29 results about "Oxyhemoglobins" patented technology

The invention provides a transcranial deep electrical stimulation closed-loop regulation and control system and method based on fNIRS dynamic guidance. The method comprises the steps that a transcranial alternating current electrical stimulation module applies an electrical signal to a target deep brain region according to preset parameters to carry out electrical stimulation regulation and control; the synchronous triggering module is used for realizing millisecond-level synchronization of a stimulation task and near-infrared brain function data acquisition; the brain function monitoring module analyzes the concentration change of cortex oxyhemoglobin in real time through the multi-channel head cap; the electrical stimulation-response coupling mapping module positions a significant activation channel by adopting statistical test, and establishes an oxyhemoglobin concentration variable and electrical stimulation current amplitude quantitative model; and the dynamic parameter adjusting module optimizes the output current in real time. Personalized closed-loop regulation and control of non-invasive deep brain stimulation can be achieved, cerebral cortex blood oxygen signals are monitored in real time through near-infrared brain function imaging, stimulation parameters are dynamically adjusted, and the accuracy and individualization level of deep brain stimulation are remarkably improved.

The invention discloses an endoscope image processing method based on oxyhemoglobin saturation and multiple central wavelengths, and relates to the field of medical image processing.The method comprises the steps that a first initial image signal, a second initial image signal, a third initial image signal and a fourth initial image signal are obtained; calculating oxyhemoglobin concentration information of the target part according to the second initial image signal and the third initial image signal; calculating deoxidized hemoglobin concentration information of the target part according to the second initial image signal and the fourth initial image signal; calculating the oxyhemoglobin saturation of the target part according to the oxyhemoglobin concentration information and the deoxidized hemoglobin concentration information; performing brightness enhancement on the second initial image signal based on the oxyhemoglobin saturation to obtain a second enhanced image signal; and generating a target image according to the second enhanced image signal, the first initial image signal and the third initial image signal, wherein the target image is used for identifying the bleeding position of the target part.

A method for non-contact oxygen saturation prediction based on a hyperspectral camera, according to one embodiment of the present invention, may comprise the steps of: acquiring a hyperspectral image of a subject by using the hyperspectral camera; measuring the absorbance of at least one face region that is detected in consideration of the correlation with a change in oxygen saturation from among the face regions of the subject from the hyperspectral image; determining at least two optimal wavelength bands from among wavelength bands measured by using the hyperspectral camera in consideration of the absorbance of oxyhemoglobin and the absorbance of deoxyhemoglobin; and predicting the oxygen saturation of the subject on the basis of the absorbance of the at least one face region and the at least two optimal wavelength bands.

The invention provides a palm vein high-security identity authentication system based on spectral analysis and deep learning, and relates to the technical field of biological recognition, the system comprises a hardware layer, a data processing layer, an algorithm layer and an application layer, through an antagonistic living body detection module in the algorithm layer, in combination with physical modeling and a GAN (Generative Adversarial Network), the high-security identity authentication of a complex imitation is realized. The method comprises the following steps: carrying out effective identification of a high-biomimetic material, carrying out physical modeling to analyze the absorption characteristics of palm veins in a hyperspectral range, such as the difference between oxyhemoglobin and oxyhemoglobin and periodic spectrum micro-interference caused by heart rate, and providing living body evidence based on physiological dynamics; meanwhile, a high-simulation template sample generated by the GAN is used for training a discriminator, the insight ability of the system to a template means is further enhanced, and compared with single traditional texture or static signal detection, the system combines physical characteristics with deep learning, and the confidence coefficient of in-vivo detection reaches up to 99.99%.

The invention discloses a hand motion FNIRS signal classification method based on t distribution optimization feature extraction, and the method specifically comprises the steps: employing a portable functional near-infrared collection device to collect an optical density signal of a forehead cortex brain region during the motion execution period during the operation of the device; after pretreatment, the concentration of oxyhemoglobin HBO and the concentration of deoxidized hemoglobin HBR are calculated according to the corrected Beer-Lambert law; according to motion execution and resting state segmentation data, time domain features and time-frequency domain features of oxyhemoglobin concentration data signals of each channel of each experiment test are extracted, and a first feature matrix is formed; performing kernel density estimation and kurtosis and skewness test on the first feature matrix to obtain a second feature matrix, performing t distribution on each corresponding feature satisfying normal distribution in the second feature matrix of the motion execution and resting states, and optimizing feature selection on the basis to obtain an optimized third feature matrix; the optimized third feature matrix is used as classifier input, a brain-computer interface system model training result is obtained, and effective feature selection and extraction are achieved; according to the method, the brain-computer interface system feature extraction of the hand motion FNIRS signals can be optimized, so that the classification performance is improved.

