Poison-related detection device based on electro-oculogram signal and detection method thereof

Abstract

The device is used for making contact with and obtaining skin around the eyes of a detected person and electromyographic signals, can obtain the electromyographic signals and transmit the electromyographic signals to a signal amplifier, and finally obtains electromyographic signal feature data of the eye muscles of the detected person through processing; comparing and analyzing the extracted characteristic parameters with a pre-established drug-related model, obtaining a drug-related probability or a judgment conclusion through an algorithm and the model, and providing the drug-related probability or the judgment conclusion to a corresponding user or mechanism for reference and decision making; the poison-related detection device based on the electro-oculogram signals can accurately obtain and analyze the electro-oculogram signals of the detected person, so that the poison-related condition of the detected person is evaluated, a real-time and accurate detection result is provided, and after facial electric signal data of the detected person is rapidly and effectively collected, poison-related detection and judgment can be carried out, so that the detection efficiency is improved. The method has the advantages of convenience, rapidness, non-invasion, high precision, real-time performance, rich information and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of drug-related detection and identification, and in particular, is based on electrical signal processing and uses electrooculographic signals to obtain the eye bioelectric signals of the person being tested, and through signal processing and analysis, determines whether the person being tested is involved in drug-related activities. Specifically, it is a drug-related detection device based on electrooculographic signals and its detection method. Background Art

[0003] How to identify and measure drug-related persons is of great significance in drug management. It can help prevent drug abuse, maintain public safety, provide data basis for decision-making, combat drug trafficking, and promote the establishment of a sound drug abuse prevention and control system. The current detection methods mainly include: urine testing, blood testing, saliva testing, etc., but these tests are complex in sampling, cumbersome in the testing process, and time-consuming, and cannot provide instant feedback results. The eye information recognition developed by the applicant can achieve the purpose of recognition through the optical and imaging technology of the eye, but there is currently a technical gap in the industry on how to identify drug-related electrooculographic signals. Summary of the invention

[0004] In order to solve the shortcomings and defects of the above-mentioned prior art, the inventor has developed and designed a drug detection device and a detection method based on eye electrograms, which can quickly and effectively collect facial electrogram data of the person being tested and then detect whether the person is drug-related. It has the advantages of convenience, non-invasiveness, high precision, real-timeness and rich information. Specifically, the present invention is implemented as follows: a drug-related detection device based on electrooculographic signals, comprising: a frame body, serving as the structural body of the device, which can be worn on the eyes of a person being tested; a plurality of electrode members, which are respectively arranged on the inner side of the frame body facing the eyes of the person being tested, and after the frame body is worn, the electrodes can contact the skin around the eye sockets of the person being tested, and can obtain electromyographic signals and transmit them to a signal amplifier; a signal amplifier, which is connected to the electrode member in a built-in or external installation manner, can obtain the electrical signal obtained by the electrode member, amplify it, and send it to a processing module; a processing module, which is connected to the signal amplifier in a built-in or external installation manner, is used to receive signal data output by the signal amplifier, and process and convert it into waveform data for analyzing whether the person being tested is involved in drug-related crimes; a power supply module, which supplies power to the electrode member, the signal amplifier, and the processing module through a built-in power supply or an external power supply.

[0005] Furthermore, the frame body includes a left eye frame and a right eye frame, and the left eye frame and the right eye frame are connected as a whole at the top, and the electrode parts are three electrode parts, including a left eye electrode part and a right eye electrode part installed on the lower frames of the left eye frame and the right eye frame, and an eyebrow electrode part installed at the connection between the left eye frame and the right eye frame at the top.

[0006] Furthermore, the electrode member is a metal or composite material electrode, and the electrode contact is exposed on the surface of the frame body.

[0007] Furthermore, the electrode member is a sheet-shaped dry electrode, which is installed or attached to the frame body in a strip-shaped sheet structure or a circular structure; wherein the dry electrodes for the left and right eyes are vertically attached to the longitudinal frames of the left and right eye frames, respectively, and after wearing, they fit into the lateral forehead between the frontal lobe and the temporal lobe of the head of the person being measured near the temple, or the dry electrodes for the left and right eyes are respectively installed in the eye sockets that can be located on both sides of the bridge of the nose of the person being measured after wearing.

[0008] Furthermore, the left eye electrode and the right eye electrode are both main electrodes, and the eyebrow electrode is the reference electrode, which are connected to the signal amplifier through their own lines. After the signal amplifier processes them respectively, they are transmitted to the processing module through their own corresponding lines.

