AU2021102773A4

AU2021102773A4 - A system and method for determining truthful and deceptive state of a person

Info

Publication number: AU2021102773A4
Application number: AU2021102773A
Authority: AU
Inventors: Annushree Bablani; Ramalingaswamy Ch.; Pankaj Kumar; Damodar Reddy Edla; P. Saidi Reddy
Original assignee: Bablani Annushree Ms
Current assignee: Bablani Annushree Ms
Priority date: 2021-05-23
Filing date: 2021-05-23
Publication date: 2022-03-24
Anticipated expiration: 2029-05-23

Abstract

The present invention generally relates to a system and method for determining truthful and deceptive state of a person. The system involves presenting three stimuli: images, video and audio to the person to identify their deceptive nature. Images, videos and audios of the interest are presented to the subjects and during the time of presentation, brain activity is recorded. Also, the method involves the mapping of the brain and shows the correlation between the various channels involved in data acquisition. The method is helpful to identify the guilty and useful in various investigation departments. 22 C LU0 CLC - -5

Description

C LU0

CLC A SYSTEM AND METHOD FOR DETERMINING TRUTHFUL AND DECEPTIVE STATE OFA PERSON FIELD OF THE INVENTION

The present disclosure relates to a usage of brain computer interface techniques for deceit detection by measuring brain signals or brain activity. The present disclosure relates to a system and method for determining truthful and deceptive state of a person.

BACKGROUND OF THE INVENTION

Deceit behaviour leads to hiding the truth henceforth leading to the adaption of illegal methods for making people believe that it's true. It is a detrimental behaviour and is unacceptable towards the morality of society we are living in. The hidden deceit behaviour cannot be identified with the simple investigation approaches. The people with deceit nature become experts in hiding the truth from society and law. Hence, there is a need for developing a method for better investigation and helping law enforcement agencies to identify the guilty.

The law enforcement agency has been adopting different ways to punish the guilty since ancient India. In the early 90s, a method to detect deceit behaviour using physiological changes was developed called the Polygraph test. During these tests, the person is asked with a certain set of questions related to crime and the activities peripheral autonomic nervous system of the person are analysed. The test involves analysis of the rising in heart rate, blood pressure, skin conductance, the rate of respiration and others. During the test, the response rate of these autonomic reflexes is recorded for relevant and irrelevant questions asked. The recording is analysed to identify deceit behaviour. But this indirect view was not successful in classifying a subject as guilty or innocent, as a subject can learn how to manipulate these autonomic reflexes, thereby deceiving the test itself. It may so happen that due to the intensity of the question asked the rate of autonomic reflexes of an innocent person shows an increase, which may lead to misjudgement. Hence, these tests are more instinctive and are vulnerable to the situation and environment. To prevent subjective disturbances, a method using brain activities were invented to detect deception.

Any person's brain signals are very complex, as they show deviations when the stimulus presented and with their mental health. Hence, they carry information about every action performed by a person. The brain signal reflects the state of mind of a person. And with different moods such as anger, fear, joy, excitement, stress, surprise etc., changes are visible in these signals. Hence, brain activities provide a more direct view of the responses generated. Brain-computer interface provides us with that ability to record brain activity using various acquisition techniques. One of the few works which initiated the process of involving brain activity is identifying deception using P300 component of ERP generated using EEG technique, also patent [US 8,014,847 B2, US9495687A, U.S. Pat. No.5, 406,956, US 5,363,858, US5467777A]. Other than EEG, techniques such as fMRI, MEG etc., are also used for measuring brain activity for deceit detection. For example, a comparison between the results achieved from channels used for polygraph and fMRI images were conducted. To detect deception, a paradigm has been developed and recording is performed using MEG.

In the view of the forgoing discussion, it is clearly portrayed that there is a need to have a system and method for determining truthful and deceptive state of a person.

SUMMARY OF THE INVENTION

The present disclosure seeks to provide a system and method for detecting deception using EEG based Brain-computer interface techniques.

