A comparison of methods for ERP assessment in a P300-based GKT

Brain Fingerprinting and Lie Detection: A Study of Dynamic Functional Connectivity Patterns of Deception Using EEG Phase Synchrony Analysis

This study investigated the brain functional connectivity (FC) patterns related to lie detection (LD) tasks with the purpose of analyzing the underlying cognitive processes and mechanisms in deception. Using the guilty knowledge test protocol, 30 subjects were divided randomly into guilty and innocent groups, and their electroencephalogram (EEG) signals were recorded on 32 electrodes. Phase synchrony of EEG was analyzed between different brain regions. A few-trials-based relative phase synchrony (FTRPS) measure was proposed to avoid the false synchronization that occurs due to volume conduction. FTRPS values with a significantly statistical difference between two groups were employed to construct FC patterns of deception, and the FTRPS values from the FC networks were extracted as the features for the training and testing of the support vector machine. Finally, four more intuitive brain fingerprinting graphs (BFG) on delta, theta, alpha and beta bands were respectively proposed. The experimental results reveal that deceptive responses elicited greater oscillatory synchronization than truthful responses between different brain regions, which plays an important role in executing lying tasks. The functional connectivity in the BFG are mainly implicated in the visuo-spatial imagery, bottom-top attention and memory systems, work memory and episodic encoding, and top-down attention and inhibition processing. These may, in part, underlie the mechanism of communication between different brain cortices during lying. High classification accuracy demonstrates the validation of BFG to identify deception behavior, and suggests that the proposed FTRPS could be a sensitive measure for LD in the real application.

Brain-based concealed memory detection is driven mainly by orientation to salient items

In the pursuit of new methods for concealed memory detection, event-related potential components (ERP) have been placed at the forefront of research. No method, however, is scientifically complete without a theory and the present study therefore aimed to unravel the cognitive processes underlying these ERPs (i.e., orienting and arousal inhibition). This was accomplished by using a Concealed Information Test (CIT) in which participants were once motivated to conceal and once motivated to reveal their identity. The results showed a similarly strong P3 CIT effect in the two motivational conditions, which was enhanced for high salience compared to low salience identity items. Similar results were observed when using a multivariate machine-learning algorithm - suggesting that brain-based concealed memory detection is driven mainly by orientation to salient stimuli, rather than by arousal inhibition. In addition, the algorithm, trained and tested on the ERPs of different identity items, achieved detection rates exceeding those achieved by the P3. This implies that CIT researchers and practitioners could potentially rely on the entire ERP waveform instead of a-priori selecting separate components. Together these results enrich current understanding of the mechanisms underlying neurophysiological responding to concealed information and pave the way for novel and powerful algorithms which could be used in real-life forensic investigations.

Functional Connectivity Pattern Analysis Underlying Neural Oscillation Synchronization during Deception

To characterize system cognitive processes during deception, event-related coherence was computed to investigate the functional connectivity among brain regions underlying neural oscillation synchronization. In this study, 15 participants were randomly assigned to honesty or deception groups and were instructed to tell the truth or lie when facing certain stimuli. Meanwhile, event-related potential signals were recorded using a 64-channel electroencephalography cap. Event-related coherence was computed separately in four frequency bands (delta (1-3.5 Hz), theta (4-7 Hz), alpha (8-13 Hz), and beta (14-30 HZ)) for the long-range intrahemispheric electrode pairs (F3P3, F4P4, F3T7, F4T8, F3O1, and F4O2). The results indicated that deceptive responses elicited greater connectivities in the frontoparietal and frontotemporal networks than in the frontooccipital network. Furthermore, the deception group displayed lower values of coherence in the frontoparietal electrode pairs in the alpha and beta bands than the honesty group. In particular, increased coherence in the delta and theta bands on specific left frontoparietal electrode pairs was observed. Additionally, the deception group exhibited higher values of coherence in the delta band and lower values of coherence in the beta band on the frontotemporal electrode pairs than did the honesty group. These data indicated that the active cognitive processes during deception include changes in ensemble activities between the frontal and parietal/temporal regions.