[0009] Furthermore, the processing module receives the data processed by the signal amplifier, obtains left eye electrical signal data, right eye electrical signal data, and reference electrical signal data, and converts them into corresponding waveform data, obtains the amplitude, frequency, and duration in the waveform data, constitutes a time series of the data, and processes and analyzes the data through the following method to determine whether it is drug-related.

[0010] Another aspect of the present invention discloses a drug-related detection method based on electrooculographic signals, which comprises the following steps based on the use of the above-mentioned drug-related detection device:

[0011] Step S1, signal acquisition: acquiring the electrooculogram signals of the left eye electrode, the right eye electrode, and the eyebrow electrode of the person being tested;

[0012] Step S2, preprocessing: performing signal gain amplification, filtering, denoising, segmentation and normalization processing on the electrooculogram signals obtained by the three electrodes respectively, to obtain three sets of electrooculogram signal data of the tested person;

[0013] Step S3, data processing: extracting features from the three sets of preprocessed electrooculogram signal data, and converting high-dimensional signals into low-dimensional feature vectors;

[0014] Step S4, data analysis: comparing and analyzing the extracted low-dimensional feature vector with the vector calculated from the standard sample of normal people;

[0015] Step S5: Classify the subjects into drug addicts or non-drug addicts according to the similarity or difference of the feature vectors, or measure the drug abuse degree of the subjects.

[0016] Working principle of the present invention: The technology of this scheme is based on electrooculogram signals for drug-related detection. Electrooculogram signals are electrical signals generated by the bioelectric activity of the eyeball and eye muscles. The eyeglass frame device with a new structural design provided by the present invention is used to arrange multiple electrodes in the eyeglass frame. After wearing, it contacts the skin surface of the person being tested to obtain electrooculogram signals in a non-invasive manner. The electrodes in the eyeglass device can measure the weak electrical signals generated by the eye muscles by contacting the skin, and these signals are amplified and processed in the device. Through the signal amplifier and processing module, the electrooculogram signals are amplified, filtered, and denoised to enhance the quality and accuracy of the signal. A series of characteristic parameters, such as amplitude, frequency, energy, etc., are extracted from the processed electrooculogram signals for evaluation and analysis of drug-related situations. Since the waveform of the electrooculogram signals of drug addicts is more irregular, with larger amplitude, lower frequency, and longer duration, it means that their eye movements are more random, slow, and uncoordinated. The electrooculogram (EO) signals of drug addicts change less before and after the stimulus presentation, as shown by a higher baseline level, a lower peak after the stimulus, and a longer recovery time, indicating that they are slower to respond to external information, have lower sensitivity, and have poorer adaptability. The EO signals of drug addicts differ less under different types of stimuli, as shown by lower discrimination between positive and negative stimuli, lower discrimination between novel and familiar stimuli, and lower discrimination between complex and simple stimuli, indicating that they have weaker emotional regulation ability, weaker memory encoding ability, and weaker cognitive processing ability. Therefore, the EO signals of drug addicts are very different from those of normal people, reflecting their serious impairment in psychological function. These differences may be caused by neuronal damage and neurotransmitter imbalance caused by drug abuse, or by individual differences or psychological problems that existed before drug abuse. Therefore, by collecting and analyzing EO signals, it can be combined with pupil detection to improve the detection level of drug addicts. The extracted feature parameters are compared and analyzed with the drug-related model established in advance, and the probability or judgment conclusion of drug-related involvement is obtained through algorithms and models. According to the analysis results, the probability of drug involvement or the judgment conclusion is output and provided to the corresponding users or institutions for reference and decision-making. The drug-related detection device based on electrooculogram signals can accurately obtain and analyze the electrooculogram signals of the tested person, thereby evaluating their drug-related situation and providing real-time and accurate detection results.

[0017] Beneficial technical effects of the present invention:

[0018] This technical solution uses an eyeglass device to contact the skin to obtain electrooculogram signals. It does not require any physical intrusion or sampling operations, does not cause any harm to the person being tested, and can provide a comfortable user experience. By comprehensively analyzing the characteristic parameters in the electrooculogram signals and the established drug-related model, this solution can accurately assess drug-related situations, can quickly process a large amount of electrooculogram signal data, and perform precise feature extraction and data analysis, thereby improving the efficiency of drug-related detection. This solution can be applied to different scenarios and needs, such as police enforcement, commercial security, etc., to provide a convenient and accurate drug-related detection tool for related fields. The solution of the present invention has high practicality and feasibility, helps to improve the efficiency and accuracy of drug-related detection, and has important application prospects and social significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a structural stereogram of a drug-related detection device based on electrooculographic signals of the present invention;

