4534 results about "Influence factor" patented technology

A system and method for processing patient data permits physicians and other medical staff personnel to record, accurately and precisely, historical patient care information. An objective measure of a physician's rendered level of care, as described by a clinical status code, is automatically generated. Data elements used in the determination of the generated clinical status code include a level of history of the patient, a level of examination of the patient, a decision-making process of the physician treating the patient, and a "time influence factor." The quantity and quality of care information for a particular patient is enhanced allowing future care decisions for that patient to be based on a more complete medical history. Enhanced care information can be used in outcome studies to track the efficacy of specific treatment protocols. Archiving of patient information is done in a manner which allows reconstruction of the qualitative aspects of provided medical services. The medical care data can be recorded, saved, and transferred from a portable system to a larger stationary information or database system. Considerable physician and staff time are saved and precision and accuracy are significantly enhanced, by generating these clinical status codes automatically (at the point of service by the care-provider without any intermediary steps) from information recorded simultaneously with the provision of services.

The invention discloses a method for analyzing high precision 4D flight trajectory of an airplane based on real-time radar data, comprising the following steps: establishing a 4D fight trajectory theoretical model based on the airplane performance; establishing a 4D fight trajectory empirical model by mining and analyzing based on the historical fight trajectory data of the airplane types in the above step; combining the theoretical model and the empirical model and quantizing various influencing factors in the flight process into adjustable parameters; and correcting the 4D flight trajectory mixed models by radar data to form the final flight trajectory of the airplane. The invention takes the airplane performance into consideration and establishes the theoretical model by performance library parameters on the basis of a standard flight procedure, thus having high reliability; the invention forms the empirical model by analyzing the historical data, thus having high reality; the invention generates the 4D flight trajectory most similar to the actual flight and can adjust the parameters to form a plan trajectory aiming at the environment of each flight, thus high sensitivity; and the invention correct the plan trajectory by introducing the real-time radar data, thus having high accuracy.

Methods and systems for transmitting compressed audio / video data streams across conventional networks or channels in real time. Each system employs the Adaptive Rate Control (ARC) technique that is based on the detection of defective packets and other influencing factors such as overall system performance, usage model and channel characteristics. To control data stream congestions in the channel and maintain the visual display quality above a certain level, the present invention exploits the human visual perception and adaptability to changing visual conditions. The ARC technique relies on the client's capacity for calculating the quality of video packets received from a server and sending information of a desired transmission rate to the server. This approach simplifies the hardware and software implementation complexity otherwise imposed on the server and reduces the overall design cost by shifting the burden of monitoring bandwidth and transmission control from the server to the client.

The invention discloses an electric power user figure establishment and analysis method based on the big data technology. The method comprises steps that the historical electricity information, basic attributes, the fee-paying information and the appeal information of electric power users are acquired; classification category sets of user figures are determined, an influence factor set of a classification result is determined, and a mapping relationship between the influence factor set and the classification set is determined; random extraction of the acquired data is carried out, one part of the data is taken as a training sample, and other data is taken as prediction sample; normalization processing, discretization processing and attribute reduction for the training sample and the prediction sample are carried out, and an influence factor set after correction is determined; the training sample is trained, ten-fold cross validation is taken as a test mode, an electric power user figure prediction model based on a naive Bayes classifier is established, data classification mining analysis on the prediction sample is carried out through utilizing the prediction model, and electric power user figures are acquired. The method is advantaged in that electric power electric quantity prediction and management can be facilitated.

The invention provides a quantitative characterization method of low penetration double-medium sandstone oil reservoir microscopic aperture structure, which comprises the following steps: selecting experiment samples, effectively combining various experiments, distributing samples, processing and analyzing experiment test data, combining macroscopic background and microscopic rock core, and combining static state analysis and dynamic production reality, thereby realizing quantitative characterization of ultra-low penetration double-medium sandstone oil reservoir microscopic aperture structure from qualitative analysis and semi-quantitative evaluation. The invention has the advantages that more comprehensive influence factors and micro crack, aperture throat parameter and nuclear magnetic resonance movable fluid parameter are considered, so the characterization result can better reflect change characteristics of ultra-low penetration double-medium sandstone oil reservoir microscopic aperture structure, which are consistent to the production exploitation real cases of the oil field, thereby effectively avoiding one-sidedness and limitation of single aspect evaluation result.

