415 results about "Infrared spectroscopy" patented technology

The present application pertains to the technical field of neural stimulation. Disclosed are a temporal interference-based closed-loop multimodal neural stimulation system and method. The system comprises a temporal interference stimulation system, an electroencephalography-functional near-infrared spectroscopy sampling system, and an upper-level control system. The temporal interference stimulation system utilizes a beat-frequency electric field generated by two sets of electrodes to precisely stimulate a specified brain region. The electroencephalography-functional near-infrared spectroscopy sampling system is a bimodal collector coupling electroencephalography and functional near-infrared spectroscopy, including two parts: signal extraction and correlation analysis, and analyzes stimulation effects and adjusts stimulation schemes by integrating unified brain signal data that combines the temporal precision of EEG and the spatial precision of fNIRS. The upper-level control system includes bimodal fusion model computation, graph convolutional neural network prediction, and stimulation scheme formulation. The present application addresses the problems that traditional stimulation methods lack a closed-loop regulation system, have no means for calibration and optimization, and require a long adaptation period between the stimulation scheme and the user, thus being disadvantageous for applications.

The invention relates to the technical field of artificial intelligence and biomedical sensing, and discloses a cognitive disorder risk identification device and method integrating multi-modal physiological data, and the device comprises an EEG module, an eye movement module, an fNIRS module, an edge calculation module and an acceleration sensor; the EEG module collects EEG data, the eye movement module collects eye movement eye-tracing data, and the fNIRS module collects near infrared spectrum fNIRS data and inputs the data to the edge calculation module; the edge calculation module runs the multi-modal space-time attention fusion model to output a cognitive impairment risk assessment result by using the multi-modal space-time attention fusion model; the acceleration sensor operates based on an operation dynamic filtering algorithm of a motion accelerometer to inhibit signal drift caused by head motion. According to the invention, through the modularized head-mounted multi-mode edge device, the physiological data is collected and edge end processing and cognitive disorder recognition and screening are carried out in combination with the edge calculation module, so that early recognition and screening of neurodegenerative diseases can be conveniently and effectively carried out at low cost.

The invention relates to the crossing field of precision agriculture and artificial intelligence technology, in particular to a soil component detection system based on machine learning and infrared spectroscopy, which is characterized in that a soil spectrum is acquired on site through a portable Fourier infrared spectrometer, and after pretreatment, feature vectors are constructed by fusing climate, soil and crop data; the deep learning decision-making module extracts spectral features by using one-dimensional convolution, fuses multi-dimensional information through an attention mechanism, synchronously outputs a fertilization scheme, crop suitability scores and soil improvement measures by a multi-task learning sub-network, and finally, verifies by combining an agronomic knowledge base so as to obtain a fertilization result. According to the method, a comprehensive decision report containing a quantitative fertilization formula, a crop suitability sequence and a soil improvement scheme is generated, precise agricultural guidance is realized, spectral features are automatically extracted by adopting a one-dimensional convolutional neural network, and a multi-modal data fusion and multi-task learning framework is combined, so that the system achieves relatively high precision in the aspect of soil nutrient prediction.

The invention relates to the technical field of garbage recognition, and particularly discloses an intelligent garbage recognition system and method based on multi-modal fusion, a hardware sensing unit is composed of a three-dimensional vision module, a touch sensing module and a near infrared spectrum module, and point cloud data, a pressure distribution matrix and spectrum data of garbage are obtained respectively; and an edge computing unit is equipped to carry an NPU acceleration chip for data processing. And the software module realizes multi-modal feature fusion by using ResNet-50, LSTM (Long Short Term Memory), 1D-CNN (Convolutional Neural Network) and Transform Encoder, and is also provided with a multi-sensor timestamp synchronous controller. And the dynamic feature database starts online learning to update the material feature library when the garbage recognition confidence coefficient is lower than 85%. During feature fusion, a cross-modal feature mapping relation is established, the weight is adjusted through an attention mechanism, and dynamic learning adopts a model lightweight method based on knowledge distillation. And starting an arbitration mechanism to correct the classification result when different modal identification results conflict. According to the method, the advantages of different modal data are fully utilized, and the recognition capability in a complex environment is improved.

