608results about How to "Improve modeling accuracy" patented technology

Neural networks are constructed (programmed), trained on historical data, and used to predict any of (1) optimal patient dosage of a single drug, (2) optimal patient dosage of one drug in respect of the patient's concurrent usage of another drug, (3a) optimal patient drug dosage in respect of diverse patient characteristics, (3b) sensitivity of recommended patient drug dosage to the patient characteristics, (4a) expected outcome versus patient drug dosage, (4b) sensitivity of the expected outcome to variant drug dosage(s), (5) expected outcome(s) from drug dosage(s) other than the projected optimal dosage. Both human and economic costs of both optimal and sub-optimal drug therapies may be extrapolated from the exercise of various optimized and trained neural networks. Heretofore little recognized sensitivities-such as, for example, patient race in the administration of psychotropic drugs-are made manifest. Individual prescribing physicians employing deviant patterns of drug therapy may be recognized. Although not intended to prescribe drugs, nor even to set prescription drug dosage, the neural networks are very sophisticated and authoritative "helps" to physicians, and to physician reviewers, in answering "what if" questions.

The invention relates to an indoor autonomous navigation method for a micro unmanned aerial vehicle, belonging to the technical field of autonomous navigation of micro unmanned aerial vehicles. The method comprises the following steps: estimating the motion state of the micro unmanned aerial vehicle based on an RGB-D camera and an MEMS inertial sensor; performing real-time three-dimensional environment modeling based on fusion of the RGB-D camera and the MEMS inertial sensor; and performing real-time trusted path planning and path tracking control, implementing position control and attitude control through the three steps, and guiding the unmanned aerial vehicle to track the preset path to fly. According to the method, the unmanned aerial vehicle positioning accuracy and the motion state estimation accuracy are improved; the indoor autonomous environmental perception capability of the micro unmanned aerial vehicle is improved; according to the generated path, the positioning accuracy can be effectively guaranteed on the basis that the path feasibility is met; and the autonomy capability of the micro unmanned aerial vehicle is effectively improved.

A storage section stores various sensor signals obtained in an input section together with operation contents instructed in an output section. A signal discrimination section references the storage section to specify a sensor of which output value is influenced by a given operation. An operation result prediction section and an operation determination section generates through learning a prediction model expressing a relationship between the operation and the specified sensor and determines, with the generated prediction model referenced, an operation that allows an output of a target sensor to be a target value.

A method of simulating fluid transport in a system for stimulating a well in a material formation of a resource reservoir, the system comprising a conduit element arranged in said well, the conduit element comprising a conduit wall including one or more openings for discharging a fluid into the material formation surrounding the conduit element; the method comprising establishing and numerically processing a transport model of fluid transport inside the conduit element. The transport model further includes a model of fluid transport in a predetermined space around said conduit element.

A monitoring system including a baseline model that automatically captures and models normal system behavior, a correlation model that employs multivariate autoregression analysis to detect abnormal system behavior, and an alarm service that weights and scores a variety of alerts to determine an alarm status and implement appropriate response actions. The baseline model decomposes the input variables into a number of components representing relatively predictable behaviors so that the erratic component e(t) may be isolated for further processing. These components include a global trend component, a cyclical component, and a seasonal component. Modeling and continually updating these components separately permits a more accurate identification of the erratic component of the input variable, which typically reflects abnormal patterns when they occur.

A predictive modeling system and methodology makes predictions using unstructured content as an input, either alone or in conjunction with structured content. Content transformation rules are selected for application to the unstructured content, such as emails, call center notes, and other forms of human communication, by identifying the rules that are likely to improve the performance of a predictive modeling system.

