545 results about "Sample classification" patented technology

The invention discloses an automatic image annotation method based on semi-supervised learning. The method comprises the steps that a data set is divided into a training data set, an unlabeled data set and a test set; the SIFT feature and the HOG feature of a training sample are extracted to train an LDA_SVM classifier; color and texture features are extracted to train a neural network; unlabeleddata are used to enable two classifiers to label and predict the same unlabeled sample simultaneously; according to the contribution of the classifiers to the unlabeled sample classification accuracy,the classification results of two classifiers are weighted and fused by an adaptive weighted fusion policy, so as to acquire the final prediction label probability vector of the sample; and finally two classifiers are updated by the sample with high confidence and the predictive label thereof until the preset maximum number of iterations is reached. According to the invention, the method can makefull use of the unlabeled sample to excavate the inherent law of the image feature; the number of annotation samples required for the classifier training is effectively reduced; the annotation effectis great.

The vehicle classification method includes: the time-domain radar signal of single-frequency continuous wave radar is used as input to conduct time-frequency analysis to obtain a radar echo Doppler frequency spectrum chart changing along time; by Hafford counterchange the Doppler chart is mapped into a scattered central position parameter image; through characteristic picking-up, Karhunen-Loeve(K-L) screening and compressing, a characteristic sample is obtained, which is classified using Fisher rule to obtain the vehicle-type classification. For multi-type condition, multiple two-type classifiers are used to conduct respectively pairwise classification, according to the result of the classifiers said above the classification result is obtained by voting. Advantage: simple and reliable structure and low cost, conducting classification synchronously with detecting and speed-measuring of vehicles.

The invention discloses a zero sample image classification method and system. The method includes the following steps of: S10, inputting training data belonging to a visible category and a category tag thereof for feature extraction; S20, inputting the semantic assistance information of all category tags to obtain the semantic embedded representations of respective tags and semantic difference measure between the tags; S30, establishing a zero sample classification model, performing semantic consistency regularization on the model based on the semantic differences between the categories; S40,iteratively updating model parameters until convergence; and S50, predicting the category tag of a test image. The method and system establish a semantic consistency regularized zero sample classification model so that the output of the model conforms to the semantic neighborhood relation between categories to adapt to the semantic structure of the target category so as to obtain high classification accuracy.

Systems and methods for classifying a object as belonging to an object class or not belonging to an object class using a boosting method with a plurality of thresholds is disclosed. One embodiment is a method of defining a strong classifier, the method comprising receiving a training set of positive and negative samples, receiving a set of features, associating, for each of a first subset of the set of features, a corresponding feature value with each of a first subset of the training set, associating a corresponding weight with each of a second subset of the training set, iteratively i) determining, for each of a second subset of the set of features, a first threshold value at which a first metric is minimized, ii) determining, for each of a third subset of the set of features, a second threshold value at which a second metric is minimized, iii) determining, for each of a forth subset of the set of features, a number of thresholds, iv) determining, for each of a fifth subset of the set of features, an error value based on the determined number of thresholds, v) determining the feature having the lowest associated error value, and vi) updating the weights, defining a strong classifier based on the features having the lowest error value at a plurality of iterations, and classifying a sample as either belonging to an object class or not belonging to an object class based on the strong classifier.

The present invention relates to a zero-sample classification technology in the computer vision field, in particular, a variational automatic encoder-based zero-sample image classification method. Asto the zero-sample image classification method, the distribution of the mappings of semantic features and visual features of categories in a semantic space is fitted, and more efficient semantic associations between the visual features and category semantics are built. According to the variational automatic encoder-based zero-sample image classification method, a variational automatic encoder is adopted to generate embedded semantic features on the basis of the visual features; it is regarded that the variational automatic encoder has a latent variable Z<^>; the latent variable Z<^> is adoptedas an embedded semantic feature; as for a zero-sample image classification task and the visual feature xj of a category-unknown sample, the encoding network of the variational automatic encoder whichis trained on visual categories is utilized to calculate a latent variable Z<^>j which is generated through encoding; the latent variable Z<^>j is adopted as an embedded semantic feature, cosine distances between the latent variable Z<^>j and the semantic feature of each invisible category are calculated, wherein the semantic feature of each invisible category is represented by a symbol describedin the descriptions of the invention; and a category of which the semantic feature is separated from the latent variable Z<^>j by the smallest distance is regarded as the category of the vision sample. The method of the present invention is mainly applied to video classification conditions.

A self-improving classification system classifies specimens based on class identifiers. The system stores specimen profiles in a database that is updated with additional specimen profiles and with follow-up data that corrects classification of specimens that were initially incorrectly classified. Algorithms use the updated database to discover new class identifiers, modify thresholds of known class identifiers, and drop unnecessary class identifiers to improve classification of specimens.