The invention discloses an intelligent positioning method of mine microquake sources, which is a microquake resource intelligent positioning system which comprehensively considers various influencing factors and targets, and integrates with sensors distribution-noise wave filtration-microquake source positioning analysis-three-dimensional display in to a whole. The method realizes the real-time analysis and the forecast of the incubation, the development and the occurrence of mine underground geological disaster through a self-developed procedure, solves the defects that the traditional sensors distribution method is not systematic, the noise wave filtration is incomplete, the microquake wave speed model is not exact and the positioning method is easily diffused, and has the characteristics of friendly operation interface, good noise wave filtration performance, exact, convenient and fast microquake source positioning analysis, visual and pictorial result display, and wide application range. The method has wide application value in the fields of mineral engineering, water conservancy and electric power engineering, petroleum engineering, soil engineering and underground engineering and the like.

The invention discloses a short-term load prediction method of a variational mode decomposition and deep belief network. The method comprises the following steps of 1) using a variational mode decomposition method to decompose original historical load data into a series of mode functions with different characteristics; 2) using an approximate entropy to calculate each modal function complexity, merging the modal functions whose approximate entropy values are similar into a new component, and carrying out characteristic analysis on each component; 3) in order to calculating correlation of an influence factor and an output variable, carrying out normalization processing on data; 4) combining a period characteristic of a load, and using a mutual information theory to select an input variable set from aspects of a historical load, a meteorology factor, a date type and the like; and 5) constructing the short-term load prediction method based on the deep belief network (DBN), and verifying method validity through a load prediction scene before 24h. By using the method, short-term load prediction precision is effectively increased and an electric power system load prediction problem can be well solved.

The invention discloses a network fault diagnosis method based on deep learning in a network virtualization environment. The network fault diagnosis method comprises the steps of: dividing a network into a physical network and a virtual network, combining the characteristics of occurrence of network faults, considering the time influencing factor, network topological connection characteristics and a mapping relation between the virtual network and the physical network, and comprehensively evaluating the network faults by means of a fault severity grading probability; regarding network characteristic parameters with influence degrees as a model learning resource, paying attention to the correspondence between variation trend of network historical data and fault tags, establishing a network fault diagnosis model with multiple fault grading probabilities in the network virtualization environment based on a viewing angle of deep learning, and training network parameters by using the network fault diagnosis model; and adjusting a fault prediction model in the training process, and utilizing an optimized and adjusted deep learning network to realize fault diagnosis in the network virtualization environment. The network fault diagnosis method can carry out deep analysis on the network parameters in the network virtualization environment, therefore the network fault diagnosis method has higher precision in predicting the network faults.

The invention discloses a building air-conditioning energy consumption prediction method based on a BP neural network model. The method comprises: analyzing influence factors of building air-conditioning energy consumption; according to influence parameters, collecting historical building air-conditioning energy consumption sample parameters, and preprocessing the parameters; using a BP neural network, according to dimensionality of the sample parameters, establishing a building air-conditioning energy consumption prediction model; using the preprocessed sample parameters as a training sample, training the building air-conditioning energy consumption prediction model; collecting near-term real-time building air-conditioning energy consumption sample parameters to evaluate the building air-conditioning energy consumption prediction model; if errors are in an allowed range, output of the model being a building air-conditioning energy consumption predicted value; if not, training the model again. The building air-conditioning energy consumption prediction method based on a BP neural network model is advantaged in that learning rules are simple, a computer can easily implement, and the method has excellent robustness, memory capability, nonlinear mapping capability, and powerful self-learning capability.

The invention discloses a genetic algorithm-based support vector regression shipping traffic flow prediction method, comprising the following steps: (1) reducing the dimensional number of factors possibly generating influences on shipping traffic flow by a weighted principal component analysis method, and selecting influencing factors with higher cumulative contribution rate; (2) carrying out normalization preprocessing on original vessel traffic flow time series data to generate a data set and then grouping; (3) selecting a kernel function to determine support vector machine (SVM) regression parameters; (4) constructing a support vector regression prediction model optimized by a genetic algorithm; (5) inputting the data set to generate a prediction function; and (6) predicting according to the prediction function generated in step (5), evaluating and analyzing prediction error, and if the error is relatively large, returning to step (2) and regulating the parameters again, predicting once again. The method of the invention has the advantages of higher prediction accuracy and higher stability of prediction accuracy.

