6 results about "Correlation coefficient" patented technology

The embodiment of the invention provides a feature processing method and device for a user classification model. The method comprises the steps that firstly, label data tables and first feature tablesare acquired, wherein each first feature table records a plurality of features of a user; and for each feature in each first feature table, a feature IV value is calculated, and first screening operation is performed on the features based on the IV value to obtain a corresponding second feature table. Then, the second feature tables and features in the second feature tables serve as first class nodes and second class nodes respectively, a bipartite graph is constructed, the minimum number of the first class nodes connected to all the second class nodes is determined in the bipartite graph, and then corresponding M second feature tables are obtained; then, the M second feature tables are combined to obtain a comprehensive feature table, and correlation coefficients between features are calculated based on the comprehensive feature table; and a second screening operation is performed on the features based on the correlation coefficient to obtain a plurality of selected features for training a user classification model.

The invention discloses a wind turbine generator key component reliability modeling method based on distribution function optimization, and the method comprises the steps: carrying out the distribution function fitting of fault interval time data of each key component of a wind turbine generator through five types of common reliability distribution functions; and adopting a maximum likelihood estimation method to perform estimation and effectiveness analysis on parameters of each distribution function. On the basis, the goodness of fit of different distribution functions of the key componentsis analyzed by utilizing a correlation coefficient method, a grey correlation degree method, a minimum distance method and a correlation entropy method, fitting optimization indexes of all the distribution functions of the key components are fused based on a DS evidence theory, the distribution functions of the key components are optimized, and thus the distribution type of the fault interval timeof each key component and the reliability function of the key components are determined; and the reliability function of the whole wind turbine generator is constructed by taking the reliability function of the key components as input.

[Problem] To provide a simple and economical device capable of providing an excellent sound field in accordance with the listener's preferences by adjusting the listener's interaural correlation coefficient. [Solution] A sound field adjustment filter (5) is provided with a pair of filter circuit groups (5L, 5R) corresponding to a left and right channel. This sound field adjustment filter divides a desired frequency band of the audio signal into multiple frequency bands and assigns prescribed transmission characteristics so as to generate a sound field adjustment signal for each frequency band such that a prescribed impulse response is configured cooperatively for the entire desired frequency band of the audio signal. The transmission characteristics adjust the audio signal for each split frequency band by the addition of time delay and gain. By means of operation output units (4L, 4R), the sound field adjustment filter (5) adds the sound field adjustment signals generated by each of the filter circuit groups (5L, 5R) to the audio signal of the other of the channels, and outputs the result to stereo speakers (2). The opening angle of virtual speakers with respect to the listener is changed by adjustment of the sound field adjustment signals so as to approximate the interaural correlation coefficient of a specific diffuse sound field.

The invention relates to a method for processing mass concentration data of a suspended sediment based on a laser particle size analyzer. The method mainly comprises the following steps of acquiring volume concentrations of suspended particles with different particle sizes at each site of an observation sea area by use of the laser particle size analyzer; performing mass control on the original data of the acquired volume concentrations of the suspended particles with different particle sizes; performing linear fitting according to the mass concentration of the suspended sediments measured bya chemical weighing method at partial sites and the total volume concentration of the suspended particles at corresponding positions by use of a least square method to acquire a fitting coefficient and a correlation coefficient; and fitting the mass concentration of the sediment at each site according to the total volume concentration of a suspended matter at each site of the surveyed sea area byuse of a fitting relation acquired by linear fitting.

The invention discloses a power grid voltage measurement abnormity identification method based on a distance correlation coefficient, and the method comprises the steps of automatically calculating adistance correlation coefficient matrix among a plurality of intervals through a given multi-dimensional voltage historical data file F1 at the same voltage level, and learning to find out a thresholdvalue for identifying the abnormity of voltage measurement data; calculating a distance correlation coefficient matrix among a plurality of intervals by utilizing the to-be-identified voltage data file F2; and judging a voltage measurement data state in the new multi-dimensional voltage data file by combining a threshold value which is automatically learned by utilizing historical voltage data and is used for identifying the abnormity of the voltage measurement data, thereby realizing the voltage measurement and transmission state identification of a transformer substation voltage transformer, a secondary transmission and transformation loop and a measurement and control device. According to the invention, the slight measurement abnormality of the voltage transformer can be discovered inadvance by applying the existing power grid voltage data without power failure, maintenance and hardware installation, and the identification precision is high.

The invention relates to a machine tool linear axis thermal temperature sensitive point optimization method based on an independent variable selection criterion, which is characterized in that in different temperature states, a machine tool linear axis positioning error is measured, the independent variable selection criterion is utilized to select an optimal regression subset so as to select an optimal temperature sensitive point, and a thermal positioning error model is established. The method comprises the following steps of: acquiring a temperature sensitive point of a machine tool, acquiring a geometric positioning error model, superposing with the geometric positioning error model to obtain a comprehensive positioning error model, measuring the temperature at the temperature sensitive point of the machine tool in real time, and the like, and effectively solving the problem of collinearity among temperature variables by adopting a temperature sensitive point selection method of a degree-of-freedom adjustment negative correlation coefficient maximum criterion Ra2 and a corrected AIC criterion. And multiple regression analysis is adopted, a temperature sensitive point selection method and a thermal error modeling method are unified, and the prediction precision and robustness of a thermal error model are improved.