CN107080545B - A kind of lie detection system based on brain electricity - Google Patents

Abstract

The invention discloses an EEG-based lie detection system, which belongs to the field of lie detection systems. An EEG-based lie detection system, including an EEG acquisition sensor system, an EEG signal preprocessing system, an EEG signal feature extraction system, an EEG signal classification modeling system, a database support system, a computer analysis system, and a computer display system . It can realize the use of the AR model to process the interference signal, and use the AR model and the adaptive predictor based on the ARMA model to effectively avoid the error caused by the interference signal and eliminate the interference factors. The data signals of the test subjects and the lying subjects with strong psychological quality will collect a large amount of characteristic information and store them in the data storage system, and analyze and compare the data signals of the collected suspects with the data signals of the subjects through the computer analysis system. So as to give rationalized lie detection results.

Description

A Lie Detecting System Based on EEG

technical field

The invention relates to the field of lie detection systems, and more specifically, relates to a lie detection system based on brain electricity.

Background technique

A lie detector is an instrument that records multiple physiological reactions, and can be used in criminal investigations to assist in interrogation, so as to determine whether it is involved in a criminal case. Using brain wave acquisition devices to collect brain waves and analyze whether they are lying is also used, but for The accuracy of polygraph detection is not high for well-trained suspects with strong psychological quality. On the one hand, the accuracy of polygraph detection decreases because brain waves are easily disturbed by environmental factors. Relatively few, the characteristics are not very clear, and it is difficult to accurately judge only based on the fluctuation of brain waves.

Contents of the invention

1. Technical problems to be solved

Aiming at the problem in the prior art that the accuracy of polygraph detection for the trained suspects with strong psychological quality is not high, the purpose of the invention is to provide a polygraph system based on EEG, which can realize the detection of the suspects with strong psychological quality. The suspects have a high degree of accuracy in polygraph detection.

2. Technical solution

In order to solve the above problems, the invention adopts the following technical solutions.

An EEG-based lie detection system, including an EEG acquisition sensor system, an EEG signal preprocessing system, an EEG signal feature extraction system, an EEG signal classification modeling system, a database support system, a computer analysis system, and a computer display system , the brain wave acquisition sensor system, the brain wave signal preprocessing system, the brain wave signal feature extraction system, the brain wave signal classification modeling system are connected in sequence, the brain wave signal classification modeling system and the database support system are all connected with the computer analysis The system is connected, the computer analysis system is connected with the computer display system, the brain wave signal preprocessing system includes a de-interference wavelet transform algorithm, an AR model and an adaptive predictor based on the AR model, and the database support system includes a data storage system , the brain wave acquisition sensor system respectively collects the brain wave signals of a large number of non-lying subjects with strong psychological quality and lying subjects with strong psychological quality, and the data storage system stores the non-lying subjects with strong psychological quality respectively and the processed brain wave signals of lying subjects with strong psychological quality. The computer analysis system includes a data extractor, a data receiver and a data comparator. The transformation algorithm initially processes the interference signal, uses the AR model to process the interference signal, and uses the AR model and the adaptive predictor based on the AR model to effectively avoid the error caused by the interference signal and eliminate the interference factors. The data signals of non-lying subjects and lying subjects with strong psychological quality will collect a large amount of characteristic information and store them in the data storage system, and the data signals of suspects and subjects will be collected through the computer analysis system. Analysis and comparison are carried out to give rationalized polygraph results.

Preferably, the brain wave acquisition sensor system uses a 3-lead electrode sensor, a preamplifier circuit, a filter circuit and an AD converter. After the 3-lead brain electrode sensor collects the signal, the weak EEG signal is amplified by the preamplifier circuit , the original EEG signal is filtered through a filter circuit, and the signal is converted into a digital signal through a 16-bit AD converter.

Preferably, the filter circuit is composed of a low-pass circuit and a notch circuit, and the notch circuit can effectively deal with power frequency interference during EEG signal collection.

Preferably, the brain wave signal classification modeling system adopts the latest "973" project experimental data analysis data model as the basic index parameter, and the data model of the huge experimental data system of the "973" project has high precision and different data models. Low balance and other characteristics, the user is easy to understand and use, and can be compared with the existing data to further improve the accuracy of lie detection.

