A brain-computer interface experimental method based on functional near infrared

Abstract

The present invention is applicable to the technical field of brain-computer interface and brain area health examination, and provides a brain-computer interface experimental method based on functional near infrared, comprising the following steps: receiving brain image templates and brain hemodynamic parameter samples collected by a brain-computer interface system, retrieving corresponding brain image templates and brain hemodynamic parameter templates according to numbers, comparing the brain image templates and brain hemodynamic parameter templates with the brain image and brain hemodynamic parameter samples of the subject, each brain area in the brain image of the subject will automatically match each brain area in the brain image template, matching the brain area image with the corresponding brain area image standard library according to the marked brain area name, outputting matching standard brain area images and standard brain area hemodynamic parameters, comparing the marked brain area hemodynamic parameter samples with the standard brain area hemodynamic parameters, outputting brain area status bar information, and making the experimental results more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of brain-computer interface and brain area health examination, and in particular to a brain-computer interface experimental method based on functional near infrared. Background Art

[0002] Functional near-infrared spectroscopy is a completely non-destructive in vivo optical detection technology developed in recent years. Biological tissue has the characteristics of low absorption and high scattering of light in the near-infrared band. Near-infrared light can penetrate several centimeters of biological tissue to detect deep biological tissue. When the brain is activated, the oxygen metabolism rate increases, and cerebral blood flow also increases, which will cause changes in the concentration of oxygenated hemoglobin (HbO2) and reduced hemoglobin (Hb). The absorption spectra of HbO2 and Hb in the near-infrared band are specific. Therefore, near-infrared spectroscopy can indirectly detect brain neural activity based on changes in the intensity or phase of the emitted light. Compared with other biomedical imaging technologies, near-infrared spectroscopy has the advantages of flexible use, portability and low cost. Therefore, near-infrared spectroscopy has been widely used in the field of brain functional imaging and detection in recent years, and also provides a new technical means for the development of non-destructive brain-computer interface (BCI).

[0003] Brain-computer interface is a system that converts neurophysiological signals in the thinking process into control signals to control external machines without relying on the peripheral nervous system and muscles. Brain-computer interface can not only help severely paralyzed patients communicate with the outside world, but also assist stroke patients in recovering motor function. Non-invasive brain-computer interface shows broad application prospects due to its relatively easy-to-obtain signals and a wide range of users. At present, many technologies have been applied to the field of non-invasive brain-computer interface, such as electroencephalography (EEG), magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI) and functional near-infrared spectroscopy. Due to the expensive and complex equipment and huge size, magnetoencephalography and functional magnetic resonance imaging are currently limited to scientific research use and have no prospects for practical application. EEG directly detects the electrical signals of neural activity and is the most commonly used technology in the field of brain-computer interface. Its advantages are simple to use, safe and cheap.

[0004] However, in the experiment of studying the health level of various brain areas of subjects (the most common are the primary motor cortex and prefrontal layer, the former is related to human muscle movements, and the latter is related to mental arithmetic or audio and video, etc.) based on the technical principle of functional near-infrared brain-computer interface, there is a problem of being unable to automatically determine whether the collected brain data of the subjects is healthy. Generally, manual automatic judgment and comparison are required, resulting in low efficiency and large errors in the judgment results. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a brain-computer interface experimental method based on functional near-infrared to solve the problems existing in the above-mentioned background technology.

[0006] The present invention is implemented as follows: a brain-computer interface experimental method based on functional near infrared, the method comprising the following steps:

[0007] The brain-computer interface system was connected to the scalp surface of the subjects, and the subjects completed the imagination task according to the prompts;

[0008] Obtaining brain hemodynamic parameter samples and brain images of the subject collected by the brain-computer interface system, wherein the brain images corresponding to the brain hemodynamic parameter samples of the subject are marked with numbers;

[0009] Retrieving the corresponding brain image template and brain hemodynamic parameter template according to the number, wherein the brain image template and the brain hemodynamic parameter template are provided with one or more information boxes, each of which corresponds to a brain region name;

[0010] Overlaying the brain image template and the brain hemodynamic parameter template on the subject's brain image and the brain hemodynamic parameter sample to obtain one or more brain region images and brain region hemodynamic parameter samples, each brain region image and brain region hemodynamic parameter sample being marked with a brain region name;

[0011] According to the marked brain region name, the brain region image is input into the corresponding brain region image standard library for matching, and the matching standard brain region image and standard brain region hemodynamic parameters are output;

[0012] Match the marked brain region hemodynamic parameter samples with the standard brain region hemodynamic parameter, and output the brain region status bar information;

[0013] Summarize the status bar information of one or more brain regions to generate experimental result information.

