460 results about "Nonlinear regression" patented technology

A method of calibrating glucose monitor data includes collecting the glucose monitor data over a period of time at predetermined intervals, obtaining reference glucose values from a reference source that temporally correspond with the glucose monitor data obtained at the predetermined intervals, calculating the calibration characteristics using the reference glucose values and corresponding glucose monitor data to regress the obtained glucose monitor data, and calibrating the obtained glucose monitor data using the calibration characteristics. In additional embodiments, calculation of the calibration characteristics includes linear regression and, in particular embodiments, least squares linear regression. Alternatively, calculation of the calibration characteristics includes non-linear regression. Data integrity may be verified and the data may be filtered. Further, calibration techniques may be modified during a fast rate of change in the patient's blood glucose level to increase sensor accuracy.

A method and system for converting low-dose tomosynthesis projection images or reconstructed slices images with noise into higher quality, less noise, higher-dose-like tomosynthesis reconstructed slices, using of a trainable nonlinear regression (TNR) model with a patch-input-pixel-output scheme called a pixel-based TNR (PTNR). An image patch is extracted from an input raw projection views (images) of a breast acquired at a reduced x-ray radiation dose (lower-dose), and pixel values in the patch are entered into the PTNR as input. The output of the PTNR is a single pixel that corresponds to a center pixel of the input image patch. The PTNR is trained with matched pairs of raw projection views (images together with corresponding desired x-ray radiation dose raw projection views (images) (higher-dose). Through the training, the PTNR learns to convert low-dose raw projection images to high-dose-like raw projection images. Once trained, the trained PTNR does not require the higher-dose raw projection images anymore. When a new reduced x-ray radiation dose (low dose) raw projection images is entered, the trained PTNR outputs a pixel value similar to its desired pixel value, in other words, it outputs high-dose-like raw projection images where noise and artifacts due to low radiation dose are substantially reduced, i.e., a higher image quality. Then, from the “high-dose-like” projection views (images), “high-dose-like” 3D tomosynthesis slices are reconstructed by using a tomosynthesis reconstruction algorithm. With the “virtual high-dose” tomosynthesis reconstruction slices, the detectability of lesions and clinically important findings such as masses and microcalcifications can be improved.

The invention discloses a convolutional neural network structure-based traffic flow prediction method. The method comprises the following steps of 1) establishing a traffic flow data set and preprocessing the data set: establishing the traffic flow data set according to obtained traffic flow data, preprocessing the data set, constructing a data set sample matrix, and dividing the data set into a training set and a test set; 2) establishing a single-layer conventional convolutional neural network, removing a pooling layer, constructing a feature extraction network of a road traffic flow matrix,adding a sigmoid nonlinear regression layer to a full connection layer, and constructing a road traffic flow nonlinear regression prediction network; and 3) training the convolutional neural networkand realizing real-time prediction of short-term traffic flow: defining a model objective function, taking the training set as an input of a convolutional neural network model, solving an optimal parameter of the model to finish model training, and performing real-time traffic flow prediction on the test set by utilizing the trained convolutional neural network model. The short-term prediction accuracy of the traffic flow is improved.

A system and method for measuring or quantifying the probability of default of a borrower. Credit factors from companies that banks have extended loans to are inputted and collected into a processor. The method employs a process utilizing an optimization function and a standard multivariate nonlinear regression to process client information and to provide an output value whose value is indicative of the likelihood or risk of default by a particular borrower.

The invention discloses a transmission type Mueller matrix spectrum ellipsometer and a measuring method thereof. The transmission type Mueller matrix spectrum ellipsometer measuring method comprises the following steps: projecting modulation rays produced by a partial arm on the surface of a to-be-tested sample, a check partial arm demodulates and receives the rays reflected (or transmitted) by the to-be-tested sample, by proceeding harmonic wave analysis to a tested spectrum, computing and acquiring the full Mueller matrix information of the to-be-tested sample, further through arithmetic of nonlinear regression, liberty matching, and the like, and fitting and extracting information of an optical constant, characteristic, morphology, size and the like of the to-be-tested sample. An ellipsometer comprises the partial arm (comprises light source, a lens group, a polarizer, and a compensator driven by a servo motor),the to-be-tested sample and the check partial arm (comprises the compensator driven by a servo motor, an analyzer the lens group and a spectrograph. The transmission type Mueller matrix spectrum ellipsometer and the measuring method thereof can achieve all kinds of materials and components with information phoelectron functions, and online measurement of all kinds of nano-structures in nano-fabrication, so that transmission type Mueller matrix spectrum ellipsometer and the measuring method thereof have the advantages of being capable of possessing non-destructive property, fast, and low in cost.

