63 results about "Mixed effects" patented technology

The invention provides an Alzheimer's disease diagnosis method based on multi-modal brain network feature fusion, which is based on a multi-modal brain image, a neural network and an attention mechanism, and has the main innovation points that: 1) effective feature combination of three types of multi-modal data of MRI, DTI and fMRI can reflect all feature information of a patient sample; and 2) aiming at different image data, a targeted feature extractor is used, the three-dimensional convolution is more suitable for feature learning of a three-dimensional MRI whole brain image, the Mama model is more suitable for learning of fMRI time sequence features, and the graph convolution network is more suitable for learning of DTI fiber number structure brain network features. And 3) the innovative mixed attention mechanism is fused with three types of multi-modal features, position coding and a Transform structure are used at the same time, the mixing effect and the classification accuracy of the multi-modal features are improved, and compared with a convolution and full connection layer structure, richer information can be learned.

The invention discloses an individualized pain prediction method and system based on a mixing effect. The method comprises the following steps: acquiring pain scores and corresponding central nervous system data when a plurality of healthy individuals receive pain stimulation; performing data processing on the obtained central nervous system data to obtain central nervous system physiological signals of pain stimulation received by corresponding individuals; combining the obtained physiological signals of the central nervous system and the corresponding pain scores to construct a mixed effect model; predicting the pain state of the individual by using the constructed mixed effect model; the system comprises a pain stimulation device, a central nervous detection system, a data acquisition module, a data analysis module, a prediction model construction module and a pain recognition module. The constructed mixed effect model gives consideration to the characteristics of an individualized model and a group model, not only can new individuals be migrated, but also individual differences are considered, the hierarchical characteristics of data are fully utilized, and the pain score prediction effectiveness can be effectively improved.

The invention relates to a gas mixing technology, and discloses a gas mixer size optimization method based on deep learning, which comprises the following steps: acquiring design parameters of a gas mixer, and establishing a gas mixer model; performing flow field simulation analysis on the model to obtain performance parameters of the gas mixer under different process parameters; establishing a database for the design parameters, the process parameters and the performance parameters; constructing a neural network prediction model based on the database, updating hyper-parameters of the prediction model based on a reverse update algorithm, obtaining an optimal hidden parameter value, and then obtaining an optimal performance parameter prediction model; and inputting to-be-optimized design parameters and process parameters of the gas mixer into the optimal performance parameter prediction model, and further obtaining optimal design parameters under the optimal performance parameters of the gas mixer based on the model. The invention also discloses a gas mixer. The optimization method is high in accuracy and optimization efficiency, and the gas mixer is simple in structure and good in mixing effect.

The invention relates to the technical field of data processing, and discloses a hydrocephalus correlation analysis method and system based on multi-dimensional data. The method comprises the steps that a feature matrix is generated by obtaining and standardizing hydrocephalus multi-dimensional data, after the matrix is discretized, an association rule mining algorithm is adopted to extract an association mode, a rule set is obtained in combination with knowledge graph verification, data clusters are divided based on mahalanobis distance clustering, mixed effect time sequence model fitting parameters are established for all the clusters, and a mixed effect time sequence model is obtained. And calculating a target sample attribution cluster and predicting a symptom improvement trajectory and a confidence interval. According to the method, automatic integration, credible association rule extraction, precise subtype division and individualized symptom trajectory prediction of the multi-dimensional data of the hydrocephalus patient are realized.

The invention discloses a quantitative analysis method for influence of environmental factors on vegetation resistance and restoring force. The influence of the environmental factors on the vegetation resistance and restoring force is quantitatively analyzed by collecting tree ring samples and meteorological data, establishing a composite drought evaluation index and constructing a mixed linear effect model. The method comprises the following steps: firstly, obtaining annual ring width standardized data, calculating monthly vapor pressure deficit and potential evapotranspiration, determining a composite drought year, then calculating vegetation resistance and restoring force indexes, and finally analyzing the influence degree of environmental factors through a mixed linear effect model. According to the method, the evaluation precision is improved through the high-resolution tree ring data, the analysis robustness is improved by adopting the mixed effect model, the key environmental factors can be effectively identified, and a scientific basis is provided for ecological system management.

