743 results about "Sample Label" patented technology

The present invention provides systems and methods for large-scale genetic measurements by generating from a sample labeled target sequences whose length, orientation, label, and degree of overlap and complementarity are tailored to corresponding end-attached probes of a solid support so that signal-to-noise ratios of measurement from specifically hybridized labeled target sequences are maximized. Systems for implementing methods of the invention include a set of sample-interacting probes to produce amplicons that either each contain a segment of a target polynucleotide or an oligonucleotide tag that corresponds to a segment of a target polynucleotide, one or more solid phase supports that contain a plurality of end-attached probes, and methods of generating from sample-interacting probe amplicons from which labeled target sequences are tailored for hybridization to the solid phase supports, such as microarrays. In one aspect, labeled target sequences and end-attached probe of the solid phase supports comprise oligonucleotide tags and tag complements, respectively, selected from a minimally cross-hybridizing set.

A method and apparatus are provided for obtaining a sub-resolution spatial information of a sample labeled with at least one type fluorescent label. The sub-resolution spatial information has localization information about the positions of fluorescent molecules of the at least one type fluorescent label in at least one spatial direction. The method acquires localization image data by employing fluorescence localization microscopy. The acquired localization image data is processed to obtain the localization information about the positions of fluorescent molecules of the at least one type fluorescent label in at least one spatial direction. The step of processing includes determining in each of the detected images of the series the positions of the barycenters of the detected fluorescence emission distributions from the single fluorescent molecules of the one or more fluorescent labels in at least one spatial direction.

The invention discloses a training method for a lane line identification model. A road image sample labeled with a target line is acquired. The road sample image is input into the lane line identification model to acquire a feature map. The target line in the road image sample is compared with proposed lines in the left, right and lower edge directions in the feature map. Parameters in the lane line identification model are adjusted according to the comparison result. The loss function of the lane line identification model is minimized. The lane line identification model is a deep learning model, so that the image feature of the target line can be learned through weight sharing. The line detection function of a lane line is greatly improved. Even if the lane line is blocked or illuminated,or the lane line is a curve or irregular line or is merged or separated, the lane line can be detected. The robustness is great. The invention further discloses a lane line identification method based on the model.

The embodiment of the invention discloses a model training method and device and a storage medium. The method includes: obtaining a multi-label image training set; selecting a target training image currently used for model training from the multi-label image training set; carrying out label prediction on the target training image by adopting a deep neural network model to obtain a plurality of prediction labels of the target training image; obtaining a cross entropy loss function corresponding to the sample label, the positive label loss in the cross entropy loss function being provided with aweight, and the weight being greater than 1; and converging the prediction label and the sample label of the target training image according to the cross entropy loss function to obtain a trained deep neural network model. According to the scheme, the model accuracy and visual expressive force can be improved.

A system for qualifying cells of a cell sample labeled with a magnetic or magnetizable moiety is provided. The system includes a cell sample holder for holding a cell of the cells and a first cell analyzer which includes a magnetic field source for applying a magnetic field to the cell and a sensor for qualifying and / or quantifying an effect of the magnetic field on the cell.

The invention provides a remote sensing image building extraction method and system based on depth learning which comprises the steps of sample preparation, model training, precision evaluation, building prediction, merging and vectorization. The invention also relates to a remote sensing image building extraction system based on depth learning, a storage medium and an electronic device. Based onthe improved RCF boundary constraint model, the invention extracts the urban single building contour, the rural isolated building contour and the peripheral boundary of the rural building dense group,at the same time, a U-Net semantic segmentation model network structure is improved, and the improved U-Net is utilized to classify the images at pixel level. Finally, the two models are fused, and the depth learning model is trained by a large number of building sample label data, so that the network model by fusing the improved U-Net and the RCF is used to extract the buildings on the sub-meterGao Fen 2 remote sensing images, so that the automatic and effective building vector data extraction is realized, and the time cost and labor cost of manual rendering is greatly reduced.

The invention discloses a federation modeling method and device and a storage medium. The method includes: inputting a first training sample and a second training sample; training the first training sample and the second training sample based on an Xgboost algorithm and an encryption algorithm to obtain a decision tree prediction model; according to the policy tree prediction model, predicting thesample to be predicted based on a preset sample label prediction method. The method predicts to-be-predicted samples based on a preset sample label prediction method according to the decision tree prediction model. The method comprises inputting a to-be-predicted sample into a first-party decision tree prediction model by a first party of federation modeling, and inputting that sample to be predicted in the decision tree prediction model by a first party and a second party of federation modeling, thereby extending the application range of federation modeling.

