209 results about "Multivariate statistical" patented technology

Disclosed are systems and methods for on-line monitoring of operation of a process in connection with process measurements indicative of the operation of the process. In some cases, the operation of the process is simulated to generate model data indicative of a simulated representation of the operation of the process and based on the process measurements. A multivariate statistical analysis of the operation of the process is implemented based on the model data and the process measurements. The output data from the multivariate statistical analysis may then be evaluated during the operation of the process to enable the on-line monitoring of the process involving, for instance, fault detection via classification analysis of the output data.

The present invention generally relates to computer databases and, more particularly, to data mining and knowledge discovery. The invention specifically relates to a method for constructing segmentation-based predictive models, such as decision-tree classifiers, wherein data records are partitioned into a plurality of segments and separate predictive models are constructed for each segment. The present invention contemplates a computerized method for automatically building segmentation-based predictive models that substantially improves upon the modeling capabilities of decision trees and related technologies, and that automatically produces models that are competitive with, if not better than, those produced by data analysts and applied statisticians using traditional, labor-intensive statistical techniques. The invention achieves these properties by performing segmentation and multivariate statistical modeling within each segment simultaneously. Segments are constructed so as to maximize the accuracies of the predictive models within each segment. Simultaneously, the multivariate statistical models within each segment are refined so as to maximize their respective predictive accuracies.

An apparatus, system, method, and computer readable medium containing computer-executable code for implementing image analysis uses multivariate statistical analysis of sample images, and allows segmentation of the image into different groups or classes, depending on a correlation to one or more sample textures, or sample surface features. In one embodiment, the invention performs multivariate statistical analysis of ultrasound images, wherein a tumor may be characterized by segmenting viable tissue from necrotic tissue, allowing for more detailed in vivo analysis of tumor growth beyond simple dimensional measurements or univariate statistical analysis. Application of the apparatus and method may also be used for characterizing other types of samples having textured features including, for example, tumor angiogenesis biomarkers from Power Doppler.

A method for differentiating complex mixtures each having one or more chemical species is provided. The method comprises producing a sample NMR spectrum by subjecting a mixture to a selective spectroscopy process, wherein the NMR spectrum has individual spectral peaks representative of the one or more chemical species within the mixture. The one or more chemical species within the mixture are identified by analyzing the individual spectral peaks, and the individual spectral peaks are then subjected to a multivariate statistical analysis.

Methods and systems to detect steady-state operations in a process of a process plant include collecting process data. The collected process data is generated from a plurality of process variables of the process. A multivariate statistical model of the operation of the process is generated using the process data. The multivariate statistical model may be generated from a principal component analysis. The model is executed to generate outputs corresponding to the most significant variations in the process. Statistical measures of the outputs are generated and used to determine whether a steady-state or unsteady-state is related to the process.

The present invention generally relates to computer databases and, more particularly, to data mining and knowledge discovery. The invention specifically relates to a method for constructing segmentation-based predictive models, such as decision-tree classifiers, wherein data records are partitioned into a plurality of segments and separate predictive models are constructed for each segment. The present invention contemplates a computerized method for automatically building segmentation-based predictive models that substantially improves upon the modeling capabilities of decision trees and related technologies, and that automatically produces models that are competitive with, if not better than, those produced by data analysts and applied statisticians using traditional, labor-intensive statistical techniques. The invention achieves these properties by performing segmentation and multivariate statistical modeling within each segment simultaneously. Segments are constructed so as to maximize the accuracies of the predictive models within each segment. Simultaneously, the multivariate statistical models within each segment are refined so as to maximize their respective predictive accuracies.

A real-time system and method for online monitoring a transient operation in a continuous casting process. The transient operation refers to, but is not limited to, submerged entry nozzle changes, flying tundish changes, product grade changes, etc. This invention treats the aforementioned transient operations as batch processes and utilizes multiway principal component analysis to develop a multivariate statistical model to characterize normal process transitions based on carefully selected historical process data. Such a model is used by an online monitoring system to determine if a continuous caster transient operation is normal. This monitoring system can further be used to predict an impending breakout, one type of catastrophic process failures which may occur in a continuous casting process, during the transient operation. Process variables that are most likely related to the predicted breakout are identified by the system such that appropriate control actions can be taken to prevent an actual breakout occurrence.

