292 results about "Analysis of variance" patented technology

The invention discloses an information entropy variance analysis-based abnormal traffic detection method. According to the method, a large quantity of Internet user access logs are obtained, and collected data is processed via a system; attack behaviors or abnormal behaviors can be rapidly identified and recorded via big data mining, association and statistical analysis; invasive attack alarm information data can be formed; a complete attack path can be constructed via relevant invasive attack data analysis, and therefore an object of invasion tracking and positioning can be attained. Via use of the abnormal traffic detection method, behavior after events can be traced and machine learning of user access behaviors can be realized, a false alarm rate of a system can be lowered, a network traffic detectability set is put forward, a baseline for normal network traffic is described, and reference is provided for abnormity detection.

Embodiments for monitoring one or more utilities consumed within a monitored area including detecting an amount of a first utility consumed by a load associated with a device and an amount of a second utility consumed by a load associated with the device. The identity of the device is determined based on the amount of the first and second utility consumed. A utility monitoring method is disclosed that includes measuring an amount of a utility consumed by a first device at a first time and an amount of a utility consumed by a second device at a second time. The identity of the first device is determined based on the measured consumption of the first and second devices at the first and second time. In certain implementations, the electricity meter uses an effective variance analysis of the conductance waveform on an electrical circuit to identify specific appliances.

A system for analyzing the performance of a network includes a data collection agent that collects performance data including first and second sets of measurements of a single network parameter. First and second variance statistics are calculated. A user is alerted about potential network performance problems based on whether a predetermined relationship exists between the variance statistics. The user may be notified by sending an e-mail to the user; and / or sending a fax to the user; and / or initiating a phone call to the user. The user may be alerted by a message to a PDA or a cellular telephone.

A system for facilitating the analysis of a transaction request. The system includes an interface. The interface is configured to receive input data related to the transaction request. The input data includes at least a selection of a variance transaction or a recourse transaction. The system further includes a transaction request processor configured to generate a transaction assessment based on at least the input data and a reporting engine configured to provide the transaction assessment.

One embodiment of the present invention sets forth a technique for translating application programs written using a parallel programming model for execution on multi-core graphics processing unit (GPU) for execution by general purpose central processing unit (CPU). Portions of the application program that rely on specific features of the multi-core GPU are converted by a translator for execution by a general purpose CPU. The application program is partitioned into regions of synchronization independent instructions. The instructions are classified as convergent or divergent and divergent memory references that are shared between regions are replicated. Thread loops are inserted to ensure correct sharing of memory between various threads during execution by the general purpose CPU.

A non-invasive tool for skin disease diagnosis would be a useful clinical adjunct. The purpose of this study was to determine whether visible / near-infrared spectroscopy can be used to non-invasively characterize skin diseases. In-vivo visible- and near-infrared spectra (400-2500 nm) of skin neoplasms (actinic keratoses, basal cell carcinomata, banal common acquired melanocytic nevi, dysplastic melanocytic nevi, actinic lentigines and seborrheic keratoses) were collected by placing a fiber optic probe on the skin. Paired t-tests, repeated measures analysis of variance and linear discriminant analysis were used to determine whether significant spectral differences existed and whether spectra could be classified according to lesion type. Paired t-tests showed significant differences (p<0.05) between normal skin and skin lesions in several areas of the visible / near-infrared spectrum. In addition, significant differences were found between the lesion groups by analysis of variance. Linear discriminant analysis classified spectra from benign lesions compared to pre-malignant or malignant lesions with high accuracy. Visible / near-infrared spectroscopy is a promising non-invasive technique for the screening of skin diseases.

Method, apparatus, and system, including computer program products, implementing and using techniques for time series analysis, wherein the time series exhibit trend and / or seasonality. Model parameters of the time series data are determined by selecting and / or suggesting a most appropriate combination of trend and seasonality of the time series data based on analysis of variances of transformed time series data.

Method, apparatus, and system, including computer program products, implementing and using techniques for time series analysis, wherein the time series exhibit trend and / or seasonality. Model parameters of the time series data are determined by selecting and / or suggesting a most appropriate combination of trend and seasonality of the time series data based on analysis of variances of transformed time series data.