The invention discloses a rice straw decomposition process full life cycle monitoring system based on a cloud platform, and relates to the field of agricultural informatization, and the system comprises a field data collection terminal which is used for collecting near infrared spectrum data, image data and operation and environment data of a straw decomposition process; the layered identification and modeling unit is used for identifying initial mass proportions and decomposition progress of soluble components, cellulose components, hemicellulose components and lignin components of the straws, and establishing a layered progress bar; the fusion progress calculation unit is used for weighting each layered progress bar based on the initial mass ratio to generate an overall decomposition progress bar; the progress output unit is used for simultaneously outputting a layered progress bar and an overall decomposition progress bar; and the mode mining unit is used for clustering the historical layered progress bars, forming a progress category prototype library and outputting potential blocking reasons. The problems that the field straw decomposition process is difficult to monitor in real time and the blocking reason is difficult to identify are solved.

The invention belongs to the technical field of agricultural pest detection, and particularly discloses a multi-modal citrus pest detection method based on a near infrared spectrum and a visible light image, and the method comprises the steps: obtaining citrus sampling data which comprises an original near infrared spectrum of a citrus and a plurality of visible light images of the citrus, different visible light images correspond to different shooting angles; preprocessing the original near infrared spectrum to eliminate scattering influence, and based on the preprocessed near infrared spectrum, screening out a key characteristic wavelength to construct a key characteristic near infrared spectrum; and based on the key feature near infrared spectrum and the plurality of visible light images, through a multi-modal network model, obtaining an insect pest detection result of the citrus, the multi-modal network model being used for fusing image features corresponding to the visible light images and spectral features corresponding to the key feature near infrared spectrum, and outputting the insect pest detection result. According to the method and the device, the detection precision can be improved from multiple dimensions, and the citrus diseased insects can be accurately detected.

Optical patient monitoring systems are disclosed. The system may comprise an optical coupling system configured to transmit to and receive light signals from one or more locations on a subject; an optical processing system configured to generate optical data using the received light signals; and a computer programmed to receive the optical data; determine, using the optical data, at least one indicator of blood pressure; estimate an estimated blood pressure using the at least one indicator of blood pressure; and generate a report indicative of the estimated blood pressure. The at least one indicator of blood pressure comprises one or more of near-infrared spectroscopy (NIRS) data; photoplethysmography (PPG) data, diffuse correlation spectroscopy (DCS) data, speckle contrast optical spectroscopy (SCOS) data, speckleplethysmography (SPG) data, first derivative PPG data, second derivative PPG data, first derivative SPG data, second derivative SPG data, inflow (Fin) data, outflow (Fout) data, heart rate data, physiological data, and combinations thereof. Methods for estimating blood pressure are also disclosed.

The invention relates to the technical field of peanut plant growth state intelligent monitoring, in particular to a peanut plant growth state intelligent monitoring method and system and electronic equipment. The method comprises the following steps: respectively acquiring visible light and near-infrared images, laser radar point cloud data, near-infrared spectra and microscopic images of peanut plants by using a multispectral camera, a laser radar, a near-infrared camera and a microscopic imager carried by a field robot; carrying out de-atomization and color correction on the image by adopting a self-adaptive illumination compensation algorithm; a laser radar point cloud is fused to construct a plant three-dimensional point cloud model; segmenting an overlapped leaf area based on a graph neural network, and extracting morphological characteristics of a single plant; the nitrogen content and the moisture content of the leaves are analyzed through near infrared spectroscopy, and early scabs are recognized in combination with microscopic imaging; and inputting the morphological characteristics and the physiological parameters into a growth state evaluation model, and outputting growth indexes and disease and pest early warning. According to the invention, automatic and refined monitoring and growth state comprehensive evaluation of peanut plant morphology and physiological parameters are realized.