Fluorescence spectral data acquired from tissues in vivo or in vitro is processed in accordance with a multivariate statistical method to achieve the ability to probabilistically classify tissue in a diagnostically useful manner, such as by histopathological classification. The apparatus includes a controllable illumination device for emitting electromagnetic radiation selected to cause tissue to produce a fluorescence intensity spectrum. Also included are an optical system for applying the plurality of radiation wavelengths to a tissue sample, and a fluorescence intensity spectrum detecting device for detecting an intensity of fluorescence spectra emitted by the sample as a result of illumination by the controllable illumination device. The system also include a data processor, connected to the detecting device, for analyzing detected fluorescence spectra to calculate a probability that the sample belongs in a particular classification. The data processor analyzes the detected fluorescence spectra using a multivariate statistical method. The five primary steps involved in the multivariate statistical method are (i) preprocessing of spectral data from each patient to account for inter-patient variation, (ii) partitioning of the preprocessed spectral data from all patients into calibration and prediction sets, (iii) dimension reduction of the preprocessed spectra in the calibration set using principal component analysis, (iv) selection of the diagnostically most useful principal components using a two-sided unpaired student's t-test and (v) development of an optimal classification scheme based on logistic discrimination using the diagnostically useful principal component scores of the calibration set as inputs.

Disclosed are systems and methods for on-line monitoring of operation of a process in connection with process measurements indicative of the operation of the process. In some cases, the operation of the process is simulated to generate model data indicative of a simulated representation of the operation of the process and based on the process measurements. A multivariate statistical analysis of the operation of the process is implemented based on the model data and the process measurements. The output data from the multivariate statistical analysis may then be evaluated during the operation of the process to enable the on-line monitoring of the process involving, for instance, fault detection via classification analysis of the output data.

A plurality of ECG Superscore formulae, created from multiple parameter ECG measurements including those from advanced ECG techniques, can be optimized using additive multivariate statistical models or pattern recognition procedures, with the results compared against a large database of ECG measurements from individuals with known cardiac conditions and / or previous cardiac events. Superscore formulae utilize multiple ECG parameters and accompanying weighting coefficients and allow data obtained from any given patient to be used in calculating that patient's ECG Superscore results. ECG Superscores have retrospectively optimized accuracy for identifying and screening individuals for underlying heart disease and / or for determining the risk of future cardiac events. They thus have greater predictive value than that of any conventional or advanced ECG measurement alone or of any non-optimized combinations of conventional or advanced ECG measurements that have been used in the past. Ongoing optimization of ECG Superscore diagnostic and predictive accuracy may be realized through the iterative adjustment of Superscore formulae based on the incorporation of data from new patients into the database and / or from longitudinal follow-up of the disease and cardiac event status of existing patients.

Thousands of process and equipment measurements are gathered by the modern digital process control systems that are deployed in refineries and chemical plants. Several years of these data are historized in databases for analysis and reporting. These databases can be mined for the data patterns that occur during normal operation and those patterns used to determine when the process is behaving abnormally.These normal operating patterns are represented by sets of models. These models include simple engineering equations, which express known relationships that should be true during normal operations and multivariate statistical models based on a variation of principle component analysis. Equipment and process problems can be detected by comparing the data gathered on a minute by minute basis to predictions from these models of normal operation. The deviation between the expected pattern in the process operating data and the actual data pattern are interpreted by fuzzy Petri nets to determine the normality of the process operations. This is then used to help the operator localize and diagnose the root cause of the problem.

The software, methods and system of the current invention creates an interactive, auto-execution financial trading platform with unique forecasting algorithms, trading graphs and data mining features. The platform uses a univariate and multivariate architecture that is designed to improve performance of predictors and speed up calculations. Trading graphs, data mining features and predictive algorithms are predominantly based on fractal mathematics and Chaos theory. Even the unique software architecture is fractal in nature. All of these features are intended to be used individually or collectively to improve forecasting performance of financial markets. The above mentioned components also make it easier to manage a portfolio of securities and / or futures.

Methods and systems to detect abnormal operations in a process of a process plant include collecting on-line process data. The collected on-line process data is generated from a plurality of dependent and independent process variables of the process, such as a coker heater. A plurality of multivariate statistical models of the operation of the process are generated using corresponding sets of the process data. Each model is a measure of the operation of the process when the process is on-line at different times, and at least one model is a measure of the operation of the process when the process is on-line and operating normally. The models are executed to generate outputs corresponding to loading value metrics of a corresponding dependent process variable, and the loading value metrics are utilized to detect abnormal operations of the process.