The invention discloses a wine origin identification technical method, relating to a wine inorganic trace element detection method and a wine origin characteristic information extraction data processing technical method, and belonging to technical field of wine product authenticity identification. The method comprises the following main steps of: a) selecting wine samples from different origins; b) performing resolution pretreatment on the samples by nitric acid; c) determining the inorganic element contents in the samples by a plasma isotope mass spectrometer; and d) after processing the obtained data, constructing a wine origin identification technical model by adopting different multivariate data processing technologies (variance analysis, principal component and neutral network), and inputting data of wine with unknown origins in the wine origin identification technical model to realize effective identification of origin attributes of wine. The wine origin identification technical method provided by the invention is beneficial to solving the technical problem of wine origin identification in China at present, and has an important significance on standardizing the wine market order.

The invention discloses a forecasting method and a device of telephone traffic in an ordinary holiday of a telecommunication network, wherein the method comprises the following steps: acquiring the history value of telephone traffic of the network as history sample data, pre-processing the history sample data and obtaining normal sample data; carrying out modeling and forecasting on the normal sample data by utilizing a forecasting model; utilizing a variance analysis method to carry out a significance test of difference of the telephone traffic in holidays and the telephone traffic at ordinary time on the normal sample data; if the difference of the telephone traffic in holidays and the telephone traffic at ordinary time is significant, carrying out correction on forecasting values of the forecasting model and obtaining a final forecasting value; or the forecasting value of the forecasting model is the final forecasting value. The invention also discloses a forecasting device of telephone traffic in an ordinary holiday telecommunication network, so the invention can carry out accurate forecasting on the telephone traffic in the ordinary holiday.

The invention discloses an image quality evaluation method based on a visual characteristic. The method is characterized by: firstly, converting original images into a xyY space or a LCH space, processing a component Y or a component C so as to obtain a group of test images; then, finding at least one JND (just noticeable difference) critical image; calculating differences of brightness (BR), color saturation (CS) and Gaussian function variance parameters in the original images and the JND critical image, wherein average values of the differences are the JND values of the BR, CS and contour rendering (CR) of the original images respectively; and then, carrying out mean calculation on the JND values of the different original images and determining the final JND values; taking the JND as a unit to change different attributes of the image at different degrees respectively; using a visual perception test to test the subjective image quality; then, using a regression analysis to establish a relation model of the image quality and the image attributes; and researching influences of the different attributes of the images according to a variance analysis. By using the method of the invention, influence on image quality which can be perceived by human eyes when improving the display parameter can be quantitatively evaluated.

The present invention provides methods for analyzing measurement errors in measured signals obtained in an experiment, e.g., measured intensity signals obtained in a microarray gene expression experiment. In particular, the invention provides a method for transforming measured signals into a domain in which the measurement errors in the transformed signals are normalized by errors as determined from an error model. The methods of the invention are particularly useful for analyzing measurement errors in signals in which at least portion of the error is dependent on the magnitudes of the signals. Such transformed signals permit analysis of data using traditional statistical methods, e.g., ANOVA and regression analysis. Magnitude-independent errors can also be used for comparing level of measurement errors in signals of different magnitudes.

The invention discloses an urban standard cyclic working condition constructing method based on genetic algorithm optimization. The urban standard cyclic working condition constructing method includes the following steps of testing vehicle working conditions, dividing a micro stroke, calculating micro stroke characteristic parameters, analyzing a main component, K-clustering of the micro stroke, optimizing a working condition segment genetic algorithm and synthesizing all kinds of optimized representative working condition segments into one standard cyclic working condition. Based on practical driving working condition test data in a certain city, the micro stroke is divided, K-clustering is carried out, the optimal cluster number is determined through variance analysis, the genetic algorithm is used for fitting and modifying all kinds of working condition segments, the error between the working condition segments and a cluster center is reduced, and the accuracy of the constructed urban standard cyclic working condition is improved.

Method and apparatus for querying a computerized database, such as a distributed database associated with an automated manufacturing process and linked across a computer network. A query engine distributes a desired range of data values to be obtained from the database across a plurality of different query statements. The query statements are simultaneously executed to access the database and transfer associated data subsets into a memory space, after which the data sets are arranged to form the desired range of data values. Preferably, the query engine executes each query statement using a different login account. An auto-brake function is preferably employed to limit input / output (I / O) transfer time for each query statement. Analysis tools perform analysis such as logistic regression and analysis of variance (ANOVA) upon the retrieved data values.

