45results about How to "Good forecast" patented technology

The invention provides a Bayesian-based aviation equipment residual life uncertainty prediction method and system. The method comprises the following steps: S1, constructing an observation function equation and a state parameter description equation of residual life of key or important systems, modules and parts of aviation equipment; s2, constructing an agent model; s3, solving joint posterior probability distribution and performing residual life prediction; and S4, according to the prediction probability distribution of the remaining life of the aviation equipment, generating an optimization control instruction or a maintenance instruction for the aviation equipment, and acting the optimization control instruction or the maintenance instruction on the aviation equipment. The method provided by the invention not only provides a theoretical basis for solving the problem of prediction, analysis and prediction of the service life of the aviation equipment, but also clearly defines how information and uncertainty thereof flow and convert between a physical world and a digital world, and provides a brand new thought for prediction of the uncertainty of the residual service life of the aviation equipment.

The application provides a method for training a blood pressure prediction model based on meta learning, which comprises the following steps: acquiring a training set, dividing the training set into a first training set, a second training set and a third training set; pre-training a blood pressure prediction model using the first training set to obtain a pre-trained blood pressure prediction model; initializing an initial meta learner using the parameters of the pre-trained blood pressure prediction model; training the initial meta learner using a plurality of training tasks in the second training set based on a meta learning algorithm to obtain a target meta learner; initializing the target meta learner for each patient in the third training set respectively to obtain an initial personalized blood pressure prediction model corresponding to each patient, and training the initial personalized blood pressure prediction model corresponding to each patient using the training data of the patient in the third training set to obtain a personalized blood pressure prediction model corresponding to the patient.

The invention discloses a credible drug target prediction method based on function space regularization, and relates to the technical field of drug research and development, and the method comprises the steps: collecting interaction data and feature data of drug molecules and EGFR mutants; constructing a drug similarity graph and a target similarity graph; defining a bilinear prediction function and a loss function; a function space regularization term based on double-graph convolution is introduced, and the regularization term forms a regularization term of the smoothness of the constraint prediction function in the joint similarity space through Laplacian matrix construction of the joint drug graph and the target graph; combining the loss function with the regularization item to construct an objective function, and performing optimization solution through a gradient descent method; and finally, predicting the interaction between the new drug and the EGFR mutant by using the optimized model. By introducing a mechanism based on double-graph convolution function space regularization, combined similarity information of a pharmaceutical chemical structure and a target sequence can be fused in drug target prediction of non-small cell lung cancer EGFR mutants.

This invention relates to the field of magnetic resonance imaging technology, specifically disclosing a method for modeling the radio frequency transfer function of active implantable medical devices. This method constructs a suitable neural network algorithm and, based on learning important features such as the geometric parameters of the active implantable medical device and the characteristics of the surrounding tissue, enables it to quickly and effectively predict the radio frequency transfer function of the active implantable medical device in homogeneous and heterogeneous tissue environments. This overcomes the limitations of traditional in vitro experimental methods, such as low efficiency, high experimental costs, and the inability to simulate homogeneous tissues, providing a new option for modeling the radio frequency transfer function of active implantable medical devices.

The invention relates to the technical field of integrated navigation, in particular to a positioning method and system based on optical angle measurement and astronomical-inertial integrated navigation. According to the method, firstly, a star image and a navigational satellite image are obtained at the same time by shooting a star map, after recognition and processing, the attitude of a camera relative to a geocentric inertial coordinate system is calculated by utilizing the star, and then the coordinate of the navigational satellite in the coordinate system is determined. And obtaining angle information of the navigation satellite relative to the observer under the earth coordinate system through coordinate transformation. Optical angle measurement information is fused with attitude, speed and position information output by an inertial navigation system, a Kalman filtering state equation and an observation equation are constructed, and finally real-time high-precision calculation and updating of the position of the observer are achieved. According to the method, the accuracy of optical angle measurement, the limited distance reference of celestial navigation and the autonomous continuity of inertial navigation are fused, and the navigation positioning accuracy and reliability under the complex environment and the satellite denial condition are effectively improved.