A temperature compensation method for denoising a fiber-optic gyroscope on the basis of time series analysis comprises four steps of: step 1, designing an experimental scheme, performing fixed point low and high temperature testing experiment on the fiber-optic gyroscope, and utilizing acquisition software for data acquisition; step 2, performing time series analysis on the zero offset data of the gyroscope, and establishing the mathematical model of the random error of the fiber-optic gyroscope; step 3, adopting a kalman filtering algorithm to filter random noise in the zero offset data of the fiber-optic gyroscope; and step 4, utilizing the data which is de-noised by the kalman filtering to identify the model structure of the temperature shift error of the fiber-optic gyroscope, and calculating the parameters of the identified model. The method establishes the multinomial model of the static temperature shift error of the fiber-optic gyroscope through time series analysis, kalman filtering denoising treatment and identification of the temperature shift error model structure and parameters. The method completely meets the real-time compensation requirement on the project, and has a better practicable value and a wide application prospect in the technical field of aerospace navigation.

The invention discloses a federated modeling method, device and equipment based on a block chain, and a storage medium. The method comprises the following steps: a training initiator issues configuration information to all training clients based on client information corresponding to the training clients when the number of the training clients is monitored to reach a preset number; the training initiator uploads a to-be-trained model to a main chain; and the training initiator determines a target model based on aggregation gradient and the to-be-trained model. Modeling of federated learning isrealized through the block chain; on the premise of protecting the privacy of federated learning data, the accuracy of federated learning is not affected, the training effect and model precision of federated learning are improved, model parameters such as gradients in transmission do not need to be modified, and the balance between privacy protection of the model parameters such as gradients andmodel convergence or model precision is achieved; and information leakage can be completely prevented, so the safety of data samples in federated learning is improved.

The present invention provides methods of calibrating photovoltaic model parameters to improve modeling accuracy of photovoltaic power product ion, methods for determining as-built photovoltaic production expectations, methods for determining weather-adjusted photovoltaic performance, methods for determining and quantifying energy losses due to equipment mismatch, methods for determining and quantifying energy losses due to snow, methods for determining and quantifying energy losses due to equipment downtime, methods for determining and quantifying energy losses due to shading, methods for determining and quantifying energy losses due to soiling and equipment degradation.

A digital computer system stratifies in a set of patients, based on a set of observations. The observations can include physical, biochemical, histological, genetic, and gene-expression data, among other types of information. Adjustments can be made to account for the possibility that observations of several patients may begin at different points in the progression of their respective disease processes. Once these adjustments are made, the data are subjected to a statistical cluster analysis. Each cluster of patients potentially represents a different disease stratum, with its own underlying cause, optimum therapy, and prognosis. Once the strata are defined and patients are assigned to them, adjustments to the data can be refined. The cluster analysis then can be repeated, and so an iterative process of stratification and staging takes place.

The invention discloses a three-dimensional modeling method for achieving building inside and outside integration in a digital map and belongs to the technical field of digital map manufacture. The three-dimensional modeling method comprises the steps of firstly, filing building data; then checking building data; extracting data until all data are right; building a data source; generating a MAXScript script according to the data source and using 3DMAX to convert a MAXScript script file into a three-dimensional model; and finally guiding into a map to finish three-dimensional modeling of the building inside and outside integration in the digital map. The three-dimensional modeling method can economically and quickly achieve a three-dimensional digital map with building information and provides decision basis for urban construction and management.

A method of reconstructing a 3D model includes reconstructing a 3D voxel-based visual hull model using input images of an object captured by a multi view camera; converting the 3D voxel-based visual hull model into a mesh model; and generating a result of view-dependent rendering of a 3D model by performing the view-dependent texture mapping on the mesh model obtained through the conversion. Further, the reconstructing includes defining a 3D voxel space to be reconstructed; and excluding voxels not belonging to the object from the defined 3D voxel space.

