological responses were measured in the Maastricht Acute Stress Test (MAST), comprising alternating trials of cold pressor (inducing physiological stress and pain) and mental arithmetics (eliciting cognitive and social-evaluative stress). The responses in these subtasks were compared to each other and to the baseline through mixed model analysis. Subsequently, stress type detection was conducted with a comprehensive analysis of several machine learning components affecting classification. Finally, explainable artificial intelligence (XAI) methods were applied to analyze the influence of physiological features on model behavior.Results: Most of the investigated physiological reactions were specific to the stressors, and the subtasks could be distinguished from baseline with up to 86.5% balanced accuracy. The choice of the physiological signals to measure (up to 25%-point difference in balanced accuracy) and the selection of features (up to 7%-point difference) were the two key components in classification. Reflection of the XAI analysis to mixed model results and human physiology revealed that the stress detection model concentrated on physiological features relevant for the two stressors.Discussion: The findings confirm that multimodal machine learning classification can detect different types of stress reactions from baseline while focusing on physiologically sensible changes. Since the measured signals and feature selection affected classification performance the most, data analytic choices left limited input information uncompensated.

Human physiology and reactions to external stimuli differ between individuals. Researchers have developed strategies to adapt to these differences but the adaptations generally require data from each individual beforehand. A cold-start occurs when there is no data from a new individual. To address this, current study proposes user calibration which uses short segments of easily obtainable baseline data to adapt to new individuals. Experiments were conducted on two public stress and affect detection datasets, WESAD and SWELL-KW, to assess the effectiveness of the proposed calibration method and to determine suitable duration of the baseline measurement. Results showed that user calibration always beat the non-personalized model and segments of 3-8 minutes seemed to be most promising to consider for future use.

This paper presents a novel approach of an ECG-based mental health biometric system that relies on ultra-short duration (2 seconds) of one-channel ECG signal segments from acute stress data for accurate user identification and authentication. The proposed method uses a simple framework for contrastive learning (SimCLR) to train the user identification and authentication models. The performance of the proposed ECG-based biometric system was evaluated for a single-session use case using an in-house dataset. The dataset consisted of ECG signals acquired during a study protocol designed to induce physical and mental stress. The proposed biometric system was able to achieve an accuracy of 98% for user identification and an equal error rate (EER) of 0.02 when trained and tested with a balanced condition with stress and baseline/recovery. Our proposed system was able to retain its accuracy to 95% and the EER to 0.05 even when the training size was significantly reduced.