This invention relates to the field of hydrogeological exploration technology and discloses a method for accurately predicting aquifer inflow by integrating conventional and electromagnetic flow logging. The method includes the following steps: Step 1: Well logging data acquisition. Electromagnetic flow logging and conventional logging are performed simultaneously in the target exploration borehole to obtain static and dynamic flow response amplitude curves, apparent resistivity curves, natural gamma curves, and sonic transit time data. This method for accurately predicting aquifer inflow by integrating conventional and electromagnetic flow logging data constructs a key parameter system covering four dimensions: "water storage space - recharge power - water storage capacity - permeability resistance." It also utilizes the powerful nonlinear fitting capability of a generalized regression neural network (GRNN) to establish a prediction model, effectively overcoming the shortcomings of traditional theoretical formulas in adapting to complex geological conditions.

The embodiment of the invention provides a mode memory enhanced dynamic graph convolution traffic flow prediction method and related equipment, and belongs to the field of intelligent traffic and spatio-temporal data prediction. According to the method, a two-state driven dynamic graph generation mechanism is constructed, and the method comprises the following steps: extracting dynamic mode embedding of traffic data through a mode memory network to capture unsteady disturbance characteristics; time period embedding is extracted through an independent period embedding unit so as to encode a steady state rule; and fusing the two to generate a dynamic graph structure at each moment. According to the method, a dynamic graph generation module is further integrated at a decoding end of an encoder-decoder architecture, so that an adaptive dynamic graph can be regenerated according to time information of a target moment when each future moment is predicted, and graph structure dynamic evolution of a whole training and prediction process is realized. According to the invention, the traffic flow prediction precision, especially the accuracy of long-term prediction, is effectively improved, and the generalization ability of the model to unexperienced scenes is enhanced.

This invention proposes a dynamic routing decision-making method, specifically a TSSDN dynamic routing decision-making method based on the DDPG deep reinforcement learning algorithm. The aim is to design dynamic routing decisions using deep reinforcement learning algorithms based on network dynamic awareness prediction results, thereby reducing the transmission latency of low-priority flows in time-sensitive networks. This invention uses a deep learning algorithm to predict switch queue lengths in real time, and then makes next-hop routing decisions based on the prediction results. Higher prediction accuracy leads to better dynamic routing performance and improved decision-making efficiency. The implementation steps are: 1) Constructing the TSSDN network node architecture; 2) Constructing the network topology; 3) Constructing a topology feature extraction method based on PCA; 4) Constructing a prediction model based on a deep learning algorithm; 5) Constructing a routing decision-making model based on a deep reinforcement learning algorithm; 6) Iteratively training the deep reinforcement learning-based routing decision-making model based on the prediction results. This invention can be applied to scenarios such as telemedicine.

The embodiment of the application relates to the battery technical field, and discloses a battery life prediction method and device, electronic equipment and a storage medium. The battery life prediction method comprises the following steps: extracting a capacity diving feature of a battery according to a capacity loss curve of the battery, and extracting a capacity increment feature of the battery according to an IC curve of the battery; wherein the capacity loss curve comprises a component of linear loss of battery capacity and a component of nonlinear loss of battery capacity, and the capacity diving feature is extracted from the component of nonlinear loss of battery capacity; the capacity increment feature and the capacity diving feature are input into a pre-trained battery life prediction model to obtain a life prediction result of the battery, and the battery life prediction model is trained by using at least one capacity diving feature and capacity increment feature of the battery to obtain an LSTM model. The battery life prediction method can realize accurate prediction of the life of a lithium ion battery under edge working conditions, so that fine management of the battery is realized.

The invention discloses a sepsis risk multi-modal prediction method and system based on deep learning, and belongs to the technical field of intelligent analysis of medical data, and the method comprises the following steps: a multi-modal data collection step: collecting vital sign sequences, bedside instant inspection, laboratories, microbial culture, images and medical history data; in the time sequence feature coding step, a time sequence embedded vector is extracted through a multi-scale time sequence coding network; the cross-modal fusion prediction step is based on the dynamic attention mechanism fusion features and predicts the sepsis occurrence probability; the organ function dynamic evaluation step is used for estimating a missing test result and calculating an organ function score; the risk layering early warning step outputs four-level risk layering results and feeds back optimized coding parameters, early warning can be output 4-8 hours before the diagnosis standard is met, and compared with qSOFA, the AUC is improved by 0.15 or above.

