Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.

5074results about How to "Improve classification accuracy" patented technology

attention CNNs and CCR-based text sentiment analysis method

The invention discloses an attention CNNs and CCR-based text sentiment analysis method and belongs to the field of natural language processing. The method comprises the following steps of 1, training a semantic word vector and a sentiment word vector by utilizing original text data and performing dictionary word vector establishment by utilizing a collected sentiment dictionary; 2, capturing context semantics of words by utilizing a long-short-term memory (LSTM) network to eliminate ambiguity; 3, extracting local features of a text in combination with convolution kernels with different filtering lengths by utilizing a convolutional neural network; 4, extracting global features by utilizing three different attention mechanisms; 5, performing artificial feature extraction on the original text data; 6, training a multimodal uniform regression target function by utilizing the local features, the global features and artificial features; and 7, performing sentiment polarity prediction by utilizing a multimodal uniform regression prediction method. Compared with a method adopting a single word vector, a method only extracting the local features of the text, or the like, the text sentiment analysis method can further improve the sentiment classification precision.

High-efficiency SVM active half-supervision learning algorithm

The invention discloses a high-efficiency SVM active half-supervision learning algorithm. The algorithm comprises: (1), training an initial SVM classifier f<SVM><0>; (2), determining whether the f<SVM><0> satisfies a learning termination condition, and if not, skipping to step (3); (3), performing prediction marking on unmarked samples Us by use of the f<SVM><0>; (4), performing Tri-learning based half-supervision learning/QBC-based active learning on samples whose prediction mark confidence are greater than/smaller than a threshold in the Us, and adding the samples selected in the half-supervision learning/active learning to a marked training sample set; (5), training a f<SVM><k> on the updated marked training sample; and (6), repeating step (2) until the SVM classifier satisfies the termination condition of the active learning. The algorithm provided by the invention has the following advantages: during an SVM training learning process, according to the learning process, the samples which best facilitate classifier performance are autonomously selected for training the classifier, after these samples are added to the tainting set, the accuracy of classifying the unmarked samples through the semi-supervision learning is improved to the maximum degree, and the SVM classification precision is enhanced.

System and method for automatically analyzing, detecting and classifying malicious program behavior

ActiveCN102930210ACause damageOvercome shortcomings such as inability to perform adequatelyPlatform integrity maintainanceSpecial data processing applicationsDomain nameNetwork behavior
The invention discloses a system and a method for automatically analyzing, detecting and classifying a malicious program behavior. The system comprises a static analysis module, a sandbox dispatching management module, a sandbox monitoring module, a behavior abstraction module and a detection and classification module. Compared with the prior art, the system has the advantages that 1, the system is based on a behavior monitoring technology in an instruction set simulation environment; and 2, a virtual Internet is established in a sandbox through means of environment configuration, server program modification and the like, and a common network service is simulated, so that operations such as domain name server (DNS) resolution, http access, file download, Email login and mailing initiated by a malicious program can be successfully executed, the malicious program is inveigled to generate a malicious network behavior, the network behaviors are prevented from damaging a host machine and a real network, and the defects that the malicious program network behavior cannot be fully expressed during dynamic behavior analysis of a malicious program and the like are overcome.

Zero sample image classification method based on combination of variational autocoder and adversarial network

ActiveCN108875818AImplement classificationMake up for the problem of missing training samples of unknown categoriesCharacter and pattern recognitionPhysical realisationClassification methodsSample image
The invention discloses a zero sample image classification method based on combination of a variational autocoder and an adversarial network. Samples of a known category are input during model training; category mapping of samples of a training set serves as a condition for guidance; the network is subjected to back propagation of optimization parameters through five loss functions of reconstruction loss, generation loss, discrimination loss, divergence loss and classification loss; pseudo-samples of a corresponding unknown category are generated through guidance of category mapping of the unknown category; and a pseudo-sample training classifier is used for testing on the samples of the unknown category. The high-quality samples beneficial to image classification are generated through theguidance of the category mapping, so that the problem of lack of the training samples of the unknown category in a zero sample scene is solved; and zero sample learning is converted into supervised learning in traditional machine learning, so that the classification accuracy of traditional zero sample learning is improved, the classification accuracy is obviously improved in generalized zero sample learning, and an idea for efficiently generating the samples to improve the classification accuracy is provided for the zero sample learning.

MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on deep cascaded convolution network

ActiveCN108492297AAlleviate the sample imbalance problemReduce the number of categoriesImage enhancementImage analysisClassification methodsHybrid neural network
The invention provides an MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on a deep cascaded convolution network, which comprises the steps of building a deep cascaded convolution network segmentation model; performing model training and parameter optimization; and carrying out fast localization and intratumoral segmentation on a multi-modal MRIbrain tumor. According to the MRI brain tumor localization and intratumoral segmentation method provided by the invention based on the deep cascaded convolution network, a deep cascaded hybrid neuralnetwork formed by a full convolution neural network and a classified convolution neural network is constructed, the segmentation process is divided into a complete tumor region localization phase andan intratumoral sub-region localization phase, and hierarchical MRI brain tumor fast and accurate localization and intratumoral sub-region segmentation are realized. Firstly, the complete tumor region is localized from an MRI image by adopting a full convolution network method, and then the complete tumor is further divided into an edema region, a non-enhanced tumor region, an enhanced tumor region and a necrosis region by adopting an image classification method, and accurate localization for the multi-modal MRI brain tumor and fast and accurate segmentation for the intratumoral sub-regions are realized.

Hyperspectral image classification method based on spectral-spatial cooperation of deep convolutional neural network

The present invention relates to a hyperspectral image classification method based on spectral-spatial cooperation of a deep convolutional neural network, which leads the conventional deep convolutional neural network applied to a two-dimensional image into the three-dimensional hyperspectral image classification problem. Firstly, the convolutional neural network is trained by using a small volume of label data, and a spectral-spatial feature of a hyperspectral image is autonomously extracted by using the network without carrying out any compression and dimensionality reduction processing; then, a support vector machine (SVM) classifier is trained by using the extracted spectral-spatial feature so as to classify an image; and finally, the trained neural network is combined with the trained classifier, the neural network extracts a spectral-spatial feature of a to-be-classified target and the classifier determines a specific category of the extracted spectral-spatial feature so as to acquire a structure (DCNN-SVM) that can autonomously extract the spectral-spatial feature of the hyperspectral image and carry out classification to the spectral-spatial feature, thereby forming a set of hyperspectral image classification method.

Image classification method capable of effectively preventing convolutional neural network from being overfit

The invention relates to an image classification method capable of effectively preventing a convolutional neural network from being overfit. The image classification method comprises the following steps: obtaining an image training set and an image test set; training a convolutional neural network model; and carrying out image classification to the image test set by adopting the trained convolutional neural network model. The step of training the convolutional neural network model comprises the following steps: carrying out pretreatment and sample amplification to image data in the image training set to form a training sample; carrying out forward propagation to the training sample to extract image features; calculating the classification probability of each sample in a Softmax classifier; according to the probability yi, calculating to obtain a training error; successively carrying out forward counterpropagation from the last layer of the convolutional neural network by the training error; and meanwhile, revising a network weight matrix W by SGD (Stochastic Gradient Descent). Compared with the prior art, the invention has the advantages of being high in classification precision, high in rate of convergence and high in calculation efficiency.

Hybrid neural network text classification method capable of blending abstract with main characteristics

The invention relates to a hybrid neural network text classification method capable of blending an abstract with main characteristics. The method comprises the following steps that: step A: extractingan abstract from each text in a training set; step B: using a convolutional neural network to learn the key local features of the abstract obtained in the step A; step C: using a long short-term memory network to learn context time sequence characteristics on the main content of each text in the training set; step D: carrying out cascade connection on two types of characteristics obtained in thestep B and the step C to obtain the integral characteristics of the text, inputting the integral characteristics of each text in the training set into a full connection layer, using a classifier to calculate a probability that each text belongs to each category to train a network, and obtaining a deep neural network model; and step E: utilizing the trained deep neural network model to predict thecategory of a text to be predicted, and outputting the category with a highest probability as a prediction category. The method is favorable for improving text classification accuracy based on the deep neural network.

