504 results about "Multi-label classification" patented technology

Disclosed herein are methods and systems for classifying cell labels, for example identifying a signal cell label. In some embodiments, the method comprises: obtaining sequencing data of barcoded targets created using targets in cells barcoded using barcodes, wherein a barcode comprises a cell label and a molecular label. After ranking the cell labels, a minimum of a second derivative plot of a cumulative sum plot can be determined. Using the methods, a cell label can be classified as a signal cell label or a noise cell label based on the number of molecular labels with distinct sequences associated with the cell label and a cell label threshold.

A method for computerizing delineation and / or multi-label classification of an ECG signal, includes: applying a neural network to the ECG whereby labelling the ECG, and optionally displaying the labels according to time, optionally with the ECG signal.

The invention discloses a pedestrian and vehicle detection method and system based on improved YOLOv3. According to the method, an improved YOLOv3 network based on Darknet-33 is adopted as a main network to extract features; the cross-layer fusion and reuse of multi-scale features in the backbone network are carried out by adopting a transmittable feature map scale reduction method; and then a feature pyramid network is constructed by adopting a scale amplification method. In the training stage, a K-means clustering method is used for clustering the training set, and the cross-to-parallel ratio of a prediction frame to a real frame is used as a similarity standard to select a priori frame; and then the BBox regression and the multi-label classification are performed according to the loss function. And in the detection stage, for all the detection frames, a non-maximum suppression method is adopted to remove redundant detection frames according to confidence scores and IOU values, and an optimal target object is predicted. According to the method, a feature extraction network Darknet-33 of feature map scale reduction fusion is adopted, a feature pyramid is constructed through feature map scale amplification migration fusion, and a priori frame is selected through clustering, so that the speed and precision of the pedestrian and vehicle detection can be improved.

A computer program product includes machine readable instructions for managing data items, the instructions stored on machine readable media, the product including instructions for: initializing a plurality of base models; minimizing a joint loss function to select models from the plurality for a plurality of labels associated with the data items; and at least one of sharing and combining the selected base models to formulate a composite classifier for each label. A computer system and additional computer program product are provided.

The invention discloses a hierarchical multi-label categorization method suitable for legal recognition. The method comprises the following steps: step 1, extracting facts of a case and legal provisions thereof from a pre-processed judgment document; step 2, based on a hierarchical structure of a label space, expanding the legal provisions corresponding to the facts of the case, so that the categorization labels of the sample of the case are a subset of the label space; step 3, performing word segmentation and part-of-speech tagging on the texts of the facts of the case, selecting features ofword segmentation results, selecting features that fully represent the facts of the case, establishing a feature vector; step 4, establishing a prediction model: finding out the set N(x) of k neighborsamples in the expanded multi-label training set of a new instance x, setting a weight for each neighbor sample, calculating confidence of the new instance to each category according to categorization weight of k neighbor samples to each category, finally, predicting the category label set of the new instance.

Effectively training machine learning systems with incomplete / partial labels is a practical, technical problem that solutions described herein attempt to overcome. In particular, an approach to modify loss functions on a proportionality basis is noted in some embodiments. In other embodiments, a graph neural network is provided to help identify correlations / causations as between categories. In another set of embodiments, a prediction approach is described to, based on originally provided labels, predict labels for unlabelled training samples such that the proportion of labelled labels relative to all labels is increased.

The invention provides a multi-label image classification method, a multi-label image classification device and the multi-label image classification equipment based on image convolution, and relates to the technical field of intelligent identification. The method comprises the steps of obtaining a to-be-classified image; performing feature extraction on the to-be-classified image to obtain the image feature information; inputting the image feature information into a pre-trained multi-label classifier, wherein the multi-label classifier is a classifier which is obtained by performing multi-label relation modeling through a graph convolutional network and performing learning and comprises multi-label relation information; and determining a label corresponding to the to-be-classified image according to the at least one label score outputted by the multi-label classifier. According to the multi-label image classification method, device and equipment provided by the embodiment of the invention, the image classification precision can be improved.