The application discloses a kind of risk factors prediction model of occurrence of initial treatment bacterium positive pulmonary tuberculosis lung cavity, belong to medical data processing technical field, the clinical data of initial treatment bacterium positive pulmonary tuberculosis patient is collected in the application, using single factor analysis, Lasso regression analysis and multivariate Logistic regression analysis, male, diabetes, smoking, white blood cell count and platelet / hemoglobin ratio are screened as the independent risk factors of initial treatment bacterium positive pulmonary tuberculosis causing lung cavity, and based on this, nomogram prediction model is constructed.H-L goodness-of-fit test, receiver operating characteristic curve and decision curve analysis are verified, the model has higher prediction efficiency and clinical practical value.The application can help clinical advance to predict and intervene the cavity caused by high-risk population of pulmonary tuberculosis, provide new ideas for the diagnosis and treatment of bacterium positive pulmonary tuberculosis causing cavity.

The invention provides a circuit board life prediction method and system based on mass failure welding spot data and a risk matrix, electronic equipment and a storage medium, and relates to the field of welding spot failure. The method comprises the following steps: acquiring massive invalid welding spot data, and extracting welding spot failure mechanism characteristics from the invalid welding spot data based on expert knowledge to obtain welding spot failure mechanism characteristics; based on the welding spot failure mechanism characteristics, welding spot failure characteristic factors are determined; acquiring welding spot failure characteristic factor data and circuit board data of a to-be-predicted circuit board, and determining welding spot failure data of the circuit board based on the welding spot failure characteristic factor data; and determining a welding spot failure type based on the welding spot failure data, and inputting the circuit board data and the welding spot failure type into a preset life prediction model to obtain a life prediction value. By means of the method, mass data are deeply utilized, essential reasons influencing welding spot faults are found out, and accurate evaluation and prediction of the residual life of the circuit board are achieved.

This invention relates to the field of hydrodynamic prediction technology, specifically to an intelligent prediction method and system for hydrodynamic effects based on a multi-factor, full-level conditional embedding network. First, key influencing factor parameters of hydrodynamic effects are obtained, and standardized conditional input vectors are constructed and preprocessed. Then, an MHCE-Net is built, comprising conditional input, encoding, and mapping modules, as well as encoders, bottleneck layers, decoders, and output modules. The standardized vectors are mapped to conditional feature layers through feature enhancement and dimension matching, and the corresponding layers of the full-level embedding network are fused with convolutional feature maps. Finally, the model is trained by extracting and reconstructing the fused features, and the actual spatial distribution field of physical quantities is obtained through inverse normalization. This invention enhances feature representation capabilities through pre-encoding enhancement of multi-factor conditional vectors, enabling rapid and accurate prediction of spatial fields related to hydrodynamic effects without complex numerical simulations, significantly reducing computational costs and improving prediction efficiency and accuracy. It is suitable for hydrodynamic effect prediction needs in groundwater environments, deformation fields of water-related engineering structures, and eco-hydrological scenarios.

This invention belongs to the field of natural gas hydrate geological exploration and well logging evaluation technology, and relates to a method for predicting the effective resistivity and inverting hydrate saturation of hydrate-bearing sediments based on a logistic function. The method includes: acquiring basic petrophysical data of the target reservoir or sample to be tested; establishing a forward model of effective resistivity based on a logistic function; determining the fixed parameters in the forward model and the fitting parameters to be inverted based on the geological characteristics or experimental conditions of the target; constructing an objective function, optimizing the fitting parameters using an optimization algorithm to obtain the optimal model parameters, and establishing a univariate response equation of effective resistivity with respect to hydrate saturation; and calculating the effective resistivity or hydrate saturation of unmeasured points based on the determined response equation. This invention significantly improves the accuracy and reliability of describing the resistivity response characteristics of complex hydrate reservoirs, laying the foundation for refined evaluation of reservoir saturation and efficient resource exploration and development.