The invention provides a contextual model setting method and a terminal device. The method includes the steps of obtaining influence factor collecting values after the terminal device collects influence factors in the environment where the terminal device is placed, determining a first contextual model according to the influence factor collecting values, the corresponding relationship of a pre-stored influence factor threshold and the influence factors and the corresponding relationship of the contextual model and the influence factors, and setting a contextual module according to the first contextual model, wherein the influence factors include at least one of environmental noise, environmental luminance, the speed of the terminal device, the accelerated speed of the terminal device, the accelerated speed change rate of the terminal device, the height of a place where the terminal device is located, the environmental temperature and time, and the first contextual model is a contextual model which the terminal device belongs to at present. According to the technical scheme, various influence factors are considered to set the contextual model, and setting precision and setting efficiency of the contextual model are improved.

The invention discloses a method for assessing the lightning flashover risks of regional power grid lines, which comprises the following steps that: through calculating the lightning-resistant level of each base rod tower and combining with a probability distribution function of lightning current amplitudes of a region, the lightning trip-out rate of each rod tower is obtained, and the average lightning trip-out rate of a line is calculated; then, through combining with an automatic reclosing failure rate and a failure rate of manual forced energization, a permanent failure rate of the line is obtained; and through considering the weight coefficient of the line in a power grid structure, the permanent failure load loss coefficient of the line at the specific time of a power grid and in an specific operation mode of the power grid, and the risk occurrence probability of other influencing factors, a lightning flashover risk assessment model of a regional power transmission grid is established. According to the invention, the shortcoming that the absolute numerical value of the lightning trip-out rate can not really reflect the lightning disaster risk level of each line is overcome, and the lightning flashover risk level of each rod tower of lines is assessed through comprehensively considering the differences among the lightning motions, topographical features, line structures, insulation configuration, lightning protection measures and the like of each line corridor in the power grid, so that more comprehensive and thorough assessment results are obtained.

The invention belongs to the technical field of vibration test, in particular to a thin-walled structure part vibration test device and a method based on a piezoelectric ceramic vibration exciter. The device comprises a signal generator, a piezoelectric ceramic drive power supply, a piezoelectric ceramic vibration exciter, a feedback attenuator, a laser vibration meter, a data acquisition analyzer and an upper computer. The method comprises the steps of performing modality test on a thin-walled structure part, determining a linear relationship between excitation voltage and critical excitation frequency of the signal generator and calibrating an excitation force of the piezoelectric ceramic vibration exciter based on a cantilever theory. According to the device and the method, an excitation signal can be effectively acquired; the magnitude of the excitation force when the piezoelectric ceramic vibration exciter excites the structure part is defined; the stable designated excitation force and the linear excitation signal of the excitation frequency can be generated; influencing factors of non-linear piezoelectric ceramic excitation are effectively eliminated; the piezoelectric ceramic vibration exciter is adopted to realize high-frequency vibration excitation; additional mass is low; and the device is convenient to use.

The invention discloses an on-line monitoring system for diesel lubrication oil, which comprises a host computer system and a slave computer system, wherein the slave computer system comprises an oil information monitoring sensor module, an automatic circularly oil-collecting module, a signal decoding and modulating module and an oil information gathering module; the oil information monitoring sensor module is respectively connected with the signal decoding and modulating module and the oil information gathering module; and the signal decoding and modulating module is connected with the oil information gathering module. The on-line monitoring system for diesel lubrication oil can realize the real-time and continuous monitoring and the fault warning for the diesel lubrication oil; monitoring and analyzing results of the on-line monitoring system are synchronous with the running state of a diesel engine; and the defects of artificial uncertainty influencing factors of off-line monitoring and delay of detecting and analyzing time of off-line sampling are overcome. Meanwhile, the defect of evaluating oil quality by using a single sensor is overcome by the on-line monitoring system, the complement characteristic of reflecting fault features by multi-information is achieved, and the accuracy of on-line monitoring and diagnosis is increased.

