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 - ß > 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 - ß = 0.89) and the number of EDRs (p < 0.05, Fisher's exact test, power 1 - ß = 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.

Interactive slide selection algorithm and machine learning in psychophysiological memory testing.

Objective. To present a new type of concealed information test (CIT) that implements the interactive slide selection (ISS) algorithm and compare its effectiveness with a standard CIT (sCIT).Approach. The ISS algorithm presents slides interactively, based on the analysis of electrodermal activity, while sCIT presents slides in a predefined, sequential order. The algorithm automatically selects irrelevant, relevant, and control slides and presents them at the moment which is physiologically most suitable for electrodermal response detection. To compare the ISS-based CIT (issCIT) and sCIT, two objects, a bag, and a wallet, were presented to 64 participants, 32 of whomwere analyzed with sCIT, and another 32 with issCIT.Main results. The results show that ISS had significantly better true/false predictions (Fisher's exact test,p< 0.01). Also, the number of false positives (FPs) was significantly lower in the issCIT group in comparison with sCIT (Fisher's exact test,p< 0.001). Machine learning (ML) classifiers improved precision from 49% to 79% in the sCIT group (McNemar's test,p< 0.05), and from 85% to 100% in the issCIT group (McNemar's test,p< 0.05). The testing time in the issCIT group ranged between 42 and 107 s, while the average was 53 s. In the sCIT group, the testing time was always 330 s.Significance. Under the presented experimental settings, the ISS algorithm obtained significantly better classification results compared to sCIT, while the application of the ML algorithms managed to improve the classification results in both groups reaching a precision of 100%. The ISS algorithm allowed for a much shorter testing time compared to sCIT.