The invention discloses a virtual model processing method and device, electronic equipment and a storage medium. The method comprises the steps that at least two model materials of a to-be-processed virtual model are acquired; obtaining at least one type of replacement parameters corresponding to the model material through at least one target function node of a target game engine; and based on the replacement parameters and the replacement maps corresponding to the model materials, performing material superposition processing to obtain a processed target model material of the virtual model. By setting a plurality of target function nodes, a real mixed model material with an undulating replacement effect can be created, the authenticity and the simulation effect of the appearance effect of the obtained virtual model are improved, programming of the manufacturing steps of the model material with the replacement effect and the mixed effect is realized, and the manufacturing efficiency of the model material is improved. A real fluctuating complex appearance effect can be rapidly manufactured, and the virtual model manufacturing efficiency is improved.

The invention relates to a left basal joint cerebral hemorrhage rat ear vagus nerve electrical stimulation fMRI brain region activation map construction method and an activation brain map. The method comprises the steps of adaptation, grouping, modeling, intervention and evaluation of rats; the brain of the rat is scanned, and image data are collected; carrying out data processing, statistics and analysis on the acquired image data based on an SPM12 algorithm architecture; based on the mixed effect model, analyzing the effectiveness of longitudinal remodeling and VNS regulation of spontaneous brain activity in the brain region of the rat, and establishing a VNS brain activity map database; and based on the mixed effect model, analyzing the effectiveness of longitudinal remodeling and VNS regulation of the core nodes in the rat brain region, and establishing a VNS brain core node database. According to the present invention, the current rat brain function change condition is detected, the VNS stimulation brain region activation map is established according to the active state of the current brain region of interest, the comparison reference data is provided for the VNS regulation brain function experiment, and the reference is provided for the experiment process of the optimization of other rat brain function pathological models.

The invention relates to the technical field of industrial economy analysis and power data mining, and provides a power utilization mode change-based industrial transfer implementation effect evaluation method, which comprises the following steps of: acquiring power utilization time sequence data before and after transfer; extracting multi-dimensional features; the relative change rate is calculated, and direction unification is carried out according to index'lifting / descending '; constructing a comprehensive effect index; performing grade judgment by adopting ordered judgment / ensemble learning; and outputting a result and confidence. An index system covering the dimensions of load, efficiency, stability and the like is constructed by establishing a power utilization mode base line and comparison before and after transfer, and an effect quantification mechanism and an integrated learning model with unified directions are introduced, so that the industrial transfer effect is objectively and interpretably evaluated and graded; the confidence coefficient adopts geometric weighting of calibrated probability, stability, integrity and time span, and the method can be selectively combined with synthetic contrast / causal recognition to eliminate hybrid influences of seasons, prices, meteorology and the like, so that the evaluation robustness is improved.

This invention belongs to the field of high-performance thermoplastic composite granule preparation and process optimization technology. Specifically, it relates to a method and system for determining the optimal process for twin-screw extrusion preparation of carbon fiber / polyetheretherketone (PEEK) granules based on numerical simulation and multi-objective optimization. A three-dimensional model of the internal flow channel of the twin-screw extruder is established, and discretization is performed using a mesh stacking method. Multiple simulation conditions are constructed within a preset temperature and extrusion speed range, and process safety constraints are established. The analytic hierarchy process (AHP) – approximation of ideal solution ranking method is used for index standardization, weight allocation, and comprehensive scoring. With process temperature and extrusion speed as decision variables, a non-dominated sorting genetic algorithm is used for multi-objective global search to obtain the Pareto optimal solution set, which is then ranked and optimized to output recommended process parameter combinations. This invention's method can reduce the risk of thermal degradation and fiber damage while considering the mixing effect, and reduces the cost and cycle time of trial and error.

The invention discloses a fish spawning site position calculation method based on otolith microchemistry and river micronization landscape atlas, which comprises the following steps: otolith and water body sample pretreatment: taking out an otolith sample from a sample tube for slice preparation, and preparing a standard solution by using the water body sample; experimental analysis: measuring trace chemical elements, namely Sr, Ba, Mn, Mg and Ca, of otolith; data analysis: drawing a river micronized landscape map, constructing a mixed effect model to calculate otolith trace element values, constructing a random forest model based on the otolith trace element values, and performing spawning site position calculation on fish otolith core microchemistry; according to the method, a brand new biogeochemical framework is constructed, and the spawning site position of the fish is accurately calculated by combining otolith microchemistry, a river micronization landscape map and a machine learning technology.