The invention discloses a two-stage coordinated optimization and control-based running method of a combined cooling heating and power supply type microgrid. The running method comprises the steps of 10) performing inter-day rolling dispatching of the combined cooling heating and power supply type microgrid, in which optimal dispatching is performed by taking minimum running cost of the combined cooling heating and power supply type microgrid as an optimal target and combining forecast renewable energy generation power and load demand according to a running constraint condition of the system, and rolling output of each equipment and electricity purchase or sale quantity from a power grid are determined; and 20) building a real-time dispatching module of the combined cooling heating and power supply type microgrid, correcting an inter-day rolling dispatching result by taking dispatching fluctuation penalty-based minimum running cost of the combined cooling heating and power supply type microgrid as the optimal target and combining the renewable energy generation power and a load demand real-time value according to a real-time running constraint condition, and determining real-time output of each equipment in the combined cooling heating and power supply type microgrid and an electricity purchase or sale quantity real-time value. By the running method, the purpose of running economy and stability of the combined cooling heating and power supply type microgrid is achieved.

Rapid calibration of a TOF system uses a stationary target object and electrically introduces phase shift into the TOF system to emulate target object relocation. Relatively few parameters suffice to model a parameterized mathematical representation of the transfer function between measured phase and Z distance. The phase-vs-distance model is directly evaluated during actual run-time operation of the TOF system. Preferably modeling includes two components: electrical modeling of phase-vs-distance characteristics that depend upon electrical rather than geometric characteristics of the sensing system, and elliptical modeling that phase-vs-distance characteristics that depending upon geometric rather than electrical characteristics of the sensing system.

The present invention discloses a troposphere atmosphere delay error correction method and correction system. The method comprises the steps of (1) obtaining GNSS observation data through a GNSS foundation reinforcement system network reference stations, (2) sending the GNSS observation data to a CORS server baseline solution system, wherein the step (2) concretely comprises the steps of (a) decomposing troposphere delay into a troposphere dry component and a troposphere wet component according to the GNSS observation data and (b) carrying out regional linear interpolation model processing on the troposphere wet component to obtain a wet component correction value, and using a troposphere prior model to carry out altitude component correction of the troposphere dry component to obtain a dry component correction value, (C) combining the wet component correction value and the dry component correction value to obtain a troposphere correction value total. According to the method, the improvement of troposphere delay error correction is facilitated.

The invention relates to a lithium ion battery state-of-charge estimation method, belongs to the field of battery charge testing and provides a lithium ion battery SOC estimation method based on a fractional order Kalman filtering method. The lithium ion battery state-of-charge estimation method comprises the specific steps of establishing a fractional order state space model of a lithium ion battery, obtaining a relation curve of open-circuit voltage and a charge state through fitting and using the fractional order Kalman filtering method to estimate the SOC of the lithium ion battery. The lithium ion battery state-of-charge estimation method simulates complicated electric chemical reaction inside the battery well, improves the modeling accuracy of the lithium ion battery and further improves the estimation accuracy of the SOC of the lithium ion battery.

The invention protects a cross-updated active noise control system based on a novel algorithm for online identification of a secondary channel. The noise control system comprises 6 modules of noise signal filtering, momentum FxLMS algorithm, white noise generator, secondary channel modeling, main channel path and third adaptive filter update module. The object of the noise control system is to solve the problem that an active noise cancellation (ANC) system has a slow convergence speed and a small noise reduction amount in indoor noise-cancellation applications. The innovation lies in the factthat the unevenness of the power spectral density of a noise signal greatly affects the convergence speed of a control filter and a modeling filter in the indoor noise-cancellation applications. Themomentum FxLMS algorithm is proposed to update the weight of the control filter, and a variable step size LMS algorithm is used to update the weight of the modeling filter. The third adaptive filter using the Newton LMS algorithm is used to eliminate an error signal and the signal related to the reference input signal, and improves the modeling accuracy of the modeling filter and the convergence speed of the entire ANC system.

The invention discloses a vertical graph recognition method for converting a building drawing into a three-dimensional BIM model, and the method comprises the following steps: a, obtaining a target graph layer of the CAD building drawing, and obtaining a wall graph layer, a door and window graph layer, an elevation graph layer, an axis symbol graph layer, and an axis network graph layer; b, performing direction identification, elevation symbol identification and story height acquisition on each vertical drawing of the CAD building drawings; c, performing building component recognition, visibility analysis and three-dimensional positioning on each layer of plane drawing of the CAD building drawing; d, carrying out bounding box construction on the elevation drawing paper in each direction ofthe CAD building drawing paper, and carrying out search and size measurement on the elevation drawing component; according to the method, when the CAD building drawing is converted into the three-dimensional BIM model, the components of the elevation map of the CAD building drawing are recognized, the size numerical value of the components is obtained, and the CAD building drawing recognition andthree-dimensional BIM model reconstruction efficiency is improved.