A system and method facilitating lithography defect solution generation is provided. The invention includes a defect solution component and a defect alert component. The defect solution component provides potential solution(s) to a defect within the lithography process utilizing artificial intelligence technique(s) (e.g., Bayesian learning methods that perform analysis over alternative dependent structures and apply a score, Bayesian classifiers and other statistical classifiers, including decision tree learning methods, support vector machines, linear and non-linear regression and/or neural network).

Measurements of fluorescence spectra of fluid samples recovered downhole are processed to give the fluid composition. The processing may include a principal component analysis followed by a clustering method or a neutral network. Alternatively the processing may include a partial least squares regression. The latter can give the analysis of a mixture of three or more fluids.

A partial least squares (PLS) regression relates spin echo signals with samples having a known parameter such as bound water (BW), clay bound water (CBW), bound volume irreducible (BVI), porosity (PHI) and effective porosity (PHE). The regression defines a predictive model that is validated and can then be applied to spin echo signals of unknown samples to directly give an estimate of the parameter of interest. The unknown samples may include earth formations in which a NMR sensor assembly is conveyed in a borehole.

The present invention provides a method and system for electrolyzer diagnosis based on curve fitting analysis and efficiency optimization. The present invention relates to monitoring the electrochemical cell components by using curve fitting and estimating the overall electrolyzer performance by using predictive models. The system according to the present invention comprises an extraction unit for selecting suitable operation zones, a filtering unit, a curve fitting unit performing linear or non-linear regression by using user-defined equations applied to current-voltage data points and a curve fitting goodness analysis unit. The zones are defined as start-up zones, shutdown zones and load change zones. The system further comprises a curve fitting parameters characterization unit for classifying curve fitting parameters by respect to the electrolyzer cells components technology and reference values, and a characterization database for storing fitting coefficients and their characterization.

Complex process control and maintenance are performed utilizing a nonlinear regression analysis to determine optimal tool-specific adjustments based on operational metrics, process adjustments and maintenance activities.

A method and system for converting low-dose mammographic images with much noise into higher quality, less noise, higher-dose-like mammographic images, using of a trainable nonlinear regression (TNR) model with a patch-input-pixel-output scheme, which can be called a call pixel-based TNR (PTNR). An image patch is extracted from an input mammogram acquired at a reduced x-ray radiation dose (lower-dose), and pixel values in the patch are entered into the PTNR as input. The output of the PTNR is a single pixel that corresponds to a center pixel of the input image patch. The PTNR is trained with matched pairs of mammograms, inputting low-dose mammograms together with corresponding desired standard x-ray radiation dose mammograms (higher-dose), which are ideal images for the output images. Through the training, the PTNR learns to convert low-dose mammograms to high-dose-like mammograms. Once trained, the trained PTNR does not require the higher-dose mammograms anymore. When a new reduced x-ray radiation dose (low dose) mammogram is entered, the trained PTNR would output a pixel value similar to its desired pixel value, in other words, it would output high-dose-like mammograms or “virtual high-dose” mammograms where noise and artifacts due to low radiation dose are substantially reduced, i.e., a higher image quality. With the “virtual high-dose” mammograms, the detectability of lesions and clinically important findings such as masses and microcalcifications can be improved.

A color characterization process utilizing nonlinear regression analysis to characterize a color input device. The color input device is used to generate a bitmap of device dependent values from a color target. The bitmap of device dependent color values is used to generate a forward model that maps device dependent color values to color values in a device independent color space using a nonlinear regression analysis that minimizes a color difference metric between the reference color values and the set of device dependent color values mapped through the forward model. The color difference metric is chosen to represent human perceived color differences in the device independent color space. The performance of the nonlinear regression analysis may be improved by initializing the nonlinear regression analysis using an initial forward model generated from a linear regression analysis.