Neuroethics of Non-primary Brain Computer Interface: Focus on Potential Military Applications

The field of neuroethics has had to adapt rapidly in the face of accelerating technological advancement; a particularly striking example is the realm of Brain-Computer Interface (BCI). A significant source of funding for the development of new BCI technologies has been the United States Department of Defense, and while the predominant focus has been restoration of lost function for those wounded in battle, there is also significant interest in augmentation of function to increase survivability, coordination, and lethality of US combat forces. While restoration of primary motor and sensory function (primary BCI) has been the main focus of research, there has been marked progress in interface with areas of the brain subserving memory and association. Non-Primary BCI has a different subset of potential applications, each of which also carries its own ethical considerations. Given the amount of BCI research funding coming from the Department of Defense, it is particularly important that potential military applications be examined from a neuroethical standpoint.

Deception Decreases Brain Complexity

Extensive evidence suggests the feasibility of lie detection using electroencephalograms (EEGs). However, it is largely unknown whether there are any differences in the nonlinear features of EEGs between guilty and innocent subjects. In this study, we proposed a complexity-based method to distinguish lying from truth telling. A total of 35 participants were randomly divided into two groups, and their EEG signals were recorded with 14 electrodes. Averages for sequential sets of five trials were first calculated for the probe responses within each subject. Next, a common wavelet entropy (WE) measure and an improved one were used to quantify complexity from each five-trial average. The results show that for both measures, the WE values in the guilty subjects are statistically lower than those in the innocent subjects for most of the 14 electrodes. More importantly, using the improved measure, the difference in WE between the two groups of subjects significantly increases for 11 brain regions compared with the values from the common measure. Finally, the highest balanced classification accuracy, 89.64%, is achieved when using the combined WE feature vector in five brain regions from the sites of Pz, P3, C4, Cz, and C3. Our findings indicate that the lying task elicits a more ordered brain activity in some specific brain regions than the task of telling the truth. This study not only demonstrates that improved WE measurements could be a powerful quantitative index for detecting lying but also sheds light on the brain mechanisms underlying deceptive behaviors.

Lie construction affects information storage under high memory load condition

Previous studies indicate that lying consumes cognitive resources, especially working memory (WM) resources. Considering the dual functions that WM might play in lying: holding the truth-related information and turning the truth into lies, the present study examined the relationship between the information storage and processing in the lie construction. To achieve that goal, a deception task based on the old/new recognition paradigm was designed, which could manipulate two levels of WM load (low-load task using 4 items and high-load task using 6 items) during the deception process. The analyses based on the amplitude of the contralateral delay activity (CDA), a proved index of the number of representations being held in WM, showed that the CDA amplitude was lower in the deception process than that in the truth telling process under the high-load condition. In contrast, under the low-load condition, no CDA difference was found between the deception and truth telling processes. Therefore, we deduced that the lie construction and information storage compete for WM resources; when the available WM resources cannot meet this cognitive demand, the WM resources occupied by the information storage would be consumed by the lie construction.

Reprint of "A new approach to analyze data from EEG-based concealed face recognition system"

The purpose of this study is to extend a feature set with non-linear features to improve classification rate of guilty and innocent subjects. Non-linear features can provide extra information about phase space. The Event-Related Potential (ERP) signals were recorded from 49 subjects who participated in concealed face recognition test. For feature extraction, at first, several morphological characteristics, frequency bands, and wavelet coefficients (we call them basic-features) are extracted from each single-trial ERP. Recurrence Quantification Analysis (RQA) measures are then computed as non-linear features from each single-trial. We apply Genetic Algorithm (GA) to select the best feature set and this feature set is used for classification of data using Linear Discriminant Analysis (LDA) classifier. Next, we use a new approach to improve classification results based on introducing an adaptive-threshold. Results indicate that our method is able to correctly detect 91.83% of subjects (45 correct detection of 49 subjects) using combination of basic and non-linear features, that is higher than 87.75% for basic and 79.59% for non-linear features. This shows that combination of non-linear and basic- features could improve classification rate.

Subject-based discriminative sparse representation model for detection of concealed information

BACKGROUND AND OBJECTIVES

The use of machine learning approaches in concealed information test (CIT) plays a key role in the progress of this neurophysiological field. In this paper, we presented a new machine learning method for CIT in which each subject is considered independent of the others. The main goal of this study is to adapt the discriminative sparse models to be applicable for subject-based concealed information test.

METHODS

In order to provide sufficient discriminability between guilty and innocent subjects, we introduced a novel discriminative sparse representation model and its appropriate learning methods. For evaluation of the method forty-four subjects participated in a mock crime scenario and their EEG data were recorded. As the model input, in this study the recurrence plot features were extracted from single trial data of different stimuli. Then the extracted feature vectors were reduced using statistical dependency method. The reduced feature vector went through the proposed subject-based sparse model in which the discrimination power of sparse code and reconstruction error were applied simultaneously.