Machine condition monitoring on a system utilizes a wireless sensor network to gather data from a large number of sensors. The data is processed using a multivariate statistical model to determine whether the system has deviated from a normal condition. The wireless sensor network permits the acquisition of a large number of distributed data points from plural system modalities, which, in turn, yields enhanced prediction accuracy and a reduction in false alarms.

A method and system for monitoring a process in a process plant includes collecting data from a process control system within the process plant, where the data is representative of a normal operation of the process when the process is on-line and operating normally, performing a multivariate statistical analysis to represent the normal operation of the process based on a set of collected on-line process data comprising a measure of the normal operation of the process when the process is on-line and operating normally, and representing a real-time on-line operation of the process using monitored on-line process data comprising a measure of a real-time operation of the process when the process is on-line as an input to the representation of the normal operation of the process.

The invention relates to a data driving method of fault detection and fault separation of a drone flight control system. The method comprises steps of based on actual flight data under normal and fault conditions of a drone, by use of normal data, establishing a data model based on multivariable statistical analysis and acquiring thresholds of T2 monitoring statistic quantity and SPE monitoring statistic quantity; by use of fault data, calculating T2 monitoring statistic quantity and SPE monitoring statistic quantity of each sample point after the occurrence of a fault and comparing the statistic quantities with the thresholds so as to obtain fault detection results; by use of a contribution graph-based method, calculating contribution values to two statistical results of each variable after the occurrence of the fault so as to obtain an accumulated contribution graph; and finally, by use of the contribution graph and the accumulated contribution graph, determining fault variables andobtaining fault separation results. According to the invention, an aliasing problem of different types of faults in the actual flight system can be effectively solved; and reference basis is providedfor analysis of drone system designing, fault positioning and fault transmission methods.

A device for assessing the effects of diffusible molecules on electrophysiological recordings from multiple neurons allows for the infusion of reagents through a cannula located among an array of microelectrodes. The device can easily be customized to target specific neural structures. It is designed to be chronically implanted so that isolated neural units and local field potentials are recorded over the course of several weeks or months. Multivariate statistical and spectral analysis of electrophysiological signals acquired using this system could quantitatively identify electrical “signatures” of therapeutically useful drugs.

A system and method of monitoring and diagnosing on-line multivariate process variable data in a process plant, where the multivariate process data comprises a plurality of process variables each having a plurality of observations, includes collecting on-line process data from a process control system within the process plant when the process is on-line, where the collected on-line process data comprises a plurality of observations of a plurality of process variables, performing a multivariate statistical analysis to represent the operation of the process based on a set of collected on-line process data comprising a measure of the operation of the process when the process is on-line, where the representation of the operation of the process is adapted to be executed to generate a result, storing the representation of the operation of the process and the set of collected on-line process data, and generating an output based on a parameter of the representation of the operation of the process, where the parameter of the representation of the operation of the process comprises one or more of a result generated by the representation of the operation of the process, a process variable used to generate the representation of the operation of the process and the set of collected on-line process data.

A near real-time system and method for continuous online monitoring of a plurality of operations in a continuous chemical process facility is described. The method of monitoring the operations is based on a multivariate statistical model developed using off-line, selected process-specific historical process data. Such a model is used by an online monitoring system to monitor the continual operation of a chemical manufacturing facility or refinery in real-time from a remote location. Such real-time monitoring allows for determination of whether one or more of the plurality of operations are operating within their normal operational parameters. This real-time, continuous monitoring system can further be used to predict impending failures or trouble-spots within the continuous production process, or to minimize catastrophic process failures which may occur in a continuous chemical manufacturing process. Process variables, or ''tags'', that are most likely related to predicted process failures can be identified by the model system, such that appropriate control actions can be taken to prevent an actual process failure occurrence, which can lead to costly production down times.

A multivariate product quality monitoring method oriented to a digital workshop includes the steps: building a quality information acquisition scheme suitable for the digital workshop; building a quality control and improvement model oriented to the digital workshop, and particularly performing multivariate process capacity analysis based on an improved principal component analysis method according to multiple quality characteristics of key processes of key products of a machining workshop; controlling and diagnosing multivariate product by the aid of principal component analysis technology to solve the problem that a multivariate statistical control chart difficultly diagnoses and positions process exception. The quality assurance capability of the key processes of the key products can be quantitatively evaluated by the workshop, and a source of a quality problem is timely positioned when the quality problem arises, so that further cost loss is avoided.

