1268 results about "Data prediction" patented technology

Systems and methods for time series data error detection, correction, and transformation may detect gaps and anomalies in time series data, such as from a meter device, and may correct the gaps and adjust the anomalies prior to long-term record storage. Data forecasting may be used to correct the errors in the time series data. The error corrected data may be regarded as an actual set of time series data and become a base data set against which additional heuristic projections are generated. In addition, the time series data may be transformed into any number of physical and virtual device hierarchies that represent the underlying data source configurations, and may then be stored in an analytical database for further analysis. The hierarchies may be irregular and may change over time.

Historical data is measured for a computer server system. Future demand for service in the computer server system is forecast based on the historical data, and the mapping of virtual machines to physical machines is updated based on the forecast of the future demand. Measurement, forecasting, and placement modules can be employed.

A method and apparatus for adaptively selecting a context model for entropy coding and a video decoder are provided. A method of coding a residual prediction flag indicating whether residual data for an enhancement layer block of a multi-layered video signal is predicted from residual data for a lower layer block corresponding to the residual data for the enhancement layer block includes the steps of calculating the energy of the residual data for the lower layer block, determining a coding method for the residual prediction flag according to the energy, and coding the residual prediction flag using the determined coding method.

A semantically organized domain space is created from a training corpus. Affective data are mapped onto the domain space to generate affective anchors for the domain space. A sentiment associated with an input text is determined based the affective anchors. A speech output may be generated from the input text based on the determined sentiment.

The present invention provides systems and methods for prosthesis fitting in joints that employ a trained neural network to predict at least one unknown set of data, such as position and contact force. The unknown data is predicted based on at least one known sensor value that is obtained intraoperatively. The predicted neural network data is made available to a physician and aids in the determination of whether to resect additional bone, release soft tissues, and/or select sizes for prosthetic components. Advantageously, increased data may be provided to a physician without the need to acquire numerous samples from a patient, and fewer sensors may be employed.

A data-driven lithium ion battery cycle life prediction method based on an AR (Autoregressive) model and an RPF (Regularized Particle Filtering) algorithm relates to a lithium ion battery cycle life prediction method and belongs to the technical field of data prediction. The invention solves the problems in the existing lithium ion battery cycle life prediction method that the model-based prediction method is complicated in modeling, and parameters are difficult to identify. The data-driven lithium ion battery cycle life prediction method combines time sequence analysis with particle filter method and comprises the following steps: the AR model is firstly utilized to realize the multi-step prediction on battery performance degradation process time sequence data; and then, aiming at the problem of uncertainty expression of the cycle life prediction result, the regularized particle filtering method is introduced, and a lithium ion battery cycle life prediction method framework is proposed. The method proposed by the invention can be used for effectively predicating the cycle life of a lithium ion battery and realizes the output of probability density distribution of the predication result, has good computational efficiency and uncertainty expression ability.

A visual analyzing and predicting method based on a virtual geological model is finished by depending on an interactive visual tool. The method mainly comprises steps of searching a multi-dimensional geological data model from a database and a file system; arranging or resetting a virtual geological scene by setting or regulating corresponding parameters and models; regulating coordinate, scale, data format and the like, of the geological model; sending results of visual calculating, analyzing, predicting and searching into a dual-display cache region; and integrally displaying geological data in a visual platform at real time. The method meets requirements of earth science application, enhances representability of geological data, improves comprehension and application environment of geological data, converts logical thinking of geologists into a trial ground having an imagery thinking of time and space in a virtual environment, helps strengthen deep recognition to complex geological phenomena, uncovers deep information and internal relation in geological data, digs out and extract knowledge unable to be obtained in a traditional mode, improves utilization rate and geospatial analytics of information, and provides a brand-new method for geologists to observe, explain, analyze and imitate geological phenomena in a three-dimensional space, predict and know geospatial distribution of geological structure in a studied area through known data, and obtain mine position, mine reserves and other important information. Furthermore, the human-computer interactive tool is simple and easy to learn to operate, saves cost, reduces blindness in application, reduces risk, conducts and makes decision for production and environment analysis and has significant economic and social benefits.

The invention relates to the technical field of computer application engineering, in particular to a method for using an improved neural network model based on particle swarm optimization for data prediction. The method includes the steps of firstly, expressing data samples; secondly, pre-processing data; thirdly, initiating the parameters of an RBF neural network; fourthly, using the binary particle swarm optimization to determine the number of neurons of a hidden layer and the center of the radial basis function of the hidden layer; fifthly, initiating the parameters of the local particle swarm optimization. By the method for using the improved neural network model based on particle swarm optimization for data prediction, the number of the neurons of the hidden layer of the RBF neural network model can be determined easily, RBF neural network performance is improved, and data prediction accuracy is increased. In addition, the improved neural network model based on particle swarm optimization is low in model complexity, high in robustness and good in expandability.