In an embodiment, a system for determining truthful and deceptive state of a person is disclosed. The system includes at least two computer machines. The system further includes an electroencephalographic (EEG) device comprises of a set of electrodes to be placed on human subject brain scalp and an amplifier with analog to digital converter acquisition device connected to one of the computer machines to present visual and audio tasks to a subject. The system further includes a presentation module which consists of a sequence of presentation of stimuli. The system further includes a recording module for recording of input EEG data received from EEG sensors, wherein recorded output is displayed on the computer machine, wherein received input consists of either elicitations or no elicitation when exposed to stimuli, wherein a probability of a subject being deceptive depends on an elicitation of a brain signals. The system further includes a filtering module for filtering output signals and thereby converting into numerical attributes followed by analyzing upon applying an analysis module. The system further includes a signal processing module for feature extraction of signal using various approaches including Common Spatial Pattern (CSP), Wavelet Transform (WT), and Fast Fourier Transform (FFT). The system further includes a classification module for classifying signal into respective classes by using classification approaches such as support vector machine, neural networks, naive Bayes, k-nearest neighbor.

In an embodiment, the elicitations are compared by generating brain activity map of a truthful response and a concealed response.

In an embodiment, in another aspect, the subject is presented stimuli and are asked a question about stimuli presented into which the subject is allowed to answer questions in a specific period and truthful or deceptive response given by number of subjects participated is compared using machine learning approaches.

In an embodiment, stimuli sequence includes at least one probe stimuli, where the probe is a stimuli which are responsible for elicitation of brain signal, wherein audio stimuli are imbedded in with a visual stimuli, where visual stimuli refer to images and video.

In an embodiment, EEG electrodes are placed to record eye activities, to record P300 activity from one or more electrodes, wherein data received from electrodes display variations in brain signals.

In an embodiment, different machine learning approaches are applied to recorded data of each subject to calculate deceptive behavior of the subject, wherein the subject is asked to provide a truthful response for a target stimuli while recording is carried out and the subject is asked to provide a concealed response for a probe stimuli while recording is carried out.

In an embodiment, recording and analysis of EEG signals from the subject is proposed which includes acquisition of data from more than one sensor.

In an embodiment, experimental procedure involves presentation of stimuli to the subject which includes images of a known person, video is related to a crime scene and audio is related to criminal activity, wherein the stimuli are categorized in three variants including probe, target and irrelevant, wherein probe are related or known to guilty subjects, target are related or known to both innocent and guilty subjects and irrelevant is unrelated or unknown to all.

In another embodiment, a method for determining truthful and deceptive state of a person is disclosed. The method includes providing a set of visual and audio stimuli, wherein the visual stimuli are presented initially and images are followed by video and then the audio is played as stimuli. The method further includes presenting brain stimuli in a set pattern, wherein initially subject an image as stimuli for 2 seconds followed by a blank image for 30 seconds and thereby providing a video stimulus for a minute followed by a blank image, wherein subject is asked to close eyes at the end and listen to audio stimuli for 30 seconds. The method further includes recording brain activity during presentation of the stimulus, wherein a response of the subject is recorded by answering question in yes or no. The method further includes generating brain activity maps in a form of component maps which gives a probability of activation of a brain region during the recording for determining truthful and deceptive state of a person.

In an embodiment, brain activity is recorded while asking a human subject set of questions which involves a target or a control question and a probe or crime-related question and allowing the human subject to respond to questions.

An object of the present disclosure is to provide a better and improved system for deceit identification, by analyzing the brain activities during different stimuli presented to the subject.

Another object of the present disclosure is to detect deception using signal generated from brain using an electroencephalographic (EEG) technique.

Another object of the present disclosure is to develop a lie detector and as an alternative to the conventional polygraphs.

Yet another object of the present invention is to deliver an expeditious and cost-effective method for detecting deception using EEG based Brain-computer interface techniques.