The invention discloses a method for detecting the nitrogen content of organ tissues of different varieties of oilseed rapes based on visible near-infrared spectroscopy, which comprises the following steps: firstly, collecting oilseed rape leaf, shell, stalk and root system samples under the conditions of multiple varieties and multiple nitrogen fertilizer levels, and acquiring spectral data within the range of 430-2500nm by using a visible near-infrared spectroscopy; and a Kjeldahl method is synchronously adopted to measure the real nitrogen content as a reference value. Preprocessing the spectral data, including de-noising, standard normal variable transformation, multivariate scatter correction and derivative processing, so as to weaken the influence of scattering and baseline drift; characteristic wavelengths related to the nitrogen content are screened through stepwise regression, variable projection importance, competitive self-adaptive reweighted sampling, a continuous projection algorithm and other methods, and a random forest model, a support vector machine model, a partial least squares discriminant analysis model, a partial least squares regression model, a support vector regression model, an XGBoost model and other models are combined. And respectively constructing a classification identification model and a regression prediction model.

The invention discloses a cordyceps sinensis intelligent bionic cultivation control system and method based on the Internet of Things, and the method comprises the steps: collecting the temperature and humidity, gas concentration, illumination intensity and larva behavior data of a cordyceps sinensis matrix through a sensor network, and carrying out the fusion through an edge calculation gateway, and generating a dynamic environment map; constructing a plateau ecological digital twinborn model based on the dynamic environment map in combination with historical meteorological data and a host-strain interaction rule, and generating a staged control time sequence; based on a staged control time sequence, temperature and humidity coupling compensation is carried out through a feedforward-feedback composite algorithm, and actuator linkage is adjusted through fuzzy PID; aI vision is used for identifying a larva infection window period and accurate spraying is carried out, and hypha infection is monitored in combination with a near infrared spectrum to dynamically adjust the CO2 concentration; and constructing an LSTM (Long Short Term Memory) model to predict the growth risk in combination with a dynamic environment map and insect body monitoring data, and actively intervening in an abnormal environment. According to the invention, high-precision, dynamic and intelligent regulation and control of the growth environment of cordyceps sinensis are realized.

The invention provides an intelligent matching method for recycling purposes of industrial solid wastes, and belongs to the technical field of industrial solid waste resources, and the method comprises the following steps: firstly, carrying out comprehensive feature extraction and fusion on solid waste samples by adopting multi-mode sensing technologies such as near infrared spectroscopy and X-ray fluorescence to generate solid waste multi-dimensional feature fingerprints; then, utilizing a solid waste physical and chemical reaction mechanism equation to analyze the recycling potential of the solid waste; meanwhile, a pre-trained WRIM model is adopted to classify the solid waste, and the model combines a convolutional neural network and a multi-head attention mechanism; then, quantifying the matching degree between the solid waste characteristics and the resource application demand by using a tensor kernel similarity calculation function; and finally, through a multi-level priority evaluation engine, the comprehensive similarity scoring matrix, the resource potential index and the basic attribute category, generating an optimal resource scheme recommendation, and realizing accurate matching of solid waste resource purposes.

The invention relates to the technical field of attention deficit hyperactivity disorder detection, and discloses a device for detecting cognitive and developmental conditions of children with hyperactivity disorder, which comprises a handle, a head-mounted device, a bracelet, a hierarchical adaptive algorithm module, a multi-dimensional execution module and a data fusion and analysis module, a multi-mode sensing module is arranged in each of the handle, the head-mounted device and the bracelet; a motion capture unit, a high-sensitivity key array, a tactile feedback module and a wireless transmission module are integrated in the handle, and a wireless electroencephalogram acquisition module, a miniature near infrared spectrum module and an eye movement tracking module are integrated in the head-mounted device. According to the invention, through deep fusion of a multi-dimensional cognitive evaluation system and gamepad hardware, the device not only breaks through the limitation of the traditional neuropsychological test in methodology, but also realizes refined capture of ADHD heterogeneity characteristics in the technical level, and provides a hardware basis for establishing an objective and quantitative diagnostic tool with high ecological efficiency.

