3results about How to "Accurate recognition rate" patented technology

The application discloses a low-voltage transformer area topology identification method based on current and electric quantity data, relates to the technical field of low-voltage transformer area topology identification, and comprises data preprocessing, a current algorithm module, an electric quantity algorithm module, a topology fusion module, a rehearsal and verification module and an output result module. The application provides the low-voltage transformer area topology identification method based on the current and electric quantity data, and aims at the deficiency of the prior art, and automatically infers the low-voltage transformer area topology connection relationship through the identification method.

The invention discloses a power transmission line fault type identification method and system based on multi-source information fusion, and relates to the technical field of power transmission line fault type identification, and the method comprises the steps: carrying out the decomposition of fault recording information in a frequency domain, and carrying out the calculation to obtain the frequency band energy of each sub-frequency band; based on the index weight, establishing a training sample according to each frequency band energy corresponding to the fault type of each fault, the meteorological information, the reclosing information and the fault recording information; training a preset initial model by using each data group in the training sample, and determining the preset initial model meeting a training ending condition as an identification model; when the judgment result is that the fault occurs, acquiring the current line state, and inputting the current line state into the recognition model for processing to obtain the fault occurrence type of the to-be-detected power transmission line; by performing fusion processing on multi-source data, key features are extracted to overcome the limitation of a single data source, and the accuracy of fault recognition is improved by fully utilizing various information.

The present application belongs to the technical field of data representation and signal classification, and relates to a face expression classification method and system. The system comprises a facial bioelectricity sensor, a hardware data noise filtering module and an upper computer. The facial bioelectricity sensor is used to collect facial electromyography, electrooculography signals and posture data. The hardware data noise filtering module is used to process the electromyography and electrooculography signals. The method extracts time domain, frequency domain and transform domain features from the digital electromyography and electrooculography data after digital-analog conversion. The features extracted are cross-correlated and fused after correlation coefficient calculation and judgment. After the average MIC is calculated, the selected data is classified to obtain the expression type. The method and system can increase the number and type of significant features by cross-correlating and fusing the features according to the correlation coefficient and threshold value. After statistics, screening and alignment, the classification is more accurate than the existing method and system.