To further clarify advantages and features of the present disclosure, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings. BRIEF DESCRIPTION OF FIGURES

These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

Figure 1 illustrates a block diagram of a system for determining truthful and deceptive state of a person in accordance with an embodiment of the present disclosure; Figure 2 illustrates flow chart of a method for determining truthful and deceptive state of a person in accordance with an embodiment of the present disclosure; Figure 3 illustrates modules applied in lie detection using EEG in accordance with an embodiment of the present disclosure; Figure 4 illustrates order of occurrence of processes in accordance with an embodiment of the present disclosure;

Figure 5 illustrates timeline of an experimental procedure in accordance with an embodiment of the present disclosure; Figures 6A and 6B illustrate component diagram showing activity of each channel during various sessions in accordance with an embodiment of the present disclosure; and Figure 7 illustrates Table 1 depicts results of analysis performed on an EEG signal on MATLAB in accordance with an embodiment of the present disclosure.

Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have been necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having benefit of the description herein.

DETAILED DESCRIPTION

For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.

Reference throughout this specification to "an aspect", "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises...a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

Referring to Figure 1, a block diagram of a system for determining truthful and deceptive state of a person is illustrated in accordance with an embodiment of the present disclosure. The system herein is developed to detect liars or people hiding information or conceal the truth or are not corporative, serpentine and show deceptive behavior. The system 100 includes at least two computer machines 102.

In an embodiment, an electroencephalographic (EEG) device 104 comprises of a set of electrodes 106 to be placed on human subject brain scalp and an amplifier 108 with analog to digital converter 110 acquisition device connected to one of the computer machines 102 to present visual and audio tasks to a subject.

In an embodiment, a presentation module 112 which consists of a sequence of presentation of stimuli. In an embodiment, a recording module 114 is used for recording of input EEG data received from EEG sensors. Recorded output is displayed on the computer machine. Received input consists of either elicitations or no elicitation when exposed to stimuli. A probability of a subject being deceptive depends on an elicitation of a brain signals.

In an embodiment, a filtering module 116 is used for filtering output signals and thereby converting into numerical attributes followed by analyzing upon applying an analysis module 118. In an embodiment, a signal processing module 120 is used for feature extraction of signal using various approaches including Common Spatial Pattern (CSP), Wavelet Transform (WT), and Fast Fourier Transform (FFT).

In an embodiment, a classification module 122 is used for classifying signal into respective classes by using classification approaches such as support vector machine, neural networks, naive Bayes, k-nearest neighbor.

In an embodiment, stimuli sequence includes at least one probe stimuli, where the probe is a stimuli which are responsible for elicitation of brain signal. Audio stimuli are imbedded in with a visual stimuli, where visual stimuli refer to images and video.

In an embodiment, EEG electrodes are placed to record eye activities, to record P300 activity from one or more electrodes. Data received from electrodes display variations in brain signals.

In an embodiment, experimental procedure involves presentation of stimuli to the subject which includes images of a known person, video is related to a crime scene and audio is related to criminal activity. The stimuli are categorized in three variants including probe, target and irrelevant. Probe are related or known to guilty subjects, target are related or known to both innocent and guilty subjects and irrelevant is unrelated or unknown to all.

Figure 2 illustrates flow chart of a method for determining truthful and deceptive state of a person in accordance with an embodiment of the present disclosure. At step 202, the method 200 includes providing a set of visual and audio stimuli. The visual stimuli are presented initially and images are followed by video and then the audio is played as stimuli.

At step 204, the method 200 includes presenting brain stimuli in a set pattern. Initially subject an image as stimuli for 2 seconds followed by a blank image for 30 seconds and thereby providing a video stimulus for a minute followed by a blank image. Subject is asked to close eyes at the end and listen to audio stimuli for 30 seconds.

At step 206, the method 200 includes recording brain activity during presentation of the stimulus. A response of the subject is recorded by answering question in yes or no. At step 208, the method 200 includes generating brain activity maps in a form of component maps which gives a probability of activation of a brain region during the recording for determining truthful and deceptive state of a person.

Figure 3 illustrates modules applied in lie detection using EEG in accordance with an embodiment of the present disclosure. The EEG recording includes data acquisition, analyzing the information recorded from the brain. The techniques used herein are commonly understood in the art, including their variants or some comparable approaches or recently developed techniques which would be seeming to be in the art.