Systems and methods for vendor managed inventory (VMI) that include a demand management system that receives customer product usage data and forecasts customer demand for products in accordance with the product usage data. The VMI system also includes an order management system that receives orders from the demand management system and sends the order for fulfillment. A relational database stores customer information for later retrieval and ad hoc querying. An aspect integrator platform is provided for collaboratively presenting the customer information.

The invention belongs to the technical field of cloud computing and network multimedia, and particularly provides an auto-expanding/shrinking cost-optimized content distribution service method based on a hybrid cloud scheduling model. The method comprises: a future number of user visits is predicted on the basis of historical data and provides basis for auto-expanding/shrinking of resources; according to the predicted value and a long-term scheduling algorithm, a rough plan of resource booking strategy is obtained through calculation; wherein a short-term scheduling model is introduced to reduce the prediction error and to improve the precision of resource supply and the quality of service. In the long-term scheduling algorithm, a locality-aware booking model is set up to derive the locality-aware resource booking algorithm. A resource prediction algorithm employs the ARIMA model. In a short-term adjustment algorithm, virtual machine status parameters are designed and a content missing algorithm is provided, so that the user experience of the entire system is further improved. The method enables hybrid cloud technology to support streaming media content distribution applications efficiently with auto-expanding/shrinking functions and optimized costs.

A system, method, and program product for enhancing keyword contribution to a code-completion facility used in association with an Integrated Development Environment source code editor. A code-completion facility supporting a source code editor includes a look-up module that retrieves keywords from a keyword compare pool responsive to a code-completion prompt. The code-completion facility further includes a contribution mechanism for contributing keywords derived from system artifacts to the keyword compare pool. The contribution mechanism includes a remote artifact contribution module for obtaining or deriving keywords from remote object interface definitions and contributing the same to the keyword compare pool. In a preferred embodiment, the remote artifact contribution module includes a keyword prediction module for accessing a remote object interface repository, predicting one or more remote object based keywords in accordance with remote object interface definition data, and contributing one or more of the predicted keywords to the code-completion facility.

An image coding apparatus for efficient coding on image data having discrete pixel values such as a CG image or a limited color image as well as a natural image where pixel value changes are mild. For this purpose, a tile dividing unit divides multi-valued image data into tiles. An occurred level count unit outputs the result of counting of the number of brightness values in the tile to a comparison unit and outputs the existing brightness values to an index table generation unit. The index table generation unit allocates continuous index values to the existing brightness values, and stores the result of allocation into an index memory table. An index conversion unit replaces the input pixel values in the tile with index values, and outputs the index values to a selector. The selector selects one of the brightness values in the tile or the index values based on the result of comparison by the comparison unit, and outputs the selected values to a tile data predictive coding unit so as to perform predictive coding processing.

The invention discloses a travel time prediction method for optimizing an LSTM neural network through a particle swarm optimization algorithm, and the method comprises the following steps: S1, collecting travel time data, performing data normalization, and dividing the data into a training set and a test set proportionally; S2, optimizing each parameter of an LSTM neural network prediction model by using the particle swarm optimization algorithm; S3, inputting the parameters, optimized through the particle swarm optimization algorithm, and the training set, and performing the iterative optimization of the LSTM neural network prediction model; S4, predicting the test set through the trained LSTM neural network model, and evaluating a model error. The method is quick in optimization. Compared with a random forest, SVM and KNN in the traditional prediction algorithm, the method of the invention has the least mean square error and square error for the data prediction, and the model reducesthe calculation burden, so the method shows better prediction performance.

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.

A particular method includes receiving aircraft state data associated with an aircraft at an air traffic control system. The aircraft state data includes a detected position of the aircraft, a velocity of the aircraft and an orientation of the aircraft. The method also includes predicting at least one future position of the aircraft based on the aircraft state data. The method further includes generating an alert in response to comparing the predicted future position to an air traffic navigation constraint assigned to the aircraft.

The invention relates to a grid load predicting method based on a support vector regression machine. The method comprises the following steps: firstly, carrying out automatic regression (AR) modelingon history property data of nodes by a time sequence method; evaluating dimensions of the input vector in SVR according to orders of an AR model; performing SVR learning on the history data, and constructing a regression function of SVR; predicting the property of the node at the next time according to the regression function and the measured history property data, and regulating the regression function of SVR on line according to the regression function. The method can provide a data reference for dispatch, property optimization and the like of grid resources, avoid passive and blind task dispatch and enhance the efficiency of the grid environment.

