10581results about How to "Improve forecast accuracy" patented technology

The present invention provides a dynamic pricing system that generates pricing recommendations for each product in each market. In particular, the system normalizes historic pricing and sales data, and then analyzes this historic data using parameters describing the user's business objectives to produce a pricing list to achieve these objectives. The system uses historical market data to forecast expected sales according to a market segment, product type, and a range of future dates and to determine the effects of price changes on the forecasted future sales. The system further calculates unit costs for the product. The system then estimates profits from sales at different prices by using the sales forecasts, adjusting these sales forecasts for changes in prices, and the costs determinations. The system optionally optimizes prices given current and projected inventory constraints and generates alerts notices according to pre-set conditions.

The present invention provides a configurable pricing system that allows users to define or modify data used to analyze, evaluate, improve, and design pricing changes according to the user's need. A Graphical user interface or some other type of user interface allows the user to access and review various data to be used during pricing optimization. The user may then modify this data as needed to improve the pricing evaluation, such as defining sales or pricing trends, or relationships between the product of interest and other competing items. The user interface may further display changes in pricing and the effects of the pricing changes, as caused by the user's changes. The interface may also allow the user to modify the mathematical model to be used during price optimization, as well as define variables, constraints, and boundaries to be considered during the price optimization.

The invention provides an unsupervised domain-adaptive brain tumor semantic segmentation method based on deep adversarial learning. The method comprises the steps of deep coding-decoding full-convolution network segmentation system model setup, domain discriminator network model setup, segmentation system pre-training and parameter optimization, adversarial training and target domain feature extractor parameter optimization and target domain MRI brain tumor automatic semantic segmentation. According to the method, high-level semantic features and low-level detailed features are utilized to jointly predict pixel tags by the adoption of a deep coding-decoding full-convolution network modeling segmentation system, a domain discriminator network is adopted to guide a segmentation model to learn domain-invariable features and a strong generalization segmentation function through adversarial learning, a data distribution difference between a source domain and a target domain is minimized indirectly, and a learned segmentation system has the same segmentation precision in the target domain as in the source domain. Therefore, the cross-domain generalization performance of the MRI brain tumor full-automatic semantic segmentation method is improved, and unsupervised cross-domain adaptive MRI brain tumor precise segmentation is realized.

The invention provides a multi-scale feature fusion ultrasonic image semantic segmentation method based on adversarial learning, and the method comprises the following steps: building a multi-scale feature fusion semantic segmentation network model, building an adversarial discrimination network model, carrying out the adversarial training and model parameter learning, and carrying out the automatic segmentation of a breast lesion. The method provided by the invention achieves the prediction of a pixel class through the multi-scale features of input images with different resolutions, improvesthe pixel class label prediction accuracy, employs expanding convolution for replacing partial pooling so as to improve the resolution of a segmented image, enables the segmented image generated by asegmentation network guided by an adversarial discrimination network not to be distinguished from a segmentation label, guarantees the good appearance and spatial continuity of the segmented image, and obtains a more precise high-resolution ultrasonic breast lesion segmented image.

The invention provides a method and a device for image prediction. The method comprises the steps of: obtaining a first reference unit of an image unit, wherein the image unit and the first reference unit obtain respective predicted images by using the same affine model; obtaining motion information of basic motion compensation units at the at least two preset positions of the first reference unit; and obtaining the motion information of the basic motion compensation units of the image unit. Therefore, by multiplexing the motion information of the first reference unit which adopts the same affine pre-model, a motion vector of the current image unit is obtained more exactly, the coding and decoding complexity is kept while the prediction accuracy is improved, and the coding and decoding performance is improved.