An electronic device comprises a housing configured to contact a user's skin, an optical transmitter array, an optical receiver, a memory element and a processing element. The optical transmitter array outputs a plurality of optical signals that pass through the user's skin, each of the plurality of optical signals having one of three wavelengths. The optical receiver receives the optical signals and generates corresponding photoplethysmogram (PPG) signals. The memory element stores absorption constants for deoxyhemoglobin blood content, oxyhemoglobin blood content and glycated hemoglobin blood content, each absorption constant associated with one of the first wavelength, the second wavelength or the third wavelength. The processing element determines a glycated hemoglobin blood level for the user based on a ratio of a determined glycated hemoglobin blood content to a sum of determined deoxyhemoglobin blood content, a determined oxyhemoglobin blood content and a determined glycated hemoglobin blood content.

The invention provides a plateau hypoxic encephaledema early warning system, which comprises a first acquisition module configured to emit ultrasonic waves to at least two tangent planes of a first area to obtain an ultrasonic image reflected after being transmitted by an eyeball, and determining the diameter of an optic nerve sheath after first preprocessing; the second acquisition module is configured to emit a near-infrared signal source to a second area to obtain a spectral image reflected after transcranial transmission, and absorption spectrums of oxyhemoglobin and deoxidized hemoglobin are obtained after second preprocessing; the data processing module is configured to obtain the optic nerve sheath diameter and the absorption spectrum and determine a first influence factor and a second influence factor about the optic nerve sheath diameter and the absorption spectrum; and the early warning module is configured to give an alarm if the first influence factor and the second influence factor exceed a preset threshold value under a first preset condition. Early warning and monitoring of encephaledema are achieved through multi-mode monitoring.

This invention discloses a method for preparing a core-shell microneedle patch loaded with dual nanoparticles, comprising: preparing silica nanoparticles loaded with oxyhemoglobin and dihydroporphyrin e6; preparing calcium carbonate nanoparticles loaded with aPD-1 antibody; dispersing the silica nanoparticles loaded with oxyhemoglobin and dihydroporphyrin e6 in a polyvinyl alcohol solution to prepare the shell structure of the microneedles; preparing a polymer hydrogel; dispersing the calcium carbonate nanoparticles loaded with aPD-1 antibody in the polymer hydrogel to prepare the core structure of the microneedles; and casting the polyvinyl alcohol solution onto the backing of the microneedles to finally obtain the core-shell microneedle patch loaded with dual nanoparticles. The core-shell microneedle patch loaded with dual nanoparticles prepared by this invention can deliver nanoparticles to the tumor site, where the nanoparticles respond to the tumor microenvironment and activate the body's own immune system, thereby achieving a therapeutic effect on tumors.

The application discloses an imaging method for fusing photon weight and diffuse light brain tissue blood oxygen concentration change quantity and related products, and relates to the technical field of biological tissue blood oxygen imaging. The method comprises the following steps: acquiring experimental data obtained by irradiating a measured tissue with light sources of two wavelengths; performing the following calculation on the experimental data corresponding to each wavelength of the light source: calculating the average photon transmission path of the kth light probe combination in the ith voxel unit by using a formula; calculating the photon weight of the kth light probe combination in the ith voxel unit by using a formula; calculating the change quantity of the tissue absorption coefficient of the ith voxel unit by using a formula; and finally calculating the change quantity of the concentrations of oxyhemoglobin and deoxyhemoglobin by using the calculation data obtained by the two wavelengths. The application proposes a method for fusing photon weight, and by means of weight calculation, the accurate brain tissue blood oxygen concentration change quantity can be obtained by using a small amount of S-D combination photon signals.

The invention provides a functional near-infrared spectrum signal decoding method, device, equipment and medium, and relates to the field of brain-computer interfaces, and the method comprises the following steps: obtaining a functional near-infrared spectrum signal, obtaining oxyhemoglobin concentration variable quantity and anaerobic hemoglobin concentration variable quantity according to the functional near-infrared spectrum signal, and preprocessing the oxyhemoglobin concentration variable quantity and the anaerobic hemoglobin concentration variable quantity to obtain a first signal fragment sequence and a second signal fragment sequence; pairing the two sequences to obtain a homologous signal fragment sequence, determining a homologous signal fragment sub-sequence, performing feature extraction to obtain a neurodynamic feature and a time sequence feature, constructing a fusion feature input sequence based on the features, and inputting the fusion feature input sequence into a neural network model to obtain multi-modal collaborative representation data for representing a spatial correlation mode of each signal fragment; and carrying out mean pooling on the data to obtain global representation data, and finally identifying to obtain a physiological state result. The high decoding accuracy is achieved, meanwhile, excessive redundancy of parameters is avoided, and therefore efficient decoding is achieved.

