13751 results about "Classification methods" patented technology

A method of thematically classifying documents, in particular for making up or updating thematic databases (42) for a search engine, includes the steps of selecting documents representative of each theme, identifying within the selected documents, elements that are characteristic of each theme, allocating a coefficient (R) to each identified element, said coefficient being representative of the relevance of said element relative to the corresponding theme, and for each document (50) for classification, identifying said elements characteristic of each theme contained in the document and, for each theme corresponding thereto, using the coefficients allocated to said elements to calculate the value of a characteristic representative of the relevance of the theme for the document (50), in order to decide whether or not the document relates to the theme.

The present invention relates to a convolutional-neural-network-based classifier, a classifying method by using a convolutional-neural-network-based classifier and a method for training the convolutional-neural-network-based classifier. The convolutional-neural-network-based classifier comprises: a plurality of feature map layers, at least one feature map in at least one of the plurality of feature map layers being divided into a plurality of regions; and a plurality of convolutional templates corresponding to the plurality of regions respectively, each of the convolutional templates being used for obtaining a response value of a neuron in the corresponding region.

A method and system for conveying an arbitrary mixture of high and low latency traffic streams across a common switch fabric implements a multi-dimensional traffic classification scheme, in which multiple orthogonal traffic classification methods are successively implemented for each traffic stream traversing the system. At least two diverse paths are mapped through the switch fabric, each path being optimized to satisfy respective different latency requirements. A latency classifier is adapted to route each traffic stream to a selected path optimized to satisfy latency requirements most closely matching a respective latency requirement of the traffic stream. A prioritization classifier independently prioritizes traffic streams in each path. A fairness classifier at an egress of each path can be used to enforce fairness between responsive and non-responsive traffic streams in each path. This arrangement enables traffic streams having similar latency requirements to traverse the system through a path optimized for those latency requirements.

Biopotential waveforms such as ERPs, EEGs, ECGs, or EMGs are classified accurately by dynamically fusing classification information from multiple electrodes, tests, or other data sources. These different data sources or “channels” are ranked at different time instants according to their respective univariate classification accuracies. Channel rankings are determined during training phase in which classification accuracy of each channel at each time-instant is determined. Classifiers are simple univariate classifiers which only require univariate parameter estimation. Using classification information, a rule is formulated to dynamically select different channels at different time-instants during the testing phase. Independent decisions of selected channels at different time instants are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. Finally, the dynamic decision fusion system provides high classification accuracies, is quite flexible in operation, and overcomes major limitations of classifiers applied currently in biopotential waveform studies and clinical applications.

The present invention provides a system and method for classifying cardiac beats based on activation-recovery intervals (ARIs) or an ARI-related parameter such as the spatial dispersion of activation, recovery or ARIs. The beat classification method may be used in monitoring and detecting cardiac rhythms and / or for controlling a cardiac stimulation therapy. The beat classification method includes acquiring a reference ARI for one or more known types of cardiac beats; measuring the activation-recovery interval of an unknown cardiac beat during cardiac activity monitoring; comparing the measured activation-recovery interval to the stored reference ARI(s); and classifying the cardiac beat based on the comparison between the measured ARI and the reference ARI(s).

The invention provides a text emotion classification method based on the joint deep learning model which relates to the text emotion classification method. The method is designed with the object of solving the problems with the dimension disaster and sparse data incurred from the existing support vector machine and other shallow layer classification methods. The method comprises: 1) processing each word in the text data; using the word2vec tool to train each processed word in the text data so as to obtain a word vector dictionary; 2) obtaining the matrix M of each sentence; training the matrix M by the LSTM layer and converting it into vector with fixed dimensions; improving the input layer; generating d-dimensional h word vectors with context semantic relations; 3) using a CNN as a trainable characteristic detector to extract characteristics from the d-dimensional h word vectors with context semantic relations; and 4) connecting the extracted characteristics in order; outputting to obtain the probability of each classification wherein the classification with the maximal probability value is the predicated classification. The invention is applied to the natural language processing field.