A driving behavior prediction apparatus includes, for accurately predicting a driving behavior, a position calculation unit for a subject vehicle position calculation, a route setting unit for setting a navigation route, a distance calculation unit for calculating a distance to a nearest object point, a parameter storage unit for storing a template weighting factor that reflects a driving operation tendency of a driver, a driving behavior prediction unit for predicting a driver's behavior based on vehicle information and the template weighting factor, a driving behavior recognition unit for recognizing driver's behavior at the object point, and a driving behavior learning unit for updating the template weighting factor so as to study the driving operation tendency of the driver in a case that a prediction result by the driving behavior prediction unit agrees with a recognition result by the driving behavior recognition unit.

The invention discloses a power grid security situation predicting method based on an improved deep learning model and belongs to the technical field of power system safety. The power grid security situation predicting method includes: performing power grid security situation evaluation through power grid data collection and preprocessing; aiming at the characteristic that indicator data of power grid security situation evaluation are high in relevance and dimension, providing an improved self-coding network method to lower dimension of the indicator data, and utilizing a data sample after dimension reduction and a power grid security situation value corresponding to a next time monitoring point; adopting an improved deep belief network to build a deep learning situation predicting model with multi-input and multi-output for power grid security situation prediction. By the power grid security situation predicting method, speed and accuracy of power grid security situation prediction can be improved effectively.

This disclosure is of 1) the utilization of the spectrum from 250 nm to 1150 nm for measurement of prediction of one or more parameters, e.g., brix, firmness, acidity, density, pH, color and external and internal defects and disorders including, for example, surface and subsurface braises, scarring, sun scald, punctures, in N—H, C—H and O—H samples including fruit; 2) an apparatus and method of detecting emitted light from samples exposed to the above spectrum in at least one spectrum range and, in the preferred embodiment, in at least two spectrum ranges of 250 to 499 nm and 500 nm; 3) the use of the chlorophyl band, peaking at 690 nm, in combination with the spectrum from 700 nm and above to predict one or more of the above parameters; 4) the use of the visible pigment region, including xanthophyll, from approximately 250 nm to 499 nm and anthocyanin from approximately 500 to 550 nm, in combination with the chlorophyl band and the spectrum from 700 nm and above to predict the all of the above parameters.

An image encoding apparatus for application to images expressed as respective frames of a digital video signal, whereby an image is converted into an array of blocks with specific blocks predetermined as being independent internally encoded blocks and the remainder as predictively encoded blocks, with predicted pixel signal values for a predictively encoded block being derived by interpolation from pixel signal values of at least one pair of blocks which have been already encoded and enclose that predictively encoded block along the row or column directions or both the row and column directions. Encoding efficiency is enhanced by applying Discrete Sine Transform processing along the interpolation direction, when encoding an array of prediction error signal values derived for a block, and by executing adaptive prediction by determining an optimum interpolation direction, when there are two possible directions for deriving predicted pixel signal values for a block.

The present invention is a power load forecasting method based on big data technology and a research application system based on the method. With the support of big data technology, a variety of mature open source products are integrated to form a data source, data integration, data storage, Data calculation, data analysis, implementation of electrical load characteristic analysis and electrical load forecast analysis. The invention effectively improves the efficiency of mass data processing, and solves the limitations of traditional statistical analysis assumptions and judgments. It can scientifically and accurately predict the electricity demand of the future power, which is conducive to the peak-shaving and valley-filling and stable operation of the power grid, and provides decision-making support for the company's power grid planning, equipment maintenance, and power deployment.

A system and method for efficient improvement of branch prediction in a microprocessor with negligible impact on die-area, power consumption, and clock cycle period. It is determined if a program counter (PC) register contains a polymorphic indirect unconditional branch (PIUB) instruction. One determination may be searching a table with a portion or all of a PC of past PIUB instructions. If a hit occurs in this table, the global shift register (GSR) is updated by shifting a portion of the branch target address into the GSR, rather than updating the GSR with a taken/not-taken prediction bit. The stored value in the GSR is input into a hashing function along with the PC in order to index prediction tables such as a pattern history table (PHT), a branch target buffer (BTB), an indirect target array, or other. The updated value due to the PIUB instruction improves the accuracy of the prediction tables.