This invention discloses a dynamic interval elastic scaling method and system based on long-term series prediction. The method includes: collecting load time-series data of applications deployed in a container cloud platform and storing it in a time-series database; using a combined time-series prediction model based on the Transformer architecture and a Bi-LSTM time-series prediction model to perform long-term time-series prediction on the load time-series data; dynamically determining the scaling interval based on the predicted load; generating and executing a scaling strategy for application replicas in the container cloud platform, scaling up and allocating sufficient resources in advance before the actual increase in application load, thus ensuring the service quality of applications in the container cloud platform. This invention can effectively reduce the number of scaling operations, avoid window jitter caused by frequent scaling up and down, and ensure the stability of the container cloud cluster; effectively meet the resource requirements of applications and avoid application service quality instability caused by rapid scaling down.

This invention belongs to the field of power equipment condition monitoring and intelligent operation and maintenance technology. It discloses a multi-model fusion method for predicting generator critical location temperatures based on PSO optimization. The key steps are: constructing a dynamic adaptive fusion model of multiple prediction models based on exponentially weighted moving average; using particle swarm optimization (PSO) to optimize the fusion parameters of the fusion model constructed in step S4, obtaining the optimal fusion parameters as the parameter configuration of the final fusion model; and using the final fusion model to predict the temperature of the generator critical location over the next m steps, outputting the prediction results. This invention's multi-model fusion method for predicting generator critical location temperatures based on PSO optimization builds a multi-model fusion framework based on the exponentially weighted moving average method and uses the particle swarm optimization (PSO) algorithm to optimize the hyperparameters in the fusion calculation process, obtaining the best prediction effect for generator critical location temperatures over multiple time steps under the optimal parameters.

The application discloses a method and device for monitoring carbon emission of a thermal power plant by excavating deep time dependence, and the method comprises the following steps: coordinating the importance of time attention and time sequence time step; taking historical statistical information as a linearly related variable, combining the linearly related variable with a preliminary time dependence extracted by TCN as input data in a seq2seq model; extracting deep time dependence of time sequence data by using a bidirectional long short-term memory in the seq2seq model; and adopting an encoding attention mechanism; taking AE as a prediction calibrator; all hyperparameters depend on the results obtained by a Bayesian hyperparameter optimization algorithm, and model parameters are adjusted by minimizing loss to realize accurate prediction of target features; the carbon emission of the thermal power plant is monitored and early warning is realized by comparing the predicted value of the carbon emission with a carbon emission threshold; and the device comprises a processor and a memory. The application accurately predicts the future emission of carbon dioxide by using multi-sensor data, and then accurately monitors the carbon emission of the thermal power plant, thereby making contribution to energy saving and emission reduction.

Embodiments of the present application provide a method, device and equipment for determining blood pressure based on PPG signal and storage medium, and relate to the field of medical treatment. The method comprises: obtaining a target signal sequence, inputting the target signal sequence into a pre-trained neural network model, and obtaining a blood pressure value sequence corresponding to the target signal sequence output by the neural network model; wherein the neural network model is trained with a sample signal sequence as a training sample and with a sample blood pressure value sequence corresponding to the sample signal sequence as a training label; at least one sample PPG signal sequence at a time in the sample signal sequence is a distorted sequence meeting a distortion condition, and a sample blood pressure value corresponding to each distorted sequence is related to a sample blood pressure value corresponding to a first PPG signal sequence at a previous time of the corresponding distorted sequence. The embodiments of the present application can ensure that the prediction effect of long-time continuous blood pressure prediction is in a good state.

The application discloses a shared bicycle demand prediction method based on a geographical distance enhanced space-time graph neural network, belongs to the technical field of bicycle demand prediction, and inputs bicycle data cleaned and aggregated into a double-branch framework integrating local and global space-time information, which is composed of a local information branch and a global information branch. In the local branch, the distance information between stations is introduced, a multi-scale Gaussian kernel is designed for processing, and is added to the calculation of attention scores to solve the deficiencies of existing models in global and local information integration and real geographical distance information extraction. In the global information branch, global spatial patterns and long-term time trends are extracted through the combination of GAT and TCN, and information is further fused through shared GNN and shared MLP to comprehensively integrate global space-time information, better grasp the overall change rule of bicycle demand in time and space, and improve the prediction accuracy and stability.