The invention discloses a deep learning-based malicious code sample classification method. The method comprises the following steps: disassembling malicious code samples to obtain assembly codes; converting the assembly codes into image sample data on the basis of a corresponding relationship between a hexadecimal code and an image gray value; and inputting the image sample data into a pre-trained convolutional neural network so as to a malicious code sample classification result. The invention furthermore discloses a deep learning-based malicious code sample classification system. According to the deep learning-based malicious code sample classification method and system, classes of the malicious code samples can be correctly recognized, and the correctness of the malicious code sample classification is improved.

A software defect priority prediction method based on an improved support vector machine is mainly characterized in that an improved support vector machine model is used for modeling defect priority prediction and judging and predicting defect report processing priority. The software defect priority prediction method includes the steps: firstly, selecting solved, closed and determined error report as training data; secondly, extracting needed characteristics; thirdly, giving a sampling weight to each sample and training a classifier to classify the samples by the aid of the support vector machine on the samples; fourthly, redistributing weight vectors by the aid of obtained error rate in the manner of distributing larger weights to mistakenly classified samples and distributing smaller weights to correctly classified samples; and fifthly, sequentially iterating in the manner to finally obtain a strong classifier equal to the weighted sum of a plurality of weak classifiers. The classifiers are trained by means of machine learning, so that defect priority is automatically determined, and consumption of staff and cost is reduced.

The present invention relates to a fine-grained zero-sample classification method based on multi-layer semantic supervised attention model. The local visual features of fine-grained images are extracted by a convolution neural network, and the local visual features of fine-grained images are supervised by the text description information of categories as category semantic features, and the local visual features of fine-grained images are weighted gradually. The loss function of the multi-level semantic supervised attention model is obtained by mapping the class semantic features to the hiddenspace local visual features. The global visual features of fine-grained images are combined with the local visual features weighted by the multi-layer semantic supervised attention model as the new visual features of images. The category semantic features are embedded into the new visual feature space, and the visual features and semantic features of the output of the multi-layer semantic supervised attention network are aligned, and the softmax function is used for classification. The method of the invention can input the extracted visual features and category semantic features, and output the classification result of the image.

The invention provides a Maxout multi-convolution neural network fusion face recognition method. The technical problem of unequal classification of positive and negative samples in a single network is solved. The method comprises the steps that a regression tree combination algorithm and affine transformation processing training data are used to acquire a database after alignment; face images in the aligned database are extracted to acquire a database simply with face area images; two networks are built, and a Maxout method is used to acquire a fused network; the database simply with face area images is used to train the fused convolution nerve network to acquire a trained network model; and a test image is pre-processed to test the trained network model. According to the invention, a Maxout module is used to fuse two or more subsystems, and then is successively connected with a full connection module and an output module to acquire a complete face recognition system; the classification sensitivity of positive and negative samples of the convolution neural network can be balanced; and the face recognition accuracy is improved.

The present invention discloses a sample classification determination method, including the following steps: collecting a sample assembly to form sample databases separately; submitting assemblies in the sample databases to the virtual sandbox environment for operation and then generating corresponding sample analysis reports; analyzing the sample analysis reports, and extracting the unique feature combination information to generate a feature vector set; inputting the feature vector set into classifiers for training to obtain an optimum model; and inputting a program to be tested to the optimum model to obtain a determination result that the program to be tested is a malicious program or a normal program. The present invention improves the efficiency and accuracy of malware detection, avoids the complicated operation and high energy consumption in the dynamic detection technique, and greatly improves the detection speed on the basis of ensuring the accuracy.

An apparatus for classifying a liquid patient sample includes at least one sample container having a quantity of a sample that is aggressively acted upon so as to create a flow field. A measurement mechanism includes at least one low angle light emitter aligned with a measurement window of the at least one sample container and a detector oppositely disposed relative to the measurement window. Measurement of the scattered light detects particle characteristics of a moving flow field from the sample to determine, for example, the amount of agglutination of the sample so as to perform blood typing or other classifications without spatial separation.

The invention proposes a model training method and device based on machine learning, and the method comprises the steps: extracting samples from a sample set according to the sampling probability of each sample in the sample set, so as to generate a training set for this time; employing the training set for the training of a machine learning model; carrying out the estimation of the trained machine learning model, so as to obtain the classification accuracy of each sample in the training set; and adjusting the sampling probability of each sample in the training set according to the classification accuracy. The adjusted sampling probability is used for generating a training set for the next training. The method can achieve the adaptive adjustment of the sampling probability of each sample, improves the classification accuracy of an important sample and solves a problem that a neural network in the prior art is not accurate in sample classification.