As provided herein the brain activity refers to the neurophysiological changes going inside the brain associated with the responses created by the neurons and transferred to other neurons through the synapse. The exchange of information between synapse happens while a person is responding to certain actions or activities.

Despite the considerable difference between the functions of different brain regions, it is possible to identify different patterns of brain activity within an individual that are explicit of deception or a deceptive state.

The invention offers approaches to define whether the responses generated of a subject's brain on presenting the stimulus of interest (or probe) is distinctive to deceiving state and truthful state. For example, the probe can be any question which can be presented as a word of mouth or as a visual on the screen. Alternatively, it can be a sound or an image related to crime incidence, which may elicit a response. In some embodiments, however, the subject will respond explicitly by speech (e.g., answering "yes" or "no") or by physical movement (e.g., raising a finger, pressing a button, blinking).

The brain activity is measured during the presentation of the stimuli. The recording period typically is from 20 to 40 seconds. The recording period may increase depending on the type of stimuli presented and on how much brain activity of interest is required.

The system provides the stimuli as a certain set of questions to which the subject has to provide a required response. In another aspect, the invention provides methods to decide whether the brain activity of the subject during asking the question is specific of a truthful or a deceptive response.

The invention provides subject with the stimulus from which the subject is supposed to provide the truthful response and for some set of stimuli the subject is supposed to provide the deceptive response. The brain activity is recorded from the period where the subject is responding truthful and deceptive. The brain activity for both will be recorded separately. The stimuli for truthful response and deceptive response are presented to the subject in random order.

The measurements of brain activity can be concentrated in different brain regions in a subject, where it is identified that there is a statistical difference in brain activity when measured during honest responses and deceiving responses. Many devices are available in the art to measure these brain activities such as EEG (Electroencephalogram), MRI (Magnetic Resonance Imaging), PET (Positron Emission Tomography), SPECT (Single Photon Emission Computed Tomography), MEG (Magnetoencephalography), etc. Each of these devices generates brain data either inform of signals or brain maps. EEG generates brain signals called EEG signals using metal electrodes placed on brain scalp, MRI generates brain images by measuring the selective absorption of high frequency radio waves. MEG records magnetic fields produced as a result of neural activity generated in response to a stimulus using Superconducting Interference Devices (SQUIDs). PET measures the functionality of the brain by injecting a nuclear substance-emitting positron and SPECT uses gamma rays to study the brain.

Above mentioned techniques can be used in some embodiments to record brain responses during the experiment. As these approaches involve a huge process, hence the response to the question is kept quite simpler. The subjects, according to some embodiments are provided with a question whose answer can be either a "yes" or a "no". The nature of asking a question can be oral, a video or audio. Also, the nature of questions depends on the technique used for brain activity measurement. For example, using an EEG device any medium of asking the question will be suitable unlike MRI where the subject is enclosed inside some device hence presenting the video becomes the better option. To avoid the movement artefacts, the subject should avoid hand movements, headshakes and other muscle movements of not interest.

A computer system is required to ask the question and a different computer system is required to record the responses. To differentiate between the various brain activities recorded, a target stimuli or control stimuli is provided to the subject. The target stimuli can be a series of images or a video stream or any audio which will be known to the subject (for example an image of the subject's family member or friends). The target stimuli will generate the response which will show that the subject is familiar with stimuli (the response wave is called P300). When the subject is shown to the stimuli which are crime-related, if the subject is deceitful, the same kind of response will be generated (P300 response). In another aspect, if the subject is truthful, a different kind of response will be generated (non P300 response). Hence, these responses can be compared to determine the behavior of the subject.

For the target or control stimuli presented in the form of questions, the subjects are instructed to reply truthfully. For other crime-related questions, the subject has been instructed to reply deceitful, during a mock crime experiment session.