The present application relates to the technical field of integrated navigation, in particular to a positioning method and system based on optical angle measurement and astronomical-inertial integrated navigation. The method first acquires star and navigation satellite images by shooting a star map, and then calculates the attitude of the camera relative to the geocentric inertial coordinate system by identifying and processing the stars, and further determines the coordinates of the navigation satellite in the coordinate system. Through coordinate conversion, the angle information of the navigation satellite relative to the observer in the earth coordinate system is obtained. The optical angle measurement information is fused with the attitude, speed and position information output by the inertial navigation system, the Kalman filter state equation and observation equation are constructed, and finally the real-time high-precision solution and update of the observer's position are realized. The present application combines the accuracy of optical angle measurement, the limited distance reference of astronomical navigation and the autonomous continuity of inertial navigation, effectively improving the navigation and positioning accuracy and reliability under complex environment and satellite denial conditions.

The invention discloses a gravity dam deformation monitoring method based on intelligent analysis. In the service process of a dam, deformation monitoring data are usually complex, non-stable and non-linear time sequences, and a simple and clear mathematical relationship is often difficult to establish. According to the method, hyper-parameters are optimized by using a northern eagle optimization algorithm, wherein the hyper-parameters comprise an initial learning rate, a BiLSTM neuron number, a key value number of a self-attention mechanism and a regularization parameter; the optimal hyper-parameter combination is applied to a CNN-BiLSTM-Attention model, and a concrete dam deformation prediction model is formed. The method has excellent prediction precision and long-term prediction performance, and a new method is provided for high-precision prediction of dam deformation.

The application discloses a monocular camera calibration method based on a phase target and a double radial basis function neural network, adopts a three-step phase shift method for feature extraction, and uses a multi-frequency method to calculate absolute phase, converts absolute phase borne by feature points of the phase target to a three-dimensional space, establishes a corresponding relationship between image coordinates and world coordinates of the feature points, and finally uses a double RBF neural network to complete direct mapping of two-dimensional image coordinates to three-dimensional space coordinates, the whole RBF neural network uses a genetic algorithm to iteratively optimize width parameters and uses an improved least mean square learning rule to prevent over-computation. Meanwhile, a function model is used for constraint in the depth direction, the convenience and accuracy of the monocular camera calibration method are improved, and the demand of camera calibration can still be met under a complex distortion environment.

The application provides an ECMWF mode element bias correction method based on AttUnet, and belongs to the meteorological prediction field. The method uses a deep convolutional neural network in 4 elements of ECMWF mode output surface, 2m temperature, surface pressure, 2m specific humidity and 10m wind, and performs bias correction on the 0.125 degree resolution ECMWF mode output result. The method first constructs a feature library according to the ECMWF mode output elements, and then uses the XgBoost tool to analyze the sample library and sort the importance, and further screens the factors combined with artificial experience and considers the terrain information. Then, the deep convolutional neural network is used for prediction and bias correction to obtain more accurate 0.125 degree grid products. At the same time, in the model debugging stage, by optimizing the learning rate and the loss function, the model has good prediction performance for extreme disastrous weather.

The invention relates to a flora prediction model for detecting premature delivery risk and a kit and application thereof. Through early-stage mNGS data collection and analysis, premature related strains are obtained, and through a large number of experimental screening and optimization, a set of optimal primer probe group is finally determined. The invention relates to a premature delivery risk calculation method, which comprises the following steps of: selecting 12 floras, namely lactobacillus crispatus, lactobacillus gasseri, lactobacillus inertus, lactobacillus jensenii, escherichia coli, enterococcus faecalis, enterobacter aerogenes, group B hemolytic streptococcus, ureaplasma parvum, chlamydia trachomatis, diplococcus gonorrhoeae and gardnerella vaginalis, and establishing a fluorescent quantitative PCR (Polymerase Chain Reaction) method and a premature delivery risk calculation model aiming at the detection of the 12 floras. Compared with an existing detection method, the method is simple, convenient, rapid, high in sensitivity and high in specificity, the false positive and false negative risk is reduced, and the purpose of batch detection is achieved. Clinically, the change of microbial flora in the reproductive system of a pregnant woman can be rapidly detected, corresponding treatment measures are taken, the risk of PTB occurrence is reduced, and the kit has a good application prospect.