The invention discloses a zero sample classification method based on an extreme learning machine, and the method is used for image classification. The method comprises the following steps: extracting the visual features of a training image at a training state, and extracting the training semantic features corresponding to the visual features of the training image; randomly generating a first input weight and a first threshold value for L junctions, and calculating a first output matrix of a hidden layer through employing a hidden layer mapping function; calculating the output weight of a network through the training semantic features and the first output matrix of the hidden layer; extracting the visual features of a test sample at a test stage, randomly generating a second input weight and a second threshold value for L junctions, and calculating a second output matrix of the hidden layer through employing the hidden layer mapping function; calculating an embedded vector, correspondingly located in a semantic space, of the second output matrix through the output weight, and judging the type of the test sample according to the similarity of the embedded vector with the semantic features in a semantic feature space. The method reduces the training time, and improves the classification speed of the image.

A zero-sample classification method based on antagonistic self-encoder model is provided. Using countermeasure self-encoder networks trained on visible classes, selecting network parameters w and v that best approximate the distribution of visual features and associate visual features with category semantic features, then the class semantic feature at of the unseen class is inputted into the network, and the Euclidean distance between the generated visual feature and the real visual feature is calculated by using the decoder network G. Finally, the category with the smallest distance is considered as the predicted category, so as to realize the task of zero-sample classification. The invention is more consistent with the characteristics of the real data, and simultaneously aligns the visual features and the category semantic features, so that better classification effect can be realized in the zero-sample task.

The invention discloses a general disturbance generation method based on a generative adversarial network. Firstly, the generative adversarial network generates general disturbance to obtain an adversarial sample; discriminating the adversarial sample and the original sample by a discriminating network, calculating a discriminating network objective function, and performing back propagation for optimization; and finally, predicting adversarial sample classification by a deep learning model, discriminating adversarial samples by a discriminant network, calculating and generating a network objective function, and performing back propagation for optimization. The GAN-based general disturbance generation method provided by the invention can provide a thought of machine learning model safety research for users in the fields of computer vision, deep learning and the like.

The invention provides a method for enhancing a pavement image, and relates to a pavement crack detecting method based on an active contour model. The pavement crack detecting method based on the active contour model comprises the following steps of: enhancing the contrast of a pavement crack image; carrying out accurate detection of a pavement crack area on the image with an enhanced contrast; and classifying pavement cracks based on an accurate detection result. According to the technical scheme provided by the invention, various crack images obtained in the high-speed operation process in a natural scene can be automatically identified. With the adoption of the method provided by the invention, the high-accuracy positioning of a crack suspicious area is realized, and the robustness identification is carried out on an area with a positioning error by using various sample classification methods.

Systems and methods that comprise receiving a training set of samples, a set of features for a first subset of the set of features, a feature value with a first subset of the training set, a weight with a second subset of the training set. Determining for a second subset of the set of features, a first threshold value with a first metric minimized, and determining, for a third subset of the set of features, a second threshold value with a second metric is minimized, then determining, for a fourth subset of the set of features, a number of thresholds, determining, for a fifth subset of the set of features, an error value based on the number of thresholds, afterward determining the feature having the lowest error, and finally updating the weights by classifying a sample as either belonging to an object class or not based on the strong classifier.

Methods, computer program products and computer systems for constructing a classifier for classifying a specimen into a class are provided. The classifiers are models. Each model includes a plurality of tests. Each test specifies a mathematical relationship (e.g., a ratio) between the characteristics of specific cellular constituents. Each test is polled using characteristic values of these specified cellular constituents from the biological specimen to be classified. In some embodiments, each test has a positive threshold and a negative threshold. When the value of the test exceeds the positive threshold, the test polls positive. When the value of the test is below the negative threshold, the test polls negative. When the value of the test is between the negative threshold and the positive threshold, the test polls indeterminate. The value of each test is combined to provide a composite score. In some embodiments, positive composite scores indicate that the specimen belongs in the class associated with the model.

A Collaborative Deep Network model method for pedestrian detection includes constructing a new collaborative multi-model learning framework to complete a classification process during pedestrian detection; and using an artificial neuron network to integrate judgment results of sub-classifiers in a collaborative model, and training the network by means of the method for machine learning, so that information fed back by sub-classifiers can be more effectively synthesized. A re-sampling method based on a K-means clustering algorithm can enhance the classification effect of each classifier in the collaborative model, and thus improves the overall classification effect. By building a collaborative deep network model, different types of training data sets obtained using a clustering algorithm are used for training a plurality of deep network models in parallel, and then classification results, on deep network models, of an original data set are integrated and comprehensively analyzed, which achieves more accurate sample classification.