The invention discloses a text multi-label classification method based on semantic unit information, which comprises the following steps: establishing a semantic unit multi-label classification modelSU4MLC, taking a recurrent neural network sequence based on an attention mechanism to a sequence model as a baseline model for improvement, and improving the expression of the attention mechanism by improving a source end; Extracting semantic unit related information from the context representation of the source end of the baseline model by using hole convolution in deep learning to obtain semantic unit information; Combining the semantic unit information with the word level information by using a multi-layer mixed attention mechanism, and providing the combined information for a decoder; Anddecoding the tag sequence by using a decoder, thereby realizing text multi-tag classification based on semantic unit information. According to the method, the problems that an existing attention mechanism is easily influenced by noise and contributes to classification insufficiently can be solved, the contribution of the attention mechanism to text classification can be improved, and the text multi-label classification problem can be more efficiently solved.

The invention provides a multi-tag entity based on a depth neural network and a tagging strategy. Relation joint extraction method based on annotation strategy can effectively avoid the error in the named entity recognition subtask will propagate to the relational classification subtask and ignore the interaction between the two subtasks. At that same time, the invention useS Tree-GRU, as the coding layer, can make the model learn the syntactic information of the whole sentence more fully, and help to identify the relationship between the two entities and the type of the relationship. In addition, because of the complexity of the massive text itself, an entity may be included in a variety of relationships, the use of multi-tag classifiers, a good solution to the above problem. The method of the invention obtains good results in different data fields, and can efficiently, accurately and intelligently extract information with practical value and research significance from massive text data.

A method for performing multi-label classification includes extracting a feature vector from an input vector including input data by a feature extractor, determining, by a label predictor, a relevant vector including relevant labels having relevant scores based on the feature vector, updating a binary masking vector by masking pre-selected labels having been selected in previous label selections, applying the updated binary masking vector to the relevant vector such that the relevant label vector is updated to exclude the pre-selected labels from the relevant labels, and selecting a relevant label from the updated relevant label vector based on the relevant scores of the updated relevant label vector.

A method of categorizing objects in which there can be multiple categories of objects and each object can belong to more than one category is described. The method defines a set of categories in which at least one category is dependent on another category and then organizes the categories in a hierarchy that embodies any dependencies among them. Each object is assigned to one or more categories in the set. A set of labels corresponding to all combinations of any number of the categories is defined, wherein if an object is relevant to several categories, the object must be assigned the label corresponding to the subset of all relevant categories. Once the new labels are defined, the multi-category, multi-label problem has been reduced to a multi-category, single-label problem, and the categorization task is reduced down to choosing the single best label set for an object.

The invention discloses a text classification method based on a generative multi-task learning model, and the method comprises the steps: alternately decoding a multi-task classification model througha training set according to a multi-label classification task and a hierarchical classification task, obtaining a current-moment semantic feature related to a coding moment feature vector through decoding, and carrying out the training of the current-moment semantic feature; optimizing the multi-task classification model according to the training result and the real label set to obtain an optimized multi-task classification model; inputting data in a to-be-detected set into the optimized multi-task classification model, and respectively obtaining classification labels to finish classification. The semantic association between the multi-label classification model and the hierarchical classification model is constructed through a multi-task mechanism in the training process of the model, sothat the semantic association between two sub-task prediction results can be enhanced, and the purpose of improving the sub-task classification performance is achieved.

The invention discloses a support vector machine sorting method based on simultaneously blending multi-view features and multi-label information. The support vector machine sorting method based on simultaneously blending the multi-view features and the multi-label information comprises the following steps, inputting multi-view feature training data and the multi-label information corresponding to each data, establishing a mathematical model which simultaneously blends the multi-view features and the multi-label information and supports a vector machine classifier, and setting value of a corresponding weight factor of each item. Training and learning each parameter of a classifier, using loop iteration interactive algorithm to update all parameter variables of target optimization formula until absolute value of the difference of whole objective function values of two iterative is less than preset threshold valve, stopping. Meanwhile, when a parameter is adopted, updated and calculated, strategy fixing other parameter values is adopted. The classifier which is obtained by training conducts multi-label classification or precasting on actual data. When technology supports classification of a vector machine, a unified data expression form in a novel data space is learned, and accuracy rate of the classifier is improved.