The invention discloses a data fusion-based rotation-oriented dynamic tool surface measurement method and device and a storage medium, and the method comprises the steps: obtaining an optimal gravity tool surface estimation value through an unscented Kalman filtering algorithm based on a quaternion theory of rotation coordinate conversion; based on a rotary steering tool surface calculation principle, obtaining a theoretical calculation gravity tool surface estimation value; and fusing the optimal gravity tool face estimation value and the theoretical calculation gravity tool face estimation value to obtain a final prediction value. The rotary steering dynamic tool surface is measured by combining an unscented Kalman filtering measurement result and a theoretical derivation calculation result, the numerical value is more stable, and the precision is higher.

The application discloses a SAR image ship target recognition method and system based on an improved NanoDet-Plus, and belongs to the field of computer vision. The method comprises the following steps: acquiring a SAR image containing a ship target, pre-processing the SAR image, and constructing a data set of labeled labels; constructing a background scene classification network and training the same by using the data set, and simultaneously obtaining a plurality of scene sub-data sets different in background scene based on the labeled data set; constructing a plurality of improved NanoDet-Plus models equal in number to the plurality of scene sub-data sets, each of the models being trained by using a scene sub-data set, and using the trained background scene classification network and the trained NanoDet-Plus models to perform target recognition on a SAR image to be subjected to ship target recognition. The application effectively improves the accuracy and real-time performance of ship target recognition, and has good engineering applicability and popularization value.

The application discloses a kind of based on label constraint's multi-modal classification model training method and device, the method includes: determining the training data of target modality for training model and corresponding data label;The training data is input into training to convergence data classification model, obtain the training data corresponding training data feature;The data label is input into the label classification model trained, obtain the label feature corresponding to the data label;The training data and the data label are input into the data classification model and are trained, in training, according to target loss function value, the model parameter of the data classification model is optimized until convergence, obtains the data classification model trained;The target loss function value includes the feature difference degree between the training data feature and the label feature.It can be seen that the present application can make the feature extraction of model more label distinguishability, and then make the prediction effect of model better.

The present application relates to the technical field of ecological risk assessment test strategy, in particular to a method for predicting the content of biological enrichment factor by using QICAR modeling. The present application uses known BCF, metal physicochemical properties and corresponding regional soil physicochemical properties as data, uses the training of QICAR coupled machine learning model to obtain the prediction value of unknown heavy metal BCF in the target region, and screens the test set data through multiple rounds of cross-validation 2 and average absolute error MAE to evaluate the performance of the model to obtain the optimal model, and then evaluates the result through feature analysis and Shapley weighted explanation to obtain accurate and scientific prediction value, which provides effective support for the prediction of heavy metal enrichment capacity of crops and guarantees food safety.

The application discloses a crowd activity prediction method based on a dynamic graph auxiliary neural differential model, and the method comprises the following steps: reading crowd activity data in history and collecting and arranging index data of a corresponding event; normalizing the crowd activity data in history and the index data of the corresponding event to obtain a standard data set, and dividing the standard data set into a training set and a verification set, which are respectively used for model training and parameter selection; training a model according to the training set to obtain an initial prediction model; adjusting the initial prediction model according to the verification set, determining network weight parameters of the model through multiple verifications, and selecting a model with the best performance on the verification set as a final prediction model; and outputting a future crowd activity track through the final prediction model. The method generates a dynamic graph structure through a control module to introduce disturbance of an event on crowd activity into the model, so that the model has stronger robustness and still has a good prediction effect in a scene influenced by a major event.

The application discloses a combined biomarker combination and evaluation model for evaluating chronic low-grade inflammation of polycystic ovary syndrome, and belongs to the technical field of biomarkers. The combined biomarker combination comprises inflammation-related proteins and metabolites; the inflammation-related proteins comprise FURIN, CCL3, CCL8, CD38, NOS2, NOS3, IL18R1 and HGF; and the metabolites comprise lithocholic acid-3-O-glucuronide and taurine. The application provides a combined biomarker combination for diagnosing and evaluating the chronic inflammation state of polycystic ovary syndrome and an application method thereof. By jointly detecting specific inflammatory proteins and metabolites, the systemic chronic inflammation load of PCOS patients is quantitatively evaluated, and the combined biomarker combination has the beneficial effects of high stability, accurate discrimination, wide applicability and easy clinical transformation, and solves the problem that there is no objective evaluation method for the chronic inflammation state of PCOS.