The invention relates to an intelligent traffic system-based intelligent vehicle lane changing decision-making method. The method comprises the following steps of firstly, parsing the received broadcast data of an intelligent traffic system by an intelligent driving system, and extracting the event information; secondly, completing the coordinate conversion of a road event by the intelligent driving system, and obtaining an event influence factor according to the event information; finally, according to the event overall influence factor and the judgment result that the current road environment allows the lane changing decision of a vehicle, allowing the lane changing path re-planning, simultaneously calculating the desired behavior of the vehicle and changing the lane of the vehicle. According to the technical scheme of the invention, according to the attribute of a road event ahead of the vehicle and the environmental information around the vehicle, the influence factor of the current vehicle driving road is calculated. Therefore, the necessity, the security and the reliability of the lane changing decision of an automatic driving vehicle are evaluated. Meanwhile, preparations are made in advance before the lane changing of the vehicle.

The invention discloses a method for controlling on-line prediction of continuous casting blank quality, which belongs to the field of metallurgical automation control. In the method, a comprehensive quality prediction rule based on an expert system, mathematical statistics and a neural network is programmed by secondary control software, and data communication is performed by the secondary control software and a primary basic automatic control system, so that the automatic prediction of casting blank quality in the continuous casting production process is realized; and a quality judgment system overall framework comprises an influence factor real-time data acquisition module, a casting state and casting information tracking module, an abnormal event and casting blank quality prediction module, an off-line simulation system, a quality prediction system database, a primary communication interface module and a system human-machine interface (HMI) picture. The method has the advantage that the on-line automatic prediction of the casting blank quality in the continuous casting production process is realized.

The invention discloses an NRIET fog forecasting method based on machine learning. The method comprises steps that historical and forecast data for model training and operational forecasting in and around the forecast area is collected; the collected data is analyzed and processed to be a sample set for training a machine learning model; for problems, an xgboost model algorithm based on a decisiontree is selected, key influence factors generated by the airport fog are screened, and a relationship model between the fog and the influence factors is established; a training set and a verificationset are trained; according to the parameter adjusting sequence, model parameters are repeatedly adjusted till a forecasting model with optimal performance is acquired; an integrated learning method is utilized, and intersect verification and iteration training are carried out for the model to further improve model forecasting performance; observed real-time data is inputted to the forecasting model to acquire the fog forecasting result.

The invention provides a multi-waypoint (destination) navigation route planning method and system in an actual demand situation that the multiple waypoints have different priority under multi-factor influence. The method adopts a weight scoring based optimum route determining model and a machine learning based multi-influence-factor weight coefficient determining method. Specifically, a multi-point road planning model oriented to multiple waypoints with different priority is designed firstly; the machine learning based influence factor weight coefficient determining method is provided for determining coefficients in the model; then the multi-point road planning system capable of being widely popularized to numerous fields is obtained. One new solution is provided for multi-influence-factor and multi-waypoint route navigation, and route planning is more intelligent, higher in efficiency, more dynamic and more automatic.

The invention discloses an oily water layer recognition method and device. The method comprises the following steps: analyzing main influencing factors of the well log response characteristic of a reservoir bed; reading well log response characteristic values of a well log interpretation layer corresponding to a test oil layer, and integrating and processing the well log response characteristic values according to the main influencing factors; calibrating the reservoir bed and a non-reservoir bed according to a physical property cross plot and a lithologic character cross plot; recognizing a typical hydrocarbon zone by utilizing an electrical property cross plot and the lithologic character cross plot; eliminating a water layer by using a resistivity ratio and the physical property cross plot; and judging whether an atypical oil layer and an oily water layer are the same layer by utilizing the apparent formation water resistivity and a lithologic character index cross plot. According to the method and device, conventional well log information is mainly utilized, cross plot techniques capable of reflecting cause factors are respectively adopted according to different causes so as to manufacture oily water layer recognition layouts, the main influencing factors of an upper grade are gradually weakened, and the main influencing factors of a next grade are highlighted, so that the oil layer, the oily water layer and the water layer and the like are respectively separated out from different cross plot layouts, thus realizing accurate recognition of the oily water layer under a bad ground condition.