[0014] As a further solution of the present invention: the step of connecting the scalp surface of the subject using the brain-computer interface system specifically includes:

[0015] A near-infrared detector and a CT device were placed close to the scalp surface of the subjects' heads to collect brain hemodynamic parameter samples and brain images, respectively.

[0016] As a further solution of the present invention: the step of obtaining the brain hemodynamic parameter sample of the subject collected by the brain-computer interface system specifically includes:

[0017] The subjects completed the imagination task according to the prompts, and the near-infrared detector was used to collect brain hemodynamic signals;

[0018] The brain hemodynamic parameters of the subjects were calculated using the signal detection method of near-infrared brain-computer interface based on independent component analysis combined with least squares method;

[0019] The subjects completed the imagination task several times according to the prompts, and the near-infrared detector collected several brain hemodynamic signals. The near-infrared brain-computer interface signal detection method based on independent component analysis combined with least squares method was used to calculate several brain hemodynamic parameters of the subjects.

[0020] A number of brain hemodynamic parameters are summarized to generate a sample of the brain hemodynamic parameters of the subject.

[0021] As a further solution of the present invention: the step of retrieving the corresponding brain image and brain hemodynamic parameter samples according to the serial number specifically includes:

[0022] Enter the number corresponding to the subject's brain parameter sample into the information box;

[0023] Output the corresponding brain images and brain hemodynamic parameter samples.

[0024] Another object of the present invention is to provide an electric power equipment detection system based on infrared images.

[0025] As a further solution of the present invention: the step of inputting the brain region image into the corresponding brain region image standard library for matching according to the marked brain region name specifically includes:

[0026] According to the marked brain region name, the brain region image is input into the corresponding brain region image standard library for matching. Each brain region name corresponds to a brain region image standard library;

[0027] Matching the brain region images marked with the brain region names with the standard brain region images in the brain region parameter standard library to obtain a number of matching values;

[0028] The standard brain region image with the highest matching value is output, and at the same time, the standard hemodynamic parameter sample information corresponding to the standard brain region image is output.

[0029] As a further solution of the present invention: the near-infrared detector is composed of a dual-wavelength light source L, a detector D1 and a detector D2. The near-infrared light emitted by the dual-wavelength light source L is incident on the brain tissue to be tested, the detector D1 is used to detect the hemodynamic signals of the primary motor cortex, and the detector D2 is used to detect the hemodynamic signals of the prefrontal layer.

[0030] As a further solution of the present invention: the steps of respectively calculating the brain hemodynamic parameter samples of the subject using the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method specifically include:

[0031] The subjects completed an imaginary task involving muscle movement or muscle tension according to the prompts. The detector D1 collected the hemodynamic change signals of the primary motor cortex and used the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method to calculate the hemodynamic parameters s(k)1a1 of the primary motor cortex.

[0032] The subjects completed imagination tasks involving mental arithmetic or musical intentions according to the prompts. Detector D2 collected and detected the hemodynamic signals of the prefrontal layer, and used the signal detection method of the near-infrared brain-computer interface based on independent component analysis and least squares method to calculate the hemodynamic parameters s(k)2b1 of the prefrontal layer.

[0033] The subject completes the imaginary task involving muscle movement or muscle tension several times according to the prompts, and several primary motor cortex hemodynamic parameters are summarized, and the subject's primary motor cortex hemodynamic parameter sample s(k)1(a1....an) is output;

[0034] The subjects completed the imagination task involving mental arithmetic or musical intention several times according to the prompts, summarized several prefrontal layer hemodynamic parameters, and output the prefrontal layer hemodynamic parameter samples s(k)2(b1....bn).