[0020] Figure 2 This is a diagram showing the position distribution of electrodes in a drug detection device based on electrooculographic signals of the present invention;

[0021] Figure 3 A schematic diagram of a drug detection device based on electrooculographic signals using dry electrodes according to the present invention;

[0022] Figure 4 It is a schematic diagram of an integrated structure with built-in integrated signal amplifier, circuit, processor, etc.;

[0023] Among them: 1 frame body, 2 electrode components, 3 signal amplifier, 4 processing module, 11 left eye frame, 12 right eye frame, 21 left eye electrode component, 22 right eye electrode component, 23 eyebrow electrode component. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0025] Embodiment 1: A drug detection device based on electrooculographic signals, comprising:

[0026] Frame body 1: As the main structure of the device, it can be worn on the eyes of the person being tested. Its function is to position the electrode 2 and ensure the comfort and stability of wearing.

[0027] Electrode 2: Several electrode 2 are arranged on the inner side of the frame body 1 facing the eyes of the person being tested. When the frame body 1 is worn, the electrode 2 can contact the skin around the eye sockets of the person being tested and obtain electromyographic signals. The number and position of the electrode 2 are properly designed to provide more accurate electrooculographic signal acquisition.

[0028] Signal amplifier 3: Signal amplifier 3 is connected to electrode 2 in a built-in or external manner. Its main function is to obtain the electrooculogram signal collected by electrode 2 and amplify it. This can enhance the strength and reliability of the signal and ensure that the subsequent analysis obtains accurate results.

[0029] Processing module 4: Processing module 4 is connected to signal amplifier 3 in an internal or external manner. It receives the signal data output by signal amplifier 3, processes the data and converts it into waveform data. Processing module 4 uses algorithms or pattern recognition technology to analyze the waveform data to determine whether the person being tested is involved in drug use. This function can achieve rapid detection and accurate judgment.

[0030] Power module: The power module supplies power to the electrode 2, the signal amplifier 3 and the processing module 4 through a built-in power supply or an external power supply. Its function is to ensure the normal operation of each component of the device, to ensure long-term use time and stable performance.

[0031] The optimized design of the frame body 1 includes the connection mode of the left eye frame body 11 and the right eye frame body 12 and the arrangement of the three electrode members 2. The left eye frame body 11 and the right eye frame body 12 are connected as one at the top, and this design makes the frame body 1 more stable and can better adapt to eyes of different sizes.

[0032] The optimized design of the electrode member 2 includes three metal electrode members 2: a left eye electrode member 21, a right eye electrode member 22, and an eyebrow electrode member 23. These electrode members 2 are connected to the signal amplifier 3 through their respective lines to obtain the left eye, right eye, and reference electrical signal data respectively. The electrode members 2 for the left and right eyes serve as the main electrodes, and the eyebrow electrode is the reference electrode. This setting can provide more accurate signal data and help improve the accuracy of drug-related detection.

[0033] In addition, the electrode member 2 can also be a sheet-shaped dry electrode. The dry electrode is installed or attached to the frame body 1 in a long sheet-shaped structure. The dry electrodes for the left and right eyes are respectively installed vertically on the longitudinal frames of the left and right eye frames 12, fitting the side forehead between the frontal lobe and the temporal lobe of the head of the person being tested, close to the temple. This setting can better contact the skin of the eyes of the person being tested, providing a more reliable electrooculographic signal.

[0034] In this embodiment, the various structural components and functional effects of the drug-related detection device based on electrooculogram signals cooperate with each other to achieve accurate electrooculogram signal acquisition, amplification processing and waveform data analysis, providing an effective and reliable tool for drug-related detection.

[0035] Embodiment 2: A drug detection method based on electrooculographic signals,

[0036] After collecting the electrooculogram signal

[0037] 1) Preprocess the electrooculogram signal first, including filtering, denoising, segmentation, normalization, etc. The purpose of preprocessing is to improve the quality of the signal, reduce noise and interference, and facilitate subsequent analysis.

[0038] 2) Then, the preprocessed EOG signal is subjected to feature extraction, which can be performed using time domain, frequency domain or time-frequency domain methods, such as mean, variance, energy, entropy, wavelet transform, etc. The purpose of feature extraction is to transform high-dimensional signals into low-dimensional feature vectors, reduce computational complexity, and highlight the main information of the signal.

[0039] 3) Then, the extracted feature vectors are classified, clustered or regressed, and supervised or unsupervised methods can be used, such as support vector machines, decision trees, neural networks, K-means, hierarchical clustering, etc. The purpose of classification, clustering or regression analysis is to classify the subjects into drug users or non-drug users based on the similarity or difference of the feature vectors, or to predict the degree of drug use of the subjects.