Multi-label classification is performed by (i) applying a set of trained base classifiers to an object to generate base classifier label prediction sets comprising subsets of a set of labels; (ii) constructing a set of second level features including at least one second level feature defined by a predetermined combination of two or more of the base classifier label prediction sets; and (iii) applying a second level classifier to label the object with a set of one or more labels comprising a subset of the set of labels, labeling being based on the set of second level features. The multi-label classifier is trained by: (iv) applying operations (i) and (ii) to labeled training objects of a set of labeled training objects to generate training metadata comprising sets of second level features for the labeled training objects; and (v) training the second level classifier using the training metadata.

The invention belongs to the technical field of natural language processing text classification, in particular to a multi-source multi-label text classification method based on an improved seq2seq model and a system thereof. The method comprises the following steps: data input and pretreatment, word embedding, encoding, encoding and splicing, decoding, model optimization and prediction output. Themethod of the invention has the following beneficial effects: adopting a seq2seq depth learning framework, constructing a plurality of encoders, and combining the attention mechanism to be used for atext classification task, so as to maximize the use of multi-source corpus information and improve the classification accuracy of the multi-label; In the error feedback process of decoding step, according to the characteristics of multi-label text, an intervention mechanism is added to avoid the influence of label sorting, which is more in line with the essence of multi-label classification problem. The encoder adopts the circulating neural network, which can learn according to the time step effectively. The decoding layer adopts one-way loop neural network and adds attention mechanism to highlight the learning focus.

The invention discloses a fast multi-label picture retrieval system and a realization method. The method comprises the following steps: deploying an RPN (Region Proposal Network) for extracting region proposals in a convolutional neural network, extracting region proposal information of pictures, and performing ROI pooling calculation on the region proposal information; after pooling, building a multi-label classification loss function through a fully connected layer according to multi-label information to train the convolutional neural network, and building a weighted three-dimensional loss function to train the convolutional neural network; extracting the hash code of each picture from a picture candidate set through the convolutional neural network after multi-task learning, saving the hash codes to a database, and comparing the hash codes with the hash codes in the database, thus completing picture retrieval. The whole network is trained through multi-task learning of classification and hashing, and therefore, the accuracy of retrieval is ensured. Moreover, the similarity is measured using Hamming distance in the process of retrieval, and the efficiency of retrieval is improved greatly.

A method for categorizing a set of objects includes defining a set of categories in which at least one category in the set is dependent on another category in the set; organizing the set of categories in a hierarchy that embodies any dependencies among the categories in the set; for each object, assigning to the object one or more categories l1 . . . lP where liε{1 . . . L} from a set {1 . . . L} of possible categories, wherein the assigned categories represent a subset of categories for which the object is relevant; defining a new set of labels z comprising all possible combinations of any number of the categories, zε{{1},{2}, . . . {L},{1,2}, . . . {1,L},{2,3}, . . . {1,2,3}, . . . {1,2, . . . L}}, such that if an object is relevant to several categories, the object must be assigned the label z corresponding to the subset of all relevant categories; and assigning to the object the several categories and the subcategories of the several categories.

The invention relates to a method for classifying legal texts by adopting a semi-supervised convolutional neural network (SSC) and belongs to the field of neural networks. According to the method, natural languages are processed by utilizing the SSC to achieve the main objective of a system; and through the processing on the legal case description, the problems that what rights and interests of parties does the legal case description violate or which laws and regulations does the parties violate are preliminarily solved, probably more than one rights and interests of the parties is violated orthe parties violate a plurality of laws and regulations at the same time and multi-label classification is realized. Through the legal service platform, case handlers are helped to efficiently handlevarious legal cases and the various legal cases are subjected to semantic analysis to achieve classification to ensure that not only the ability to understand literal meanings but also the ability tologically reason and understand deep meanings are provided in the aspect of the natural language understanding function.

