An Automatic Lie Detection Model Using EEG Signals Based on the Combination of Type 2 Fuzzy Sets and Deep Graph Convolutional Networks.

In recent decades, many different governmental and nongovernmental organizations have used lie detection for various purposes, including ensuring the honesty of criminal confessions. As a result, this diagnosis is evaluated with a polygraph machine. However, the polygraph instrument has limitations and needs to be more reliable. This study introduces a new model for detecting lies using electroencephalogram (EEG) signals. An EEG database of 20 study participants was created to accomplish this goal. This study also used a six-layer graph convolutional network and type 2 fuzzy (TF-2) sets for feature selection/extraction and automatic classification. The classification results show that the proposed deep model effectively distinguishes between truths and lies. As a result, even in a noisy environment (SNR = 0 dB), the classification accuracy remains above 90%. The proposed strategy outperforms current research and algorithms. Its superior performance makes it suitable for a wide range of practical applications.

Health-related quality of life in Iranian adolescents: a psychometric evaluation of the self-report form of the PedsQL 4.0 and an investigation of gender and age differences.

BACKGROUND: Research on the psychometric properties of the Persian self-report form of the Pediatric Quality of Life Inventory Version 4.0 (PedsQL 4.0) in adolescents has several gaps (e.g., convergent validity) that limit its clinical application and therefore the cross-cultural impact of this measure. This study aimed at investigating the psychometric properties of the PedsQL 4.0 and the effects of gender and age on quality of life in Iranian adolescents. METHOD: The PedsQL 4.0 was administered to 326 adolescents (12-17 years). A subsample of 115 adolescents completed the scale two weeks after the first assessment. Confirmatory Factor Analysis (CFA), correlation of the PedsQL 4.0 with the Weiss Functional Impairment Rating Scale-Self-report (WFIRS-S), and Item Response Theory (IRT) analysis were conducted to examine validity. Cronbach's alpha, McDonald's Omega, and Intra class correlation (ICC) were calculated as well to examine reliability. Gender and age effects were also evaluated. RESULTS: Internal consistency and test-retest reliability of the total PedsQL 4.0 scale was .92 and .87, respectively. The PedsQL 4.0 scores showed negative moderate to strong correlations with the WFIRS-S total scale. The four-factor model of the PedsQL 4.0 was not fully supported by the CFA-the root mean square error of approximation and the comparative fit index showed a mediocre and poor fit, respectively. IRT analysis indicated that all items of the PedsQL 4.0 fit with the scale and most of them showed good discrimination. The items and total scale provided more information in the lower levels of the latent trait. Males showed significantly higher scores than females in physical and emotional functioning, psychosocial health, and total scale. Adolescents with lower ages showed better quality of life than those with higher ages in all scores of the PedsQL 4.0. CONCLUSION: The PedsQL 4.0 showed good psychometric properties with regard to internal consistency, test-retest reliability, and convergent validity in Iranian adolescents, which supports its use in clinical settings among Persian-speaking adolescents. However, factor structure according to our CFA indicates that future work should address how to improve fit. In addition, studies that include PedsQL 4.0 should consider gender and age effects were reported.