The invention discloses an automatic filling detection control method and device for a reaction kettle. The method comprises the following steps: acquiring image data of material mixing states at different positions in a reaction kettle at intervals of preset time, preprocessing a color image to enhance the material particle feature identification degree, extracting features by using a machine learning algorithm, identifying feature units meeting a mixing uniformity standard through a classification model, and counting the number, and adopting a corresponding control method for the specific image features based on the statistical result and a preset rule. The device comprises an image acquisition module, an image preprocessing module, an image feature processing module and a control module which are respectively used for realizing image acquisition, preprocessing, feature processing and rule-based automatic control. Through the image detection and intelligent control technology, the problems that an existing reaction kettle is lagged in mixing effect monitoring and insufficient in automatic control are solved, the production efficiency and the mixing uniformity are improved, and the reaction kettle is suitable for the fields of new energy materials, chemical engineering and the like.

The invention discloses a method and a system for identifying key biological class groups influencing a lake ecosystem based on a sectional structure equation model, relates to the technical field of environmental ecology, and comprehensively investigates the biocenosis diversity and ecological function characteristics of a lake. A nutrition structure of a lake ecosystem is constructed by analyzing the predation relationship among biological groups; the multifunctionality of the lake is evaluated by integrating clustering analysis and a functional threshold method; the method comprises the following steps: constructing a sectional structure equation model based on a nutrition structure relationship of a food web, fitting each path in the model through a mixed effect model, analyzing a path coefficient between nutrition level richness and multifunctionality, and calculating direct and indirect effects of the path coefficient; and finally, identifying the key biological class group which has the greatest influence on the ecological function of the lake. According to the method, the key biological class groups with decisive influence on the ecological function of the lake can be accurately identified, a clear target is provided for ecological protection and restoration, and the method has practical reference significance in making practical restoration management measures.

An embodiment of the present invention provides a method, device, electronic device and readable medium for processing a grass model, including: determining a normal vector of each vertex in the grass model to be rendered; controlling the normal vector to offset in a first direction, where the first direction is the opposite direction of the gravity direction; determining a force vector based on the offset normal vector, where the force vector is used to simulate gravity; determining a target position to be offset for each vertex of the grass model according to the force vector and the current position of each vertex of the grass model; controlling each vertex of the grass model to move to the corresponding target position respectively to obtain a grassland under the influence of gravity. And it realizes the rapid adjustment of the grass model, so that the grass model can naturally show the drooping effect. And it is easy to adjust the grass model subsequently, and it is relatively easy to show the mixed effect of the gravity effect and other effects.

The invention relates to a method for evaluating the correlation of anti-seismic deformation capability of a bridge structural member, which comprises the following steps of: firstly, collecting bridge pier column engineering parameters such as reinforcement ratio, axial compression ratio and the like and an anti-seismic deformation capability quantitative index, and dividing into a training set and a test set after sample screening, feature optimization and data conversion; then, constructing a Gaussian process regression model fusing a mixed effect and a multi-output kernel function so as to synchronously describe association among multiple damage states; the optimal kernel function is screened through training, hyper-parameters are optimized, and finally based on a trained model, two types of correlation of'different damage states of the same component 'and'the same damage state of different components' are scientifically quantified. According to the design, the defects of a traditional experience hypothesis method are overcome, automatic and accurate quantification of the anti-seismic deformation capacity correlation is achieved through data driving, and a reliable result of convergence verification lays a solid foundation for bridge pre-seismic anti-seismic analysis, post-seismic damage rapid evaluation and anti-seismic design optimization.

In order to describe the coupling effect of various stresses, two types of multi-stress acceleration models are respectively constructed, a selection method of the multi-stress acceleration models is provided, and the constructed multi-stress models comprise a multi-stress acceleration model based on stress synthesis and a multi-stress acceleration model based on a mixed effect; aiming at the two multi-stress acceleration models, an acceleration model selection method based on mechanism consistency is provided. The two established multi-stress acceleration models can quantitatively describe the positive correlation effect and the negative correlation effect among multiple stresses, the coupling effect among the multiple stresses is accurately described, and method support is provided for improving the product life prediction precision under the multi-stress condition.