The invention relates to a multi-label image classification technology oriented to the field of multimedia content understanding and analysis so as to construct a new classification model and realizea correlation-level-based multi-label classification algorithm. A ranking-learning-based multi-label zero sample classification method provided by the invention comprises the following steps: at a feature extraction stage, carrying out feature description of different modes by using an existing feature extractor to obtain a training data set; at a multi-mode feature transformation stage, giving atraining sample set pair including an original image and a corresponding label between which determined marking information is provided so as to train the model; and at a classification marking stage,giving an original image of a testing sample and a possible label to carry out testing. At the classification marking stage, the correspondence relationship between the original image and the label is not determined. The ranking-learning-based multi-label zero sample classification method is mainly applied to the multi-label image classification occasions.

The invention discloses a method for determining data sample class and a system thereof. The method of the invention comprises the following steps: performing a plurality of first Map tasks in parallel, wherein each Map task obtains parts of data samples integrated by data samples to be classified; calculating the similarity of each data sample in parts of data samples and a training sample centralized by the data sample; taking the class corresponding to the first K descending sort similarities by aiming at each data sample; performing an Reduce task which respectively collects the classes corresponding to the K similarities of each data; and determining the majority of class in each data sample to the class of the data sample. The invention can improve the efficiency of classified treatment of a data sample.

An automated method for classifying a cytological sample is provided. The method comprises interrogating the sample with one or more wavelengths of light to obtain a result, and then attaching one or more designators to the sample based on whether the result meets a given criterion. The method allows for rapid feedback on the characteristics of the sample, permitting automated designation of the sample as positive for a given characteristic, and allowing for immediate remedial actions if the sample fails to meet the criterion.

The invention provides an imbalance sample classification method based on a PSO (Particle Swarm Optimization) algorithm. A PSO algorithm is adopted, the sampling rates of a boundary sample and a safe sample in an oversampling process are optimized to obtain an optimal oversampling multiplying power, and meanwhile, characteristics are optimized so as to select a characteristic combination which can simplify operations and improve a classification result and has best representativeness. The imbalance sample classification method adopts AUC / F-Mea as the fitness function of the algorithm so as to improve the effect of a final classifier.

The invention provides a driving style classification and identification system and method suitable for domestic crowds. The identification system comprises a driving style road environment simulationmodule, a data acquisition module, a database processing module, a dimension reduction module, a database sample classification module and a driving style identification module. 29 driving style characteristic parameters are provided so that the driving style is comprehensively analyzed and judged from multiple aspects. A thought of establishing a driving style database of domestic drivers is provided. A fuzzy C-means classifier is proposed to classify the driving styles. The problem of how to accurately classify driving style samples is solved, and reasonable classification of a driving style database is realized; and a driving style identification model is established by using a mode identification neural network, so that the driving style identification precision is improved, and the driving style identification difficulty is reduced.

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.

The invention discloses a clinical tissue sample bank information management method, which comprises the following steps of: establishing a clinical tissue sample bank, wherein the sample bank information comprises sample classification label information and positioning label information, the sample classification label information comprises information of hospital, patient hospitalization number, sample type and number and the like, and the positioning label information comprises information of storage equipment, drawers divided in the storage equipment, test tube boxes, test tube number and the like; dividing the storage equipment according to the positioning label information; acquiring a patient sample, correspondingly sticking a sample classification label and a positioning label, and storing the patient sample in the storage equipment according to the positioning label information; submitting a calling request according to the patient hospitalization number; and acquiring the positioning label information of the patient from the sample bank, taking out the positioning label information from the storage equipment, exporting complete sample information of the patient, and returning to the step four. The method greatly improves the sample management efficiency and quality of the sample bank.

Systems and methods are disclosed that facilitate producing probabilistic outputs also referred to as posterior probabilities. The probabilistic outputs include an estimate of classification strength. The present invention intercepts non-probabilistic classifier output and applies a set of kernel models based on a softmax function to derive the desired probabilistic outputs. Such probabilistic outputs can be employed with handwriting recognition where the probability of a handwriting sample classification is combined with language models to make better classification decisions.

The invention discloses a word embedding-based deep zero sample classification method. Types not appearing in a learning stage still can be identified in a prediction stage. A word embedding and depthfeature extraction-based zero sample image learning model is proposed; according to the method, a subspace of image feature and semantic feature joint embedding is learnt through a strong deep neuralnetwork; and by utilizing a semantic capability of word vectors, the purpose of zero sample learning of an image is achieved. A deep learning method and zero sample learning combination-based model is proposed; a large amount of improvements are made for a combination part embedding space; reference and guidance are provided for learning of image zero samples or zero samples in other modes; and the shortcomings of indefinite sample attribute definition, manual feature extraction and the like in conventional zero sample learning are overcome. The method is widely used in an end-to-end type prediction task, and is especially suitable for the type prediction task short of training samples and even short of a type of training samples.