The invention relates to a cognitive state classification method based on EEG-fNIRS spatio-temporal fusion features, which comprises the following steps of: setting an experiment according to a mental calculation experiment normal form, and synchronously acquiring EEG data and fNIRS data of a tested mental calculation task; preprocessing the two collected data to obtain electroencephalogram signal data and hemoglobin concentration change data; eEG signal data and hemoglobin concentration change data are taken, data enhancement is carried out through a time window, then the data are sent to a space-time fusion network, EEG features, oxyhemoglobin HBO features and deoxyhemoglobin HBR features are obtained, fusion features are obtained through fusion, and an EEG classification result, an fNIRS classification result and a fusion feature classification result are obtained. According to the method, the characteristics of the EEG signal and the fNIRS signal are effectively combined, the overfitting problem in modal deep learning is relieved, and cognitive state classification can be accurately carried out.

The invention provides a surgical process management method and system, and relates to the technical field of surgical process management.The method comprises the steps that DTI, fMRI and 3D-T1WI image data are fused through a non-rigid registration algorithm, a three-dimensional brain network atlas is generated, then an LSTM deep learning model is constructed, a brain surface displacement field monitored in real time in an operation is used as input, and an LSTM deep learning model is constructed; a deep tissue displacement value is used as a label for training to obtain a deep tissue displacement predicted value, and a dynamic relation between brain neural element electrical activity and oxyhemoglobin saturation is analyzed by combining data monitored by high-frequency EEG and near infrared spectrum and utilizing a wavelet time-frequency coherence algorithm to obtain a dynamic influence coefficient; and finally, combining the deep tissue displacement predicted value with the dynamic influence coefficient, calculating a comprehensive evaluation index, and comparing the comprehensive evaluation index with a preset threshold value, so that a surgeon can quickly adjust an operation strategy and timely deal with possible risks.

The invention relates to a wide-temperature-range stable dual-band infrared optical filter for an extreme environment and a preparation method thereof. The wide-temperature-range stable dual-band infrared optical filter comprises a front film system, a substrate and a back film system, the front film system and the back film system are formed by alternately overlapping germanium layers and zinc sulfide film layers; the drift distance of the central wavelength of the passband of the infrared optical filter is less than 0.05% within the temperature range of-120 DEG C to + 85 DEG C. According to the invention, the internal stress of the film layer is obviously reduced through the optimized film system design, so that the excellent stability of the optical performance in an extreme temperature environment is realized, the technical problem that some special infrared spectrum detection systems work in a wide temperature range is solved, and a reliable solution is provided for high-end aerospace infrared application.

Provided are a coal testing system and method, and a storage medium. The system comprises: a detection unit, which is used for collecting spectral data of a coal sample under test; a training unit, which is used for constructing, by means of the spectral data, neural networks across neural network dimensions on the basis of a greedy search, and obtaining a coal sample test model by means of performing training on the basis of simulated samples which have been subjected to sample augmentation; and an analysis unit, which is used for executing fusion processing on the spectral data to obtain target spectral data, and on the basis of the coal sample test model, executing target spectral data inference to obtain a coal test result, wherein the detection unit comprises a near-infrared spectroscopy collection module and an X-ray fluorescence spectroscopy collection module.

The invention discloses a honey adulteration detection method, which belongs to the technical field of food detection, and comprises the following steps: collecting an absorbance spectrum of a honey sample by using a near infrared spectrometer; extracting characteristic absorbance values A < lambda > 1 and A < lambda > 2 at a 1450 nm water molecule absorption peak and a 1490 nm saccharide molecule absorption peak; the ratio R is equal to A lambda 1 / A lambda 2; and comparing the R with a threshold range of 0.85-1.15 of pure honey so as to judge whether the honey is true or false. The portable device comprises a sample bin, a near infrared spectrum module, a control unit and a human-computer interaction interface, wherein a rotatable sample table is arranged in the sample bin to accommodate a plurality of disposable sample cups. The method abandons a complex black box model, adopts a characteristic wavelength ratio method with clear physical significance, has the outstanding advantages of simple principle, rapid detection (less than 30 seconds), high accuracy, low cost, simplicity and convenience in operation and the like, perfectly solves the problems of expensive equipment, long time consumption, limited identification capability and dependence on professionals in the prior art, and has a wide application prospect. The method is especially suitable for market on-site rapid screening.