Preferably, the brain wave acquisition sensor system uses Bluetooth 2.0 to send the collected EEG signals to the EEG signal preprocessing system, and sends the EEG signals to the computer through Bluetooth 2.0, with high transmission efficiency.

Preferably, the computer display system adopts the dynamic display of the EEG power spectrum array graph or the EEG index histogram such as θ, α, β, etc., through the dynamic display of the EEG power spectrum array graph or the EEG θ, α, β index histogram. EEG indicators are monitored in real time to intuitively and accurately grasp the brain function status of the suspect.

3. Beneficial effect

Compared with the prior art, the advantages of the invention are:

(1) The EEG acquisition sensor system of this program collects EEG signals, and the interference signals are preliminarily processed through the de-interference wavelet transform algorithm, and the AR model is used to process the interference signals, and the AR model and the adaptive predictor based on the AR model are used to effectively Avoid errors caused by interference signals, eliminate interference factors, and use the system to collect multiple non-lying subjects with strong psychological quality and lying subjects with strong psychological quality, and store a large amount of characteristic information in the data storage system , through the computer analysis system to analyze and compare the data signal of the suspect and the data signal of the subject, so as to give a rationalized lie detection result.

(2) After the 3-lead brain electrode sensor collects the signal, the weak EEG signal is amplified by the pre-amplification circuit, and the original EEG signal is filtered by the filter circuit, and the signal is converted into a digital signal by a 16-bit AD converter.

(3) The notch circuit can effectively deal with the power frequency interference during EEG signal acquisition.

(4) The data model of the huge experimental data system of the "973" project has the characteristics of high precision and low imbalance of the data model. It is easy for users to understand and use, and can be compared with existing data to further improve the accuracy of lie detection. Spend.

(5) Send the EEG signal to the computer through Bluetooth 2.0, with high transmission efficiency.

(6) Through the dynamic display of the EEG power spectrum array diagram or EEG histogram of θ, α, β and other indicators, the real-time monitoring of EEG indicators can be realized, and the brain function status of the suspect can be grasped intuitively and accurately.

Description of drawings

Fig. 1 is a system schematic diagram of the present invention;

Fig. 2 is a block diagram of the brainwave acquisition sensor system of the present invention;

Fig. 3 is a schematic diagram of the brainwave signal preprocessing system of the present invention;

Fig. 4 is a block diagram of the database support system of the present invention;

Fig. 5 is a block diagram of the computer analysis system of the present invention.

detailed description

The technical solutions in the embodiments of the invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the invention; obviously, the described embodiments are only part of the embodiments of the invention; not all of them. Based on the embodiment in the invention; all other embodiments obtained by those skilled in the art without creative work; all belong to the protection scope of the invention.

Example 1:

Please refer to Figure 1-5, a lie detection system based on EEG, including EEG acquisition sensor system, EEG signal preprocessing system, EEG signal feature extraction system, EEG signal classification modeling system, database support system, The computer analysis system and computer display system, brain wave acquisition sensor system, brain wave signal preprocessing system, brain wave signal feature extraction system, and brain wave signal classification modeling system are connected in sequence, and the brain wave signal classification modeling system and database support system are both It is connected with the computer analysis system, the computer analysis system is connected with the computer display system, the brain wave signal preprocessing system includes the de-interference wavelet transform algorithm, the AR model and the adaptive predictor based on the AR model, the database support system includes the data storage system, the brain wave signal The acquisition sensor system collects the brain wave signals of a large number of non-lying subjects with strong psychological quality and lying subjects with strong psychological quality, and the data storage system stores the non-lying subjects with strong psychological quality and the lying subjects with strong psychological quality respectively. The computer analysis system includes a data extractor, a data receiver and a data comparator for the processed brain wave signal of the test subject. The brain wave acquisition sensor system collects the brain wave signal. The model processes the interference signal, and uses the AR model and the adaptive predictor based on the AR model to effectively avoid the error caused by the interference signal and eliminate the interference factors. For the data signal of strong lying subjects, a large amount of characteristic information will be collected and stored in the data storage system, and the data signal of the suspect will be analyzed and compared with the data signal of the subject through the computer analysis system, so as to give a rationalized answer. Polygraph results.

