Johanna Närväinen

Despite growing interest in monitoring cognitive states, current studies inadequately address individual differences in physiological reactions. Whereas prior works require extensive data from each individual to personalize the model, the current article explores personalization approaches operating with minimal baseline data. We propose three novel methods to personalize the model with only baseline data available for personalization. Further, we systematically compare those to an existing baseline calibration method, a non-personalized model, and a model using all available data for personalization. We conduct experiments with four open datasets with a total of 170 participants, classifying the cognitive states with a prevalent feature-based approach and a recent large time-series foundation model, MOMENT. The experiments target stress and cognitive load detection in realistic classification tasks, which require models to adapt to a new person. The best classification scores after personalizing with minimal data were around 0.7−0.9 and 0.7 balanced accuracy in binary and three-class tasks, respectively. Two of the proposed personalization methods outperformed the non-personalized model in most cases with the feature-based approach, especially in classification tasks with more than two classes, although their performance remained lower than that of the model using all data for personalization. MOMENT showed little benefit from personalization and performed comparably to the feature-based approach even with a non-personalized model. The findings provide a critical overview of the generalizability and necessity of model personalization with little data, and valuable insights into the development of personalized cognition-aware applications.

This study explores how the Finnish concept of "sisu," denoting perseverance and inner strength in the face of adversity, manifests in the daily states. Moreover, the associations between beneficial and harmful sisu and positive and negative affectivity, which have implications for well-being and personality, were examined. Data was collected from 82 knowledge workers in four Finnish organizations, utilizing the Sisu Scale to assess beneficial and harmful sisu. Participants evaluated their sisu-related states and affectivity daily for three weeks using a mobile application. Multilevel modeling was employed to analyze the associations between sisu traits, sisu-related states, and affects, controlling for age and sex. Results indicate that high beneficial sisu is associated with increased determination, feelings of control, and positive affect. On the other hand, harmful sisu is linked to accepting overly challenging tasks, getting stuck on unproductive activities, and persisting in mundane tasks. High harmful sisu is also associated with decreased satisfaction and feelings of control. The findings illustrate how sisu manifests in everyday life, and indicate the significance of affective states in the expression of mental fortitude. It also seems that sisu plays a role in facing everyday challenges despite its traditional association with major adversities in the Finnish language. Further research is required to explore sisu-situation interactions and the role of negative affectivity in sisu.

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.

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.

We present a novel application of contrastive learning technique in learning the feature representation of ECG signal in a self-supervised manner for the classification of acute stress types. Acute stress types that occur for a very short period and are rapidly changing and alternating in nature are difficult to classify using conventional ECG features. This is because the change in conventional ECG features due to rapid and alternating acute stressors do not reflect instantaneously. We hypothesize that deep-learned features from ECG signals can better distinguish between the different stress types than conventional ECG features. Our proposed approach can generate distinct feature representations for the physical and mental stress task type using very short window lengths. Our results show that the deep-learned features perform better in terms of accuracy and F1 score in distinguishing between physical and mental stress task types. In the future, our proposed method can be used in a real world setting for understanding the dynamics of different stressors in a self-supervised fashion without the need for human labeling.

Easier recognition and enhanced visibility of healthy options supposedly increase healthy choices, but real-world evidence remains scarce. Addressing this knowledge gap, we promoted nutritionally favourable foods in a workplace cafeteria with three choice-architectural strategies—priming posters, point-of-choice nutrition labels, and improved product placement—and assessed their effects on visual attention, food choices, and food consumption. Additionally, we developed a method for analysing real-world eye-tracking data. The study followed a pretest–posttest design whereby control and intervention condition lasted five days each. We monitored visual attention (i.e., total number and duration of fixations) and food choices with eye tracking, interviewed customers about perceived influences on food choices, and measured cafeteria-level food consumption (g). Individual-level data represents 22 control and 19 intervention participants recruited at the cafeteria entrance. Cafeteria-level data represents food consumption during the trial (556/589 meals sold). Results indicated that the posters and labels captured participants’ visual attention (~13% of fixations on defined areas of interest before food choices), but the intervention had insignificant effects on visual attention to foods, on food choices, and on food consumption. Interviews revealed 17 perceived influences on food choices, the most common being sensory appeal, healthiness, and familiarity. To conclude, the intervention appeared capable of attracting visual attention, yet ineffective in increasing healthier eating. The developed method enabled a rigorous analysis of visual attention and food choices in a natural choice setting. We discuss ways to boost the impact of the intervention on behaviour, considering target groups’ motives. The work contributes with a unique, mixed-methods approach and a real-world setting that enabled a multi-dimensional effects evaluation with high external validity.

The aim was to create and study a possible behavioural measure for trait(s) in humans that reflect the ability and motivation to continue an unpleasant behaviour, i.e., behavioural perseverance or persistence (BP). We utilised six different tasks with 54 subjects to measure the possible BP trait(s): cold pressor task, hand grip endurance task, impossible anagram task, impossible verbal reasoning task, thread and needle task, and boring video task. The task performances formed two BP factors. Together, the two-factor solution is responsible for the common variance constituting 37.3% of the total variance in the performances i.e., performance times. Excluding the impossible anagram task, the performance in any given task was better explained by performances in the other tasks (i.e., “trait”, η² range = 0.131–0.253) than by the rank order variable (“depletion”, i.e., getting tired from the previous tasks, η2 range = 0–0.096).