The invention relates to a search term recommendation method and device. The search term recommendation method comprises the steps that candidate search terms are determined according to user input terms; a prediction model of a first evaluation value of the search terms used in search behaviors is established according to the history search behavior data of a user, and the first evaluation value represents the trade information of commodities led by the search terms within a set time; the first evaluation value of the candidate search terms is predicated according to the prediction model and the user history search behavior data corresponding to the candidate search terms; according to the first evaluation value, the candidate search terms are filtered or ranked, and the candidate search terms after filtering or ranking are recommended to the user. Accordingly, the search term recommendation method and device achieve the purpose that the commodities corresponding to the recommended search terms can better clinch a deal, and increase cheating cost.

It was difficult for previous health management support systems to grasp daily health condition quantitatively through using comprehensive indexes of personal health conditions, optimize advice as healthcare guidance, and show its expected effect in a favorable way. The disclosed method and system implement the following: estimating a predicted period of healthy life expectancy of each person who underwent health screening from health screening report data obtained through the health screening report data entry step, wherein healthy life expectancy prediction data is used that is prepared as basic data for predicting healthy life expectancy from a diversity of health screening report data. The predicted period of healthy life expectancy and related information for each person are displayed by display means or printed out by printing means.

The invention discloses an ARIMA-BP neutral network-based bridge monitoring data prediction method. The method comprises the following steps of 1) building an ARIMA(p,d,q) model of bridge monitoring data; 2) performing monitoring value estimation on a monitoring cycle of existent actual measurement data through the ARIMA(p,d,q) model to obtain an estimated value Ypn; performing monitoring value estimation on an expected prediction cycle of inexistent actual measurement data to obtain an estimated value Ynm; 3) obtaining a residual error of the monitoring data: performing subtraction on an actual value of the monitoring data and the estimated value Ypn of the ARIMA(p,d,q) to obtain a residual error Epn of a prediction result; 4) performing a process for predicting a residual error by a BP neutral network; 5) predicting a residual error in a prediction cycle through the established network to obtain an estimated value Enm; and 6) performing superposition on linear trend information predicted by the ARIMA(p,d,q) and a prediction result of the residual error by the BP network to obtain a combined prediction model result. According to the method, nonlinear information is effectively analyzed and a prediction error is relatively small.

The invention provides a user electricity consumption relevant factor identification and electricity consumption quantity prediction method under the environment of big data. Multiple electricity consumption modes of users are mined and existing electricity consumption behavior analysis methods are expanded by applying a mass user electricity consumption characteristic subspace clustering analysis method based on the research of the user electricity consumption characteristic evaluation index by aiming at the characteristics that the big data relevant to electricity consumption quantity prediction are various, large in size, high in dimension and high in generation speed. Meanwhile, group division is performed on the users according to different electricity consumption modes, factors relevant to user group electricity consumption quantity are identified from the aspects of regional and industry economic data, weather conditions and electricity price by utilizing mutual information matrixes, and an electricity consumption quantity big data prediction model based on a random forest algorithm is constructed so that data driving of the whole process of electricity consumption prediction is realized, adverse influence on electricity consumption quantity prediction caused by difference of the electricity consumption modes can be avoided, and thus the method has relatively high prediction precision and is suitable for big data analysis and processing.

The invention discloses a data prediction method and apparatus. The method comprises: obtaining time sequence data from a server, the time sequence data comprising data of N time points already occurred; analyzing stability of the time sequence data to obtain a stability analysis result; in dependence on the stability analysis result, selecting a first prediction model; and in dependence on the selected first prediction model, predicting data of future K time points.

A method of predicting deterioration in a mechanical device includes the steps of providing a health model for the mechanical device, the health model including a plurality of health states for modeling the mechanical device, receiving device data for the mechanical device, estimating values for the plurality of health states, based on the device data, predicting one or more events based on the health model and the device data, each of the one or more events affecting one or more of the plurality of health states, and generating a prediction of deterioration in the mechanical device from the estimated values for the plurality of health states and the one or more predicted events.

The invention discloses a traffic demand forecasting method and system for a dynamic road network. According to the invention, multi-source traffic data is collected and integrated all the time; dynamic grid data is formed through overlapping traffic flow data, geographic information data and traffic management information on the road network; and a data forecasting model is established on the basis of dynamic road network data. The method has characteristics of good real time performance, high accuracy and the like, can improve jamming study and judge precision effectively, so as to provide reasonable traffic demand data (queue, flow, speed, occupancy rate and the like) for signal optimization. The system can improve an optimization model and relieves traffic jams.