RESULTS

Experimental results showed that the proposed approach achieved better performance than other competing discriminative sparse models. The classification accuracy, sensitivity and specificity of the presented sparsity-based method were about 93%, 91% and 95% respectively.

CONCLUSIONS

Using the EEG data of a single subject in response to different stimuli types and with the aid of the proposed discriminative sparse representation model, one can distinguish guilty subjects from innocent ones. Indeed, this property eliminates the necessity of several subject EEG data in model learning and decision making for a specific subject.

A new approach to analyze data from EEG-based concealed face recognition system

The purpose of this study is to extend a feature set with non-linear features to improve classification rate of guilty and innocent subjects. Non-linear features can provide extra information about phase space. The Event-Related Potential (ERP) signals were recorded from 49 subjects who participated in concealed face recognition test. For feature extraction, at first, several morphological characteristics, frequency bands, and wavelet coefficients (we call them basic-features) are extracted from each single-trial ERP. Recurrence Quantification Analysis (RQA) measures are then computed as non-linear features from each single-trial. We apply Genetic Algorithm (GA) to select the best feature set and this feature set is used for classification of data using Linear Discriminant Analysis (LDA) classifier. Next, we use a new approach to improve classification results based on introducing an adaptive-threshold. Results indicate that our method is able to correctly detect 91.83% of subjects (45 correct detection of 49 subjects) using combination of basic and non-linear features, that is higher than 87.75% for basic and 79.59% for non-linear features. This shows that combination of non-linear and basic- features could improve classification rate.

Exploring time- and frequency- dependent functional connectivity and brain networks during deception with single-trial event-related potentials

To better characterize the cognitive processes and mechanisms that are associated with deception, wavelet coherence was employed to evaluate functional connectivity between different brain regions. Two groups of subjects were evaluated for this purpose: 32 participants were required to either tell the truth or to lie when facing certain stimuli, and their electroencephalogram signals on 12 electrodes were recorded. The experimental results revealed that deceptive responses elicited greater connectivity strength than truthful responses, particularly in the θ band on specific electrode pairs primarily involving connections between the prefrontal/frontal and central regions and between the prefrontal/frontal and left parietal regions. These results indicate that these brain regions play an important role in executing lying responses. Additionally, three time- and frequency-dependent functional connectivity networks were proposed to thoroughly reflect the functional coupling of brain regions that occurs during lying. Furthermore, the wavelet coherence values for the connections shown in the networks were extracted as features for support vector machine training. High classification accuracy suggested that the proposed network effectively characterized differences in functional connectivity between the two groups of subjects over a specific time-frequency area and hence could be a sensitive measurement for identifying deception.

Frontal negativity: An electrophysiological index of interpersonal guilt

The present study aimed to reveal the temporal course and electrophysiological correlates of interpersonal guilt. Human participants were asked to perform multiple rounds of a dot-estimation task with their partners, while event-related potential being recorded. The paired participants were informed that they would win money if both responded correctly; otherwise, both of them would lose money. The feeling of guilt in Self-Wrong condition (SW) was significantly higher than that in Both-Wrong and Partner-Wrong conditions. At approximately 350 ms after the onset of feedback presentation, greater negativities were observed in the frontal regions in the guilt condition (i.e., SW) than those in the non-guilt condition. The guilt-modulated frontal negativity might reflect the interactions of self-reflection, condemnation, and negative emotion.

A novel algorithm to enhance P300 in single trials: application to lie detection using F-score and SVM

The investigation of lie detection methods based on P300 potentials has drawn much interest in recent years. We presented a novel algorithm to enhance signal-to-noise ratio (SNR) of P300 and applied it in lie detection to increase the classification accuracy. Thirty-four subjects were divided randomly into guilty and innocent groups, and the EEG signals on 14 electrodes were recorded. A novel spatial denoising algorithm (SDA) was proposed to reconstruct the P300 with a high SNR based on independent component analysis. The differences between the proposed method and our/other early published methods mainly lie in the extraction and feature selection method of P300. Three groups of features were extracted from the denoised waves; then, the optimal features were selected by the F-score method. Selected feature samples were finally fed into three classical classifiers to make a performance comparison. The optimal parameter values in the SDA and the classifiers were tuned using a grid-searching training procedure with cross-validation. The support vector machine (SVM) approach was adopted to combine with an F-score because this approach had the best performance. The presented model F-score_SVM reaches a significantly higher classification accuracy for P300 (specificity of 96.05%) and non-P300 (sensitivity of 96.11%) compared with the results obtained without using SDA and compared with the results obtained by other classification models. Moreover, a higher individual diagnosis rate can be obtained compared with previous methods, and the presented method requires only a small number of stimuli in the real testing application.