The invention relates to the technical field of lithium battery health state estimation, in particular to a lithium ion battery health state estimation method based on individual characteristics, which comprises the following steps of: providing a lithium ion battery degradation modeling framework, mapping a relationship between an operation factor and a mixed effect by utilizing a B-spline primary function, and establishing a large covariance matrix model; estimating coefficients of the noise and the spline basis function respectively; according to the Bayesian theorem, different parameter updating strategies are provided for different conditions; performing SOH prediction of the battery; the lithium ion battery health state evaluation method based on the individual characteristics has the beneficial effects that the degradation process is modeled through operation factors; the method is different from a traditional degradation model, only overall behaviors among batteries are considered, and individual differences are ignored. By using the operation factors, the model can more accurately capture the unique degradation path of each battery, so that the prediction precision and stability are improved.

Methods, systems, and devices for providing game classification are disclosed. In particular, example embodiments provide game classification with respect to a degree of chance or skill that influences game outcomes, for example with chance-based games and skill-based games. In an example method, a threshold training dataset is obtained to train a classification model to classify a given game as one of multiple game types that describe different degrees of chance or skill involved in the given game. From the threshold raining dataset, outcome factor distributions of games are determined and used to set trained thresholds of the classification model. The classification model can then be deployed in a computer service platform that receives queries from client devices.

The invention provides an emotional health data processing system and method and computer equipment. Based on the method, before specific implementation, continuous sample detection data of a long-term sample test time period of a sample test object can be collected and utilized, and the continuous sample detection data of the long-term sample test time period of the sample test object can be obtained through combined use of logistic regression analysis, a generalized linear mixed effect model, Poisson regression analysis and a latent category mixed effect model. And training to obtain a preset prediction model suitable for emotion health prediction. In specific implementation, firstly, an acquisition module and a processing module are used for acquiring blood cell detection data of a target object in a first time period, and a key feature change track of blood cells of the target object in the first time period is determined according to the blood cell detection data; and determining an emotion health prediction result of the target object according to the key feature change track of the blood cells of the target object in the first time period by using a preset prediction model through a determination module. Therefore, the emotion health condition of the target object can be efficiently, intelligently and automatically determined.

The present invention relates to a method for predicting a disease decline rate through a mixed effect model, and belongs to the field of medical data analysis. A method for predicting a disease decline rate through a mixed effect model comprises the following steps: S1, inputting basic information and time series detection data of a patient; S2, calculating the decline rate of the HBsAg level of the patient at each detection moment relative to the baseline; S3, establishing a group trajectory model, using a conditional probability formula to calculate the probability that the patient belongs to different heterogeneous latent category groups, and judging the heterogeneous latent category group to which the patient is most likely to belong; S4, establishing a time effect prediction model, using the patient's HBsAg level decline rate data to predict the patient's future HBsAg level decline trend; S5, coupling the time effect prediction model with the group trajectory model to improve the prediction accuracy of the patient's future HBsAg level decline rate. By combining the time effect prediction model with the group trajectory model to predict the decline rate, the individual differences of the patient and the dynamic changes of time are considered, and the prediction accuracy is improved.

This application belongs to the field of microgrid frequency control, specifically disclosing a model-free adaptive microgrid frequency control method to resist network attacks. The method includes the following steps: considering the mixed effects of denial-of-service attacks and spoofing attacks, a system output model incorporating attack coefficients is established, modeling the microgrid frequency control system as a discrete-time nonlinear system; dynamic linearization technology is used to transform the nonlinear system into an equivalent linear data model; for the linear data model, a partial pseudo-derivative estimation algorithm is designed, and a model-free adaptive control law incorporating a decay function is designed; the time-varying partial pseudo-derivative matrix is ​​iteratively updated using the partial pseudo-derivative estimation algorithm, and based on the updated partial pseudo-derivative matrix, the control input at the current moment is calculated using the model-free adaptive control law to control the microgrid frequency. This application can achieve effective frequency control even when the microgrid frequency control system model is unknown and faces mixed network attack threats.