The invention discloses a coding method for a three-dimensional video. The method comprises the following steps of: inputting a first frame image which comprises image texture information and depth information at a plurality of different viewpoints at the same time so as to form depth pixel images of the plurality of the viewpoints; selecting a viewpoint which is closest to a center as a main viewpoint and mapping the depth pixel image of each viewpoint onto the main viewpoint; acquiring motion information from the texture information by a motion target detection method, rebuilding all depth pixel points in the mapped depth pixel images by using the depth information and/or the motion information to acquire a background image layer image and one or more foreground image layer images; and coding the background image layer image and the foreground image layer images respectively, wherein the depth information and the texture information are coded respectively. The invention also discloses a decoding method for the three-dimensional video, a coder and a decoder. The coding method is particularly suitable for coding a multi-viewpoint video sequence with a stationary background, can enhance prediction compensation accuracy and decreases code rate on the premise of ensuring subjective quality.

The invention discloses a machine learning model training method and device. The method comprises the following steps: on the basis of initialized first weight and second weight of each sample in a training set, and with features of each sample as granularity, training a machine learning model; on the basis of prediction loss of each sample in the training set, determining a first sample set, where corresponding target variables are predicated inaccurately, and a second sample set, where corresponding target variables are predicated accurately; on the basis of the prediction loss of each sample in the first sample set and the corresponding first weight, determining overall prediction loss of the first sample set; on the basis of the overall prediction loss of the first sample set, improving the first weight and the second weight of each sample in the first sample set; and inputting the updated second weight of each sample in the training set and features of each sample and the target variables into the machine learning model, and with the features of each sample as granularity, training the machine learning model. Through the machine learning model training method and device, prediction accuracy and training efficiency of the machine learning model can be improved.

The invention discloses a method for predicting an hourly cooling load of a central air-conditioner in an office building on line based on indoor temperature and humidity parameters. The method for predicting the cooling load comprises the following steps of: performing time sequence prediction on outdoor meteorological parameters and air-conditioner operation input parameters, establishing an Online support vector regression (SVR) dynamic prediction model of the air-conditioner cooling load by using the data, predicting 24-hour air-conditioner cooling load in the current day in advance, and performing compensation by using a residual sequence of the actual value and the predication value of the 24-hour air-conditioner load in the previous day. The predication data of the air-conditioner cooling load prediction model established by the method is high in reliability; and the method can be applied to occasions for prediction of the hourly cooling load of the central air-conditioner in the office building in a single building or a large range, energy-saving control of a central air-conditioner system, energy consumption prediction of the air-conditioner, power peak clipping in areas and the like.

The invention discloses an image forecasting method and a related device. The image forecasting method includes: confirming K1 pixel samples in an image block x, and confirming a candidate movement information unit set corresponding to each of the K1 pixel samples; enabling each candidate movement information unit set corresponding to each pixel sample to include at least one candidate movement information unit; confirming a merger movement information unit set i which includes K1 movement information units; using a non-translation movement model and the merger movement information unit set i to forecast pixel values of the image block x, wherein all the movement information units in the merger movement information unit set i are respectively selected from at least a part of the movement information units in the candidate movement information unit sets corresponding to the different pixel samples in the K1 pixel samples. The image forecasting method and the related device facilitate reduction of computation complexity of image forecasting based on the non-translation movement model.