A wavelet based algorithm for the identification of oscillatory event-related potential components

Event related potentials (ERPs) are very feeble alterations in the ongoing electroencephalogram (EEG) and their detection is a challenging problem. Based on the unique time-based parameters derived from wavelet coefficients and the asymmetry property of wavelets a novel algorithm to separate ERP components in single-trial EEG data is described. Though illustrated as a specific application to N170 ERP detection, the algorithm is a generalized approach that can be easily adapted to isolate different kinds of ERP components. The algorithm detected the N170 ERP component with a high level of accuracy. We demonstrate that the asymmetry method is more accurate than the matching wavelet algorithm and t-CWT method by 48.67 and 8.03 percent, respectively. This paper provides an off-line demonstration of the algorithm and considers issues related to the extension of the algorithm to real-time applications.

Pants on fire: the electrophysiological signature of telling a lie

Even though electroencephalography has played a prominent role for lie detection via personally relevant information, the electrophysiological signature of active lying is still elusive. We addressed this signature with two experiments in which participants helped a virtual police officer to locate a knife. Crucially, before this response, they announced whether they would lie or tell the truth about the knife's location. This design allowed us to study the signature of lie-telling in the absence of rare and personally significant oddball stimuli that are typically used for lie detection via electrophysiological markers, especially the P300 component. Our results indicate that active lying attenuated P300 amplitudes as well as N200 amplitudes for such non-oddball stimuli. These results support accounts that stress the high cognitive demand of lie-telling, including the need to suppress the truthful response and to generate a lie.

Detecting deception via eyeblink frequency modulation

To assess the efficacy of using eyeblink frequency modulation to detect deception about a third party, 32 participants were sent on a mission to deliver a package to an interviewer. 17 of the participants lied to the interviewer about the details of their mock mission and 15 responded truthfully. During the interview, eyeblink frequency data were collected via electromyography and recorded video. Liars displayed eyeblink frequency suppression while lying, while truth tellers exhibited an increase in eyeblink frequency during the mission relevant questioning period. The compensatory flurry of eyeblinks following deception observed in previous studies was absent in the present study. A discriminant function using eyeblink suppression to predict lying correctly classified 81.3% of cases, with a sensitivity of 88.2% and a specificity of 73.3%. This technique, yielding a reasonable sensitivity, shows promise for future testing as, unlike polygraph, it is compatible with distance technology.

Impact of stimulus similarity between the probe and the irrelevant items during a card-playing deception detection task: the "irrelevants" are not irrelevant

Event-related brain potential paradigms for the detection of concealed information commonly involve presenting probes embedded within a series of irrelevant items. This study investigated the impact of similarity of the irrelevant items with the probe. For the task, a card was shown followed by the sequential presentation of six "test" cards, one of which was the same as the initial card (the probe) along with five "irrelevant" cards that varied in terms of similarity with the probe. Participants either identified or denied recognition of the probe. The results show that P300 amplitude is modulated by stimulus similarity and highlight the importance of the irrelevant items on deception detection rates.

Effects of the combination of P3-based GKT and reality monitoring on deceptive classification

The study aimed to investigate whether a combination of the P3-based Guilty Knowledge Test (GKT) and reality monitoring (RM) distinguished between individuals who are guilty, witnesses, or informed, and using both tests provided more accurate information than did the use of either measure alone. Participants consisted of 45 males that were randomly and evenly assigned to three groups (i.e., guilty, witness, and informed). The guilty group conducted a mock crime where they intentionally crashed their vehicle into another vehicle in a virtual environment (VE). As those in the witness group drove their own vehicles, they observed the guilty groups' vehicle crash into another vehicle. The informed group read an account and saw screenshots of the accident. All participants were instructed to insist that they were innocent. Subsequently, they performed the P3-based GKT and wrote an account of the accident for the RM analysis. A higher P3 amplitude corresponded to how well the participants recognized the presented stimulus, and a higher RM score corresponded to how well the participants reported vivid sensory information and how much less they reported uncertain information. Findings for the P3-based GKT indicated that the informed group showed lower P3 amplitude when presented with the probe stimulus than did the guilty and witness groups. Regarding the RM analysis, the informed group obtained higher RM scores on visual, temporal, and spatial details and lower scores on cognitive operations than the guilty and witness groups. Finally, discriminant analysis revealed that the combination of the P3-based GKT and RM more accurately distinguished between the three groups than the use of either measure alone. The findings suggest that RM may build upon a weakness of the P3-based GKT's. More specifically, it may build upon its susceptibility to the leakage of information about the crime, therefore helping protect innocent individuals who have information about a crime from being perceived as guilty.