The invention discloses an angle and myoelectricity continuous decoding method for a human body lower limb walking joint. The movement track of a lower limb body surface optical marking point in the human body walking process is recorded through an optical movement capture system, and the movement angle of the lower limb joint is precisely calculated through the human body lower limb kinematical modeling; surface electromyogram signals of eight main muscles related to lower limb movement in the human body walking process are synchronously acquired, the activity intensity information of the signals is extracted through filtering and rectifying preprocessing, and the optical independent feature vector set describing the intensity of the surface electromyogram signals is extracted through the principle component analysis method; a nonlinear regression model from surface electromyogram signal features (independent variables) to the vertical plane joint movement angles (dependent variables) is established through the gene expression programming symbol regression analysis method, and the lower limb movement track is predicted. The method is mainly applied to design and manufacture of medical rehabilitation machines.

Systems and methods of complex process control utilize driving factor identification based on nonlinear regression models and process step optimization. In one embodiment, the invention provides a method for generating a system model for a complex process comprised of nonlinear regression models for two or more select process steps of the process where process steps are selected for inclusion in the system model based on a sensitivity analysis of an initial nonlinear regression model of the process to evaluate driving factors of the process.

The invention provides a method for evaluating service reliability of numerical control equipment. According to the original input and output vectors of data after zero dimension treatment, an optimized nonlinear regression function for the input-output of the numerical control equipment is obtained by using a support vector regression machine for training, and furthermore the indexes of the reliability such as point estimation, confidence interval and reliable sensitivity are solved by the self-adapting selective sampling method and bootstrap method. The method can accurately evaluate and predict the influence of different factors on the service reliability of the numerical control equipment under the condition of a small sample, find out a weak link of the numerical control equipment and indicate a direction of improving the design, manufacturing, process, maintenance and the like of the numerical control equipment.

Failure prediction for complex processes is performed utilizing one or more nonlinear regression models to relate operational variable values measured at two or more times to predicted process metric values and maintenance variable values.

The invention relates to a no-reference image quality evaluation method based on Curvelet transformation and phase coincidence. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence comprises the following steps: (1), images are transformed to a Curvelet domain and a phase coincidence domain; (2), a series of natural scene statistical characteristics are extracted from the Curvelet domain and the phase coincidence domain; the series of natural scene statistical characteristics comprise logarithm histogram peak value coordinates of Curvelet coefficients and phase coincidence coefficients, direction energy distribution characteristics and dimension energy distribution characteristics; and (3), a two-step frame is used, the series of characteristics extracted in the step 2 and a support vector machine are utilized for firstly classifying distorted images of unknown types, and then nonlinear regression of a specific type is conducted on the distorted images according to a classification result, and DMOS is forecasted according to an objective quality evaluation result of the images. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence has the advantages of being high in human eye subjective consistency, small in time complexity, and high in application value.

The invention discloses a system state estimation method based on an improved nonlinear robust filtering algorithm and relates to the technical field of space navigation. The method is based on a Huber nonlinear regression algorithm, so that high filtering accuracy and stable filtering output can be obtained under the condition that a measuring output equation is nonlinear, and measuring noises are in non-Gaussian distribution.

The health of a tool is predicted based on temporally ordered input data representing parameters indicative of tool health. A sliding time window is used to partition input data into temporally displaced data sets. Non-linear regression models determine, based on the data sets, a set of predictive values relating to tool health at a future time. A tool-health metric is then determined based on one or more of the predictive values.

The invention discloses a method identifying a non-front-side facial expression based on attitude normalization. The method comprises that facial expressions in a training sample set are learned via a nonlinear regression model to obtain a mapping function from non-front-side facial characteristic points to front-side facial characteristic points; attitude estimation and characteristic point positioning are carried out on to-be-tested non-front-side facial images via a multi-template active appearance model, and the characteristic points of a non-front-side face are normalized to a front-side attitude via the corresponding attitude mapping function; and geometric positions of the characteristic points of a front-side face are classified into expressions via a support vector machine. The method identifying the non-front-side facial expression is simple and effectively, which solves the problem that different facial attitudes cause different expressions, and satisfies the requirement of identifying non-front-side facial expressions in real time.

The invention discloses an intelligent monitoring method for a blast furnace cooling wall, which comprises the following steps that: a cooling wall heat transfer model is established, a heat transfer core model is extracted through a non-linear regression mode, the core model and an artificial neural network are combined to produce a monitoring model for a highest temperature value of a hot surface of the cooling wall and form monitoring software, and the running state and local high-temperature positions of the cooling wall as well as the safety of the cooling wall are evaluated by combining the heat transfer model with temperature values of test points of an in-situ sensor. The method has the advantages of simple data acquisition for theoretical analysis, quick and accurate result generation, and less damage to shells of blast furnaces.