The present invention belongs to the field of environmental microorganisms, and specifically relates to a method for constructing and testing a medicinal plant quality prediction model based on a mixed-effect model and rhizosphere microorganisms, comprising the following steps: (1) determining sampling points in a medicinal plant planting area; (2) collecting, processing, and quantifying quality indicators of plant samples; (3) collecting rhizosphere soil samples, extracting DNA, and conducting high-throughput sequencing; (4) constructing a training set and a test set; (5) screening associated microorganisms, model construction, and coefficient extraction based on the training set; and (6) model verification based on the test set. The present invention, through high-throughput sequencing, sample set splitting, and a mixed-effect model, establishes a medicinal plant quality prediction model using rhizosphere microorganisms for the first time, which can effectively predict the content of the main active substances in medicinal plants, laying a foundation for scientifically and efficiently predicting and improving the quality of medicinal plants during the medicinal plant planting process, and has great significance for the quality control and production of high-quality traditional Chinese medicines.

The invention discloses a diabetic nephropathy prediction system and prediction device based on a mixed index, and belongs to the technical field of computer systems based on a specific calculation model, the system comprises an acquisition module, a weighting module and a prediction module, the acquisition module is used for acquiring clinical characteristics and retinal vascular geometric parameters of a patient; the weighting module is used for constructing a mixing index through the geometric parameters of the retinal vessels based on a weighted quantile regression model; and the prediction module is used for predicting the clinical features and the mixed indexes based on a prediction model, and predicting the clinical features and the mixed indexes as diabetic nephropathy or non-diabetic nephropathy. A weighted quantile regression model is adopted to calculate a mixing effect, differences and internal correlation among individuals are fully considered, and geometric parameters of the retinal vessels are effectively integrated; therefore, the prediction model can identify the diabetic nephropathy more accurately, thereby providing earlier intervention opportunities.

The invention discloses a data collection and analysis method and system based on artificial intelligence, and belongs to the technical field of education systems.The data collection and analysis method based on artificial intelligence comprises the following steps that S1, data collection is conducted, specifically, fixed factor data and random factor data of students and data indicating whether the corresponding students pass an examination or not are collected, the fixed factor data comprises learning behavior data, historical score data and learning participation degree data, and the random factor data comprises teacher teaching methods and class average scores; s2, data processing: carrying out data processing on the fixed factor data and the random factor data, wherein the data processing comprises data cleaning, normalization and feature selection; and S3, model training: taking the processed fixed factor data and random factor data as input, taking data indicating whether the students pass the examination as output, and constructing a mixed effect model. The method has the advantage that the data accuracy is improved by integrating the fixed factors and the random factors.

The invention discloses an unmanned aerial vehicle remote sensing-based single tree biomass estimation method for catalpa bungei of different genotypes. The method comprises the following steps: acquiring unmanned aerial vehicle LiDAR data and catalpa bungei biomass ground measurement data of catalpa bungei in a preset area; according to unmanned aerial vehicle LiDAR data and catalpa bungei biomass ground measurement data, a biomass inversion basic model is constructed and screened, a dummy variable model is introduced to optimize the basic model, and a catalpa bungei genotype is used as a random effect to construct an unmanned aerial vehicle LiDAR-based nonlinear mixed effect individual tree biomass estimation model; and inputting the unmanned aerial vehicle LiDAR data of different genotypes of catalpa bungei in the to-be-processed area into the obtained nonlinear mixed effect individual tree biomass estimation model based on the unmanned aerial vehicle LiDAR data to obtain the individual tree biomass of the catalpa bungei. By adopting the technical scheme provided by the invention, the single tree biomass of the catalpa bungei with different genotypes in a large range can be effectively estimated, and improved variety breeding of the catalpa bungei is assisted.

The application discloses a biological rhythm-light interaction regulation method based on comprehensive cognitive ability index under value more conditions and an intelligent light environment regulation system, and belongs to the technical field of biological rhythm regulation and intelligent environment control. The method comprises the following steps: constructing an individualized comprehensive cognitive ability index, and fitting a solidified mixed effect model parameter based on pre-experiment data; obtaining a real-time biological rhythm phase of a person, combining the solidified parameter to calculate a cognitive ability benchmark value of the person under no light intervention, and determining a cognitive ability gap amount to be compensated; and under the physical constraint of light parameters, optimization solving is carried out to obtain optimal light intensity and color temperature, and a light source is driven to perform adjustment to change a physical light environment, and adaptive optimization is realized through a closed-loop feedback mechanism. The application realizes the transformation from a group statistical model to an individual real-time control strategy, can implement precise light regulation according to people and time, and effectively maintains cognitive ability and rhythm health during value more work.