The invention discloses a near infrared spectrum modeling method and system based on merge matrix PCA, and relates to the technical field of near infrared spectrum and the field of chemometrics. The method comprises the following steps: acquiring original near infrared spectrum data and reference data of a to-be-detected sample as independent variable data and corresponding dependent variable data respectively; respectively performing data set division on the independent variable data and the dependent variable data by adopting a sample set division method; and constructing a regression prediction model based on a least square regression method, training and verifying the regression prediction model by using the preprocessed data set, performing correlation analysis on the data set and a prediction target based on a principal component analysis method in the training process of the regression prediction model, and performing principal component extraction. According to the near infrared spectrum modeling method and system based on merging matrix PCA, dimensionality reduction is carried out on high-dimensional data possibly existing in a sample, then a robust prediction model is established, and rapid and accurate quantitative analysis is achieved.

The invention discloses a multi-scale adversarial decoupling near infrared spectrum model transfer method. The method comprises the following steps: acquiring near infrared spectrum data sets of a source domain and a target domain, executing a spatio-temporal data distribution strategy in time and space dimensions, carrying out proportion division on the spectrum data sets, and carrying out near infrared spectrum model pre-training; respectively extracting instrument irrelevant features and instrument relevant features through a neural network, performing adversarial training to minimize domain difference loss, and outputting a domain invariant subset; inputting the related characteristics of the instrument, the near infrared spectrum data set of the target domain and the domain invariant subset into a generator to generate virtual spectrum data; and adopting a dynamic weighted sampling strategy, adaptively adjusting the sampling probability of the virtual spectrum data and the real spectrum data, performing model training fine tuning, deploying the fine-tuned model to a target instrument, and realizing cross-instrument transfer of the near infrared spectrum model. According to the method, the cross-instrument generalization ability of the model is greatly improved, and the robustness of the spectrum model in the space-time dimension is enhanced.

The invention belongs to the technical field of tea processing, and particularly relates to a high-precision grading and directional processing system for Qihong tea. The system comprises an intelligent tea leaf grading module based on hyperspectral imaging and machine vision, wherein the intelligent tea leaf grading module is used for realizing accurate classification of raw materials; an AI-controlled dynamic withering module is used for optimizing enzyme activity and water evaporation; a pressure-rotating speed self-adaptive intelligent rolling module ensures that cells are uniformly broken; an electronic nose is combined with a multispectral real-time fermentation monitoring module to accurately control the fermentation degree; a far infrared-hot air coupled precise drying module is used for realizing gradient dehydration; the near infrared spectrum and deep learning quality detection module is used for completing finished product quality evaluation; the data traceability module of the block chain technology is used for recording whole-process processing parameters; and a big data-driven process optimization module continuously improves the product stability. According to the invention, the intellectualization, precision and standardization of the Qihong Huang tea processing process are realized, and the consistency and the superior product rate of the product quality are obviously improved.

The invention relates to the technical field of component detection, in particular to a dairy product component real-time detection system based on near infrared spectroscopy, which is provided with a feature acquisition module, a preprocessing module, a feature pre-analysis module, a feature recognition module, a feature marking module and a feature judgment module. Whether a near infrared spectrum confidence coefficient abnormal risk exists or not is judged through a feature pre-analysis module, local surface images and near infrared spectrums of all recognition light paths are obtained through a feature recognition module, an incidence relation is established, feature recognition light paths are marked through a feature marking module, light path synchronism analysis is carried out through a feature judgment module, and the accuracy of light path synchronism analysis is improved. And judging whether abnormal early warning is sent out or not. According to the method, the abnormal risk of the confidence coefficient of the near infrared spectrum is identified, spectrum distortion is identified and eliminated according to the actual condition of the dairy product to be detected, and the reliability and accuracy of real-time detection of dairy product components are improved.