A depolarization waveform classifier based on the Modified lifting line wavelet Transform is described. Overcomes problems in existing rate-based event classifiers. A task for pacemaker / defibrillators is the accurate identification of rhythm categories so correct electrotherapy can be administered. Because some rhythms cause rapid dangerous drop in cardiac output, it's desirable to categorize depolarization waveforms on a beat-to-beat basis to accomplish rhythm classification as rapidly as possible. Although rate based methods of event categorization have served well in implanted devices, these methods suffer in sensitivity and specificity when atrial / ventricular rates are similar. Human experts differentiate rhythms by morphological features of strip chart electrocardiograms. The wavelet transform approximates human expert analysis function because it correlates distinct morphological features at multiple scales. The accuracy of implanted rhythm determination can then be improved by using human-appreciable time domain features enhanced by time scale decomposition of depolarization waveforms.

The invention discloses a short text classification method based on a convolution neutral network. The convolution neutral network comprises a first layer, a second layer, a third layer, a fourth layer and a fifth layer. On the first layer, multi-scale candidate semantic units in a short text are obtained; on the second layer, Euclidean distances between each candidate semantic unit and all word representation vectors in a vector space are calculated, nearest-neighbor word representations are found, and all the nearest-neighbor word representations meeting a preset Euclidean distance threshold value are selected to construct a semantic expanding matrix; on the third layer, multiple kernel matrixes of different widths and different weight values are used for performing two-dimensional convolution calculation on a mapping matrix and the semantic expanding matrix of the short text, extracting local convolution features and generating a multi-layer local convolution feature matrix; on the fourth layer, down-sampling is performed on the multi-layer local convolution feature matrix to obtain a multi-layer global feature matrix, nonlinear tangent conversion is performed on the global feature matrix, and then the converted global feature matrix is converted into a fixed-length semantic feature vector; on the fifth layer, a classifier is endowed with the semantic feature vector to predict the category of the short text.

Optical classification method for classifying an occupant in a vehicle by acquiring images of the occupant from a single camera and analyzing the images acquired from the single camera to determine a classification of the occupant. The single camera may be a digital CMOS camera, a high-power near-infrared LED, and the LED control circuit. It is possible to detect brightness of the images and control illumination of an LED in conjunction with the acquisition of images by the single camera. The illumination of the LED may be periodic to enable a comparison of resulting images with the LED on and the LED off so as to determine whether a daytime condition or a nighttime condition is present. The position of the occupant can be monitored when the occupant is classified as a child, an adult or a forward-facing child restraint.

A method for building a classification model for classifying unclassified documents based on the classification of a plurality of documents which respectively have been classified as belonging to one of a plurality of classes, said documents being digitally represented in a computer, said documents respectively comprising a plurality of terms which respectively comprise one or more symbols of a finite set of symbols, and said method comprising the following steps: representing each of said plurality of documents by a vector of n dimensions, said n dimensions forming a vector space, whereas the value of each dimension of said vector corresponds to the frequency of occurrence of a certain term in the document corresponding to said vector, so that said n dimensions span up a vector space; representing the classification of said already classified documents into classes by separating said vector space into a plurality of subspaces by one or more hyperplanes, such that each subspace comprises one or more documents as represented by their corresponding vectors in said vector space, so that said each subspace corresponds to a class.

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features, The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

A technique for vehicle classification and identification from images successively narrows the classification of a vehicle down to vehicle make, model, and other specific characteristics. This process uses location, size, color, shape, and other image characteristics that help differentiate vehicles from other kinds of objects in an image. A broad categorization of the target vehicle is performed by classifying the vehicle according to a predetermined set of general vehicle types. A short list is then created of potential matching vehicle makes and models within the broad category that have the best chance of matching the target vehicle. Specific visible points on the target vehicle are identified and then a wire-frame matching with pre-recorded wire-frame models of the short listed vehicles is performed to produce a set of selected vehicle makes and models.