The application discloses a kind of infrastructure flood resilience evaluation methods, comprising: using flood simulation coupling model to carry out the whole process simulation of urban flood in multiple scenarios to target area;From the simulation process, the spatial attribute index of blue-green-gray infrastructure is extracted as the independent variable, the flood dynamic index of different flood stages is extracted as the dependent variable, to form a sample data set, and the independent variable is divided into multiple independent variable groups according to function;Standardization is carried out on the independent variable and the dependent variable respectively, and data enhancement is carried out;Bayesian mixed effect model is constructed, prior distribution is set for model parameters, posterior distribution of parameters is obtained based on the enhanced sample data set using sampling algorithm, and the evaluation result is output according to the posterior distribution.The application can clearly reveal the dynamic action law of blue-green-gray infrastructure in initial rising period, flood peak period and recession period, output more stable and reliable phased dynamic resilience evaluation result, and significantly improve the safety guarantee level of urban flood control and drainage.

The present application relates to the technical field of power system, specifically relates to a kind of multi-modal fusion and dynamic game driven power grid special cost intelligent review method, comprising the following steps: S1, the multi-source data of power grid special cost project is uniformly collected and processed, including field structured, check, deduplication, fill and exception identification, generate standardized review dataset;S2, based on attention PCA and density peak clustering Weighted feature space is constructed, and same kind cost category is divided;S3, establish log-normal mixed effect model and fuse multi-level factors, estimate reasonable unit price interval in combination with experience bayes method;S4, construct Markov decision process, optimize review strategy and output conclusion and adjustment suggestion.The present application, by constructing multi-source data processing, attention clustering modeling, mixed effect statistical analysis and dynamic game decision fusion Intelligent review system, realizes the high precision, automation and strategy explainability of power grid special cost review.

The application discloses a kind of based on segmented structural equation model's influence lake ecosystem key biological group identification method and system, it is related to environmental ecology technical field, comprehensively investigates the biological community diversity and ecological function characteristics of lake;Through the analysis of the predatory relationship between biological groups, the trophic structure of lake ecosystem is constructed;Comprehensive cluster analysis and function threshold method assesses the multifunctionality of lake;Based on the trophic structure relationship of food web, segmented structural equation model is constructed, each path in the model is fitted by mixed effect model, the path coefficient between trophic level richness and multifunctionality is analyzed, and its direct and indirect effects are calculated;Finally, the key biological group that has the greatest influence on lake ecological function is identified.The present application can accurately identify the key biological group that has a decisive influence on lake ecological function, provide a clear target for ecological protection and restoration, and has practical reference significance in actual restoration management measure formulation.

In some implementations, adjusting entity activities in response to media mentions can include actions of detecting media mentions, calculating the effect of media mentions using a mixed effect model, and generating recommendations using a machine-learning model to adjust a predicted outcome of the entity activity. The prediction of effects can include data processing using a mixed model comprising a statistical model containing both fixed effects and random effects. The dynamic adjustment can be based on recommendations provided using a machine-learning model. The recommendations can include a dimensional projection matrix including a spatial and temporal dimension.

The present application relates to a kind of community old people health management system and method based on metabolic equivalent, through the comprehensive collection of multidimensional health data, and the processing of multi-source heterogeneous time series data, construct health database;Then adopt mixed effect model and gradient boosting decision tree model, with metabolic equivalent as core quantitative index, extract individual random effect as personalized correction factor by mixed effect model, output personalized metabolic equivalent prediction value combined with gradient boosting decision tree model, solve the problem of existing technology evaluation standard missing, group evaluation one-size-fits-all;Then through time domain, frequency domain, nonlinear feature extraction, the motion load characteristics are fully described, and the association between motion load and health risk is accurately captured by Transformer-LSTM hybrid network, which significantly improves the prediction accuracy of cardiovascular events and fall risk;Finally, through the collaborative optimization model of multi-agent reinforcement learning, dynamically generate and optimize multi-dimensional exercise programs according to the real-time health status of the user.