A method for identifying diseases and pests of fruit trees under complex background based on cavity convolution is disclosed, At first, that original train set with sample labels is obtain by collecting images of diseases and insect pests of fruit tree leaves, and then the expanded train sample set is obtained by data augmentation operation, and then the average value is obtained, all the originaltraining set images are averaged, and then randomly scrambled to form a training data set; Then, the cavity convolution neural network model is established, and the disease classification training iscarried out by using the training data set. The characteristic image of the input image is extracted by the cavity convolution layer, and the nonlinear characteristic image of the input image is obtained by using the nonlinear activation function. Pooling layer is used to reduce the convolution layer weight parameters. Using multi-scale convolution kernel to obtain different features of the inputimage, and finally using Soft Max classifier to classify the disease types of the input image; The invention shortens the training time of the model, accelerates the recognition speed and improves the recognition accuracy.

The invention discloses a behavior identification method based on a 3D convolution neural network, and relates to the fields of machine learning, feature matching, mode identification and video image processing. The behavior identification method is divided into two phases including the off-line training phase and the on-line identification phase. In the off-line training phase, sample videos of various behaviors are input, different outputs are obtained through calculation, each output corresponds to one type of behaviors, parameters in the calculation process are modified according to the error between an output vector and a label vector so that all output data errors can be reduced, and labels are added to the outputs according to behavior names of the sample videos corresponding to the outputs after the errors meet requirements. In the on-line identification phase, videos needing behavior identification are input, calculation is conducted on the videos through the same method as the training phase to obtain outputs, the outputs and a sample vector for adding the labels are matched, and the name of the sample label most matched with the sample vector is viewed as a behavior name of the corresponding input video. The behavior identification method has the advantages of being low in complexity, small in calculation amount, high in real-time performance and high in accuracy.

A system for qualifying cells of a cell sample labeled with a magnetic or magnetizable moiety is provided. The system includes a cell sample holder for holding a cell of the cells and a first cell analyzer which includes a magnetic field source for applying a magnetic field to the cell and a sensor for qualifying and / or quantifying an effect of the magnetic field on the cell.

The invention relates to a face identification method and an attendance system based on a deep convolution neural network. The system comprises that user information and face sample labels are input into a user management server and then sent to a central server; in the central server, the pre-processed sample labels are used to establish a face identification model based on the deep convolution neutral network; employees carry out the online face identification through a trained neutral network on attendance machines at each site, and face identification results will be returned to the user management server by an internal local area network; and management staffs can carry out checking, modification and other operations to attendance records on the user management server. A face identification algorithm based on the deep convolution neutral network used by the invention can avoid problems such as incomplete and uncertain characteristic description caused by traditional manual extraction, can also make use of advantages of a receptive field and weight sharing, and can increase a face identification rate so as to increase an accuracy rate of the attendance system.

The invention discloses an epilepsy seizure prediction method based on a semi-supervised deep generative adversarial network. The method comprises the following steps: carrying out segmentation windowing processing on each EEG(electroencephalography) data of N original EEG samples through a sliding window in specified length, and during segmentation, carrying out superposition expansion processingon adjacent sub-windows to obtain S sections of sub-signals; carrying out short-time Fourier transform on the S sections of sub-signals to obtain spectrum signals, and converting the obtained spectrum data into an image for expression; inputting the processed picture information to a discriminator in the semi-supervised deep generative adversarial network for training and classification accordingto labeled training samples, training sample labels and unlabeled training samples; and inputting Z-dimensional noise data into a generator, and generating a pseudo-data image similar to distributionof the unlabeled data through the generator. The method gradually releases dependence of epilepsy seizure prediction on the labeled data through a semi-supervised learning mode, and obtains better classification accuracy.