[0035] As a further solution of the present invention: the step of matching the brain region images marked with brain region names with standard brain region images in the brain region parameter standard library specifically includes:

[0036] The hash method based on discrete cosine transform (DCT) is used to calculate the hash values ​​of the subject's primary motor cortex image and the standard primary motor cortex image, respectively, to obtain h_1 and h_2.

[0037] The hash method based on discrete cosine transform (DCT) is used to calculate the hash values ​​of the subject's prefrontal layer image and the standard prefrontal layer image, and h_3 and h_4 are obtained;

[0038] Calculate the Hamming distance dis_h1 between h_1 and h_2, and calculate the Hamming distance dis_h2 between h_3 and h_4;

[0039] The similarity between the subject's primary motor cortex image and the standard primary motor cortex image is calculated according to the Hamming distance dis_h1, and the similarity between the subject's prefrontal layer image and the standard prefrontal layer image is calculated according to the Hamming distance dis_h2. The similarity is the matching value.

[0040] As a further solution of the present invention: the step of matching the labeled brain region hemodynamic parameter sample with the standard brain region hemodynamic parameter specifically includes:

[0041] The primary motor cortex hemodynamic change signal sample s(k)1(a1-a2) and the prefrontal layer hemodynamic change signal sample s(k)2(b1-b2) are respectively compared with the standard value of the brain hemodynamic change signal using the Tanimoto coefficient, and the comparison values ​​T1 and T2 are output;

[0042] When T1 and T2 are close to 1, the information that the brain area is in good condition is output;

[0043] When T1 and T2 are close to 0, information about the poor state of the brain area is output.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] In the present invention: after receiving the brain image template and brain hemodynamic parameter samples collected by the brain-computer interface system, the corresponding brain image template and brain hemodynamic parameter template are retrieved according to the number, and the brain image template and the brain hemodynamic parameter template each have a corresponding brain region name on the corresponding information box. When the brain image template and the brain hemodynamic parameter template are compared with the subject's brain image and the brain hemodynamic parameter sample, each brain region in the subject's brain image will automatically match each brain region in the brain image template, thereby obtaining one or more brain region images, and the brain region hemodynamic parameter samples will automatically match each brain region in the brain image template. The brain region hemodynamic parameters samples and brain region images are automatically marked with corresponding names, and the brain region images are matched with the corresponding brain region image standard library according to the marked brain region names, and the matching standard brain region images and standard brain region hemodynamic parameters are output, and the marked brain region hemodynamic parameter samples are compared with the standard brain region hemodynamic parameters for differentiation or similarity. After the comparison results come out, the brain region status bar information can be output. By observing the brain region status bar information, the staff can understand the health status of each brain region of the subject, and the experimental results will be more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The figure is a flow chart of a method for detecting electric power equipment based on infrared images.

[0047] Figure 2 The present invention is a flow chart for obtaining samples of brain hemodynamic parameters of subjects collected by a brain-computer interface system in an infrared image-based power equipment detection method.

[0048] Figure 3 The present invention is a flow chart for calculating and obtaining samples of brain hemodynamic parameters of subjects respectively using a signal detection method of a near-infrared brain-computer interface based on independent component analysis and least squares method in an infrared image-based power equipment detection method.

[0049] Figure 4 The present invention is a flow chart of inputting brain region images into a corresponding brain region image standard library for matching according to marked brain region names in an infrared image-based power equipment detection method.

[0050] Figure 5 The present invention is a flow chart for matching a brain region image marked with a brain region name with a standard brain region image in a brain region parameter standard library in an infrared image-based power equipment detection method.