The invention belongs to the technical field of urban mass transit and particularly relates to an energy-saving method of train operation of the urban mass transit. The energy-saving method comprises the steps of 1, analyzing operation matching rules of adjacent trains and computing the size of utilized regeneration energy; 2, establishing an optimization model of the train operation by taking the utilized regeneration energy as the target; 3, solving the optimization model to obtain an energy-saving time table of the train operation of the urban mass transit. By means of the energy-saving method, energy consumption during train operation is reduced, and security of an overhead line system is improved. Furthermore, the energy-saving method has the advantages of (1) being high in operation speed and applicable to large-scale computer simulation by adopting an integer programming method; (2) considering comprehensive factors, being high in modeling accuracy and strong in applicability of the planned operation time table; (3) being capable of embedded into hardware of a train energy-saving driving auxiliary system in an online mode, easy to implement, low in cost and wide in application range.

The invention discloses a comprehensive error correction method of a short-period wind power prediction system. The method comprises wind power plant power output link error correction and numerical value weather forecast link error correction; the step of correcting an error of a wind power plant power output link comprises the steps of calculating the best modeling granularity of a power output model, accumulating after modeling by a plurality of fans instead of a single unit, rejecting an abnormal data point on a scatter diagram of the power output model with a times-variance method, and correcting the system error of the power output model by related factors; the step of correcting an error of a numerical value weather forecast link comprises the steps of obtaining a leading value weather forecast wind speed sequence by comparing actually measured wind speed with related coefficients of the numerical value weather forecast wind speeds in different time and space and correcting the system error, and correcting a cold front arrival time-delay error by a correlation analysis method. As to the problem of low input data quality of the existing short-period wind power prediction system, the comprehensive error correction method is generally applicable to various short-period wind power prediction methods, and can be conveniently applied to actual engineering, so that the modeling precision and the prediction precision of the short-period wind power prediction can be obviously improved.

The invention relates to an underground high-precision navigation map establishment system and an establishment method. On the basis of the system comprising an underground geographic information system, an intrinsically safe modeling device and each intrinsically safe ultra wide band (UWB) anchor node which is set in each underground tunnel, the establishment method is further designed and introduced. According to the whole design, an underground high-precision navigation map can be rapidly established, environment model functions can be dynamically updated, a modeling result is input into the underground geographic information system, and a multilayer map model capable of providing auxiliary positioning and route planning for automatic movement of vehicles underground is established.

The invention discloses a plant three-dimensional reconstruction method based on an image and scanning data. The plant three-dimensional reconstruction method is characterized by comprising the following steps: S100, three-dimensional plant skeleton of the image of a plant is extracted; S200, organ three-dimensional point cloud obtaining, organ characteristic parameter extraction and organ pattern construction are conducted to organs of the plant; and S300, assembling is conducted on the three-dimensional plant skeleton by using a constructed organ pattern according to extracted organ characteristic parameter, and three-dimensional reconstruction is finished. The plant three-dimensional reconstruction method enables the reconstructed three-dimensional mold to be fitted with the height of a practical to-be-constructed plant in the aspects of leaf vein tracing pattern and stalk pattern, and the organs such as leaves and stalk can sufficiently reflect three-dimensional details of the maize variety, and therefore the constructed plant is good in sense of reality, and the method is simple and practical.