[0040] 4) Finally, the results of classification, clustering or regression analysis are evaluated and optimized, and indicators such as accuracy, recall rate, F1 value, or methods such as cross-validation and grid search can be used. The purpose of evaluation and optimization is to test the effectiveness and stability of the analysis method and improve the credibility and accuracy of the analysis results.

[0041] Embodiment 3: A drug detection method based on electrooculogram signals, based on the use of a drug detection device based on electrooculogram signals described in Embodiment 1, specifically comprising the following steps:

[0042] Step S1, signal acquisition: acquiring the electrooculogram signals of the left eye electrode, the right eye electrode, and the eyebrow electrode of the person being tested;

[0043] Step S2, preprocessing: performing signal gain amplification, filtering, denoising, segmentation and normalization processing on the electrooculogram signals obtained by the three electrodes respectively, to obtain three sets of electrooculogram signal data of the tested person;

[0044] Step S3, data processing: extracting features from the three sets of preprocessed electrooculogram signal data, and converting high-dimensional signals into low-dimensional feature vectors;

[0045] Step S4, data analysis: comparing and analyzing the extracted low-dimensional feature vector with the vector calculated from the standard sample of normal people;

[0046] Step S5: Classify the subjects into drug addicts or non-drug addicts according to the similarity or difference of the feature vectors, or measure the drug abuse degree of the subjects.

[0047] Preferably, step S4 comprises the following steps:

[0048] For the three sets of collected time series {x(n)} consisting of N data, the following calculations are performed respectively:

[0049] (1) A vector sequence of dimension m is formed according to the sequence number, X m (1),…,X m (N-m+1), where X m (i)={x(i),x(i+1),…,x(i+m-1)}, 1≤i≤N-m+1;

[0050] The vector sequence represents the m consecutive values ​​of x starting from the i-th point;

[0051] (2) Define vector X m (i) With X m (j) The distance d[X m (i), X m (j)] is the absolute value of the maximum difference between the two corresponding elements; that is:

[0052]

[0053] (3) For a given X M (i), statistics X m (i) With X m (j) The distance between them is less than or equal to r (1

[0054] ≤j≤Nm, j≠i), and record it as B;

[0055] For 1≤i≤Nm, define:

[0056]

[0057] (4) Definition B (m) (r) is:

[0058]

[0059] (5) Increase the dimension to m+1 and calculate X m+1 (i) With X m+1The number of distances (j)(1≤j≤Nm, j≠i) less than or equal to r, denoted as A i , A m i (r) is defined as:

[0060]

[0061] (6) Definition A m (r) is:

[0062]

[0063] Take m=2, r=0.2SD(x) (SD(x) is the standard deviation of the sequence)

[0064] Find the value of the group

[0065] Step S4, data analysis: perform operations on the extracted low-dimensional feature vector A composed of En(i) and the vector B calculated from the standard sample of normal people:

[0066]

[0067] Get the similarity or difference of vectors;

[0068] Step S5, based on the similarity or difference coefficient cosθ of the feature vector, if cosθ=-1, the subject is taking drugs, if cosθ=1, the subject is not taking drugs, and between [-1, 1] it indicates the degree of drug taking of the subject, the closer to -1, the greater the possibility that the subject is taking drugs.

[0069] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. A drug detection device based on electrooculographic signals, characterized in that include: The frame body (1) is used as the structural body of the device and can be worn on the eyes of the person being tested; A plurality of electrode members (2) are respectively arranged on the inner side of the frame body (1) facing the eyes of the person being tested. After the frame body (1) is worn, the electrodes can contact the skin around the eye sockets of the person being tested and can obtain myoelectric signals and transmit them to the signal amplifier (3); The signal amplifier (3) is connected to the electrode component (2) in an internal or external installation manner, and can obtain the electrical signal obtained by the electrode component (2), amplify the signal, and send it to the processing module (4); The processing module (4) is connected to the signal amplifier (3) in a built-in or external installation manner, and is used to receive the signal data output by the signal amplifier (3), and process and convert it into waveform data for analyzing whether the person being tested is involved in drug use; The power module supplies power to the electrode member (2), the signal amplifier (3), and the processing module (4) through a built-in power source or an external power source.