[0051] Figure 6 The present invention is a flowchart for matching the marked brain region hemodynamic parameter samples with the standard brain region hemodynamic parameter in an infrared image-based power equipment detection method. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0054] like Figure 1 As shown, an embodiment of the present invention provides a brain-computer interface experimental method based on functional near infrared, and the method comprises the following steps:

[0055] S100 uses a brain-computer interface system to connect to the scalp surface of the subjects, and the subjects complete the imagination task according to the prompts;

[0056] S200, obtaining brain hemodynamic parameter samples and brain images of the subject collected by the brain-computer interface system, wherein the brain images corresponding to the brain hemodynamic parameter samples of the subject are marked with numbers;

[0057] S300, calling the corresponding brain image template and brain hemodynamic parameter template according to the serial number, wherein the brain image template and the brain hemodynamic parameter template are provided with one or more information boxes, each of which corresponds to a brain region name;

[0058] S400, overlaying the brain image template and the brain hemodynamic parameter template on the subject's brain image and the brain hemodynamic parameter sample to obtain one or more brain region images and brain region hemodynamic parameter samples, each brain region image and brain region hemodynamic parameter sample being marked with a brain region name;

[0059] S500, inputting the brain region image into the corresponding brain region image standard library for matching according to the marked brain region name, and outputting the matching standard brain region image and standard brain region hemodynamic parameters;

[0060] S600, matching the marked brain region hemodynamic parameter sample with the standard brain region hemodynamic parameter, and outputting brain region status bar information;

[0061] S700, summarizing status bar information of one or more brain regions to generate experimental result information.

[0062] It should be noted that functional near-infrared spectroscopy is a completely non-destructive in vivo optical detection technology developed in recent years. Biological tissue has the characteristics of low absorption and high scattering of light in the near-infrared band. Near-infrared light can penetrate several centimeters of biological tissue to detect deep biological tissue. When the brain is activated, the oxygen metabolism rate increases, and cerebral blood flow also increases, which will cause changes in the concentration of oxygenated hemoglobin (HbO2) and reduced hemoglobin (Hb). The absorption spectra of HbO2 and Hb in the near-infrared band are specific. Therefore, near-infrared spectroscopy can indirectly detect brain neural activity based on changes in the intensity or phase of the emitted light. Compared with other biomedical imaging technologies, near-infrared spectroscopy has the advantages of flexible use, portability and low cost. Therefore, near-infrared spectroscopy has been widely used in the field of brain functional imaging and detection in recent years, and also provides a new technical means for the development of non-destructive brain-computer interface (BCI).

[0063] Brain-computer interface is a system that converts neurophysiological signals in the thinking process into control signals to control external machines without relying on the peripheral nervous system and muscles. Brain-computer interface can not only help severely paralyzed patients communicate with the outside world, but also assist stroke patients in recovering motor function. Non-invasive brain-computer interface shows broad application prospects due to its relatively easy-to-obtain signals and a wide range of users. At present, many technologies have been applied to the field of non-invasive brain-computer interface, such as electroencephalography (EEG), magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI) and functional near-infrared spectroscopy. Due to their expensive and complex equipment and huge size, magnetoencephalography and fMRI are currently limited to scientific research and have no prospects for practical application. EEG directly detects the electrical signals of neural activity and is the most commonly used technology in the field of brain-computer interface. Its advantages are simple to use, safe and cheap. However, the disadvantage of EEG is that the spatial resolution is low and the activation of brain areas cannot be located, which limits its further improvement in the recognition accuracy of brain-computer interface. In addition, there is a phenomenon of brain-computer interface illiteracy in brain-computer interface based on EEG, that is, some users cannot operate the brain-computer interface system anyway. Therefore, it is necessary to develop a technology to make up for the shortcomings of EEG and expand the field of brain-computer interface.