The invention relates to a photoelectric detection system and method for hemoglobin detection, and relates to the technical field of spectral analysis and biomedical engineering. The method mainly comprises the following steps: controlling a light source module in the buckle type shell structure to emit light with different wavelengths, and enabling the light to penetrate through a blood transfusion tube and blood placed in the buckle type shell structure; a photoelectric detector module in the buckle type shell structure is controlled to obtain the blood transmission light intensity of the multi-wavelength light to the blood transfusion tube; calculating basic absorbance corresponding to the first wavelength and the second wavelength by using a hemoglobin absorption model, and correcting the basic absorbance by using a correction model to obtain final absorbance; according to the final absorbance corresponding to the first wavelength and the final absorbance corresponding to the second wavelength and the effective optical path length, predicting the concentration of deoxyhemoglobin and the concentration of oxyhemoglobin; and adding the deoxyhemoglobin concentration and the oxyhemoglobin concentration to obtain the total hemoglobin concentration.

This application discloses an endoscopic image processing method based on blood oxygen saturation and multi-center wavelength, relating to the field of medical image processing. The method includes acquiring a first initial image signal, a second initial image signal, a third initial image signal, and a fourth initial image signal; calculating oxyhemoglobin concentration information at a target site based on the second and third initial image signals; calculating deoxyhemoglobin concentration information at the target site based on the second and fourth initial image signals; calculating blood oxygen saturation at the target site based on the oxyhemoglobin and deoxyhemoglobin concentration information; enhancing the brightness of the second initial image signal based on the blood oxygen saturation to obtain a second enhanced image signal; and generating a target image based on the second enhanced image signal, the first initial image signal, and the third initial image signal. The target image is used to identify the bleeding location at the target site.

Systems and methods are provided that include use of near infrared spectroscopy (NIRS) brain monitoring in providing feedback and adjustments relating to treatment being provided to a patient. In some examples, at least one controller receives, from a NIRS system, signals associated with the brain of the patient receiving CPR chest compression treatment. The at least one controller, based on the signals, estimates at least two physiological parameters associated with the brain of the patient, such as hemoglobin concentration and oxygen saturation, or oxyhemoglobin concentration and deoxyhemoglobin concentration. The at least one controller, based at least in part on at least one relationship between the at least two physiological parameters, provides feedback or adjustments relating to the CPR chest compressions being provided to the patient. The at least one relationship may be associated with a multidimensional space including at least two axes associated with the at least two physiological parameters.

This patent describes an advanced method for the accurate optical quantification of antioxidant carotenoids in biological tissues. The method addresses interference from melanin and hemoglobin through comprehensive correction techniques. It involves creating a tangent line for melanin correction using absorbance values at 650 nm and 700 nm, measuring the corrected optical density (OD) of carotenoids at 488 nm, measuring the corrected OD of blood at 577 nm, converting the Blood OD from 577 nm to 488 nm using oxyhemoglobin and deoxyhemoglobin extinction coefficients, and subtracting the Blood OD from the Carotenoid OD to obtain the final Carotenoid OD. This innovative approach provides reliable, non-invasive, and precise measurements of carotenoid levels in tissues, facilitating improved health assessments and personalized nutrition strategies.

The invention discloses an epilepsy child brain oxygen monitoring method based on a near-infrared gating ICCD imaging technology, and belongs to the technical field of medical monitoring and brain function imaging. Pulse is transmitted to the head of an epilepsy child through a laser, and photons return again after reaching brain tissue; setting an acquisition interval of the near-infrared gating ICCD detector to acquire a plurality of brain frame images; acquiring the light intensity of each pixel point in the plurality of brain frame images, and establishing a light intensity response curve; photon flight parameters are extracted to invert an absorption coefficient and a scattering coefficient corresponding to each pixel point; fitting oxyhemoglobin concentration and reduced hemoglobin concentration corresponding to each pixel point, and calculating oxygen saturation; and generating a brain oxygen saturation image for brain oxygen monitoring. The space coverage range, the imaging efficiency and the quantitative accuracy of brain oxygen monitoring are remarkably improved, and a powerful visual tool is provided for epilepsy focus positioning and preoperative brain function evaluation of child epilepsy.