2. The drug detection device based on electrooculographic signals according to claim 1 is characterized in that: The frame body (1) comprises a left eye frame (11) and a right eye frame (12), wherein the left eye frame (11) and the right eye frame (12) are connected as a whole at the top, and the electrode member (2) comprises three electrode members (2), comprising a left eye electrode member (21) and a right eye electrode member (22) mounted on the lower frames of the left eye frame (11) and the right eye frame (12), and an eyebrow center electrode member (23) mounted at the top connection of the left eye frame (11) and the right eye frame (12).

3. The drug detection device based on electrooculographic signals according to claim 2 is characterized in that: The electrode member (2) is a metal or composite material electrode, and the electrode contact is exposed on the surface of the frame body (1).

4. The drug detection device based on electrooculographic signals according to claim 1 is characterized in that: The electrode member (2) is a sheet-shaped dry electrode, which is installed or attached to the frame body (1) in a strip-shaped sheet structure or a circular structure; The dry electrodes for the left and right eyes are respectively attached vertically to the longitudinal frames of the left and right eye frames (12), and after being worn, they fit the lateral forehead between the frontal lobe and the temporal lobe of the head of the person being tested and close to the temple, or The dry electrodes for the left and right eyes are respectively installed at the eye sockets which can be located on both sides of the bridge of the nose of the person being tested after wearing.

5. The drug detection device based on electrooculographic signals according to claim 2 is characterized in that: The left eye electrode (21) and the right eye electrode (22) are both main electrodes, and the eyebrow electrode is the reference electrode, and are respectively connected to the signal amplifier (3) through their own lines. After being processed by the signal amplifier (3), the signals are transmitted to the processing module (4) through their own corresponding lines.

6. The drug detection device based on electrooculographic signals according to claim 5 is characterized in that: The processing module (4) receives the data processed by the signal amplifier (3), obtains left eye electrical signal data, right eye electrical signal data, and reference electrical signal data, and converts them into corresponding waveform data, obtains the amplitude, frequency, and duration in the waveform data, and forms a time series of data for determining whether drugs are involved.

7. A drug detection method based on electrooculographic signals, based on the use of a drug detection device as described in any one of claims 1 to 6, characterized in that The following steps are involved: Step S1, signal acquisition: acquiring electrooculographic signals of the left eye electrode (21), the right eye electrode (22), and the eyebrow electrode of the person being tested; Step S2, preprocessing: performing signal gain amplification, filtering, denoising, segmentation and normalization processing on the electrooculogram signals obtained by the three electrodes respectively, to obtain three sets of electrooculogram signal data of the tested person; Step S3, data processing: extracting features from the three sets of preprocessed electrooculogram signal data, and converting high-dimensional signals into low-dimensional feature vectors; Step S4, data analysis: comparing and analyzing the extracted low-dimensional feature vector with the vector calculated from the standard sample of normal people; Step S5: Classify the subjects into drug addicts or non-drug addicts according to the similarity or difference of the feature vectors, or measure the drug abuse degree of the subjects.

8. The drug-related detection method according to claim 7, characterized in that: The step S4 comprises the following steps: For the three sets of collected time series {x(n)} consisting of N data, the following calculations are performed respectively: (1) A vector sequence of dimension m is formed according to the sequence number, X m (1),…,X m (N-m+1), where X m (i)={x(i),x(i+1),…,x(i+m-1)}, 1≤i≤N-m+1; The vector sequence represents the m consecutive values ​​of x starting from the i-th point; (2) Define vector X m (i) With X m (j) The distance d[X m (i), X m (j)] is the absolute value of the maximum difference between the two corresponding elements; that is: d[X m (i),X m (j)]= maxX / =o..…,m-1( lx ( i +h) - x (j +k)|) (1) (3) For a given X M (i), statistics X m (i) With X m (j) The number of j (1≤j≤Nm, j≠i) whose distance between them is less than or equal to r, and is denoted as B; For 1≤i≤Nm, define: (4) Definition B (m) (r) is: (5) Increase the dimension to m+1 and calculate X m+1 (i) With X m+1 The number of distances (j)(1≤j≤Nm, j≠i) less than or equal to r, denoted as A i , A m i (r) is defined as: (6) Definition A m (r) is: Take m=2, r=0.2SD(x) (SD(x) is the standard deviation of the sequence) Find the value of the group Step S4, data analysis: perform operations on the extracted low-dimensional feature vector A composed of En(i) and the vector B calculated from the standard sample of normal people: Get the similarity or difference of vectors; Step S5, based on the similarity or difference coefficient cosθ of the feature vector, if cosθ=-1, the subject is taking drugs, if cosθ=1, the subject is not taking drugs, and between [-1, 1] it indicates the degree of drug taking of the subject, the closer to -1, the greater the possibility that the subject is taking drugs.

Images