[0064] In the embodiment of the present invention, the brain image template and the brain hemodynamic parameter template are brain images and brain hemodynamic parameters that meet health requirements that have been determined before the experiment. One or more information boxes will appear for each brain image and brain hemodynamic parameter sample of the subject, and the corresponding brain region name will be displayed in the information box. After receiving the brain image template and brain hemodynamic parameter sample collected by the brain-computer interface system, the corresponding brain image template and brain hemodynamic parameter template will be retrieved according to the number. Since the brain contains multiple brain regions, the brain image template and the brain hemodynamic parameter template are provided with one or more information boxes, and each information box corresponds to a brain region name. When the brain image template and the brain hemodynamic parameter template are overlaid on the subject's brain image and the brain hemodynamic parameter sample, each brain region in the subject's brain image will automatically be associated with the brain. The brain regions in the image template are automatically matched to obtain one or more brain region images, and the brain region hemodynamic parameter samples are automatically corresponding to the corresponding brain region images, and the brain region hemodynamic parameter samples and the brain region images are automatically marked with corresponding names, and the brain region images are continuously input into the corresponding brain region image standard library according to the marked brain region names for matching, and the matching standard brain region images and standard brain region hemodynamic parameters are output, and the standard brain region images and standard brain region hemodynamic parameters refer to the brain region images and brain region hemodynamic parameters that meet the health requirements, and the marked brain region hemodynamic parameter samples are differentiated or compared with the standard brain region hemodynamic parameters for similarity, and the brain region status bar information can be output after the comparison results come out, and the staff can understand the health status of each brain region of the subject by observing the brain region status bar information, and the experimental results will be more accurate.

[0065] As a preferred embodiment of the present invention, the step of connecting the scalp surface of the subject using the brain-computer interface system specifically includes:

[0066] A near-infrared detector and a CT device were placed close to the scalp surface of the subjects' heads to collect brain hemodynamic parameter samples and brain images, respectively.

[0067] In the embodiment of the present invention, the near infrared detector and the CT device are both fixedly installed.

[0068] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of obtaining the brain hemodynamic parameter sample of the subject collected by the brain-computer interface system specifically includes:

[0069] S201, the subjects completed the imagination task according to the prompts, and the near-infrared detector was used to collect brain hemodynamic signals;

[0070] S202, calculating the brain hemodynamic parameters of the subject using a signal detection method of a near-infrared brain-computer interface based on independent component analysis combined with a least squares method;

[0071] S203, the subject completes the imagination task several times according to the prompt, the near-infrared detector collects several brain hemodynamic signals, and the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method is used to calculate several brain hemodynamic parameters of the subject;

[0072] S204, summarizing a number of brain hemodynamic parameters to generate a sample of the brain hemodynamic parameters of the subject.

[0073] In the embodiment of the present invention, the existing main technologies include electroencephalogram, magnetoencephalogram, positron emission tomography, and functional magnetic resonance imaging. Based on the relationship between neuronal activity, local energy metabolism and local hemodynamics, by measuring the absorption characteristics of brain tissue to near-infrared light waves, hemodynamic changes based on information such as the concentration of oxygenated hemoglobin and reduced hemoglobin can be provided. Therefore, by using near-infrared spectroscopy technology to measure the optical parameters, blood oxygen and hemodynamic parameter information of the region, the functional response of the cerebral cortex to stimuli such as limb movement, vision, hearing, touch and language can be obtained, which is used for the study of brain-computer interfaces. When the subject completes the imagination task according to the prompt, the near-infrared detector is used to collect brain hemodynamic signals. Independent component analysis combined with the least squares method is a means of calculating brain hemodynamic parameters according to changes in brain hemodynamic signals in the prior art, so it will not be repeated.

[0074] As a preferred embodiment of the present invention, the step of retrieving the corresponding brain image template and brain hemodynamic parameter template according to the serial number specifically includes:

[0075] Enter the number corresponding to the subject's brain parameter sample into the information box;

[0076] Output the corresponding brain image template and brain hemodynamic parameter template.

[0077] In the embodiment of the present invention, the corresponding brain image template and brain hemodynamic parameter template are retrieved according to the number. Since the brain contains multiple brain regions, the brain image template and the brain hemodynamic parameter template are provided with one or more information boxes, and each information box corresponds to a brain region name.

[0078] like Figure 4 As shown, the embodiment of the present invention also provides a brain-computer interface experimental method based on functional near infrared, wherein the step of inputting the brain region image into the corresponding brain region image standard library for matching according to the marked brain region name specifically includes:

[0079] S501, inputting the brain region image into the corresponding brain region image standard library for matching according to the marked brain region name, wherein each brain region name corresponds to a brain region image standard library;

[0080] S502, matching the brain region image marked with the brain region name with the standard brain region image in the brain region parameter standard library to obtain a plurality of matching values;

[0081] S503, outputting the standard brain region image with the highest matching value, and at the same time outputting the standard hemodynamic parameter sample information corresponding to the standard brain region image.