The invention discloses a data prediction classification method and device relating to the data process technique field, solving the problem in the prior art that classification result itself and classification count value are possible to leak the private information of a user. The method comprises: building a random forest namely multiple decision trees through a training dataset; carrying out prediction classification to a test dataset by the decision trees in the random forest, and obtaining the classification result satisfying differential privacy. The invention can realize high accuracy prediction classification of the high-dimension large-scale data.

A method and system of predicting market information includes the steps of receiving first data, forecasting further data based on the first data, receiving second data and comparing the further data with the second data, and creating an adjustment factor to account for any difference between the further data and the second data.

The invention provides a cloud computing resource pre-distribution achievement method. The cloud computing resource pre-distribution achievement method detailedly analyzes design and realization of a model, helps an information technology (IT) administrator to beforehand deploy various virtual machines to satisfy unexpected requests by forecasting possible user requests, and meanwhile forecasts possible physical resource demands aiming at specific resource types so as to beforehand purchase corresponding resources. The cloud computing resource pre-distribution achievement method comprises data collection; data washing, filtering requests of users, wherein the number of times of the requests is smaller than a preset number of times; model training, building a combined forecast model based on an array of time and types of the virtual machines, and then continuously leading in washed data and carrying out the model training according to a time window until the time window is filled, and accomplishing model convergence; data forecast, forecasting resource requests of a preset time based on the trained combined forecast model; and result processing, wherein under the premise of a preset forecast time, forecast results comprise total required quantity of each type of virtual machines, required quantity of the virtual machines in the next circle, and required quantity of a specific physical resource.

The invention provides a method for predicting data and an equipment. The method comprises the following steps of: reading a plurality of first data related to a first period which contains a plurality of first sub periods, wherein a plurality of first data and a plurality of first sub periods are in a one-to-one correspondence relationship; based on a plurality of first data and a plurality of first sub periods, determining a plurality of first trend values which are in a one-to-one correspondence relationship with a plurality of first sub periods; based on a plurality of first data and a plurality of first trend values, obtaining a compensation sequence constituted by a plurality of compensation amount, wherein a plurality of compensation amount and a plurality of first sub periods are in a one-to-one correspondence relationship; based on the compensation sequence, obtaining estimation values of the compensation dosage which corresponds to a second period by utilizing a support vector machine, wherein the time of the second period is later than that of the first period; based on the estimation values of compensation amount, predicting a second data related to the second period. The embodiment of the invention has effective prediction, thereby being capable of bringing considerable economic benefits for operators.

The invention regards a method for assisting a driver of a vehicle by computationally predicting a future movement behaviour of a target vehicle. The method comprises steps of acquiring data describing a traffic environment of a host vehicle, computing a plurality of future movement behaviour alternatives for a target vehicle, by predicting movement behaviour of the target vehicle based on the data describing the traffic environment. The prediction step calculates a probability that the target object will execute a movement behaviour and information relating to future behaviour of the target vehicle is output. The method estimates a global scene context and adapts the predicted behaviour based on the estimated global scene context. The adaptation of the behaviour prediction is performed by at least one of adapting indicator values in situation models employed by a context-based prediction, by adapting a result of the context-based prediction and adapting the overall prediction result.

The invention relates to the technical field of traffic intelligent management and control and discloses a forecasting method and device for traffic impact ranges. The forecasting method for the traffic impact ranges comprises obtaining traffic state information; judging whether traffic states suddenly change or not; extracting current decided attribute data of sudden change of the traffic states if the traffic states suddenly change; classifying history sample sets of the sudden change of the traffic states according to the traffic impact ranges and confirming a central value of the decided attribute data which is corresponding to every category of traffic impact range data; obtaining traffic impact range data which is corresponding to the current decided attribute data according to confirmed every category of the traffic impact range data and forecasting the current impact ranges according to the traffic impact range data. According to the forecasting method for the traffic impact ranges, accuracy for forecasting traffic influence ranges is improved.

Processing a wafer using a double side grinder having a pair of grinding wheels. Warp data is obtained by a warp measurement device for measuring warp of a wafer as ground by the double side grinder. The warp data is received and a nanotopography of the wafer is predicted based on the received warp data. A grinding parameter is determined based on the predicted nanotopography of the wafer. Operation of the double side grinder is adjusted based on the determined grinding parameter.