Rapid calibration of a TOF system uses a stationary target object and electrically introduces phase shift into the TOF system to emulate target object relocation. Relatively few parameters suffice to model a parameterized mathematical representation of the transfer function between measured phase and Z distance. The phase-vs-distance model is directly evaluated during actual run-time operation of the TOF system. Preferably modeling includes two components: electrical modeling of phase-vs-distance characteristics that depend upon electrical rather than geometric characteristics of the sensing system, and elliptical modeling that phase-vs-distance characteristics that depending upon geometric rather than electrical characteristics of the sensing system.

The process of obtaining 3D model of object quickly based on active vision includes calibrating the light planar equation of the grating planes of the projector under reference coordinate system and the projecting transformation matrix from the reference coordinate system to the camera; taking one frame of object picture with grating and one frame with grains only; inputting the images into computer; extracting the edges of grating from the image automatically or via man-machine interaction and clustering; finding out the 3D coordinates of all the grating edge points of object in the reference coordinate system via reverse projection to obtain the 3D model of the visible object surfaces; performing triangular decomposition of 3D points on object surface and mapping the grain information onto the 3D model; rotating the object in certain angle before repeating the said steps to obtain one other 3D model of other side; and data fusion to obtain complete 3D model of the object.

The present invention provides a fluorescence-based modeling method that is capable of capturing the dynamic changes of different membrane foulant fractions that occur in fluid filtration operations. Principal component analysis is utilized to de-convolute spectral information captured within fluorescence EEMs into principal component scores that are related to different known foulant groups. The principal component scores are then used as states within a system of differential equations representing approximate mass balances of the main foulant groups to obtain a dynamic forecasting of membrane fouling. Based on the fouling dynamics forecasted by this modeling method, an optimization strategy can be developed for estimating the optimal membrane back-washing scenario for minimizing energy consumption while maximizing clean fluid production.

A method and a calculating device are for modeling the temperature of a catalytic converter in the exhaust gas of an internal combustion engine. In this context, the heat input into the catalytic converter based on exothermic reactions is taken into consideration. The method provides that a first correcting quantity delta_T1 and a second correcting quantity delta_T2 are formed, which each take into consideration a heat input into the catalytic converter based on exothermic reactions in the catalytic converter, delta_T1 being formed as a function of the ratio of the first fuel mass, combusted in the internal combustion engine simultaneously with an air mass, to the air mass, and delta_T2 being formed as a function of a heat input that results from an exothermic reaction of a second fuel mass, which was metered in for the regeneration of the catalytic converter in addition to the fuel proportion of the fuel / air mixture combusted in the internal combustion engine.

The present disclosure provides a method for automatic modeling of an architecture based on an architectural drawing, comprising steps of: reading parameter information of the architectural drawing, identifying a category to which any architectural object belongs by acquiring line segments constituting the architectural object and coordinate data of endpoints of the line segments; generating a binary file or a preset number of binary files based on the coordinate data and elevation data of the endpoints of all the line segments of architectural objects belonging to the same category for all storeys of the architectural drawing; optimizing the binary file or the binary files corresponding to the architectural objects belonging to the same category for all the storeys of the architectural drawing; and generating a three-dimensional model of the architecture. The modeling precision and modeling efficiency of the architecture can be improved by adopting the technical solution of the present disclosure.

The invention discloses a modeling and compensation method of a thermal error of a numerical control machine tool. The method includes the first step of searching heat points of the machine tool by means of an infrared imager, finding an area with a highest temperature in each heat area by means of heat infrared images of all portions of the machine tool displayed by the infrared imager, and arranging a temperature sensor at a position with the highest temperature in each heat area; the second step of taking heat source temperatures measured through tests as input signals and hot deformation of the machine tool as an output signal, and obtaining system pulse response models in the method of deconvolution; and the third step of sequentially inputting temperature change sequences and the corresponding machine tool pulse response models in compensation and carrying out the deconvolution to obtain a heat error predicted value of the machine tool. According to the modeling and compensation method, searching for best temperature measurement points is simple and quick; by the method of the deconvolution, the modeling precision is high; by means of the pulse response models, transportability is good; and the response speed is high, and real-time performance requirements for compensation of the machine tool can be completely met.