The current and future status of the concealed information test for field use

The Concealed Information Test (CIT) is a psychophysiological technique for examining whether a person has knowledge of crime-relevant information. Many laboratory studies have shown that the CIT has good scientific validity. However, the CIT has seldom been used for actual criminal investigations. One successful exception is its use by the Japanese police. In Japan, the CIT has been widely used for criminal investigations, although its probative force in court is not strong. In this paper, we first review the current use of the field CIT in Japan. Then, we discuss two possible approaches to increase its probative force: sophisticated statistical judgment methods and combining new psychophysiological measures with classic autonomic measures. On the basis of these considerations, we propose several suggestions for future practice and research involving the field CIT.

P300 amplitudes in the concealed information test are less affected by depth of processing than electrodermal responses

The Concealed Information Test (CIT) has been used in the laboratory as well as in field applications to detect concealed crime related memories. The presentation of crime relevant details to guilty suspects has been shown to elicit enhanced N200 and P300 amplitudes of the event-related brain potentials (ERPs) as well as greater skin conductance responses (SCRs) as compared to neutral test items. These electrophysiological and electrodermal responses were found to incrementally contribute to the validity of the test, thereby suggesting that these response systems are sensitive to different psychological processes. In the current study, we tested whether depth of processing differentially affects N200, P300, and SCR amplitudes in the CIT. Twenty participants carried out a mock crime and became familiar with central and peripheral crime details. A CIT that was conducted 1 week later revealed that SCR amplitudes were larger for central details although central and peripheral items were remembered equally well in a subsequent explicit memory test. By contrast, P300 amplitudes elicited by crime related details were larger but did not differ significantly between question types. N200 amplitudes did not allow for detecting concealed knowledge in this study. These results indicate that depth of processing might be one factor that differentially affects central and autonomic nervous system responses to concealed information. Such differentiation might be highly relevant for field applications of the CIT.

Brain fingerprinting: a comprehensive tutorial review of detection of concealed information with event-related brain potentials

Brain fingerprinting (BF) detects concealed information stored in the brain by measuring brainwaves. A specific EEG event-related potential, a P300-MERMER, is elicited by stimuli that are significant in the present context. BF detects P300-MERMER responses to words/pictures relevant to a crime scene, terrorist training, bomb-making knowledge, etc. BF detects information by measuring cognitive information processing. BF does not detect lies, stress, or emotion. BF computes a determination of "information present" or "information absent" and a statistical confidence for each individual determination. Laboratory and field tests at the FBI, CIA, US Navy and elsewhere have resulted in 0% errors: no false positives and no false negatives. 100% of determinations made were correct. 3% of results have been "indeterminate." BF has been applied in criminal cases and ruled admissible in court. Scientific standards for BF tests are discussed. Meeting the BF scientific standards is necessary for accuracy and validity. Alternative techniques that failed to meet the BF scientific standards produced low accuracy and susceptibility to countermeasures. BF is highly resistant to countermeasures. No one has beaten a BF test with countermeasures, despite a $100,000 reward for doing so. Principles of applying BF in the laboratory and the field are discussed.

A novel concealed information test method based on independent component analysis and support vector machine

The concealed information test (CIT) has drawn much attention and has been widely investigated in recent years. In this study, a novel CIT method based on denoised P3 and machine learning was proposed to improve the accuracy of lie detection. Thirty participants were chosen as the guilty and innocent participants to perform the paradigms of 3 types of stimuli. The electroencephalogram (EEG) signals were recorded and separated into many single trials. In order to enhance the signal noise ratio (SNR) of P3 components, the independent component analysis (ICA) method was adopted to separate non-P3 components (i.e., artifacts) from every single trial. In order to automatically identify the P3 independent components (ICs), a new method based on topography template was proposed to automatically identify the P3 ICs. Then the P3 waveforms with high SNR were reconstructed on Pz electrodes. Second, the 3 groups of features based on time,frequency, and wavelets were extracted from the reconstructed P3 waveforms. Finally, 2 classes of feature samples were used to train a support vector machine (SVM) classifier because it has higher performance compared with several other classifiers. Meanwhile, the optimal number of P3 ICs and some other parameter values in the classifiers were determined by the cross-validation procedures. The presented method achieved a balance test accuracy of 84.29% on detecting P3 components for the guilty and innocent participants. The presented method improves the efficiency of CIT in comparison with previous reported methods.