A system, computer program, and method for organizing and managing data structures including based on input from a feedback agent is provided, the method including: (a) a method for faceted classification that is applicable to a domain of information, said method of faceted classification including: (i) a facet analysis of said domain or receiving the results of facet analysis of the domain; and (ii) applying a faceted classification synthesis of said domain; and (b) a complex-adaptive method for selecting and returning information, on one or more iterations, from said faceted classification synthesis, said complex-adaptive method varying the organizing and managing of data structures in response to said returned information. A system and method for faceted classification of a domain of information is also provided that includes providing a faceted data set including facet attributes with which to classify information, such facet attributes including optionally facet attribute hierarchies for the facet attributes; (b) providing a dimensional concept taxonomy in which the facet attributes are assigned to objects of the domain to be classified in accordance with concepts that associate meaning to the objects, said concepts being represented by concept definitions defined using said facet attributes and associated with the objects in the dimensional concept taxonomy, said dimensional concept taxonomy expressing dimensional concept relationships between the concept definitions in accordance with the faceted data set; and (c) providing or enabling a complex-adaptive system for selecting and returning dimensional concept taxonomy information to vary the faceted data set and dimensional concept taxonomy in response to the dimensional concept taxonomy information. In another aspect of the method of the present invention the method for faceted classification of the domain of information further includes performing faceted classification synthesis to relate a set of concepts represented by concept definitions defined in accordance with a faceted data set including facet attributes, and optionally facet attribute hierarchies. The invention also provides a computer system for enabling a user to manipulate dimensional concept relationships. A further aspect of the system is a system for organizing and managing data structures including based on input from a feedback agent, in which the system includes or is linked to a complex-adaptive system for selecting and returning dimensional concept taxonomy information to vary a faceted data set and a dimensional concept taxonomy in response to dimensional concept taxonomy information, the dimensional concept taxonomy expressing dimensional concept relationships between the concept definitions in accordance with the faceted data set.

A method and system for providing detecting and classifying coronary stenoses in 3D CT image data is disclosed. Centerlines of coronary vessels are extracted from the CT image data. Non-vessel regions are detected and removed from the coronary vessel centerlines. The cross-section area of the lumen is estimated based on the coronary vessel centerlines using a trained regression function. Stenosis candidates are detected in the coronary vessels based on the estimated lumen cross-section area, and the significant stenosis candidates are automatically classified as calcified, non-calcified, or mixed.

The invention discloses an attention mechanism-based in-depth learning diabetic retinopathy classification method comprising the following steps: a series of eye ground images are chosen as original data samples which are then subjected to normalization preprocessing operation, the preprocessed original data samples are divided into a training set and a testing set after being cut, a main neutralnetwork is subjected to parameter initializing and fine tuning operation, images of the training set are input into the main neutral network and then are trained, and a characteristic graph is generated; parameters of the main neutral network are fixed, the images of the training set are adopted for training an attention network, pathology candidate zone degree graphs are output and normalized, anattention graph is obtained, an attention mechanism is obtained after the attention graph is multiplied by the characteristic graph, an obtained result of the attention mechanism is input into the main neutral network, the images of the training set are adopted for training operation, and finally a diabetic retinopathy grade classification model is obtained. Via the method disclosed in the invention, the attention mechanism is introduced, a diabetic retinopathy zone data set is used for training the same, and information characteristics of a retinopathy zone is enhanced while original networkcharacteristics are reserved.

The invention discloses an image classification method based on a convolution neural network. The method comprises the following steps: constructing a deep convolution neural network; improving the deep convolution neural network; training and testing the deep convolution neural network; and optimizing the network parameter. By using the image classification method disclosed by the invention, the improvement and the optimization are respectively performed on the network structure and multiple parameters of the convolution neural network, the recognition rate of the deep convolution neural network can be effectively improved, and the accuracy of the image classification is improved.

The invention discloses a method and a system for identifying moving objects. The method for identifying the moving objects comprises the following steps: detecting the objects, namely extracting interesting areas from a video image; tracking the objects, namely establishing the association and consistency between the extracted areas between the frames to form the objects; and classifying the objects, namely classifying the areas and the objects by a classification method, wherein the classification method comprises an area classification method and an object classification method. The method and the system realize detection, tracking and classification of the moving objects, and solve the problems of image jitter, brightness change, shadow, leaf swing and the like.

The invention relates to the technical field of image information processing, in particular to a multiclass image classification method based on active learning and semi-supervised learning. The method comprises five steps: initial sample selection and classifier model training, BvSB active learning sample selection, CST semi-supervised learning, training sample set and classifier model updating and assorting process iteration. Through the operations of BvSB active learning sample selection, CST semi-supervised learning and SVM classification, the invention has efficient image classification effect under the condition of less manual tagging, does not increase overmuch computation burden, can quickly provide classification effects and also can take consideration of the demand of a classification system on the computation complexity.