The invention relates to the technical field of medical imaging, in particular to an oxygen saturation quantitative imaging device and method for an endoscope. The shooting part is configured to collect reflected light of the target area under illumination of the light source and output a collected color image and an exposure control parameter corresponding to the color image; the image processing part comprises a spectrum reconstruction module which is used for carrying out image de-gain processing on the color image and reconstructing a single-band image signal with a set wavelength; the light intensity estimation module is used for respectively calculating light intensity data of the light sources; and the quantitative calculation module is used for calculating a light absorption coefficient based on the light intensity data, calculating oxyhemoglobin concentration, deoxidized hemoglobin concentration and an oxygen saturation value based on the light absorption coefficient, and generating an oxygen saturation distribution image. The oxygen saturation image generated by the method has rich anatomical structure information and accurate physiological parameter information, and a tissue hypoxia region can be visually displayed.

The invention provides bionic blood and a preparation method and application thereof, the bionic blood comprises a first dye, a second dye and a solvent, the absorption wavelength of the first dye is 620-750 nm, the absorption wavelength of the second dye is 760 nm-1. 4 [mu] m, and both the first dye and the second dye can be dissolved in the solvent. The first dye and the second dye are dissolved in the solvent to prepare the bionic solution, the preparation method is simple, reduced hemoglobin of human blood is simulated through the first dye, oxyhemoglobin of the human blood is simulated through the second dye, the bionic blood can be used for simulating the oxyhemoglobin saturation of the human blood, and the biomimetic effect is good. The oxyhemoglobin saturation value is adjusted by adjusting the proportion of the first dye and the second dye in the bionic blood, the oxyhemoglobin saturation value does not need to be obtained by a human body, and convenience and safety are improved. Moreover, the bionic blood can be prepared in batches, is not limited by the blood donation amount and is long in storage life, and the application of the bionic blood in the field of medical health is greatly expanded.

1. The name of this design product: Portable near-infrared muscle oxygen sensor. 2. Purpose of the product of this design: used to measure the changes in the deoxyhemoglobin concentration, oxyhemoglobin concentration, and total hemoglobin concentration of local human tissues, and monitor the changes in tissue oxygenation and hemodynamics of local tissues. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

Methods and systems for measuring hemoglobin concentration (cHb). A retinal tissue having blood vessels is illuminated by light including two isosbestic wavelengths (λ1,λ2). The isosbestic wavelengths(λ1,λ2) correspond to isosbestic points where oxy- and deoxyhemoglobin (HbIO2,Hb) have the same molar extinction coefficient. Measurements are collected of a plurality of backscattered reflection intensities (I(χb,λ1), I(xt,λ1), I(χb,λ2), I(xx,X2)). Preferably, the measurements are spectrally resolved at least for the two isosbestic wavelengths (λ1,λ2) and position-resolved for at least a blood vessel location (xb) coinciding with a selected blood vessel and a tissue location (xt) coinciding with the retinal tissue without blood vessel. The hemoglobin concentration (cHb) can be calculated based on a combination of the measurements at the two isosbestic wavelengths (λt,λ2).

The invention relates to a three-dimensional model construction system and method for wound detection. The system comprises an acquisition module and a processing module, the acquisition module is provided with at least two cameras with different shooting angles so as to acquire images of the wound part of the patient at different shooting angles at the same moment, and the images at different shooting angles reflect the size difference of the same object in the image at different visual angles; the image comprises shooting angle information of a camera acquiring the image; the processing module processes the image by using a modeling unit so as to establish a three-dimensional model of the wound part of the patient; the modeling unit obtains the visual angle difference generated by the image of the wound part of the patient at different shooting angles, and maps the depth information difference of each object in the corresponding image based on the visual angle difference to realize three-dimensional imaging. The three-dimensional model reflects the wound size, blood distribution and the concentration of oxyhemoglobin and deoxyhemoglobin in blood vessels, and evaluation and analysis of characteristic parameters of the wound part of a patient and the healing condition of the wound part are facilitated.

