Machine learning-based classifying of risk-takers and risk-aversive individuals using resting-state EEG data: A pilot feasibility study

BACKGROUND

Decision-making is vital in interpersonal interactions and a country's economic and political conditions. People, especially managers, have to make decisions in different risky situations. There has been a growing interest in identifying managers' personality traits (i.e., risk-taking or risk-averse) in recent years. Although there are findings of signal decision-making and brain activity, the implementation of an intelligent brain-based technique to predict risk-averse and risk-taking managers is still in doubt.

METHODS

This study proposes an electroencephalogram (EEG)-based intelligent system to distinguish risk-taking managers from risk-averse ones by recording the EEG signals from 30 managers. In particular, wavelet transform, a time-frequency domain analysis method, was used on resting-state EEG data to extract statistical features. Then, a two-step statistical wrapper algorithm was used to select the appropriate features. The support vector machine classifier, a supervised learning method, was used to classify two groups of managers using chosen features.

RESULTS

Intersubject predictive performance could classify two groups of managers with 74.42% accuracy, 76.16% sensitivity, 72.32% specificity, and 75% F1-measure, indicating that machine learning (ML) models can distinguish between risk-taking and risk-averse managers using the features extracted from the alpha frequency band in 10 s analysis window size.

CONCLUSIONS

The findings of this study demonstrate the potential of using intelligent (ML-based) systems in distinguish between risk-taking and risk-averse managers using biological signals.

Neural activity in self-identified claustrophobic individuals under in-vivo stimuli: A human electroencephalography dataset

The electrocortical activity in claustrophobic situations is a very limited field of study and has recently caught researchers' attention. This article represents a set of electroencephalographic (EEG) data obtained from twenty-two participants. The volunteers include 9 participants with self-identified claustrophobia and 13 healthy controls under in-vivo stimuli. The EEG data were recorded using Mitsar 31-channel EEG system. Before cortical signal recording, Individuals were asked to identify themselves as healthy controls or claustrophobic participants. The EEG data collection process consisted of three experimental conditions. In all conditions, the participants were asked to stay calm and keep their eyes open. The first experimental condition was at seated resting state in a relatively large and well-lit laboratory (8m × 15m) area. In the second experimental condition, the subjects entered a moderately-lit chamber and repeated the previous resting situation. The final condition of the EEG data acquisition was performed in the same chamber but with reduced dimensions. For each experimental condition, duration of data collection was approximately 300 s. This data can be used to understand the brain's response in claustrophobic situations through various statistical or data-driven methods.

Electroencephalographic Activity in Patients with Claustrophobia: A Pilot Study

Background

Exposure to small confined spaces evokes physiological responses such as increased heart rate in claustrophobic patients. However, little is known about electrocortical activity while these people are functionally exposed to such phobic situations. The aim of this study was to examine possible changes in electrocortical activity in this population.

Method

Two highly affected patients with claustrophobia and two healthy controls participated in this in vivo study during which electroencephalographic (EEG) activity was continuously recorded. Relative power spectral density (rPSD) was compared between two situations of being relaxed in a well-lit open area, and sitting in a relaxed chair in a small (90 cm × 180 cm × 155 cm) chamber with a dim light. This comparison of rPSDs in five frequency bands of EEG was intended to investigate possible patterns of change in electrical activity during fear-related situation. This possible change was also compared between claustrophobic patients and healthy controls in all cortical areas.

Results

Statistical models showed that there is a significant interaction between groups of participants and experimental situations in all frequency bands (P < 0.01). In other words, claustrophobic patients showed significantly different changes in electrical activity while going from rest to the test situation. Clear differences were observed in alpha and theta bands. In the theta band, while healthy controls showed an increase in rPSD, claustrophobic patients showed an opposite decrease in the power of electrical activity when entering the confined chamber. In alpha band, both groups showed an increase in rPSD, though this increase was significantly higher for claustrophobic patients.

Conclusion

The effect of in vivo exposure to confined environments on EEG activity is different in claustrophobic patients than in healthy controls. Most of this contrast is observed in central and parietal areas of the cortex, and in the alpha and theta bands.

Objective assessment of spasticity by pendulum test: a systematic review on methods of implementation and outcome measures

Background

Instrumented pendulum test is an objective and repeatable biomechanical method of assessment for spasticity. However, multitude of sensor technologies and plenty of suggested outcome measures, confuse those interested in implementing this method in practice. Lack of a standard agreement on the definition of experimental setup and outcome measures adds to this ambiguity and causes the results of one study not to be directly attainable by a group that uses a different setup. In this systematic review of studies, we aim to reduce the confusion by providing pros and cons of the available choices, and also by standardizing the definitions.

Methods

A literature search was conducted for the period of 1950 to the end of 2019 on PubMed, Science Direct, Google Scholar and IEEE explore; with keywords of “pendulum test” and “Spasticity”.

Results

Twenty-eight studies with instrumented pendulum test for assessment of spasticity met the inclusion criteria. All the suggested methods of implementation were compared and advantages and disadvantages were provided for each sensor technology. An exhaustive list categorized outcome measures in three groups of angle-based, angular velocity-based, and angular acceleration-based measures with all different names and definitions.

Conclusions

With the aim of providing standardized methodology with replicable and comparable results, sources of dissimilarity and ambiguity among research strategies were found and explained with the help of graphical representation of pendulum movement stages and corresponding parameters on the angular waveforms. We hope using the provided tables simplify the choices when implementing pendulum test for spasticity evaluation, improve the consistency when reporting the results, and disambiguate inconsistency in the literature.