The invention relates to a Fourier parallel magnetic resonance imaging method based on a one-dimensional part of a deep convolutional network, and belongs to the technical field of magnetic resonance imaging. The method comprises the following steps: a sample set for training and a sample label set are created; an initial deep convolutional network is built; a training sample of the sample set is input into an initial deep convolutional network model to perform forward propagation, an output result of the forward propagation is compared with an expect result in the sample label set, and training is performed using a gradient descent algorithm until various layer parameters maximizing the consistency between the output result and the expect result are obtained; an optimal deep convolutional network model is established by utilizing the obtained various layer parameters; and a multi-coil under-sampling image obtained through online sampling is input into the optimal deep convolutional network model, forward propagation is performed on the optimal deep convolutional network model, and a rebuilt single-channel whole-sampling image is output. A noise of the rebuilt image can be removed well, a magnetic resonance image having a good visual effect is rebuilt, and the Fourier parallel magnetic resonance imaging method has high practical value.

The invention relates to the technical field of text processing, in particular to a keyword extraction method, apparatus and device and a storage medium. The method includes: obtaining corpus text tobe extracted; inputting the to-be-extracted corpus text into a text labeling model for character type labeling processing to obtain a label corresponding to each character in the to-be-extracted corpus text, wherein the text labeling model is determined by performing supervised training based on a preset neural network model by using a training corpus text with a sample label, and the preset neural network model comprises a semantic representation model, a full connection layer connected with the semantic representation model, a conditional random field connected with the full connection layerand an output layer connected with the conditional random field; obtaining a character corresponding to a preset label in the corpus text to be extracted; and determining a keyword of the corpus textto be extracted according to the character corresponding to the preset label. According to the method, the accuracy and recall rate of keyword extraction can be improved.

The invention discloses a method for segmenting images by sparse representation and dictionary learning, and the method is mainly used for solving the problem of unstable division result under the condition of no sample label in the prior art. The method comprises the following steps: (1) inputting an image to be segmented, and extracting the gray co-occurrence features and wavelet features of the image to be segmented; (2) carrying out K-means clustering on the image to be segmented by utilizing the features so as to obtain K-feature points; (3) acquiring K dictionaries corresponding to the K-feature points by an KSVD (K-clustering with singular value decomposition) method; (4) carrying out sparse decomposition on all the features of the K dictionaries by a BP (back propagation) algorithm to obtain a sparse coefficient matrix; (5) calculating the sparse representation error of each dictionary according to each feature point, and dividing the point corresponding to the feature to the type with the smallest dictionary error; and (6) repeating the step (5) until all the points have label values, and finishing final segmentation. Compared with the prior art, the method can be used for significantly improving the image stability and the segmentation performance, and can be used for target detection and background separation.

The present invention provides parallel methods for determining nucleotide sequences of polynucleotides associated with sample tags. Applications of sequence information acquired by these methods are also provided.

The invention provides a classifier training method, a device, an electronic device and a computer-readable medium, belonging to the technical field of the Internet. A method for train that classifierinclude training labeled samples in a plurality of data feature to obtain a primary classifier; Inputting an unlabeled sample from the plurality of data features to the primary classifier for training to output a label of the unlabeled sample, and calculating a probability that the unlabeled sample labels the label; According to the probability of the label, a part of the unlabeled samples is selected for expert labeling, and the samples labeled by the expert are retrained to obtain a new classifier. This method is based on active learning to update the classifier. Combined with a large number of data and artificial experience, the classifier model can make the classification results more accurate and improve the classification effect. There are only a small number of labeled samples anda small number of manual labeling in the training samples, which can quickly process the classification of a large number of unlabeled samples and improve the efficiency.

The invention relates to a touch information classified computing and modelling method based on machine learning. The method comprises the following steps: acquiring a touch sequence of a training set sample, modelling by adopting a linear dynamic system model, extracting dynamic characteristics of a sub touch sequence, calculating distance of the dynamic characteristics of the sub touch sequence by adopting Martin distance, clustering a Martin matrix by adopting a K-medoids algorithm, constructing a code book, carrying out characterization on each touch sequence by adopting the code book to obtain a system packet model, putting the system packet model of the training set sample and a training set sample label into an extreme learning machine for training a classifier, and putting the system packet model of a to-be-classified sample into the classifier to obtain a label for type of an object. The touch information classified computing and modelling method has the advantages that the actual demand of a robot on stable and complaisant grasping of a non-cooperative target is met, data foundation is provided for completion of a precise operation task, and other sensing results can be fused and computed, so that the description and recognition capability on different targets is enhanced by virtue of multi-source deep perception, and a technical foundation is laid for implementation of intelligent control.