The brain wave acquisition sensor system uses a 3-lead electrode sensor, a preamplifier circuit, a filter circuit and an AD converter. After the 3-lead brain electrode sensor collects the signal, the weak EEG signal is amplified through the preamplifier circuit, and the filter circuit is used to amplify the weak EEG signal. The original EEG signal is filtered and processed, and the signal is converted into a digital signal through a 16-bit AD converter. The filter circuit is composed of a low-pass circuit and a trap circuit. The signal classification modeling system uses the latest "973" project experimental data analysis data model as the basic index parameter. The data model of the huge experimental data system of the "973" project has the characteristics of high precision and low imbalance of the data model. Users It is easy to understand and use, and can be compared with existing data to further improve the accuracy of lie detection. The brain wave acquisition sensor system uses Bluetooth 2.0 to send the collected EEG signals to the brain wave signal preprocessing system. The EEG signal is sent to the computer, and the transmission efficiency is high. The computer display system adopts the dynamic display of the EEG power spectrum array graph or the EEG θ, α, β and other index histograms. Through the EEG power spectrum array graph or the EEG θ, α, The dynamic display of the histogram of β and other indicators realizes the real-time monitoring of EEG indicators, and intuitively and accurately grasps the brain function status of the suspect.

Working principle: Firstly, through the system, the data signals of multiple non-lying subjects with strong psychological quality and lying subjects with strong psychological quality are respectively collected, and a large amount of characteristic information collected is stored in the data storage system, thereby constructing a reasonable The database support system, when detecting the lie of suspects with strong psychological quality, collects brain wave signals through the brain wave acquisition sensor system, and sends the collected signals to the brain wave signal preprocessing system through Bluetooth 2.0, through the interference wavelet transform algorithm Preliminarily process the interference signal, use the AR model to process the interference signal, and use the AR model and the adaptive predictor based on the AR model to effectively avoid the error caused by the interference signal, eliminate the interference factors, and extract the preprocessed brain wave signal through the EEG signal feature The system extracts a large amount of feature information, and uses the latest "973" project experimental data analysis data model as the basic index parameter to carry out classification modeling. The data receiver in the computer analysis system receives the modeling information, and extracts the database support through the data extractor A large amount of data information in the system is analyzed and compared with the EEG information of the suspect and the EEG information of the subject by using the data analysis comparator, and displayed through the computer display system, so as to give a rationalized lie detection result.

The above is only a preferred embodiment of the invention; but the protection scope of the invention is not limited thereto; any person familiar with the technical field is within the technical scope disclosed by the invention; according to the technical scheme of the invention and its improved concept Equivalent replacement or change shall be included within the scope of protection of the invention.

Claims (5)

1. A lie detection system based on electroencephalogram, is characterized in that: comprise electroencephalogram acquisition sensor system, electroencephalogram signal preprocessing system, electroencephalogram signal feature extraction system, electroencephalogram signal classification modeling system, database support system, computer The analysis system and the computer display system, the brain wave acquisition sensor system, the brain wave signal preprocessing system, the brain wave signal feature extraction system, and the brain wave signal classification modeling system are connected in sequence, and the brain wave signal classification modeling system and the database The support systems are all connected to the computer analysis system, the computer analysis system is connected to the computer display system, the brain wave signal preprocessing system includes a de-interference wavelet transform algorithm, an AR model and an adaptive predictor based on the AR model, and the database The support system includes a data storage system. The brainwave acquisition sensor system collects the brainwave signals of a large number of non-lying subjects with strong psychological quality and lying subjects with strong psychological quality. The processed brain wave signals of non-lying subjects and lying subjects with strong psychological quality, the computer analysis system includes a data extractor, a data receiver and a data comparator. 2. A kind of lie detection system based on EEG according to claim 1, characterized in that: said EEG acquisition sensor system adopts 3 conductive electrode sensors, a preamplifier circuit, a filter circuit and an AD converter. 3. A lie detection system based on EEG according to claim 2, characterized in that: the filter circuit is composed of a low-pass circuit and a trap circuit. 4. A kind of lie detection system based on EEG according to claim 1 or 2, characterized in that: the EEG acquisition sensor system adopts bluetooth technology to send the collected EEG signals into the EEG signal preprocessing system . 5. A kind of lie detection system based on EEG according to claim 1, characterized in that: the computer display system adopts the dynamic display of EEG power spectrum array diagram or EEG index histograms such as θ, α, β.