The invention provides a hidden failure diagnostic method of a digital transformer protector measuring loop, which belongs to the technical field of secondary power device failure diagnosis. The hidden failure diagnostic method comprises the following steps: 1. a hidden failure diagnostic computer collects the current measuring value amplitude at the high voltage side and the low voltage side of a differential protector of the digital transformer and the current and voltage measuring values of a back-up protector (1) and a back-up protector (2) in real time; 2. the collected current and voltage measuring values are respectively analyzed and compared by a method of analysis of variance according to the relativity of the input information of the differential protector as well as the back-up protector (1) and the back-up protector (2); and 3. the hidden failure diagnostic result is analyzed and outputted. The method can monitor whether the current and voltage measuring values of the digital transformer protector as well as the back-up protector (1) and the back-up protector (2) are normal or not in real time and judge whether the measuring loops of the digital transformer protector as well as the back-up protector (1) and the back-up protector (2) have failure or not hereby.

A VLSI implementation system of a revised histogram equalization image based on statistical property comprises a block scanning element, a cumulative distribution function unit, a mean value, a variance analysis unit, a mapping table, an amendment element of grey mapping function, a grey mapping processing unit. The invention can improve the phenomenon of integral dark and integral bright caused by the uneven grayscale distribution of the digital image, which reasonably allocates distribution of the grayscale of the image and is suitable for the sequential image treatment processing of fingerprint identification.

A system for performing an inventory count. A scan of an object is initiated according to a profile in order to perform the inventory count of the object. A scan result is compared with a recorded level for the object to determine if a variance exists between the scan result and the recorded level. A variance analysis is performed if the variance exists.

The acoustic impedance of the respiratory system can be inferred from oscillations that are generated in an airway of a subject. The impedance describes the frequency-dependent relation between the resulting oscillations in flow and pressure. When the impedance varies from inspiration to expiration, it has to be estimated with a high time resolution. A method is provided that reliably estimates the impedance in time intervals that are short enough for physiological purposes. A simple version of the uncertainty principle has been derived for discrete time and frequency. A discrete time-frequency transform has been developed that gives an optimal time-frequency resolution according to this principle. The transform is orthonormal, which permits an analysis of variance in the discrete time-frequency domain. The impedance follows from bivariate least-squares analysis in the time-frequency domain, under the assumption that noise is present in both flow and pressure.

Routing and connectivity in the Internet is largely governed by the dynamics and configuration of the Border Gateway Protocol (BGP). A configuration analysis toolkit enables network operators to discover, analyze and diagnose their BGP configuration, policies and peering relationships. Statistical variance analysis in such a toolkit exploits the recurrence of policies in large networks for analysis. In a large network, policies that have similar functions are examined, e.g. all inbound route maps associated with customer autonomous systems. For n occurrences of similar policy P, it is possible to flag k deviant configurations, and evaluate the probability that the deviant configurations are in error. Analysis and policy visualization of implemented BGP configurations enable service providers to move from checking of low-level configuration to extracting analyzable BGP level policy information across a multitude of BGP routers in order to validate consistency of policies and operator intent across distributed BGP configurations using a flexible, customizable analysis engine.

The invention belongs to the technical field of biological monitoring environment, and specifically relates to a shellfish monitoring method for ocean oil spill pollution. The shellfish monitoring method comprises the steps of utilizing typical bivalve mollusk such as short-necked clam and chlamys farreri in China to determine the shellfish visceral mass autioxidant enzyme activities including superoxide dismutase, glutathione glutathione S-transferase, peroxidase, glutathione peroxidase and catalase activity, integrating the enzyme activities so as to form an integration biomarker responding index (IBR), establishing a dose-effect relationship between the IBNNR and petroleum concentration, adopting a one-dimensional variance components method (ANOVA) to carry out notable difference analysis, determining the forcing degree of petroleum pollution on organisms, and finally judging pollution level of the ocean oil spill.

A method for reducing the weight of saloon car bodies based on the response surface method includes: a, improving the structure of the spare parts to select the optimum structure, b, carrying out code transformation to the test design variables, c, arranging test points with the isometiric design method to determine a test plan, d, setting up a response surface model based on the test result, e, validating the effectiveness of the response surface model, f, optimizing the spare parts of the body taking the quality of the spare parts as the target function and the energy absorption parameter as the restriction condition.