[0082] In an embodiment of the present invention, when the brain image template and the brain hemodynamic parameter template are overlaid on the subject's brain image and the brain hemodynamic parameter sample, each brain region in the subject's brain image will automatically match each brain region in the brain image template, thereby obtaining one or more brain region images, and the brain region hemodynamic parameter samples will automatically correspond to the corresponding brain region images, and the brain region hemodynamic parameter samples and the brain region images will be automatically marked with corresponding names.

[0083] As a preferred embodiment of the present invention, the near-infrared detector is composed of a dual-wavelength light source L, a detector D1 and a detector D2. The near-infrared light emitted by the dual-wavelength light source L is incident on the brain tissue to be tested. The detector D1 is used to detect the hemodynamic signals of the primary motor cortex, and the detector D2 is used to detect the hemodynamic signals of the prefrontal layer.

[0084] In this embodiment, the near-infrared light emitted by the near-infrared probe is incident on the brain tissue to be tested, the detector D1 can sense the hemodynamic changes of the primary motor cortex, and the detector D2 can sense the hemodynamic changes of the prefrontal layer.

[0085] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of respectively calculating and obtaining the brain hemodynamic parameter samples of the subject using the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method specifically include:

[0086] S2031, the subject completes an imaginary task involving muscle movement or muscle tension according to the prompts, the detector D1 collects the primary motor cortex hemodynamic change signal, and uses the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method to calculate the primary motor cortex hemodynamic parameters s(k)1a1 respectively;

[0087] S2032, the subject completes an imagination task involving mental arithmetic or musical intention according to the prompts, and the detector D2 collects and detects the hemodynamic signals of the prefrontal layer, and uses the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method to calculate the hemodynamic parameters s(k)2b1 of the prefrontal layer respectively;

[0088] S2033, the subject completes the imagination task involving muscle movement or muscle tension several times according to the prompt, summarizes several primary motor cortex hemodynamic parameters, and outputs the subject's primary motor cortex hemodynamic parameter sample s(k)1(a1....an);

[0089] S2034, the subject completes the imagination task involving mental arithmetic or musical intention several times according to the prompts, summarizes several prefrontal layer hemodynamic parameters, and outputs the prefrontal layer hemodynamic parameter samples s(k)2(b1....bn).

[0090] In an embodiment of the present invention, the formula for solving the hemodynamic signal in the brain-computer interface signal based on independent component analysis and least squares method is: s(k)=bl(k)+c, a1....an and b1....bn represent the number of experiments. There is no specific restriction on the number of experiments here, so no restriction will be imposed.

[0091] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of matching the brain region image marked with the brain region name with the standard brain region image in the brain region parameter standard library specifically includes:

[0092] S5021, using a hash method based on discrete cosine transform DCT, respectively calculating the hash values ​​of the subject's primary motor cortex image and the standard primary motor cortex image to obtain h_1 and h_2;

[0093] S5022, using a hash method based on discrete cosine transform (DCT) to calculate hash values ​​of the subject's prefrontal layer image and the standard prefrontal layer image, respectively, to obtain h_3 and h_4;

[0094] S5023, calculating the Hamming distance dis_h1 between h_1 and h_2, and calculating the Hamming distance dis_h2 between h_3 and h_4;

[0095] S5024, calculating the similarity between the primary motor cortex image of the subject and the standard primary motor cortex image according to the Hamming distance dis_h1, and calculating the similarity between the prefrontal layer image of the subject and the standard prefrontal layer image according to the Hamming distance dis_h2, and the similarity is the matching value.