The invention discloses a medical data processing and system based on migration learning. The medical data processing comprises the following steps: acquiring text data outside the medical field, andtraining to obtain a text classification model; acquiring a case set in the medical field, wherein the case set comprises symptoms and labels, and the labels are symptoms corresponding to the diseasesymptoms; extracting the characteristic vectors of the symptoms by using the text classification model as the symptom vectors, and converting the labels into label vectors according to the disease symptom types corresponding to the symptoms; constructing a multi-label training sample set by integrating the symptom vectors and the corresponding label vectors, and training to obtain a multi-label classification model according to the multi-label training sample set; inputting the medical samples to be analyzed into the multi-label classification model, determining the probability values of the medical samples belonging to each type of labels, and obtaining an analysis label set according to the probability values to serve as the analysis result of the medical samples. Therefore, the defect of manual selection of features is avoided through migration learning, and the medical disease prediction accuracy based on outpatient cases is improved.

The invention discloses a graph representation learning framework based on specific semantics and a multi-label classification method thereof. The framework comprises a semantic coupling module used for extracting image features from an input image by using a convolutional neural network, combining the image features with semantic features, introducing an attention mechanism, guiding learning of image feature weights by using the semantic features, and acting on the image features to obtain new feature vectors; a semantic interaction module which is used for constructing a large knowledge graph by constructing the relevance of category coexistence in the knowledge graph statistical data set, then performing feature expression on the knowledge graph by utilizing a door graph network, and iteratively updating the knowledge graph to obtain feature representation of the knowledge graph; and a knowledge embedding expression module which is used for combining the feature representation learned by the knowledge expression of the semantic interaction module with the image feature learning extracted by the semantic coupling module so as to realize multi-label classification.

The invention relates to an artificial intelligence-based multi-label classification method and system of multi-level text. The method includes: 1) utilizing a neural network to construct a multi-label classification model of the multi-level text, and obtaining text class prediction results of training text according to the model; 2) carrying out learning on parameters of the multi-label classification model of the multi-level text according to existing text class labeling information in the training text and the text class prediction results, which are of the training text and are obtained inthe step 1), to obtain a multi-label classification model of the multi-level text with determined parameters; and 3) utilizing the multi-label classification model of the multi-level text with the determined parameters to classify to-be-classified text. The method infers labels of the formed text simply through the document-level labeling information, and can be well applied to scenes where labels of formed text are difficult to collect; compared with traditional multi-instance learning (MIL) methods, the method of the invention introduces minimal assumptions, and can better fit actual data;and the method of the invention has good scalability.

The invention discloses a multi-label classifier constructing method based on cost-sensitive active learning. Specific label information of each sample is directly used, an initial classifier is trained on a marked set, then, learning is performed on a non-marked set through a current classifier, a certain number of sample-label pairs of non-marked samples largest in misclassification cost are selected, real label values of the selected sample-label pairs are marked and added into the marked set, and a training sample set and the classifiers are updated. According to the method, target misclassification cost can be achieved with a small number of iteration times, and learning efficiency is greatly improved; sampling granularity is shrunk to the sample-label pairs, cost for marking samples is greatly reduced, and more remarkable effect is achieved in multi-label classification with a large label number.

The invention discloses a graph node multi-tag classification method based on depth learning. The method comprises the steps that a graph data module is loaded, and graph data are analyzed and stored in the form of a dictionary; a walk path module is generated to complete random walk in the graph data, and a generated walk path is returned; a node eigenvector module is generated, and the walk path returned by the previous step, the specified vector representing dimension and the context window size are used as input to call a word2vec algorithm to calculate the eigenvector representation of each graph node; a training data module is generated, and nodes of a certain percentage are randomly selected from all graph nodes as training node data; for each node, the eigenvector and the tag sequence corresponding to the node are taken to form a two-tuple set as a training sample; and finally, a depth confidence network model is built. The graph node multi-tag classification algorithm proposed by the invention has higher correct rate than a traditional multi-tag classification algorithm.

The invention relates to a cross-modal image mode identification method for the biomedical literature, belongs to the field of image identification and natural language processing and aims to solve across-modal image identification problem in the medical literature. The method is characterized in that an image and a text are processed through utilizing a pre-trained cross-modal composite image detection model, and whether the to-be-identified image is a composite image is determined; the image and the text are processed through utilizing a pre-trained cross-modal composite image multi-label classification model to output a biomedical pattern category of a composite image sub picture; a pre-trained cross-modal simple image pattern classification model is utilized to process the image and the text to output a biomedical pattern category of simple images. The method is advantaged in that image pattern identification tasks in the biomedical literature are effectively completed, resourcesin the general and biomedical fields are utilized to improve the identification performance, and labor and time cost is reduced.