The invention provides a detection method for producing areas of Xihulongjing tea based on genetic algorithm optimization. The method is characterized in that an electronic nose is utilized to acquire fingerprints of the smell of Xihulongjing tea from different producing areas, sensors having special contribution to modeling of the producing areas are screened out based on analysis of average fingerprints and a principal component score chart through three key techniques of genetic algorithm, i.e., a roulette selection method, a single-point crossover method and a simple mutation method, with an integral recognition rate as a fitness function, optimization is carried out so as to reduce the amount of sensors needed in modeling, and fingerprint response values of the sensors are subjected to matrix analysis through an F value obtained through variance analysis and principal component load.

A security method compares a present verbal utterance with a previously recorded verbal utterance by comparing frequency domain representations of the utterances, with multiple repeat utterances forming a basis for determining a variation in repetitious performance by an individual, and similar differences between enrollment and challenge utterances forming a basis for a similar analysis of variance between enrollment and challenge utterances. In one embodiment a set of enrollment data is searched by each challenge until either a match is made, indicating an action, possibly dependent upon the specific match, or no match is made indicating an abort.

A method and system of analyzing signal-vector data from first order sensors including providing a training data set, adjusting the training data set using a background adjustment technique, normalizing and transforming the training data set into wavelet coefficients, using an automated analysis of variance feature selection technique and a pattern recognition technique to classify the training data set. The method and system may also include performing these operations on an unknown sample data set collected under unknown conditions and comparing the unknown sample data set to the classification model to provide an identity of the unknown conditions associated with the unknown sample data set. The present invention is also directed to a computer system for analyzing signal-vector data according to this method and a sensing system that includes a sensor and a microprocessor on which is stored a classification model for real-time sensing of unknown sample data sets.

The invention discloses an early warning method for a lithium ion battery based on an artificial intelligence algorithm and system. The method comprises steps: the operation data of each conventionalparameter in multiple conventional parameters of each of multiple lithium ion batteries are acquired; the acquired operation data of each conventional parameter are classified and stored to establisha lithium ion battery operation database; the conventional parameters are evaluated by using the artificial intelligence algorithm and the operation data in the database, and the evaluation value of each lithium ion battery is acquired; the deviation degree of each lithium ion battery is calculated through variance analysis based on the evaluation value of each lithium ion battery; a lithium ion battery whose deviation degree is greater than a deviation threshold is determined to a to-be-monitored lithium ion battery; and whether the operation data of the conventional parameters of the to-be-monitored lithium ion battery exceed an early warning preset value is judged, and when the operation data of the conventional parameters of the lithium ion battery exceed the early warning preset value, an early accident warning for the lithium ion battery is given.

The invention discloses a method for carrying out fusion processing on meteorological data and generating a numerical weather forecast, which comprises the following steps: step 1, collecting and receiving various meteorological element data from meteorological observation detection equipment or CCTV to obtain a meteorological element set X1; step 2, performing standardized preprocessing on the acquired meteorological element data to obtain a standardized meteorological element set X; step 3, performing three-dimensional data variation assimilation on the meteorological element set X, performing characteristic error analysis and cross covariance analysis on the data in the meteorological element set X to obtain a covariance error root mean square of each data in the meteorological elementset X, and obtaining an optimal meteorological element data type according to the covariance error root mean square; step 4, performing WRF numerical weather forecast mode compiling according to the optimal meteorological element type; and step 5, performing forecast post-processing on the WRF mode result to generate meteorological element numerical forecast.

The invention discloses a fatigue driving identification method based on driving behaviors and eye movement characteristics. The method comprises the steps that 1) a fatigue driving simulation experiment is designed, and the driving behavior data of a driver and the eye movement data of the driver under different fatigue states are collected through the experiment; 2) the experiment data are segmented and screened to establish a fatigue driving sample database; 3) a single-factor variance analysis method is used to carry out statistic analysis on the significance of the difference of driving behavior parameters and eye movement characteristic parameters of the driver under different fatigue states, and the optimal time window of each characteristic parameter is found out; 4) bivariate Spearman correlation analysis is carried out on initially selected characteristic parameters; 5) the optimal characteristic parameters are selected; 6) a BP neural network identification model for fatigue driving is established; and 7) Matlab software is used to write a model program, and a training sample and test sample set are randomly selected to train the model and identify a fatigue state.

The present invention provides improved ANOVA methods for analyzing measured data and transformed data. The improved ANOVA method takes two data types as its input, one is the measurements, the other is a predetermined error associated with the measurements. The latter can come from a technology / platform-specific error model. Because of the additional input information, the statistical power is increased. The methods of the invention is particularly useful for analyzing gene or protein expression data.