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 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.