[0096] In an embodiment of the present invention, a hash method based on discrete cosine transform DCT is used to identify an image, which is an AI image recognition method in the prior art. The hash method based on discrete cosine transform DCT uses discrete cosine transform to extract low-frequency components of the image, first converts the image into a grayscale image of standard size, then performs discrete cosine transform DCT transform on the grayscale image, and then extracts a 64-bit hash value from the coefficient matrix as a fingerprint, and then calculates the Hamming distance dis_h between h_1 and h_2, and calculates the similarity between the primary motor cortex image of the subject and the standard primary motor cortex image and the similarity between the prefrontal layer image of the subject and the standard prefrontal layer image based on the Hamming distance dis_h. This method for calculating the similarity between two images is a prior art and will not be described in detail here.

[0097] like Figure 6 As shown, as a preferred embodiment of the present invention, the step of matching the marked brain region hemodynamic parameter sample with the standard brain region hemodynamic parameter specifically includes:

[0098] S601, using Tanimoto coefficients to compare the primary motor cortex hemodynamic change signal sample s(k)1(a1-a2) and the prefrontal layer hemodynamic change signal sample s(k)2(b1-b2) with the brain hemodynamic change signal standard value, and output comparison values ​​T1 and T2;

[0099] S602, when T1 and T2 are close to 1, the information that the brain area is in a good state is output;

[0100] S603, when T1 and T2 are close to 0, output the information of poor brain area status.

[0101] In the embodiment of the present invention, the Tanimoto coefficient is used as an algorithm to calculate the similarity of two groups of data. When several groups of measurement results in the primary motor cortex hemodynamic change signal sample s(k)1(a1-a2) are compared with the labeled value of the primary motor cortex hemodynamic change signal, when the similarity is close to 1, it means that the health state of the primary motor cortex is good, and when the similarity is close to 0, it means that the health state of the primary motor cortex is poor, and the same is true for the prefrontal layer.

[0102] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0103] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0104] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A brain-computer interface experimental method based on functional near infrared, characterized in that: The method comprises the following steps: The brain-computer interface system was connected to the scalp surface of the subjects, and the subjects completed the imagination task according to the prompts; Obtaining brain hemodynamic parameter samples and brain images of the subject collected by the brain-computer interface system, wherein the brain images corresponding to the brain hemodynamic parameter samples of the subject are marked with numbers; Retrieving the corresponding brain image template and brain hemodynamic parameter template according to the number, wherein the brain image template and the brain hemodynamic parameter template are provided with one or more information boxes, each of which corresponds to a brain region name; Overlaying the brain image template and the brain hemodynamic parameter template on the subject's brain image and the brain hemodynamic parameter sample to obtain one or more brain region images and brain region hemodynamic parameter samples, each brain region image and brain region hemodynamic parameter sample being marked with a brain region name; According to the marked brain region name, the brain region image is input into the corresponding brain region image standard library for matching, and the matching standard brain region image and standard brain region hemodynamic parameters are output; Match the marked brain region hemodynamic parameter samples with the standard brain region hemodynamic parameter, and output the brain region status bar information; Summarize the status bar information of one or more brain regions to generate experimental result information.

2. The brain-computer interface experimental method based on functional near infrared according to claim 1 is characterized in that: The step of connecting the scalp surface of the subject using the brain-computer interface system specifically includes: A near-infrared detector and a CT device were placed close to the scalp surface of the subjects' heads to collect brain hemodynamic parameter samples and brain images, respectively.

3. The brain-computer interface experimental method based on functional near infrared according to claim 2 is characterized in that: The step of obtaining the brain hemodynamic parameter sample of the subject collected by the brain-computer interface system specifically includes: The subjects completed the imagination task according to the prompts, and the near-infrared detector was used to collect brain hemodynamic signals; The brain hemodynamic parameters of the subjects were calculated using the signal detection method of near-infrared brain-computer interface based on independent component analysis combined with least squares method; The subjects completed the imagination task several times according to the prompts, and the near-infrared detector collected several brain hemodynamic signals. The near-infrared brain-computer interface signal detection method based on independent component analysis combined with least squares method was used to calculate several brain hemodynamic parameters of the subjects. A number of brain hemodynamic parameters are summarized to generate a sample of the brain hemodynamic parameters of the subject.