Denoised P300 and machine learning-based concealed information test method

In this paper, a novel P300-based concealed information test (CIT) method was proposed to improve the efficiency of differentiating deception and truth-telling. Thirty subjects including the guilty and innocent performed the paradigm based on three types of stimuli. In order to reduce the influence from the occasional variability of cognitive states on the CIT, several single-trials from Pz in probe stimuli within each subject were first averaged. Then the three groups of features were extracted from these averaged single-trials. Finally, two classes of feature samples were used to train a support vector machine (SVM) classifier. Meanwhile, the optimal number of averaged Pz waveforms and some other parameter values in the classifiers were determined by the cross validation procedures. Results show that if choosing accuracy of 90% as a detecting standard of P3 component to classify a subject's status (guilty or innocent), our method can achieve individual diagnostic rate of 100%. The individual diagnostic rate of our method was higher than the results of the other related reports. The presented method improves efficiency of CIT, and is more practical, lower fatigue and less countermeasure behavior in comparison with previous report methods, which could extend the laboratory study to the practical application.

A Concealed Information Test with multimodal measurement

A Concealed Information Test (CIT) investigates differential physiological responses to deed-related (probe) vs. irrelevant items. The present study focused on the detection of concealed information using simultaneous recordings of autonomic and brain electrical measures. As a secondary issue, verbal and pictorial presentations were compared with respect to their influence on the recorded measures. Thirty-one participants underwent a mock-crime scenario with a combined verbal and pictorial presentation of nine items. The subsequent CIT, designed with respect to event-related potential (ERP) measurement, used a 3-3.5s interstimulus interval. The item presentation modality, i.e. pictures or written words, was varied between subjects; no response was required from the participants. In addition to electroencephalogram (EEG), electrodermal activity (EDA), electrocardiogram (ECG), respiratory activity, and finger plethysmogram were recorded. A significant probe-vs.-irrelevant effect was found for each of the measures. Compared to sole ERP measurement, the combination of ERP and EDA yielded incremental information for detecting concealed information. Although, EDA per se did not reach the predictive value known from studies primarily designed for peripheral physiological measurement. Presentation modality neither influenced the detection accuracy for autonomic measures nor EEG measures; this underpins the equivalence of verbal and pictorial item presentation in a CIT, regardless of the physiological measures recorded. Future studies should further clarify whether the incremental validity observed in the present study reflects a differential sensitivity of ERP and EDA to different sub-processes in a CIT.

Detection of concealed information: combining a virtual mock crime with a P300-based Guilty Knowledge Test

The present study examined the detection of concealed information by combining a virtual mock crime with a P300-based Guilty Knowledge Test (GKT). Thirty-eight male participants were assigned to one of two groups: a guilty group that committed a mock crime to conceal a lost roll of bills in a computer simulation of a virtual library and an innocent group that was free from concealed information. Remarkably, the guilty group reacted with stronger P300 peak amplitudes to crime-relevant than to irrelevant stimuli, whereas the innocent group had similar P300 responses between crime-relevant and irrelevant stimuli. Deception-related cognitive activity based on P300 was revealed as a valid marker to differentiate between guilty and innocent. This is a highly empirical study combining a virtual mock crime with a P300-based GKT to detect deception. These results may be applied to a variety of areas dealing with not only forensic investigation but also health and medical research concerning deception as a symptom.

A new approach for EEG feature extraction in P300-based lie detection

P300-based Guilty Knowledge Test (GKT) has been suggested as an alternative approach for conventional polygraphy. The purpose of this study was to extend a previously introduced pattern recognition method for the ERP assessment in this application. This extension was done by the further extending the feature set and also the employing a method for the selection of optimal features. For the evaluation of the method, several subjects went through the designed GKT paradigm and their respective brain signals were recorded. Next, a P300 detection approach based on some features and a statistical classifier was implemented. The optimal feature set was selected using a genetic algorithm from a primary feature set including some morphological, frequency and wavelet features and was used for the classification of the data. The rates of correct detection in guilty and innocent subjects were 86%, which was better than other previously used methods.