The invention relates to a vehicle flow predicting method based on an integrated LSTM neural network. On the basis of historical data obtained by vehicle flow detection, an integrated LSTM neural network vehicle flow prediction model is established to carry out vehicle flow prediction, so that the generalization error of the prediction model is reduced and the accuracy is improved. The method comprises the following steps that: data preprocessing is carried out; according to a preprocessed vehicle flow time sequence value, a vehicle flow matrix data set is constructed and the vehicle flow of an (n+1)th period of time is predicted by using first n periods of time, wherein each period of time is delta t expressing the time length and the unit is min; a plurality of different LSTM neural network models are constructed by using different initial weights; on the basis of a bagging integrated learning method, a training set and a verification set are constructed; a plurality of LSTM neural networks are trained to obtain an optimized module; a weighting coefficient of the single LSTM model is calculated by using the verification set; and inverse transformation and reverse normalization are carried out on a predicted vehicle flow value to obtain a predicted vehicle flow and integrated weighting is carried out to obtain a vehicle flow value predicted finally by the model.

The invention discloses a short-time traffic flow prediction method based on a long-time and short-time memory recurrent neural network. The method comprises the following steps: aggregating inputted historical traffic flow data according to a prediction time interval of a short-time traffic flow; carrying out pretreatment on the aggregated historical traffic flow; setting a reasonable parameter for a long-time and short-time memory recurrent neural network; training a neural network prediction model by using data after pretreatment; and invoking a traffic flow, predicted by the prediction model, of a designated time interval and evaluating a prediction error. According to the invention, because the long-time and short-time memory recurrent neural network has the advantage of being capable of memorizing inputted historical data for long time, the high prediction precision is realized; and the expansibility for different prediction intervals is good.

The invention discloses a hybrid machine learning credit scoring model building method. The method comprises the steps of 1, determining client risk classification standards based on a loan client historical data set; 2, based on the loan client historical data set, obtaining a loan client data feature set through feature extraction; 3, selecting at least two model algorithms from an alternative model library, building corresponding models based on the selected algorithms, performing model performance check on the built models by adopting a K-fold cross check method, performing standard check on the models about to pass the model performance check based on model check standards, obtaining evaluation index statistical quantity values, and selecting a model type used by final modeling according to the evaluation index statistical quantity values returned by the standard check of the models; and 4, based on the algorithm corresponding to the selected model type, building a credit scoring model. The technical effect of efficiently and accurately finishing user credit evaluation through the built hybrid machine learning credit scoring model is achieved.

The invention discloses an automotive exhaust emission data fusion system. The automotive exhaust emission data fusion system comprises a roadside air pollutant concentration estimation module, a roadside air pollutant concentration prediction module, a city global atmospheric environment prediction module, an automotive exhaust emission factor estimation module and an automotive exhaust emission feather analysis module, wherein the five modules are used for respectively realizing different data analysis functions, and the different functions can be realized by virtue of the different modules; the modules can be independently used, or two or more modules can be combined for use, so as to realize the storage, analysis and fusion of automotive exhaust telemetering data, automotive attributes, driving working stations, detection time and meteorological condition data; and by combining with a vehicle-mounted diagnosis system database, a portable emission test system database, a vehicle inspection station offline database, a traffic information database and a geographic information database, automotive exhaust telemetering data is analyzed, and the highest discriminatory key indexes and statistical data are acquired, so that effective supports are provided for the formulation of relevant decisions of government departments.

The invention provides a system and a method for predicting the coal and gas outburst risk of a mine in real time, which relate to a system and a method for judging mine natural disaster of coal and gas outburst risk degree through combination of artificial intelligence and expert analysis. The system uses a microseismic signal for reflecting the ground stress intensity and the gas outburst quantity for reflecting the gas change as analysis parameters to be combined with the expert experience, and can improve the predicting accuracy of the coal and gas outburst risk to high than 90 percent. The system and the method are characterized in that the system mainly consists of a data collection module, a data transmission module, a real-time data tracking and analysis center and an integrated early warning module, wherein after the data collection module collects underground data, the data is transmitted to the real-time data tracking and analysis center through the data transmission modulefor calculation, analysis and reasoning, and the integrated early warning module gives the early warning when a reasoning result shows that the risk occurs. The invention is applicable to similar mines with the coal and gas outburst risk.