The invention relates to a method for improving portable near infrared spectrum data analysis precision, which comprises the following steps: carrying out spectrum scanning on different grape samples to obtain a plurality of original near infrared spectrum data; preprocessing the original near infrared spectrum data to obtain corresponding preprocessed data, and performing dimension transformation on the preprocessed data to obtain a two-dimensional image; processing the two-dimensional image to obtain a reconstructed image, and training the initial convolutional neural network model based on the reconstructed image to obtain a target convolutional neural network model; and taking the output result of the feature extraction layer of the target convolutional neural network model as the input of a partial least square regression model, and constructing a fusion model so as to detect the soluble solid content of the to-be-detected grape through the fusion model. According to the invention, the hardware limitation of the portable near-infrared spectrometer is overcome, and the precision and efficiency of the portable near-infrared spectrum data analysis precision are improved.

An apparatus and method directed to sample characterization with an AFM using a pulsed IR laser in force volume mode, i.e., force volume mode combined with AFM-IR, referred to herein as FV AFM-IR. In this way, lateral forces are suppressed during probe positioning, and precise force control allows adjusting the tip-sample interaction force, including keeping the tip-sample interaction force constant or exerting pulling forces. Nano-spectroscopic measurements with sub-20 nm, and even sub-10 nm resolution can be acquired together with nano-mechanical and other property measurements. Notably, probe resonance shifts can be compensated with frequency tracking methods, and signal normalization by the Q-factor can be used to ensure that the extracted light-induced surface pulse force is substantially independent of damping.

The invention provides a waste PET lining cloth grading alcoholysis and in-situ polymerization regeneration method, and relates to the technical field of waste textile recycling, and the method comprises the following steps: adopting a near infrared spectrum combined AI image identification technology to realize waste PET lining cloth material classification, and removing pollutants through low temperature plasma-biological enzyme synergistic cleaning; putting the pretreated PET fragments into three-stage series reaction kettles, and dynamically adjusting the temperature and the catalyst concentration of each stage of reaction kettle through a control algorithm to realize PET depolymerization degree gradient control; according to the method, the graded alcoholysis and in-situ polymerization synergistic technology is adopted, so that the performance of the waste PET lining cloth regenerated fiber is improved in a leap-over manner, the molecular weight and the fiber strength of the regenerated PET are improved through the three-stage tandem reaction kettle and the control algorithm, and the technical bottlenecks that the strength of a physical method is low and the molecular weight loss of a chemical method is large are broken through; the mechanical property of the regenerated material is obviously improved.

The invention relates to the technical field of novel material chemical analysis, and discloses a triphenyl phosphate purity standard substance valuing method, which comprises the following steps: filtering, drying, dissolving and sterilizing a triphenyl phosphate sample; a triphenyl phosphate sample is comprehensively analyzed from different angles by comprehensively applying a GC-MS (Gas Chromatography-Mass Spectrometry) technology, an NMR (Nuclear Magnetic Resonance) technology, an infrared spectroscopy, a gas chromatography-flame ionization detector method, a Karl Fischer method and an inductively coupled plasma mass spectrometry, and finally, the purity value of the triphenyl phosphate purity standard substance is calculated by a mass balance method. The method provides a scientific and accurate technical means for quality control and standard formulation of the triphenyl phosphate product, has important practical application value for related industries in the fields of chemical engineering and material science, and is beneficial for improving the product quality and promoting industrial upgrading.

The invention belongs to the field of food processing and safety, and provides a steam explosion improved grain processing byproduct and application thereof in preparation of low-GI coarse grain biscuits. The triticale bran is pretreated through a steam explosion (SE) technology, the content of soluble dietary fibers is increased by 53.63% under the conditions of 1.0 MPa and 90 s, and the content of free phytochemicals and the oxidation resistance are the highest; the color of the wheat bran is changed into dark brown / dark brown from light brown, the interior of the wheat bran is of a porous honeycomb structure, the water binding capacity and the swelling property are improved, and an infrared spectrum shows that methyl and methylene structures are damaged and tissues are loosened; the fatty acid value is remarkably reduced, the storage period and the shelf life are effectively prolonged, comprehensive improvement of nutritional ingredients, physicochemical properties, biological activity and storage characteristics is achieved, and remarkable technical advantages are achieved.