The invention discloses an intracranial pressure detection method and system based on multi-wavelength photoacoustic imaging. The method comprises the following steps: respectively irradiating the neurocranium of a subject by using a plurality of lasers with different wavelengths; for single irradiation, original photoacoustic data generated by the neurocranium of the subject is collected, image reconstruction is carried out, a two-dimensional amplitude image under the irradiation is obtained, and a corresponding blood vessel mask is generated according to the image; performing spectral unmixing on the blood vessel mask, and then extracting the response under the irradiation; combining the response under each illumination to generate a multi-wavelength response vector; performing least square fitting on the multi-wavelength response vector by using a molar extinction coefficient matrix to calculate the relative concentration of oxyhemoglobin and the relative concentration of deoxyhemoglobin; and calculating the intracranial pressure of the subject according to the relative concentration of the oxyhemoglobin and the relative concentration of the deoxyhemoglobin. According to the invention, non-invasive, quantitative and real-time monitoring of deep cerebral vessels can be realized, and the intracranial pressure of a subject can be accurately evaluated.

The invention discloses a brain function connection network prediction method for transcranial magnetic stimulation. The method specifically comprises the following steps: obtaining a functional near infrared spectrum signal, and carrying out data preprocessing; calculating the hemoglobin concentration and the oxyhemoglobin concentration in the cerebral cortex from the preprocessed signal; generating a spatial-temporal characteristic network corresponding to the brain function connection network by using the hemoglobin concentration and the oxyhemoglobin concentration; and training a pre-constructed neural network model by using the spatial-temporal feature network to obtain a time sequence brain function connection network prediction model based on a gated time sequence diagram convolutional network, and estimating the dynamic connectivity between brain function connection network nodes of a next time slice. Compared with a conventional brain function connection network prediction method, the brain function connection network prediction method oriented to transcranial magnetic stimulation has the advantages of higher precision and individuation, can more comprehensively and efficiently identify and recommend treatment targets, and provides more accurate data support for diagnosis and treatment of mental diseases.

The invention discloses a photon weight fused diffused light brain tissue blood oxygen concentration variable quantity imaging method and related products, and relates to the technical field of biological tissue blood oxygen imaging. The method comprises the steps that experimental data obtained by irradiating a tested tissue through light sources of two wavelengths are obtained; for the experimental data corresponding to the light source of each wavelength, performing the following calculation: calculating an average photon transmission path obtained by the kth light probe combination in the ith voxel unit by using a formula; calculating the photon weight obtained by the kth light detection combination in the ith voxel unit by using a formula; calculating the tissue absorption coefficient variation of the ith voxel unit by using a formula; and finally, calculating the variation of the concentration of the oxyhemoglobin and the concentration of the deoxidized hemoglobin by utilizing calculation data obtained by the two wavelengths respectively. According to the method for fusing the photon weight, the accurate blood oxygen concentration variation of the brain tissue can be obtained by using a small number of S-D combined photon signals in a weight calculation mode.

This invention relates to a home-use physiotherapy device for PTSD intervention based on fNIRS neurofeedback and its usage method, belonging to the field of brain-computer interface technology. It includes a light signal acquisition module, a control conversion module, and a feedback physiotherapy module. The light signal acquisition module includes an acquisition cap and a data acquisition unit. The control conversion module includes a concentration conversion unit, a storage unit, and an output control unit connected in sequence. The feedback physiotherapy module includes a display screen. The data acquisition unit and control conversion module are integrated into a housing. The display screen is connected to the housing, the acquisition cap is connected to the data acquisition unit, the data acquisition unit is connected to the concentration conversion unit, and the output control unit is connected to the display screen. Data acquisition and processing analysis are performed based on the absorption degree of near-infrared light intensity in the user's prefrontal cortex to obtain the blood oxygen concentration level in the prefrontal cortex for neurofeedback physiotherapy training. This increases the oxyhemoglobin concentration level in the target area, thereby exerting a certain degree of control over the user's amygdala to improve PTSD symptoms.

A functional near-infrared spectral signal enhancement and classification method based on spatiotemporal autocorrelation and attention encoding is proposed to address the limitations of limited sample size and insufficient generalization ability of classification models in functional near-infrared spectral signal data. This method is applicable to the auxiliary diagnosis of neurodevelopmental disorders such as attention deficit hyperactivity disorder (ADHD). The method first preprocesses the raw near-infrared spectral data, extracting oxyhemoglobin signals and calculating spatial autocorrelation parameters, channel-level temporal autocorrelation parameters, and the eigenvalue distribution of the functional connectivity matrix. Then, enhanced data is generated based on the spatiotemporal autocorrelation model. Finally, the raw and enhanced data are input into the STEAFNet deep learning model for accurate classification. This invention generates high-quality enhanced data, expands the sample size, and maintains high fidelity. Combined with deep learning, it improves classification accuracy and generalization ability, providing technical support for clinical applications.