4. The brain-computer interface experimental method based on functional near infrared according to claim 3 is characterized in that: The step of retrieving the corresponding brain image template and brain hemodynamic parameter template according to the serial number specifically includes: Enter the number corresponding to the subject's brain parameter sample into the information box; Output the corresponding brain image template and brain hemodynamic parameter template.

5. The brain-computer interface experimental method based on functional near infrared according to claim 4 is characterized in that: The step of inputting the brain region image into the corresponding brain region image standard library for matching according to the marked brain region name specifically includes: According to the marked brain region name, the brain region image is input into the corresponding brain region image standard library for matching. Each brain region name corresponds to a brain region image standard library; Matching the brain region images marked with the brain region names with the standard brain region images in the brain region parameter standard library to obtain a number of matching values; The standard brain region image with the highest matching value is output, and at the same time, the standard hemodynamic parameter sample information corresponding to the standard brain region image is output.

6. The brain-computer interface experimental method based on functional near infrared according to claim 5 is characterized in that: The near-infrared detector is composed of a dual-wavelength light source L, a detector D1 and a detector D2. The near-infrared light emitted by the dual-wavelength light source L is incident on the brain tissue to be tested. The detector D1 is used to detect the hemodynamic signals of the primary motor cortex, and the detector D2 is used to detect the hemodynamic signals of the prefrontal layer.

7. The brain-computer interface experimental method based on functional near infrared according to claim 6 is characterized in that: The steps of respectively calculating the brain hemodynamic parameter samples of the subject using the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method specifically include: The subjects completed an imaginary task involving muscle movement or muscle tension according to the prompts. The detector D1 collected the hemodynamic change signals of the primary motor cortex and used the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method to calculate the hemodynamic parameters s(k)1a1 of the primary motor cortex. The subjects completed an imagination task involving mental arithmetic or musical intention according to the prompts. The detector D2 collected and detected the hemodynamic signals of the prefrontal layer, and used the signal detection method of the near-infrared brain-computer interface based on independent component analysis combined with the least squares method to calculate the hemodynamic parameters s(k)2b1 of the prefrontal layer respectively; The subject completes the imaginary task involving muscle movement or muscle tension several times according to the prompts, and several primary motor cortex hemodynamic parameters are summarized, and the subject's primary motor cortex hemodynamic parameter sample s(k)1(a1....an) is output; The subjects completed the imagination task involving mental arithmetic or musical intention several times according to the prompts, summarized several prefrontal layer hemodynamic parameters, and output the prefrontal layer hemodynamic parameter samples s(k)2(b1....bn).

8. The brain-computer interface experimental method based on functional near infrared according to claim 7 is characterized in that: The step of matching the brain region images marked with the brain region names with the standard brain region images in the brain region parameter standard library specifically includes: The hash method based on discrete cosine transform (DCT) is used to calculate the hash values ​​of the subject's primary motor cortex image and the standard primary motor cortex image, respectively, to obtain h_1 and h_2; The hash method based on discrete cosine transform (DCT) is used to calculate the hash values ​​of the subject's prefrontal layer image and the standard prefrontal layer image, and h_3 and h_4 are obtained; Calculate the Hamming distance dis_h1 between h_1 and h_2, and calculate the Hamming distance dis_h2 between h_3 and h_4; The similarity between the subject's primary motor cortex image and the standard primary motor cortex image is calculated according to the Hamming distance dis_h1, and the similarity between the subject's prefrontal layer image and the standard prefrontal layer image is calculated according to the Hamming distance dis_h2. The similarity is the matching value.

9. The brain-computer interface experimental method based on functional near infrared according to claim 8 is characterized in that: The step of matching the marked brain region hemodynamic parameter samples with the standard brain region hemodynamic parameter specifically includes: The primary motor cortex hemodynamic change signal sample s(k)1(a1-a2) and the prefrontal layer hemodynamic change signal sample s(k)2(b1-b2) are respectively compared with the standard value of the brain hemodynamic change signal using the Tanimoto coefficient, and the comparison values ​​T1 and T2 are output; When T1 and T2 are close to 1, the information that the brain area is in good condition is output; When T1 and T2 are close to 0, information about the poor state of the brain area is output.

Images