The invention discloses a triphenyl phosphate standard substance structure identification method, and relates to the technical field of fluorine-containing gas emission reduction, and the method comprises the following steps: obtaining a standardized analysis sample through fluorine-containing matrix separation, target substance enrichment and solvation treatment; a multi-dimensional chromatographic system and a heart cutting technology are adopted, and temperature programming optimization is combined to realize separation and purification of a sample; carrying out multi-dimensional structure analysis and confirmation by using gas chromatography-mass spectrometry, infrared spectroscopy and nuclear magnetic resonance technologies; a five-stage progressive identification algorithm is constructed, and systematic identification is realized by combining a confidence evaluation system and a fluorine-containing interference correction technology; establishing a structural integrity verification and purity quantitative evaluation standard, and outputting a standardized identification report; a method applicability database is established through multi-type fluorine-containing environment verification and process condition adaptability testing. The method effectively solves the problem of accurate identification of triphenyl phosphate in a complex fluorine-containing matrix, and realizes effective removal of interference components such as light gas, hydrofluorocarbon, perfluorinated compounds and the like.

The invention provides a method for rapidly and non-destructively detecting the quality of beet seeds based on a near infrared spectrum technology, and relates to the technical field of non-destructive detection of the quality of the seeds, the near infrared spectrum of the beet seeds is collected, and the characteristic wavelength is extracted through an improved competitive self-adaptive reweighted sampling algorithm; meanwhile, depth features are extracted by using a customized convolutional neural network, and the depth features and the depth features are fused to form a fusion feature vector with high characterization force. Secondly, establishing a quality scoring system based on key agronomic characters after single seed sowing, and constructing a spectral feature and quality score contrast database; for to-be-tested seeds, the most reliable reference seed group is screened out from the database by calculating the weighted similarity and adopting a dual dynamic threshold strategy. And finally, in combination with the local space density of the reference seed and the correlation degree between the reference seed and the to-be-detected seed, carrying out credibility weighted local regression calculation, accurately predicting the final quality score of the to-be-detected seed, and realizing grading judgment.

The invention is suitable for the field of medical technology, and provides a cerebral apoplexy monitoring method and system based on a multi-modal brain-computer interface, and the system comprises a multi-modal physiological data acquisition module, a data denoising and feature extraction module, a multi-modal data fusion module, an abnormal mode recognition module, and a risk signal alarm module. The system can be combined with different types of physiological signals to provide a comprehensive and real-time monitoring platform so as to support early recognition and timely intervention of cerebral apoplexy. The system can effectively capture the electrical activity and blood flow change of the brain of a patient by monitoring electroencephalogram and near infrared spectrum data in real time, so that deep physiological state analysis is provided for doctors; by simultaneously acquiring the electroencephalogram signal and the blood flow change data, the system not only can analyze the neural activity of the brain, but also can evaluate the blood supply condition of the brain. By means of the comprehensive monitoring, a doctor can judge the health condition of the patient more accurately on the basis of comprehensively considering the brain function and the blood flow state.

The invention discloses a method for nondestructively detecting the content of beta-1, 3-glucan in ganoderma mycelium, and relates to the technical field of biological detection, and the method comprises the following steps: preparing different varieties of ganoderma mycelium samples; determining the content of beta-1, 3-glucan in different varieties of ganoderma mycelium samples by adopting an aniline blue fluorescence method; acquiring near infrared spectrum data of different varieties of ganoderma mycelia; preprocessing the spectral data; screening characteristic wavelengths; establishing a prediction model; and predicting by using the model. According to the prediction model for detecting the content of the beta-1, 3-glucan in the ganoderma mycelium based on the near infrared spectrum technology and the fluorescent quantitative technology, the content of the beta-1, 3-glucan can be rapidly and nondestructively detected at high flux, the prediction effect is good, the determination time is short, and the prediction model has the advantages of being easy and convenient to operate, rapid, low in cost and the like.