The invention discloses a user-based multi-access network selection method being used under a wireless heterogeneous network environment and provides a dynamic multi-access selection method which is combined with an object cost function and the analytic hierarchy process by starting from user interests and fully considering cost, QoS and stability of pre-access to a network. A network selection decision model is established by analyzing and judging influencing factors; furthermore, the method has the advantages of the multi-factor-based network selection method, and can correctly and effectively carry out network selection and be conveniently realized in a user terminal.

The invention discloses a multi-system dynamic PPP resolving method based on robust self-adaption Kalman smoothing. The method includes the steps that receiving machine outline coordinates and receiving machine clock bias of all systems are solved through selecting-weight-iteration pseudo-range single-point positioning, and accordingly all positioning error correction values are calculated according to an error correction model in combination with the satellite precise ephemeris and satellite precise clock bias; strict data quality control is conducted on observation data. Due to the fact that dynamic PPP accuracy is easily affected by undetected small cycle slips or the gross error and the like, an observation equation weight matrix is adjusted according to the observation value residual vectors, and the undetected small cycle slips or the gross error and other influence factors are removed; self-adaption factors are determined according to the state predictive information, and thus the influence on parameter estimation of the predictive information is controlled. By means of the method, when multi-system dynamic PPP is conducted through a single receiving machine, the feature that the number of multi-system satellites is increased greatly, on the basis that the stability of the satellite structure is guaranteed, the influence of the gross error is weaken effectively, the dynamic noise abnormity in dynamic positioning is improved, and finally the high-precision and high-stability multi-system dynamic PPP result is achieved.

The invention discloses a transformer electromagnetic vibration noise calculating method based on the finite element method. The transformer electromagnetic vibration noise calculating method comprises the steps of 1, establishing a structured grid model and an acoustics grid model according to a three-dimensional geometrical model of a transformer; 2, conducting transient electromagnetic simulation on the structured grid model to obtain transient electromagnetic force waves borne by each phase winding and an iron core; 3, conducting FFT on the transient electromagnetic force waves borne by each phase winding and the iron core to obtain the frequency domain distribution of electromagnetic force borne by each phase winding and the iron core; 4, conducting harmonic response analysis on the structured grid model to obtain the vibration displacement data of nodes on the surfaces of the windings and the iron core; 5, conducting sound field calculation on the acoustics grid model to obtain the radiation noise distribution of the transformer. According to the transformer electromagnetic vibration noise calculating method, all noise influence factors are considered, and calculation results are accurate and reliable. The transformer electromagnetic vibration noise calculating method can be used for winding short circuit vibration deformation analysis and the like and can also provide method and basis for motor noise analysis.

The invention discloses an online car-hailing service demand prediction method based on a deep neural network. The method comprises the following steps: S1, dividing a region of a city road network, and calculating and counting the network car-hailing demand of each region; S2, designing a prediction model of the demand of the network car-hailing: based on the deep neural network, learning and training the spatio-temporal characteristics of the demand of the network car-hailing, combining the influence factors of the weather factors on the willingness of the network car-hailing users, and predicting the regional demand of the next period of time; S3, according to the historical data, training the prediction model of regional car call demand, and then predicting the demand of network car call in each region by using the trained model. By combining external factors and spatio-temporal correlation, this method uses depth neural network to express the complex non-linear spatio-temporal correlation characteristics of the demand for network car-hailing, and can achieve high prediction accuracy.

The invention discloses a model for causing ground setting due to an engineering environment effect and a test method thereof. The model comprises a model casing, simulation materials, measuring equipment, data acquisition equipment and water pressure controlling equipment, wherein the simulation materials for simulating a research area are placed in the model casing; the measuring equipment is arranged in the model casing for measuring parameters; the data acquisition equipment is connected with the measuring equipment and is used for acquiring and processing the parameters measured by the measuring equipment; and the water pressure controlling equipment is connected with the model casing and provides water pressure for the model casing and is used for simulating a water table aquifer and an artesian aquifer on a practical soil layer. the test method comprises the following steps of: determining influence factors to be researched; considering the size and the distance of a simulationbuilding and the plane size of the model casing according to the consolidation principle; determining various similar constants by adopting a dimensional method; determining the simulation materials;simulating the early-stage preparations of the test; and carrying out a simulation test. According to the invention, the ground deformation due to the underground water level lifting and the ground setting due to the engineering environment effect can be researched.

