Investigation of different ML approaches in classification of emotions induced by acute stress.

Background: Machine learning is becoming a common tool in monitoring emotion. However, methodological studies of the processing pipeline are scarce, especially ones using subjective appraisals as ground truth. New method: A novel protocol was used to induce cognitive load and physical discomfort, and emotional dimensions (arousal, valence, and dominance) were reported after each task. The performance of five common ML models with a versatile set of features (physiological features, task performance data, and personality trait) was compared in binary classification of subjectively assessed emotions. Results: The psychophysiological responses proved the protocol was successful in changing the mental state from baseline, also the cognitive and physical tasks were different. The optimization and performance of ML models used for emotion detection were evaluated. Additionally, methods to account for imbalanced classes were applied and shown to improve the classification performance. Comparison with existing methods: Classification of human emotional states often assumes the states are determined by the stimuli. However, individual appraisals vary. None of the past studies have classified subjective emotional dimensions with a set of features including biosignals, personality and behavior. Conclusion: Our data represent a typical setup in affective computing utilizing psychophysiological monitoring: N is low compared to number of features, inter-individual variability is high, and class imbalance cannot be avoided. Our observations are a) if possible, include features representing physiology, behavior and personality, b) use simple models and limited number of features to improve interpretability, c) address the possible imbalance, d) if the data size allows, use nested cross-validation.

Multiomics and digital monitoring during lifestyle changes reveal independent dimensions of human biology and health.

We explored opportunities for personalized and predictive health care by collecting serial clinical measurements, health surveys, genomics, proteomics, autoantibodies, metabolomics, and gut microbiome data from 96 individuals who participated in a data-driven health coaching program over a 16-month period with continuous digital monitoring of activity and sleep. We generated a resource of >20,000 biological samples from this study and a compendium of >53 million primary data points for 558,032 distinct features. Multiomics factor analysis revealed distinct and independent molecular factors linked to obesity, diabetes, liver function, cardiovascular disease, inflammation, immunity, exercise, diet, and hormonal effects. For example, ethinyl estradiol, a common oral contraceptive, produced characteristic molecular and physiological effects, including increased levels of inflammation and impact on thyroid, cortisol levels, and pulse, that were distinct from other sources of variability observed in our study. In total, this work illustrates the value of combining deep molecular and digital monitoring of human health. A record of this paper's transparent peer review process is included in the supplemental information.

Metabolic state as a modulator of neural event-related potentials for food stimuli in an implicit association test.

The Implicit Association Test (IAT) has become a ubiquitous measure of implicit associations or preferences in several fields of research, including research related to food choices. The neural dynamics of the IAT have been explored in several contexts, but in a food-related IAT with stimuli of natural motivational value they are yet to be studied. Additionally, the effect of metabolic state on them is poorly known. The present study examined the event-related potentials (ERP) in healthy non-obese females (n = 32) while they performed a food-related IAT in two sessions, in a fasted state and after a meal. The results showed differences in the ERP components N400, P3 and LPP by congruence categories. Additionally, the individual N400 and LPP deflections correlated strongly with individual IAT effects. ERP deflections were weaker in the fasted state than after the meal despite greater implicit hedonic motivation towards food in the fasted state. In conclusion, the results suggest that ERPs reflect the IAT effect. The N400, P3 and LPP components were evoked in a food-related IAT in a similar way observed in IAT tests in other contexts, reflecting a difference in meaning and motivation between congruence categories. The strong correlations of individual IAT effect with individual N400 and LPP deflections further suggests that the food-related IAT effect strength reflects the size of implicit food bias seen in neural deflections. Moreover, fasting increased implicit hedonic motivation towards food, but likely reduced cognitive resources at the same time. This could have made it harder to determine the value of novel, task-relevant stimuli, whereas it became easier postprandially and with practice.

Accelerometry-based berg balance scale score estimation.

The objective of the study was to investigate the validity of 3-D-accelerometry-based Berg balance scale (BBS) score estimation. In particular, acceleration patterns of BBS tasks and gait were the targets of analysis. Accelerations of the lower back were measured during execution of the BBS test and corridor walking for 54 subjects, consisting of neurological patients, older adults, and healthy young persons. The BBS score was estimated from one to three BBS tasks and from gait-related data, separately, through assessment of the similarity of acceleration patterns between subjects. The work also validated both approaches' ability to classify subjects into high- and low-fall-risk groups. The gait-based method yielded the best BBS score estimates and the most accurate BBS-task-based estimates were produced with the stand to sit, reaching, and picking object tasks. The proposed gait-based method can identify subjects with high or low risk of falling with an accuracy of 77.8% and 96.6%, respectively, and the BBS-task based method with corresponding accuracy of 89.5% and 62.1%.

Human balance estimation using a wireless 3D acceleration sensor network.

Balance and gait are a consequence of complex coordination between muscles, nerves, and central nervous system structures. The impairment of these functions can pose serious threats to independent living, especially in the elderly. This study was carried out to evaluate the performance of a wireless acceleration sensor network and its capability in balance estimation. The test has been carried out in eight patients and seven healthy controls. The Patients group had larger values in lateral amplitudes of the sensor displacement and smaller values in vertical displacement amplitudes of the sensor. The step time variations for the Patients were larger than those for the controls. A fuzzy logic and clustering classifiers were implemented, which gave promising results suggesting that a person with balance deficits can be recognized with this system. We conclude that a wireless system is easier to use than a wired one and more unobtrusive to the user.