The invention discloses an SAR (stop and reveres) image segmentation method based on dictionary migration clustering, which mainly solves the problems that the existing artificial mark SAR image has high cost and the existing non-mark SAR image can not assist a target SAR image in segmenting. The method has the following realization processes: 1) extracting wavelet characteristics for the target SAR image and the non-mark assistant SAR image; 2) setting circulation ending times, and preliminarily dividing the target SAR image with a k-means method; 3) training a dictionary for each class of target SAR image data; 4) migrating a group of samples for each class of target SAR image data from the assistant SAR image data; 5) removing the assistant data sample with an unstable label by a spectral clustering integration method; 6) training an assistant dictionary by each bath of purified assistant samples; and 7) updating a sample label and outputting a clustering segmenting result according to a target dictionary, the assistant dictionary and a corresponding clustering center. The SAR image segmentation method has the advantage of good segmenting effect and can be used for further identifying the SAR image target.

The invention relates to a method, system and device for updating model parameters based on federated learning. The method, system and device can be used for data privacy protection. The method is realized by any training member in participants, and the method comprises the following steps: carrying out multiple rounds of iterative updating on model parameters, wherein one round of iterative updating comprises the following steps: obtaining a to-be-trained model with the same structure as other participants; training the to-be-trained model based on a self-held training sample and a sample label to obtain a gradient matrix; calculating a first operation value matrix at least based on the gradient matrix and a first hyper-parameter; calculating a second operation value matrix based on the gradient matrix; uploading the first operation value matrix and the second operation value matrix to the server, so that the server updates model parameters of a to-be-trained model of a server side; and obtaining updated model parameters from the server so as to take the updated model parameters as a to-be-trained model for the next round of iterative update, or determining a final model based onthe updated model parameters.

The invention provides a face identification method based on iteration re-constraint group sparse expression classification. Therefore, large-area shielding images, high-complexity congestion images, camouflage images or images with drastic expression change can be effectively classified. With an objective of obtaining the higher identification rate, the method comprises following steps of: a) randomly selecting image samples for classification, and grouping the image samples into a training dictionary set, wherein each type is provided with the corresponding sample label; b) calculating an initial value of a residual value e and a sparse expression coefficient theta generated by comparing a to-be-tested sample with each type in the dictionary set, and calculating a weight initial value of the residual value e and the sparse expression coefficient theta; c) carrying out iteration calculation on the residual value e of each type, the sparse expression coefficient theta and their weight values, repeating the iteration process until reaching a convergence condition or the biggest iteration number, and outputting the final theta value; and d) classifying the to-be-tested sample according to the smallest e value so as to obtain an identification result to classify the to-be-tested sample.

The embodiment of the invention discloses a federated learning method and device, computer equipment and a medium, and belongs to the technical field of computers. The method comprises the following steps that: first computer equipment acquires sample label information corresponding to a sample identifier, and acquires first fusion information corresponding to the sample identifier; the second computer equipment acquires second fusion information corresponding to the sample identifier and sends the second fusion information to the first computer equipment; the first computer equipment acquiresa gradient operator corresponding to the sample identifier based on the first fusion information, the second fusion information and the sample label information, and sends the gradient operator to the second computer equipment; and the first computer equipment and the second computer equipment respectively adjust model parameters of a first sub-model and model parameters of a second sub-model inthe machine learning model based on the gradient operator. According to the method, the training speed of the model is increased while the privacy of the user is ensured, the information amount of thecharacteristics of the sample is enriched, and the accuracy of the model is improved.

The invention relates to a method for establishing a weather forecasting model. The method includes the steps: step S1: acquiring historical weather forecast data of a geographical location, wherein the historical weather forecast data includes a plurality of features; step S2: acquiring weather record data of the geographical location, wherein the weather record data includes a weather indicator;step S3: using the weather record data to extract a feature or a feature group associated with the weather indicator from the plurality of features; step S4: taking the weather record data as a sample label to process the feature or the feature group in the historical weather forecast data, and establishing the weather forecasting model. The invention further relates to a weather forecasting method and device using the weather forecasting model.

