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.

The P300 and MFN as indicators of concealed knowledge in situations with negative and positive moral valence

Many studies on concealed knowledge involve mock-thefts. The present study compares ERPs of participants concealing knowledge of a morally negative behavior (mock-theft) with ERPs of participants concealing knowledge of a morally positive behavior. Some participants (n= 33) stole a candy box out of an office, whereas others (n= 28) put the candy box into an office as a present. During a concealed information test, participants concealed knowledge of the candy box and a key they had seen in the office (probe stimuli) and honestly indicated not knowing similar irrelevant stimuli. P300s were enlarged for probe, compared to irrelevant stimuli in both conditions, revealing that probe stimuli were more salient than irrelevant stimuli regardless of their moral valence. Likewise, medial frontal negativities were enlarged for probe versus irrelevant stimuli in both conditions, indicating response conflicts when answering deceptively to probe items in both situations.

Hierarchical Bayesian models for the autonomic-based concealed information test

The concealed information test (CIT) is a psychophysiological memory detection technique for examining whether an examinee recognizes crime-relevant information. In current statistical analysis practice, the autonomic responses are usually transformed into Z scores within individuals to remove inter- and intra-individual variability. However, this conventional procedure leads to overestimation of the effect size, specifically the standardized mean difference of the autonomic responses between the crime-relevant information and the crime-irrelevant information. In this study, we attempted to resolve this problem by modeling inter- and intra-individual variability directly using hierarchical Bayesian modeling. Five models were constructed and applied to CIT data obtained from 167 participants. The validity of the CIT was confirmed using Bayesian estimates of the effect sizes, which are more accurate and interpretable than conventional effect sizes. Moreover, hierarchical Bayesian modeling provided information that is not available from the conventional statistical analysis procedure.

Motivational significance and cognitive effort elicit different late positive potentials

OBJECTIVE

The interaction between affective and cognitive processes has been examined using the late positive potential (LPP) component of the event-related brain potential. The LPP is elicited not only by affective stimuli but also by nonaffective stimuli that require effortful cognitive processing. However, it is unclear whether these LPPs are equivalent. The present study decomposed the LPP into subcomponents that responded differently to affective content and cognitive demands.

METHODS

The participants (N=21) performed four types of revised oddball tasks, in which one affective and five nonaffective pictures were presented. For one of the nonaffective pictures, different cognitive demands were loaded: viewing the display, updating a count, updating two different items, or concealing knowledge of the picture.

RESULTS

A temporal-spatial principal component analysis revealed two major subcomponents of the LPP. The central-parietal subcomponent was elicited by affective stimuli, whereas the occipital subcomponent was elicited by nonaffective stimuli with cognitive demands in the two-item updating and concealment conditions.

CONCLUSIONS

The results suggest that the central-parietal dominant LPP may reflect motivated attentional processing, whereas the occipital dominant LPP may reflect effortful controlled processing.

SIGNIFICANCE

Dealing with these two LPP subcomponents separately may be useful for examining the interaction between affective and cognitive processing of stimuli.

A comment on Farwell (2012): brain fingerprinting: a comprehensive tutorial review of detection of concealed information with event-related brain potentials

In a recent issue of Cognitive Neurodynamics Farwell (Cogn Neurodyn 6:115-154, 2012) published a comprehensive tutorial review of the use of Event Related Brain Potentials (ERP) in the detection of concealed information. Farwell's review covered much of his own work employing his "brain fingerprinting" technology. All his work showed a 100 % accuracy rate in detecting concealed information. We argue in this comment that Farwell (Cogn Neurodyn 6:115-154, 2012) is misleading and misrepresents the scientific status of brain fingerprinting technology.