36results about How to "High correlation coefficient" patented technology

The invention discloses a nearest neighbor hyperspectral image classification method based on dictionary and band recombination. The realization steps include: using the spatial information of the hyperspectral image to perform L-neighborhood mean value processing on each pixel; The point mean value band is reorganized and divided into n-equal sub-bands; some pixels are randomly selected to form a dictionary, and other pixels form a test sample set, and the dictionary and test sample set are divided into n sub-dictionaries and sub-test sample sets according to sub-bands and compared correspondingly The sub-dictionary is used for nearest neighbor discrimination to obtain n initial classification maps; n-KNN discrimination is performed to obtain the final result map. The invention solves the problems of low classification accuracy, poor classification effect, high time complexity of the ordinary space-spectrum combination method, and loose combination of space-spectrum information. ‑ Spectral combination method for classification, in a short period of time, a higher precision classification map was obtained. High precision and low time complexity.

The invention discloses an improved double-variable fusion method of soil moisture products. In the method, two sets of soil moisture product data are input, time offsets of instrumental variables are set for the two sets of soil moisture products, and the optimal time offset is selected. Based on this, the optimal instrumental variable is obtained, and the weights of the two sets of soil moisture products are calculated through the optimal instrumental variable, and a fusion product is formed accordingly to obtain accurate soil moisture information.

An improved IHS transformation remote sensing image fusion method and system, comprising the steps of (1) resampling a multispectral image to achieve the resolution of a panchromatic image; (2) performing IHS transformation on the resampled multispectral image, Obtain I, H, and S components respectively; (3) simulate a new panchromatic image; (4) take the I component image histogram as a reference, perform histogram matching on the new panchromatic image, and obtain the matched panchromatic image I new ; (5) full-color image I after histogram matching new Replacing the I component to perform inverse IHS transform to complete remote sensing image fusion. The purpose of the present invention is to improve the IHS transformation and fusion rules, so that the spectral range of the panchromatic image and the multispectral image are consistent, and the brightness and contrast of the fusion result are not lower than those before fusion.

The present invention proposes an improved method for preparing an ino-inositol test inoculum suspension, comprising the steps of: A, resuscitating the inoculum inoculum to obtain the resuscitated strain; B, inoculating the resuscitated strain into the culture medium for inositol determination, and obtaining the inoculum Bacteria-based solution; C. The absorbance of the inoculated bacteria-based solution is detected, and the inoculated bacteria-based solution with an absorbance of 0.2 to 0.4 is taken for subsequent steps; D. The inoculated bacteria-based solution is placed in a sterile centrifuge tube, and after centrifugation and cleaning, Add 0.9% sterile saline, oscillate and mix to prepare a concentrated bacterial suspension; select an appropriate amount of concentrated bacterial suspension and add it to 0.9% sterile saline, and control the concentration within the range of 0.55-0.65 McFarland turbidity to obtain the inoculum Suspension; E. Take the inoculum suspension for testing the inositol content. In step C of the present invention, the inoculum base liquid whose absorbance is greater than 0.4 is replaced by the recovered strain in step B, and steps B to E are carried out again. The invention has the characteristics of easy operation and high accuracy.

The invention provides an image analyzer and a method for measuring line fractal dimensions of a granular material, solving the problems that the conventional image analyzer can only obtain two-dimensional image data of the granular material, the line fractal dimensions of the granular material can be only obtained by using power exponents and fractal dimension relationship regression analysis after the two-dimensional image data are processed, and moreover, the regression analysis coefficient is relatively low and the fractal dimension result cannot be directly read. The technical key points are as follows: a data processing system comprises a measuring and control module, a granular image processing module and a line fractal dimensional calculation module, and a method is used in match with the image analyzer. According to the image analyzer and the method, by adding the granular image processing module and the line fractal dimensional calculation module in the measuring and control software of a granular image analysis system, a new granular two-dimensional image outline fractal dimension measurement function is added to the granular image analysis system on the basis of the conventional functions, and the measurement result of the two-dimensional image line fractal dimensions of the granular material can be directly output.

The invention provides a wireless sensor network node positioning method based on a compressed sensing theory. Firstly, special information sent by beacon nodes is used for obtaining communication information of all nodes to the beacon nodes; and then a sampling matrix is obtained through the communication information obtained by the utilization of the beacon nodes, compressed communication information is obtained through target nodes, and correlation coefficients of the target nodes and all beacon nodes are obtained through a compressed sensing algorithm. Lastly, a weight coefficient of each beacon node to the target nodes is obtained by using the correlation coefficients, and an estimate position of each target node is obtained by the utilization of a centroiding algorithm. According to the wireless sensor network node positioning method based on the compressed sensing theory, the compressed sensing theory is introduced, and the correlation of the target nodes and the beacon nodes on geographic positions is fully dug. Due to the fact that the wireless sensor network node positioning method based on the compressed sensing theory fulfills four conditions, the wireless sensor network node positioning method based on the compressed sensing theory is reliable, effective, general in application, and suitable for node self-positioning of large scale networks.

The invention relates to a weak transient zero sequence current fault feature extraction method based on PSO (Particle Swarm Optimization). The method comprises the steps: firstly setting a potential function parameter as an optimization object, and forming a group through random initialization particles; secondly carrying out the feature extraction of a weak transient zero sequence current through a variable scale bistable state system, and calculating a cross correlation coefficient between an initial current and the current; thirdly taking the maximization of the cross correlation coefficient as a measurement rule of the detection effect of the transient zero sequence current and the basis for parameter optimization selection, and updating particle position and flying speed according to a fitness value; finally stopping updating and outputting an optimal parameter when the number of evolution times reaches a maximum threshold value, and carrying out the feature extraction of the transient zero sequence current under the condition: completing the fault feature extraction if the cross correlation coefficient is greater than 0.85; or else, carrying out optimization again till the cross correlation coefficient is greater than 0.85, which indicates that the fault feature extraction is completed.