From Figure 3, the human subject is presented with the stimuli on a system (11). During stimuli presentation, the recording is done using an acquisition device i.e. EEG (12). EEG device is connected with a system on which recording software is available (13). The EEG devices comprise of a set of electrodes to be placed on the human subject brain scalp (121) and an amplifier with analog to digital converter (122). The recorded output will be displayed on a computer system (14). The output signals will be filtered (15) and are converted into numerical attributes (16) then analyzed by applying an analysis module (17). The analysis module comprises a signal processing module (1701) which involves feature extraction of the signal. According to some embodiments, the signal extraction can be performed using various approaches such as Common Spatial Pattern (CSP), Wavelet Transform (WT), and Fast Fourier Transform (FFT) etc. After feature extraction, the signal is classified into respective classes by using classification approaches such as support vector machine, neural networks, naYve Bayes, k-nearest neighbor etc. (1702).

Figure 4 illustrates order of occurrence of processes in accordance with an embodiment of the present disclosure. Figure 4 includes EEG signal processing module 1701, EEG Signal classification 1702, and output module 1703. The EEG signal processing module 1701 is used to filter noise and irrelevant signals from EEG signals. The EEG Signal classification 1702 is used to classify EEG signals according to threshold value.

Figure 5 illustrates timeline of an experimental procedure in accordance with an embodiment of the present disclosure. The timeline or system of presentation of stimuli (11) is given in Figure 5. During the experiment, the human subject is asked with the set of question in two sessions. In another aspect, the sessions are conducted in two parts, one truth session and one lie session. The subject will be asked to sit with closed eyes for 2 min to relax before the experiment starts. In some embodiments after the brain waves of the subject are relaxed recording will be started. The recording will be performed for two minutes. For the first 30 seconds, target or control images will be presented, one image will be presented for 2 seconds and a blank image for 1 second. The stimuli presentation will start with a blank image (1101), followed by a control image (1102). The pattern of one blank and a control image will be followed for 30 seconds. After that, a video stimulus (1112) for one minute will be presented as a probe (related to crime). An audio stimulus (1114) for 30 seconds will be given as another probe to calculate the N200 response generated in different guilty and innocent subjects. Following the experiment, the blank stimuli are presented to give the subject a break and its activity to relax so that there is no effect of the previously presented stimuli on the next upcoming stimuli.

Figures 6A and 6B illustrate component diagram showing activity of each channel during various sessions in accordance with an embodiment of the present disclosure. Figures 6A and 6B show the component diagram showing the activity of the brain during recording for a guilty and innocent subject respectively.

Example 1

A subject of interest has been identified and is examined for the session. The subject is required to be able to read and write English (or the language in which examination will be conducted). The subject should have the ability to provide informed consent to the examiner. Subject with any kind of neuro or psychological disorder is not considered. Brain activity was measured using Brain Vision Recorder with Easy Cap (a 32 Channel EEG Standard Cap Set (Munich, Germany)), a V-amp amplifier, and set of 16 electrodes.

The subject is seated comfortably in the experiment room on a chair with one system displaying stimuli and other system attached to the recorder. The EEG electrodes (14 in number) are placed on the subject scalp. They are placed on 14 different positions i.e Fz, Fpl, Fp2, P3, Pz, P4, T7, T8, C3, Cz, C4, Oz, 01,02, one Reference (anywhere) electrode and a Ground electrode (Behind ears). After the whole setup is done, the experiment is started with the presentation of a series of questions. Three types of stimuli were presented with different questions. For the first set of questions, control stimuli or target stimuli is presented asking "Whether you know the person shown?" The target stimuli are a set of 5 images that are known to the subjects. These images are of either a celebrity or friends or relatives or acquaintances to the subject, whom he or she will recognize in the first attempt. For the second set of question, one video will be presented to the subject asking "whether they have witnessed the crime shown in the video?" This video will be the crime related video and hence will be called as the probe stimuli. This video will be known only for the guilty subjects and not for the innocent subject. Before experiment begin this video has been shown to the subject who mocks as guilty for the scenario. Hence, the responses for the stimuli will be different for innocent and guilty subject respectively. For the third set of question, an audio stimulus is presented to the subject asking "Whether you have heard the conversation or voice played?" The audio stimuli unlike visual stimuli presented in before sets will generate an N200 response. Hence, the audio stimuli presented will be crime-related or a probe stimulus, known before the guilty subject. The response generated from the guilty and innocent subject will be different. The brain activity generated during the guilty session is as depicted in figure-4 and brain activity generated during the innocent session is as depicted in figure-5. The regions in the figure show the activation of brain various parts during recording. The figures here are of one subject during a trial. The MATLAB (EEGLAB) software is used for generation of these brain maps. The analysis done on the EEG signal is also performed on MATLAB and the results acquired are given in TABLE-1. The the analysis is performed based on various performance measures.