The invention provides an SAR (Synthetic Aperture Radar) image change detection method based on a pyramid pooling twinning network, which mainly solves the problem of inaccurate result caused by the fact that the change detection precision depends on a difference graph in the traditional method. The method comprises the following steps: 1) generating a training sample, a test sample and a sample label; 2) constructing a deep pyramid pooling twin network; 3) constructing a classification network; 4) training the deep pyramid pooling twin network and the classification network by using the training samples and the sample labels to obtain a trained model. According to the method, the use of a difference graph can be avoided, the influence of the difference graph on the change detection resultis effectively solved, the accuracy of change detection is improved, and the method can be used for environmental detection and disaster detection.

The invention provides a method and a system for multi-label active learning classification. The method comprises: respectively using a logarithm likehood method to obtain likehood ratio of a labeled sample label pair and using an entropy method to obtain nondeterminacy of a to-be-labeled sample label pair; respectively calculating KL distances of different labels of a plurality of same samples, and weight factors of a plurality of different labels; performing multiplication on each KL distance and the corresponding weight factor, to obtain a corresponding result, adding the plurality of results, to obtain the KL distance sum of the to-be-labeled sample label pair related to the to-be-labeled sample label pair, using the KL distance sum to determine the nondeterminacy of cross labels; determining final nondeterminacy of the to-be-labeled sample label pair; and using the likehood ratio and the final nondeterminacy of the to-be-labeled sample label pair to obtain a new sample label pair training set, and using the new sample label pair training set to train a classifier.

The invention discloses a mechanical fault migration diagnosis method based on an adaption sharing deep residual network (ASResNet). A labeled monitoring data set of a laboratory device and a monitoring data set of an engineering device are firstly acquired, and stacked residual units are used to extract migration fault characteristics of the monitoring data of the laboratory device and the engineering device; through a fully connected network, the mapping relationship between the migration fault characteristics and sample health labels is built, distribution differences between the migrationfault characteristics are calculated, the probability distribution of the sample labels is predicted, and pseudo labels of the monitoring data samples of the engineering device are generated; the monitoring data sets of the laboratory device and the engineering device are then used, a to-be-trained parameter set of the ASResNet is trained through object functions constructed by maximizing and minimizing, and a migration diagnosis model is acquired; and the monitoring data of the engineering device are inputted to realize mechanical fault migration diagnosis. The differences between the monitoring data of the laboratory device and the monitoring data of the engineering device are narrowed, and ideal effects are achieved for fault diagnosis for the engineering device.

The embodiment of the invention provides a question answer acquisition method and system based on machine reading understanding. The method comprises the following steps: inputting a question and a corresponding document set into a trained neural network model, and obtaining an output result of the trained neural network model; determining an answer corresponding to the question from the documentset according to the output result; wherein the trained neural network model is obtained through training according to a training set, and the training set comprises a plurality of sample problems anda sample document set and a sample label set corresponding to each sample problem. According to the method and the system provided by the embodiment of the invention, the question and the corresponding document set are input into the trained neural network model, and the answer corresponding to the question is determined from the document set according to the output result of the trained neural network model. The method has the advantages that the shortage of a machine reading understanding model of the description type problem is filled, the characteristics of multiple documents are effectively utilized, more document information is reserved, and the answer of the description type problem can be extracted more accurately.

A visual scene recognition system based on a deep neural network, comprises: a vehicle-mounted vision system for acquiring vehicle front view visual images; an offline training module for utilizing adeep convolutional neural network to perform sampling on the vehicle front view visual images acquired by the vehicle-mounted vision system, performing labeling, generating sample labels, and performing neural network parameter step-by-step training, wherein the deep convolutional neural network is composed of a three-branch classification network sharing two layers of shallow convolution features, and the network parameters are trained through samples and a training task; and an online analysis module for adopting a network compression and time-sharing parallel analysis strategy to perform real-time scene analysis on the samples trained by an offline training module, and outputs the weather time and the weather of a road scene in which the vehicle vision system is located and a scene abnormal state.

The invention provides a method and a device for determining sample labels. The method for determining the sample labels comprises the following steps of extracting on-line feedback data to acquire initial model training data; extracting scene features from the initial model training data; adding the scene features into the initial model training data to acquire sample data; calculating the sample quality score of each group of sample data; labeling each group of sample data according to the corresponding sample quality score of the corresponding group of sample data; learning the labeled sample data to generate a model; and predicting labels of the sample data by using the model. In a multi-example learning problem, labor is reduced when the sample is labeled, a large amount of labor is saved, and the labeling efficiency can be improved.