An apparatus, system, method, and computer readable medium containing computer-executable code for implementing image analysis uses multivariate statistical analysis of sample images, and allows segmentation of the image into different groups or classes, depending on a correlation to one or more sample textures, or sample surface features. In one embodiment, the invention performs multivariate statistical analysis of ultrasound images, wherein a tumor may be characterized by segmenting viable tissue from necrotic tissue, allowing for more detailed in vivo analysis of tumor growth beyond simple dimensional measurements or univariate statistical analysis. Application of the apparatus and method may also be used for characterizing other types of samples having textured features including, for example, tumor angiogenesis biomarkers from Power Doppler.

The method of the present invention provides a fast, robust, and automated multivariate statistical analysis of gas chromatography / mass spectroscopy (GC / MS) data sets. The method can involve systematic elimination of undesired, saturated peak masses to yield data that follow a linear, additive model. The cleaned data can then be subjected to a combination of PCA and orthogonal factor rotation followed by refinement with MCR-ALS to yield highly interpretable results.

A method and apparatus for detecting faults. A set of data samples is received, the set of data samples including multiple process variables. One or more multivariate statistical models are adapted, wherein adapting includes applying a change to at least one univariate statistic of the one or more multivariate statistical models if the change is greater than a threshold value. The one or more multivariate statistical models are used to analyze subsequent process data to detect faults.

An identification method of the brewing distilled spirit and the matching distilled spirit by alcohol includes the below processes: (1) setting the brewing and matching distilled spirit fingerprint chart by the coulomb array HPLC and getting the fingerprint chart data; (2) setting the fingerprint chart static module; (3) analysis of the detecting distilled spirit sample by the above method and getting the coulomb array HPLC data to identify by the fingerprint chart module. The invention is to analyze the distilled spirit quality by the HPLC-ECD and set the fingerprint module using the multivariate statistical software, also it can distinguish the original drink with different concentration and quality and has high sensitivity and visual result. So the method of invention can set the fingerprint chart module of different kind drink to form the fingerprint chart bank.

Localization methods and methods for localizing a light source using multivariate statistical analysis. In particular, a multi-variate distribution, such as a multi-variate normal distribution, may be used to localize photons originating from a light source and, in particular, may be used to analyze photon position maps acquired by Photon Event Distribution Sampling (PEDS). The multi-variate distribution assigned to each of the photons in the photon position map may be summed to predict a most probable location for the light source.

The invention discloses an alfalfa drought tolerance identification method, comprising the following steps: after sterilization on seeds, carrying out a conventional sprouting experiment, after a seedling has 3-4 main leaves, performing thinning and final singling, reserving materials whose plant size and height are roughly consistent, and carrying out a water controlling experiment in a greenhouse; in the 8th-11th day, taking the plants out to count the number of roots of each plant of alfalfa, including the number of main roots, lateral roots, and fibrils on the lateral roots; after processing for 20 d, respectively measuring seedling height, fresh weight of root systems, dry weight of root systems, leaf chlorophyll contents, stomatal conductance, leaf free water content, leaf surface bound water content, proline content and root volume of each processing group; performing data reduction, calculating average values, and calculating a drought tolerance coefficients and a comprehensive drought tolerance value of each variety; and determining salt tolerance of the varieties according to the comprehensive drought tolerance value. The method performs multivariate statistical analysis on agronomical characters and indexes of an alfalfa seedling stage, so as to perform comprehensive judgement and evaluation on the drought tolerance of alfalfa.

In order to overcome the defects of an existing gingival margin curve extraction mode, the present invention discloses a gingival margin curve design method for a personalized implant tooth. The gingival margin curve design method for the personalized implant tooth comprises the following steps of: a step 1 of respectively reconstructing gingival margin profiles of a residual tooth of a patient suffering from tooth missing and a three-dimensional dental model of a sample, extracting feature regions of gingival margin curves according to an obtained maximum principal curvature value, extracting gingival margin feature lines of the residual tooth of the patient suffering from tooth missing and the sample by utilizing a granular computing and cellular automaton combining method, then respectively fitting the gingival margin feature curves of the residual tooth of the patient suffering from tooth missing and the dental model of the sample, and finally, constructing a single gingival margin curve of the residual tooth of the patient suffering from tooth missing and the sample; a step 2 of constructing a gingival margin biological multivariate statistical analysis model of the sample; and a step 3 of designing a personalized gingival margin curve of a missed tooth of the patient. The method disclosed by the present invention aims to improve accuracy and efficiency of designing the implant tooth gingival margin curve, improve the repaired gingival margin profile form of the implant tooth, and improve a repair success rate of the personalized implant tooth.