A method of automatically classifying images in a consumer digital image collection, includes generating an event representation of the image collection; computing global time-based features for each event within the hierarchical event representation; computing content-based features for each image in an event within the hierarchical event representation; combining content-based features for each image in an event to generate event-level content-based features; and using time-based features and content-based features for each event to classify an event into one of a pre-determined set of semantic categories.

A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.

For a system in which data packets are to be handled according to one of several rules, depending on two (or more) criteria present in each packet, such as source and destination addresses, a classification method is disclosed that allows to determine the applicable rule by a longest-matching-prefix search operation. Range tokens of non-uniform length are assigned to basic ranges of criterion values so that each combination of input values from a packet can be represented by a particular variable length combination of range tokens. A search tree containing stored rule identifiers is so designed that each particular range token combination, used as input for a longest-matching-prefix lookup operation, will provide the required identifier. Different range token combinations having the same prefix can use the same path to one stored rule identifier, so that this method reduces the storage and time requirements for the classification procedure and allows simple updating when rules change.

The invention relates to the field of computer vision recognition and transfer learning, and provides a small sample and zero sample image classification method based on metric learning and meta-learning, which comprises the following steps of: constructing a training data set and a target task data set; selecting a support set and a test set from the training data set; respectively inputting samples of the test set and the support set into a feature extraction network to obtain feature vectors; sequentially inputting the feature vectors of the test set and the support set into a feature attention module and a distance measurement module, calculating the category similarity of the test set sample and the support set sample, and updating the parameters of each module by utilizing a loss function; repeating the above steps until the parameters of the networks of the modules converge, and completing the training of the modules; and enabling the to-be-tested picture and the training picture in the target task data set to sequentially pass through a feature extraction network, a feature attention module and a distance measurement module, and outputting a category label with the highestcategory similarity with the test set to obtain a classification result of the to-be-tested picture.

A complex-adaptive system is described for providing a faceted classification of a domain of information. A dimensional concept taxonomy classifying a domain may be constructed from a faceted data set comprising facets, facet attributes, and facet attribute hierarchies. An enhanced method of faceted classification provides the taxonomy which assigns facet attributes to objects of the domain to be classified in accordance with concepts (defined using the facet attributes) that ascribe meaning to the objects. Further the taxonomy expresses dimensional concept relationships between concept definitions in accordance with the faceted data set. The complex-adaptive system selects dimensional concept taxonomy information to facilitate varying the faceted data set and subsequent iterations of the taxonomy. The complex-adaptive system may involve a machine-based approach using statistical analysis of source data structures or user interactions with the taxonomy to provide the feedback. Computer system, method and software aspects are provided.

The invention discloses an attention mechanism-based video classification method. The attention mechanism-based video classification method comprises the steps of extracting space characteristic of a video by a convolution neural network (CNN), combining all space characteristics by attention weight, sending all space characteristics to a long- and short-time memory (LSTM) network, extracting time characteristics of the video, and finally, classifying video contents by employing a multi-classification function. An attention mechanism introduced to the LSTM network can be used for simulating an identification function of a human brain, different video contents are distinguished and handled, and the video classification accuracy is effectively improved.

The invention relates to a space-time attention based video classification method, which comprises the steps of extracting frames and optical flows for training video and video to be predicted, and stacking a plurality of optical flows into a multi-channel image; building a space-time attention model, wherein the space-time attention model comprises a space-domain attention network, a time-domain attention network and a connection network; training the three components of the space-time attention model in a joint manner so as to enable the effects of the space-domain attention and the time-domain attention to be simultaneously improved and obtain a space-time attention model capable of accurately modeling the space-domain saliency and the time-domain saliency and being applicable to video classification; extracting the space-domain saliency and the time-domain saliency for the frames and optical flows of the video to be predicted by using the space-time attention model obtained by learning, performing prediction, and integrating prediction scores of the frames and the optical flows to obtain a final semantic category of the video to be predicted. According to the space-time attention based video classification method, modeling can be performing on the space-domain attention and the time-domain attention simultaneously, and the cooperative performance can be sufficiently utilized through joint training, thereby learning more accurate space-domain saliency and time-domain saliency, and thus improving the accuracy of video classification.