The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

Claims

WE CLAIM

1. A method for determining truthful and deceptive state of a person, said method comprises:

providing a set of visual and audio stimuli, wherein said visual stimuli are presented initially and images are followed by video and then said audio is played as stimuli; presenting brain stimuli in a set pattern, wherein initially subject an image as stimuli for 2 seconds followed by a blank image for 30 seconds and thereby providing a video stimulus for a minute followed by a blank image, wherein subject is asked to close eyes at the end and listen to audio stimuli for 30 seconds; recording brain activity during presentation of the stimulus, wherein a response of said subject is recorded by answering question in yes or no; and generating brain activity maps in a form of component maps which gives a probability of activation of a brain region during said recording for determining truthful and deceptive state of a person.

2. The method as claimed in claim 1, wherein brain activity is recorded while asking a human subject set of questions which involves a target or a control question and a probe or crime-related question and allowing said human subject to respond to questions.

3. A system for determining truthful and deceptive state of a person, said system comprises:

at least two computer machines; an electroencephalographic (EEG) device comprises of a set of electrodes to be placed on human subject brain scalp and an amplifier with analog to digital converter acquisition device connected to one of said computer machines to present visual and audio tasks to a subject; a presentation module which consists of a sequence of presentation of stimuli; a recording module for recording of input EEG data received from EEG sensors, wherein recorded output is displayed on said computer machine; wherein received input consists of either elicitations or no elicitation when exposed to stimuli, wherein a probability of a subject being deceptive depends on an elicitation of a brain signals; a filtering module for filtering output signals and thereby converting into numerical attributes followed by analyzing upon applying an analysis module; a signal processing module for feature extraction of signal using various approaches including Common Spatial Pattern (CSP), Wavelet Transform (WT), and Fast Fourier Transform (FFT); and a classification module for classifying signal into respective classes by using classification approaches such as support vector machine, neural networks, nave Bayes, k-nearest neighbor.

4. The system as claimed in claim 3, wherein said elicitations are compared by generating brain activity map of a truthful response and a concealed response.

5. The system as claimed in claim 3 and 4, wherein in another aspect, said subject is presented stimuli and are asked a question about stimuli presented into which said subject is allowed to answer questions in a specific period and truthful or deceptive response given by number of subjects participated is compared using machine learning approaches.

6. The system as claimed in claim 3, wherein stimuli sequence includes at least one probe stimuli, where the probe is a stimuli which are responsible for elicitation of brain signal, wherein audio stimuli are imbedded in with a visual stimuli, where visual stimuli refer to images and video.

7. The system as claimed in claim 3, wherein EEG electrodes are placed to record eye activities, to record P300 activity from one or more electrodes, wherein data received from electrodes display variations in brain signals.

8. The system as claimed in claim 3, wherein different machine learning approaches are applied to recorded data of each subject to calculate deceptive behavior of said subject, wherein said subject is asked to provide a truthful response for a target stimuli while recording is carried out and said subject is asked to provide a concealed response for a probe stimuli while recording is carried out.

9. The system as claimed in clam 3, wherein recording and analysis of EEG signals from the subject is proposed which includes acquisition of data from more than one sensor.

10. The system as claimed in clam 3, wherein experimental procedure involves presentation of stimuli to said subject which includes images of a known person, video is related to a crime scene and audio is related to criminal activity, wherein said stimuli are categorized in three variants including probe, target and irrelevant, wherein probe are related or known to guilty subjects, target are related or known to both innocent and guilty subjects and irrelevant is unrelated or unknown to all.

Figure 3

Figure 4

Figure 6A

Figure 6B

Figure 7