315results about How to "Improve classification results" patented technology

Automated mapping of part numbers associated with parts in a bill of materials (BOM) submitted by a BOM originator to internal part numbers assigned to those parts by a BOM receiver is performed by one or more computers connected to one or more networks through one or more network interfaces. A first receive component receives one or more data sets containing historical data on bills of materials received in the past by the BOM receiver. A second receive component receives one or more data sets containing known mappings between internal part numbers used by the BOM receiver, and part numbers used by various BOM originators. A third receive component receives one or more data sets containing information of various parameters and their values describing the parts to which the BOM receiver has assigned internal part numbers. A fourth receive component receives one or more methods of automatically learning models for predicting internal part numbers from the above mentioned historical BOM data, mapping data and part parametric data. A learning component learns the models from the data. A fifth receive component receives a BOM from a requesting process. The BOM has one or more parts with a missing internal part number. A mapping component applies the learned models to the received BOM to automatically determine internal part numbers for all unmapped BOM originator part numbers. A release process assigns internal part numbers to all unmapped parts in the BOM and releases the BOM to the requesting process.

Disclosed, among other things, is a computer device and computer-implemented method of classifying cells within an image of a tissue sample comprising providing the image of the tissue sample as input; computing nuclear feature metrics from features of nuclei within the image; computing contextual information metrics based on nuclei of interest with the image; classifying the cells within the image using a combination of the nuclear feature metrics and contextual information metrics.

A method for identifying potential recipients of a message wherein the message comprises a text message and wherein the message is in electronic form is—regarding a possibly simple usability and user-friendliness—designed and further developed in such a way that the content of the message undergoes a text analysis and based on the result of the text analysis a potential recipient or a group of potential recipients are identified from a list of recipients.

The invention discloses a passenger going-out behavior analysis method based on subway card-swiping data. The passenger going-out behavior analysis method is characterized in that the subway going-out behaviors can be classified, and the classification results have the obvious and easy-to-observe characteristics, and can be widely used for the intelligent traffic passenger going-out behavior analysis. The passenger going-out behavior analysis method is characterized in that S1, data pre-processing can be carried out; original data can be merged and organized, and passenger going-out records can be acquired; every passenger going-out record comprises a passenger going-out entrance station, an entrance card-swiping time, an exit station, and an exit card-swiping time; S2, characteristics can be extracted; according to the passenger going-out records, the passenger entrance temporal clustering can be carried out to acquire the fixed going-out days of every passenger, and then the passenger going-out characteristics can be acquired after the extraction of the passenger going-out characteristics; S3, passengers can be clustered; the passenger clustering can be carried out according to the passenger going-out characteristics, and the passenger clustering result can be acquired and analyzed.

The invention relates to an electroencephalogram feature extraction method based on CSP and R-CSP algorithms. According to the electroencephalogram feature extraction method, when a traditional CSP algorithm is used for extracting small sample electroencephalograms, covariance estimation of the traditional CSP algorithm will generate a larger error; according to the electroencephalogram feature extraction method, the traditional CSP algorithm is improved, and the regularization CSP algorithm R-CSP is put forward. Firstly, a small wave threshold denoising algorithm is used for conducting de-noising processing; secondly, covariance matrixes of five experimenters are solved, one target experimenter is selected, and the rest of the experimenters are auxiliary experimenters, an optimal spatial filter is constructed through selection of regularization parameters, and feature vectors are accordingly extracted; and finally, a genetic algorithm is used for optimizing a support vector machine classifier, and the correct rate of the classification result is further improved. The final classification result shows that the R-CSP algorithm is better in correct rate of the classification result compared with a traditional CSP algorithm.

The invention relates to a steel rail crack detection method based on multiple acoustic emission event probabilities. According to the steel rail crack detection method, the relative probability output by a convolutional neural network is used as the probability of an acoustic emission event, and the problem that temporal information between samples is not fully used by an existing steel rail crack detection method is solved. The steel rail crack detection method comprises the steps of (1) loading an acoustic emission time domain signal data matrix, and performing FFT (Fast Fourier Transformation) and pretreatment on acoustic emission signals, so that a spectral matrix which is folded into a three-dimensional matrix and a label vector are obtained; (2) setting structural parameters and an initial value of the convolutional network; (3) inputting the spectral matrix, calculating and iterating errors of a convolutional neural network model layer by layer, updating a weight matrix and bias, performing feature extraction, and outputting classification results and classification probabilities of a test set; (4) correcting the outputting of the convolutional neural network on the basis of the multiple acoustic emission event probabilities, and optimizing the classification results. According to the steel rail crack detection method, the classification results are improved according to the multiple acoustic emission event probabilities, so that the detection precision of steel rail crack damages is increased, and high theoretical and practical engineering significance is obtained.

The invention discloses a hyperspectral image semi-supervised classification method based on space-spectral information. The hyperspectral image semi-supervised classification method combines spectral information and spatial information in a hyperspectral image to act on a support vector machine classifier, adopts a self-training semi-supervised classification framework, utilizes an active learning method as a sample selecting strategy of semi-supervised classification, decomposes initial classification results obtained through semi-supervised classification according to classes so as to obtain various classes of binary images as input images of an edge preserving filter, regards a first principal component content as a reference image of the filter, utilizes the edge preserving filter to perform local smoothing, eliminates noise, and classifies image elements according to a class with maximum probability, thus the classification process is completed. The hyperspectral image semi-supervised classification method combines the spectral information and the spatial information to improve the classifiability of classes, utilizes the self-training semi-supervised classification framework to solve the classification problem of hyperspectral image small samples, can effectively eliminate spot-like errors in the initial classification results, and increases classification precision.

A method for estimating the performance of a statistical classifier. The method includes inputting a first set of business data in a first format from a real business process and storing the first set of business data in the first format into memory. The method applying a statistical classifier to the first set of business data and recording its classification decisions and obtaining a labeling that contains the correct decision for each data item. The method includes computing a weight for each data item that reflects its true frequency and computing a performance measure of the statistical classifier based on the weights that reflect true frequency. The method also displays the performance measure to a user.