Saccadic eye movements estimate prolonged time awake

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.

Novel methods for elucidating modality importance in multimodal electrophysiology classifiers

Introduction

Multimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying explainability methods. This is concerning because explainability is vital to the development and implementation of clinical classifiers. As such, new multimodal explainability methods are needed.

Methods

In this study, we train a convolutional neural network for automated sleep stage classification with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global explainability approach that is uniquely adapted for electrophysiology analysis and compare it to an existing approach. We present the first two local multimodal explainability approaches. We look for subject-level differences in the local explanations that are obscured by global methods and look for relationships between the explanations and clinical and demographic variables in a novel analysis.

Results

We find a high level of agreement between methods. We find that EEG is globally the most important modality for most sleep stages and that subject-level differences in importance arise in local explanations that are not captured in global explanations. We further show that sex, followed by medication and age, had significant effects upon the patterns learned by the classifier.

Discussion

Our novel methods enhance explainability for the growing field of multimodal electrophysiology classification, provide avenues for the advancement of personalized medicine, yield unique insights into the effects of demographic and clinical variables upon classifiers, and help pave the way for the implementation of multimodal electrophysiology clinical classifiers.

Human Alertness Optimization with a Three-Process Dynamic Model

Circadian rhythm is an important biological process for humans as it modulates a wide range of physiological processes, including body temperature, sleep-wake cycle, and cognitive performance. As the most powerful external stimulus of circadian rhythm, light has been studied as a zeitgeber to regulate the circadian phase and sleep. This paper addresses the human alertness optimization problem, by optimizing light exposure and sleep schedules to relieve fatigue and cognitive impairment, in cases of night-shift workers and subjects with certain mission periods based on dynamics of the circadian rhythm system. A three-process hybrid dynamic model is used for simulating the circadian rhythm and predicting subjective alertness and sleepiness. Based on interindividual difference in sleep type and living habits, we propose a tunable sleep schedule in the alertness optimization problem, which allows the appropriate tuning of sleep and wake times based on sleep propensity. Variational calculus is applied to evaluate the impacts of light and sleep schedules on the alertness and a gradient descent algorithm is proposed to determine the optimal solutions to maximize the alertness level in various cases. Numerical simulation results demonstrate that the cognitive performance during certain periods can be significantly improved by optimizing the light input and tuning sleep/wake times compared to empirical data.