The application discloses a method for evaluating upper limb motor function of a stroke patient, which comprises the following steps: firstly, collecting near-infrared signals of the brain of a subject, and preprocessing the collected signals through band-pass filtering and cubic spline interpolation, so as to convert the optical signals into oxyhemoglobin concentration data; secondly, calculating the Pearson correlation coefficient between the preprocessed multi-channel signals, constructing a functional connection matrix under different sparsity thresholds, observing the brain network connection, and performing graph theory analysis on the brain network connection; thirdly, performing b-clustering, classifying to obtain disease subtypes, and taking the functional connection matrix of the healthy people as the input of a convolutional neural network; and finally, fusing the output reliability of the convolutional neural network with demographic information features, performing support vector regression, and selecting an optimal model as a scoring model; the application constructs a brain network under different sparsity thresholds, and determines the optimal threshold through subsequent analysis, so that the data is more accurate and the space-time resolution is higher.

The invention relates to a preparation method of an atomic precision nano-cluster-based contrast agent and an in-vivo multispectral photoacoustic imaging method of the atomic precision nano-cluster-based contrast agent. According to the method, an atomic precision metal nano-cluster is used as a precursor, amphiphilic phospholipid molecules are used for realizing hydrophobic-hydrophilic conversion and amino functionalization, and the contrast agent modified by the anti-epidermal growth factor receptor antibody is obtained through biological coupling. Based on characteristic spectrums of a contrast agent, deoxyhemoglobin and oxyhemoglobin, a plurality of section diagrams of excitation wavelengths of 680, 715, 730 and 926 nanometers in the whole tumor range are collected, three-dimensional photoacoustic signals of three components are obtained through spectrum separation and three-dimensional reconstruction, and three-dimensional multispectral photoacoustic imaging of the three components of the tumor-bearing mouse is achieved. The contrast agent synthesized by the invention has an important application prospect in the aspect of in-vivo multispectral photoacoustic imaging.

The invention belongs to the technical field of cardio-pulmonary resuscitation, and discloses a system and a method for optimizing a cerebral protection mechanism of hypoxic ischemia encephalopathy after cardio-pulmonary resuscitation, which are characterized in that an intracranial pressure monitoring device is used for monitoring the change of intracranial pressure in real time and evaluating the degree of brain injury and the condition of encephaledema; through intracranial pressure monitoring, a treatment scheme can be adjusted in time, and serious complications of cerebral hernia are prevented; meanwhile, the concentration change of oxyhemoglobin and deoxidized hemoglobin in the brain tissue is monitored through the brain oxygen saturation monitor by utilizing a near infrared spectrum technology, and the oxygenation state of the brain tissue is accurately reflected. Brain oxygen saturation monitoring is beneficial for guiding oxygen therapy and ventilation therapy and optimizing oxygen supply and oxygen consumption balance of brain tissue. The optimization system for the cerebral protection mechanism of the ischemic-hypoxic encephalopathy after the cardio-pulmonary resuscitation operation can remarkably reduce the degree of brain injury, promote neural function recovery and reduce the case fatality rate and disability rate of a patient.

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle control method and system based on EEG and fNIRS multi-modal feature fusion, and the method comprises the steps: synchronously obtaining scalp electroencephalogram and near-infrared blood oxygen signals, extracting the electroencephalogram frequency band power spectrum density to construct a fast variable feature matrix, and obtaining a fast variable feature matrix; extracting oxyhemoglobin concentration variation time sequence characteristics to construct a slow variable characteristic matrix, and compensating a slow variable timestamp by using a phase-space reconstruction algorithm to realize alignment; taking the aligned slow variable as a query matrix, taking the fast variable as a key matrix and a value matrix, and obtaining a fusion feature matrix through attention mechanism fusion; inputting the discrete instruction and the continuous variable into a double-branch network to decode the discrete instruction and the continuous variable respectively, and splicing to generate an intention decoding instruction; and finally, calculating a cognitive load index by integrating the concentration variable quantity, dynamically allocating weights of an intention decoding instruction and a bottom-layer autonomous safety control law, and generating a final instruction to be issued and executed. According to the invention, the problems of low control dimension and easy out-of-control air crash are solved.