The invention discloses a system for forecasting traffic flow of urban ring-shaped roads, relating the related technical fields of database management, data analysis and processing and data speculation. The system comprises a traffic flow data management system, a traffic flow data characteristic analysis system and a traffic flow data speculation system. The traffic flow data management system is used for maintaining the traffic flow database, realizing reading of real-time traffic flow data and input of predicted data; the traffic flow data characteristic analysis system is used for realizing characteristic analysis of traffic flow data and pre-processing traffic flow data; the traffic flow data speculation system is used for selecting traffic flow prediction models and analyzing predicting outcomes, realizing prediction method comparison and display and saving of the predicting outcomes. The system can solve the quality problem of traffic flow data and deviated prediction in the traditional traffic flow prediction, introduces various influencing factors of upper sections and lower sections of roads for predicting road traffic flow and realize real-time and accurate traffic flow prediction of the road network.

The invention discloses a simulating method of numerical values of sediment movement of silty and muddy coast. The simulating method mainly comprises the following steps of: step one. establishing basic equations which comprise a water current continuity equation, a water current movement equation, a suspended load transporting and diffusing equation and a bed surface scouring and silting variation equation; step two. calculating the shearing stress of a bed surface under the combined action of settling velocity of suspended sediment, scouring and silting functions of sediment and wave currents; step three. establishing a sediment mathematical model and solving; step four. verifying the model, including water current verification and sand content verification; and step five. judging a settling velocity field of the suspended sediment according to the sediment mathematical model. According to the simulating method, the sediment mathematical model is established on the basis of considering the characteristics of muddy and silty sediment, and the movement of two different types of sediment can be simulated simultaneously; and more than that, the established sediment mathematical model also can be used for calculating the settling velocity field of the suspended sediment; and accordingly, the characteristics of a region and influence factors are analyzed and researched.

The invention discloses a decision making method and system based on big data. The method integrates a series of decision making influence factors commonly used for all industries in advance and has the setting function of setting all the influence factors so that users in all walks of life can customize acquisition rules, decision making rules and the like required by decision making through simple setting, and for instance, the users can set industry types and data keywords to formulate the acquisition rules. Meanwhile, a universal classification model is built in advance, data to be classified can be classified by the model on the basis of auxiliary information set by the users according to service requirements of the users, so that data required by the users can be further mined conveniently, and target data are obtained. For instance, acquired medical data can be classified in terms of diseases by the model according to the auxiliary information of the diseases set by the users, and finally decisions are made according to the decision making rules set by the users. It is clear that the decision making method and system based on big data overcome the defect that an existing decision making method is not universal.

A system and method for software estimation. In one embodiment, the software estimation system comprises a pre-processing neuro-fuzzy inference system used to resolve the effect of dependencies among contributing factors to produce adjusted rating values for the contributing factors, a neuro-fuzzy bank used to calibrate the contributing factors by mapping the adjusted rating values for the contributing factors to generate corresponding numerical parameter values, and a module that applies an algorithmic model (e.g. COCOMO) to produce one or more software output metrics.

The invention relates to the technical field of power batteries of electric automobiles, and discloses a composite estimating method of a power battery SOC based on a PNGV equivalent circuit model. The composite estimating method comprises the following steps that A, the open-circuit voltage of the power battery is detected; B, an open-circuit voltage method is used for calculating the primary SOC (t0) of the power battery; C, in the time period of t0-t1, an EKF algorithm is used for correcting the primary SOC (t0), and an SOC (t1) is obtained; D, in the time period of t1-t2, an improved ampere-hour integral method is used for estimating; E, when the power battery is continuously used, the steps from the step C to the step D are circulated; the t0 represents the primary time, and the t1 and t2 represent the time points after the t0. According to the composite estimating method of the power battery SOC based on the PNGV equivalent circuit model, the correction coefficients of influencing factors such as the charging and discharging currents of the power battery, the environment temperatures, the battery health state are considered, the improved ampere-hour internal method is used, and the defect that the influence from outside factors is large when the ampere-hour internal method is used for estimating the power battery SOC can be overcome. The advantage that an EKF method has a powerful correcting effect on initial errors of the SOC is fully used.