Conditioning to true content and artificial intelligence in psychophysiological intention recognition

OBJECTIVE

The objective is to introduce a novel method for classical conditioning to true content (CtTC), and for the first time, apply this approach in the concealed information test (CIT) to effectively discern intentions. During CtTC, participants are trained to exhibit electrodermal responses whenever they recognize true content on a screen. Additionally, the objective is to evaluate a novel CIT-dataset preprocessing algorithm, employed to enhance machine learning (ML) classification performance.

METHODS

A total of 84 participants were evenly divided into four groups. Two groups of participants devised plans for stealing money from a supermarket, while the other two groups did not engage in any planning. One planning group and one non-planning group underwent CIT examination, while the remaining groups were subjected to CtTC.

RESULTS

The CIT accuracy initially stood at 52 % and increased to 71 % after Z-score and ML classification (McNemar test, p < 0.05). Conversely, the CtTC accuracy was 76 % and significantly improved to 93 % following Z-score and 95 % following ML classification (McNemar test, p < 0.05). In the best-performing classifiers, CtTC exhibited significantly superior metrics for guilty/innocent classification compared to CIT (Fisher's exact test, p < 0.05, power 1 - β > 0.90). In the CtTC group, reactivity and sensitivity significantly increased, indicated by higher EDR amplitudes (p < 0.05, two-tailed t-test, power 1 - β = 0.89) and the number of EDRs (p < 0.05, Fisher's exact test, power 1 - β = 0.90). There was no statistically significant difference between the Z-score and ML classification.

CONCLUSIONS

In the assessment of intentions, CtTC enhances both the sensitivity and accuracy of the CIT.

Evaluation of bicyclist physiological response and visual attention in commercial vehicle loading zones

INTRODUCTION

With growing freight operations throughout the world, there is a push for transportation systems to accommodate trucks during loading and unloading operations. Currently, many urban locations do not provide loading and unloading zones, which results in trucks parking in places that obstruct bicyclist's roadway infrastructure (e.g., bicycle lanes).

METHOD

To understand the implications of these truck operations, a bicycle simulation experiment was designed to evaluate the impact of commercial vehicle loading and unloading activities on safe and efficient bicycle operations in a shared urban roadway environment. A fully counterbalanced, partially randomized, factorial design was chosen to explore three independent variables: commercial vehicle loading zone (CVLZ) sizes with three levels (i.e., no CVLZ, Min CVLZ, and Max CVLZ), courier position with three levels (i.e., no courier, behind the truck, beside the truck), and with and without loading accessories. Bicyclist's physiological response and eye tracking were used as performance measures. Data were obtained from 48 participants, resulting in 864 observations in 18 experimental scenarios using linear mixed-effects models (LMM).

RESULTS

Results from the LMMs suggest that loading zone size and courier position had the greatest effect on bicyclist's physiological responses. Bicyclists had approximately two peaks-per-minute higher when riding in the condition that included no CVLZ and courier on the side compared to the base conditions (i.e., Max CVLZ and no courier). Additionally, when the courier was beside the truck, bicyclist's eye fixation durations (sec) were one (s) greater than when the courier was located behind the truck, indicating that bicyclists were more alert as they passed by the courier. The presence of accessories had the lowest influence on both bicyclists' physiological response and eye tracking measures.

PRACTICAL APPLICATIONS

These findings could support better roadway and CVLZ design guidelines, which will allow our urban street system to operate more efficiently, safely, and reliable for all users.

Wireless, continuous monitoring of daily stress and management practice via soft bioelectronics

Stress has become a significant factor, directly affecting human health. Due to the numerous sources of stress that are inevitable in daily life, effective management of stress is essential to maintain a healthy life. Recent advancements in wearable devices allow monitoring stress levels via the detection of galvanic skin response on the skin. Some of these devices show the capability of assessing stress relief methods. However, prior works have been limited in a controlled laboratory setting with a short period assessment (<1 h) of stress intervention. The existing systems' main issues include motion artifacts and discomfort caused by rigid and bulky electronics and mandatory device connection on active fingers. Here, we introduce soft, wireless, skin-like electronics (SKINTRONICS) that offers continuous, portable daily stress and management practice monitoring. The ultrathin, lightweight, all-in-one device captures the change of a subject's stress over six continuous hours during everyday activities, including desk work, cleaning, and resting. At the same time, the SKINTRONICS proves that typical stress alleviation methods (mindfulness and meditation) can reduce stress levels, even in the middle of the day, which is supported by statistical analysis. The low-profile, wireless, gel-free device shows enhanced breathability and minimized motion artifacts compared to a commercial stress monitor. Collectively, this study shows the first demonstration of soft, nanomembrane bioelectronics for long-term, continuous assessment of stress and intervention effectiveness throughout daily life.

Complexity-based decoding of brain-skin relation in response to olfactory stimuli

BACKGROUND AND OBJECTIVE

Human body is covered with skin in different parts. In fact, skin reacts to different changes around human. For instance, when the surrounding temperature changes, human skin will react differently. It is known that the activity of skin is regulated by human brain. In this research, for the first time we investigate the relation between the activities of human skin and brain by mathematical analysis of Galvanic Skin Response (GSR) and Electroencephalography (EEG) signals.

METHOD

For this purpose, we employ fractal theory and analyze the variations of fractal dimension of GSR and EEG signals when subjects are exposed to different olfactory stimuli in the form of pleasant odors.

RESULTS

Based on the obtained results, the complexity of GSR signal changes with the complexity of EEG signal in case of different stimuli, where by increasing the molecular complexity of olfactory stimuli, the complexity of EEG and GSR signals increases. The results of statistical analysis showed the significant effect of stimulation on variations of complexity of GSR signal. In addition, based on effect size analysis, fourth odor with greatest molecular complexity had the greatest effect on variations of complexity of EEG and GSR signals.

CONCLUSION

Therefore, it can be said that human skin reaction changes with the variations in the activity of human brain. The result of analysis in this research can be further used to make a model between the activities of human skin and brain that will enable us to predict skin reaction to different stimuli.

An improved algorithm for model-based analysis of evoked skin conductance responses

•

We improve predictive validity of a general linear convolution method to analyse evoked SCR.

•

A constrained individual response function provides highest predictive validity.

•

This IRF is realised by a canonical SCRF together with its time derivative.

•

A high pass filter of 0.05 Hz cut-off frequency is optimal for analysis.

•

Non-linear models better reconstruct the observed time-series but have lower predictive validity.

Model-based analysis of psychophysiological signals is more robust to noise – compared to standard approaches – and may furnish better predictors of psychological state, given a physiological signal. We have previously established the improved predictive validity of model-based analysis of evoked skin conductance responses to brief stimuli, relative to standard approaches. Here, we consider some technical aspects of the underlying generative model and demonstrate further improvements. Most importantly, harvesting between-subject variability in response shape can improve predictive validity, but only under constraints on plausible response forms. A further improvement is achieved by conditioning the physiological signal with high pass filtering. A general conclusion is that precise modelling of physiological time series does not markedly increase predictive validity; instead, it appears that a more constrained model and optimised data features provide better results, probably through a suppression of physiological fluctuation that is not caused by the experiment.