Flow velocity monitoring implementation method based on adversarial generative network

The invention provides a flow velocity monitoring implementation method based on an adversarial generative network. The flow velocity monitoring implementation method comprises the following steps that (1) water flow image preprocessing is performed; (2) image classification is performed based on the adversarial generative network; (3) flow velocity determination: the image classification results and flow velocity intervals are corresponding in a one-to-one way; and (4) state analysis: a state abnormal signal is transmitted when the monitoring result indicates that the flow velocity exceeds the preset threshold. The beneficial effects mainly reside in that the advantages of discriminant and generative classification algorithms are effectively combined in adversarial training of a generator and a discriminator and unsupervised learning is realized, and the synthetic water flow image outputted by the generator of the adversarial generative network and the real image act as the input of the discriminator together so that the robustness of a classifier for the noised water flow image can be greatly enhanced, classification is performed according to the water flow image and rapid flow velocity determination can be realized in a way of being corresponding to the preset flow velocity intervals and classified management of mass water flow information is facilitated.

Web-based text classification mining system and web-based text classification mining method

The invention discloses a web-based text classification mining system and a web-based text classification mining method. The system mainly comprises a text pre-processing module, a word segmentation processing module and a classification algorithm module, wherein the text pre-processing module is used for automatically screening specific information from texts to be tested, pre-processing the specific information, and filtering out irrelevant information to effectively represent the texts; the word segmentation processing module is used for carrying out word segmentation on the texts, finding attributes/attributive words of each text, and making preparation for selection of characteristic words; and the classification algorithm module is used for carrying out characteristic selection to obtain an optimum characteristic sub-set, or finding corresponding probabilities according to data which is provided by a file of a training result, comparing the corresponding probabilities to obtain the type of the maximum probability, drawing a conclusion and storing the conclusion in the file finally. The system overcomes the shortcoming of conditional independence assumption of a naive Bayes algorithm by using a hypertext markup language (HTML) tag weight, improves a classifier and can improve the recall ratio and precision ratio of data mining.

Methods and apparatus for privacy preserving data mining using statistical condensing approach

ActiveUS20050049991A1Enhance privacyHigh classification accuracyData processing applicationsDigital data processing detailsMultiple dimensionPrivacy preserving
Methods and apparatus for generating at least one output data set from at least one input data set for use in association with a data mining process are provided. First, data statistics are constructed from the at least one input data set. Then, an output data set is generated from the data statistics. The output data set differs from the input data set but maintains one or more correlations from within the input data set. The correlations may be the inherent correlations between different dimensions of a multidimensional input data set. A significant amount of information from the input data set may be hidden so that the privacy level of the data mining process may be increased.

Firework identification method and firework identification system based on deep learning of image

InactiveCN104408469AImproving the Speed ​​of Unsupervised LearningFew parametersCharacter and pattern recognitionData setFireworks
The invention discloses a firework identification method and a firework identification system based on deep learning of an image. The firework identification method comprises the following steps of step 1, acquiring a label-free sample image set and a label sample image set; step 2, obtaining a label-free training data set and a label training data set; step 3, performing whitening preliminary processing on training data; step 4, based on the label-free training data subjected to the whitening preliminary processing, constructing a deep neutral network based on sparse self coding by adopting unsupervised learning, and extracting a basic image feature set of the label-free training data; step 5, convolving basic image features and pooling image data; step 6, training a Softmax classifier based on the convolved and pooled label training data set; step 7, inputting the convolved and pooled images to be identified into the trained Softmax classifier to obtain the identification result. According to the firework identification method and the firework identification system disclosed by the invention, the visual identification rate of fireworks and a similar object can be effectively improved, and automatic identification with higher precision for the fireworks can be realized.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products