30 results about "Fast ica" patented technology

The invention provides a rotating machine fault diagnosis method based on Fast ICA-spectrum kurtosis-envelope spectrum analysis. The method includes the steps that (1), an acceleration sensor is used for obtaining vibration acceleration test signals of a rotating machine; (2), the test signals are separated in a decoupling mode by the adoption of a Fast ICA method with negentropy maximized; (3), the spectrum kurtosis of the separated signals is calculated, and the separated signals capable of representing fault information best are screened out; (4), Hilbert envelope spectrum analysis is performed on the selected separated signals; (5), the frequency corresponding to the peak value of an envelope spectrum is compared with the fault character frequency of a bearing, so that a concrete fault is diagnosed. The effectiveness of the method is verified well by the inner ring fault diagnosis of a rolling bearing of the rotating machine, the fault information is obviously increased, the precision of the fault diagnosis is greatly improved, the fault diagnosis method is easy to achieve and good in real-time performance, and it is illustrated that the rotating machine fault diagnosis method has good application prospects.

The invention discloses a method for objectively evaluating the quality of a three-dimensional image without a reference. According to the method for objectively evaluating the quality of the three-dimensional image without the reference, in the training stage, multiple original undistorted three-dimensional images and corresponding distorted three-dimensional images are selected to form a training image set, then dictionary training is conducted according to the Fast-ICA method, so that the visual dictionary table of each image in the training image set is constructed, and visual quality tables corresponding to the visual dictionary tables are constructed by calculating the frequency responses of each pixel point in each original undistorted three-dimensional image and each pixel point in the corresponding distorted three-dimensional image in the training image set under the conditions of different center frequencies and different directional factors; in the testing stage, for the tested three-dimensional image, a predicted objective evaluation value of the quality of the tested three-dimensional image is obtained by calculating the frequency responses of each pixel point in the tested three-dimensional image under the conditions of different center frequencies and different directional factors according to the constructed visual dictionary tables and the constructed visual quality tables. The method for objectively evaluating the quality of the three-dimensional image without the reference has the advantages that calculation complexity is low, and the relevancy between objective evaluation results and subjective sensing is high.

The invention relates to a J-wave detection and classification method, in particular to a J-wave detection and classification method based on Q-switched wavelet transform and high-order cumulants. The present invention first collects ECG data through an electrocardiograph, obtains two types of normal signal and J wave signal, uses stationary wavelet transform to detect R peak point, and intercepts 128 points after R point as initial data samples. Apply stationary wavelet transform and Q-switched wavelet transform to decompose initial samples and extract feature vectors. Input feature vectors to ensemble C4.5 decision trees. Then extract the feature vector of the test sample according to the above process, input it to the trained integrated C4.5 decision tree, and obtain the category attribute of the test sample. The present invention can more simply and conveniently obtain a feature vector with a lower dimension that is highly representative of the original signal through serial fusion and rapid ICA dimension reduction, and input it to the integrated decision tree classifier, which can be fast and efficient To realize the accurate classification of J wave signal.

The invention discloses a long-short code estimation method of a multi-speed long-short code direct sequence-code division multiple access signal. Firstly, according to the largest long scrambling code cycle and the smallest spreading code cycle of a received signal, the received signal is segmented twice to obtain a signal matrix, and according to a Fast-ICA algorithm, complex code fragments of all users are obtained through separation; then, with gradual reducing of information speeds, a user long-short code sequence is estimated, the complex code fragments obtained by separating the Fast-ICA algorithm are spliced to constitute a fuzzy sequence, a secondary delay multiplying method is adopted to remove sequence fuzziness and spreading code interference, and in combination of a cyclotomiccoset and three-order relevant characteristics and according to a characteristic information matching method, long interference code estimation corresponding to all users at the same speed is completed; meanwhile, relevant calculation estimates the short spreading code, and then through a similarity coefficient matrix, all the complex code fragments of the estimated users are removed till long-short code estimation of all the users is completed.

The invention discloses a no-reference fuzzy distorted stereo image quality evaluation method, which comprises the following steps: in a training stage, selecting a plurality of undistorted stereo images and corresponding fuzzy distorted stereo images to form a training image set; then, carrying out a dictionary training operation by a Fast-ICA (independent component analysis) method, and constructing a visual dictionary table of each image in the training image set; constructing the visual quality table of the visual dictionary table of each distorted stereo image by calculating a distance between the visual dictionary table of each undistorted stereo image and the visual dictionary table of each corresponding fuzzy distorted stereo image; in a testing stage, for any one tested stereo image, carrying out non-overlapping partitioning processing to a left sight point image and a right sight point image of the tested stereo image; and according to the constructed visual dictionary table and the constructed visual quality table, obtaining an objective evaluation prediction value of the image quality of the tested stereo image. The no-reference fuzzy distorted stereo image quality evaluation method has the advantages of low computation complexity and good relevance between an objective evaluation result and subjective perception.

The invention provides a method for rapidly and automatically identifying and removing ocular artifacts in an electroencephalogram signal and belongs to the technical field of biological information and the method is mainly applied to a process of acquiring and preprocessing the electroencephalogram signal. The method comprises the following specific steps of: carrying out discrete wavelet transformation on an acquired multi-channel electroencephalogram signal and an electro-oculogram signal to obtain multi-scale wavelet coefficients; using the wavelet coefficients connected in series as an input for analyzing an independent component, and rapidly acquiring the independent component by using a negative entropy criterion-based Fast ICA (Independent Component Analysis) algorithm; identifying the ocular artifacts through a cosine method, performing zero resetting on the independent component, and projecting the other components through ICA inverse transformation and returning to all electrodes of an original signal; and finally obtaining the electroencephalogram signal for removing the ocular artifacts through inversion of the wavelet transformation. By utilizing the method for rapidly and automatically identifying and removing the ocular artifacts in the electroencephalogram signal, the problems that an ICA method is poor in discrete effect and low in convergence rate when being applied to noisy electroencephalogram signals are solved, and the function of rapidly and automatically identifying and removing the ocular artifacts in the electroencephalogram signal is realized.

The invention discloses a magnetic induction cardiopulmonary activity signal separation method based on a Fast-ICA method. The magnetic induction cardiopulmonary activity signal separation method includes the following steps: sending magnetic induction signals of the left chest and the right chest into a 12MHz narrow-band filter to filter the signals to obtain a left chest phase difference signal and a right chest phase difference signal, conducting wavelet denoising on the left chest phase difference signal and the right chest phase difference signal, adopting the independent variable analyzing method (Fast-ICA) to separate a heartbeat signal and a respiratory signal to achieve synchronous monitoring of magnetic induction cardiopulmonary activity.