The invention discloses a composite fault diagnosis method and device based on a multi-label classification convolutional neural network. The method comprises: steps 1, collecting and extracting vibration acceleration signal samples under single fault and composite fault working conditions; step 2, giving a label to each sample according to the type, and dividing the sample into a training set anda test set; step 3, establishing a deep one-dimensional convolutional neural network, and setting a Sigmoid activation function and a boundary loss function Margin Loss; step 4, directly inputting the vibration data of the training set into the built deep one-dimensional convolutional neural network for training; and step 5, selecting an optimal model through Grid Search, and applying the optimalmodel to the test set to obtain a fault state classification result. The method enables the classifier to adaptively output a plurality of labels for the composite fault, is high in fault diagnosis precision, can overcome the limitation that a traditional classifier can only output one label, and achieves the diagnosis of the composite fault.

The invention provides a weak supervised image semantic segmentation method based on iterative mining common features of objects, belonging to the technical field of pattern recognition. In the training phase, the method acquires the training data set, constructs and trains the multi-label classification network, and acquires the initial seed area corresponding to each training image. Then, the superpixel region and the region label of each training image are obtained for training the region classification network, and the updated region label of the superpixel region is obtained for trainingthe semantic segmentation network. After iteration, when the performance of the semantic segmentation network converges, the trained semantic segmentation network is obtained. In the use stage, the color image is input into the trained semantic segmentation network, and the network outputs the semantic segmentation results of the image. The invention can realize reliable pixel-level semantic segmentation under the condition of only image class label, reduces the time and labor cost of data labeling, and has wide application prospect.

The invention relates to a device for assisting judicial case judgment based on machine learning, which utilizes a large amount of document data and trains a model to learn the relationship between case fact description and the fine range and relevant legal provisions, and realizes the prediction of the fine range and the law label of any given case fact description text. The invention relates toa device for assisting judicial case judgment based on machine learning. Including: defining the proper nouns in the description of the facts of a given case and dealing with them; Extracting multiplesemantic features from the text to achieve a deeper level of semantic representation; Machine learning method based on multi-label classification is used to classify the law items and obtain the lawlabels related to the description text of the case facts. Single-label classification training model based on machine learning predicts the range of possible fines in related cases. The invention applies machine learning to the judicial field for the first time, realizes deeper semantic representation by multiple feature extraction modes, improves the accuracy and generalization ability of the training model well, has higher reference significance for the final judgment of a case, and is conducive to the realization of the same case and the same judgment.

The invention relates to the field of bioinformatics and data mining, in particular to a hierarchical multi-label classification method for protein function prediction, and aims at solving the data set imbalance problem, multi-label problem and hierarchical constraint problem when the conventional classification methods are used for predicting protein functions. The method comprises the following steps of: 1, a training stage: training a data set of each node in a class label hierarchical structure by adopting an SVM classifier in the training stage so as to obtain a group of basic classifiers; and 2, a prediction stage: firstly obtaining preliminary results of unknown samples by using the group of basic classifiers obtained in the training stage in the prediction stage, and processing the results by adopting a TPR algorithm with a weight so as to obtain a final result which satisfies a hierarchical constraint condition and realize the prediction of the protein functions. The hierarchical multi-label classification method for protein function prediction is applied to the field of bioinformatics and data mining.

The present application relates to a method for classifying a cardiovascular sound recorded from a living subject. The method comprises the step of extracting at least two signal parameters (309) from said cardiovascular sound, said at least two signal parameters characterizes at least two different properties of at least a part of said cardiovascular sound. The method further comprises the step of classifying said cardiovascular sound using said at least two signal parameters in a multivariate classification method (310). Furthermore, the application relates to a system, stethoscope and server for classifying a cardiovascular sound recorded from a living subject, where the above-described method has been implemented.