5077results about How to "Improve classification accuracy" patented technology

A system and method for distinguishing human input events from malware-generated events includes one or more central processing units (CPUs), one or more input devices and memory. The memory includes program code that when executed by the CPU causes the CPU to obtain a first set of input events from a user utilizing the input device. The first input events are used to obtain or derive a feature indicative of the user, such as a multi-dimensional feature vector as provided by a support vector machine. Second input events are then obtained, and the second input events are classified against the feature to determine if either the user or malware initiated the second input events.

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.

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.

A method and system for domain adaptation based on multi-layer fusion in a convolutional neural network architecture for feature extraction and a two-step training and fine-tuning scheme. The architecture concatenates features extracted at different depths of the network to form a fully connected layer before the classification step. First, the network is trained with a large set of images from a source domain as a feature extractor. Second, for each new domain (including the source domain), the classification step is fine-tuned with images collected from the corresponding site. The features from different depths are concatenated with and fine-tuned with weights adjusted for a specific task. The architecture is used for classifying high occupancy vehicle images.

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.

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.

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.

The invention provides an SAR image terrain classification method based on a depth RBF network. The method mainly solves the problem of the prior art that the accuracy of classification is low. The method comprises the steps of (1) extracting the texton features of an SAR image; (2) training the texton features of the SAR image through a first-layer RBF neural network of the depth RBF network to obtain the advanced features of the image; (3) training the advanced features through a second-layer sparse autocoder network SAE of the depth RBF network to obtain more advanced features of the image; (4) training the more advanced features through a third-layer RBF neural network of the depth RBF network to obtain the terrain classification features of the image; (5) comparing the terrain classification features of an image test sample with a test sample label, adjusting the parameters of each layer of the depth RBF network, and obtaining an optimal test classification accuracy. The method is high in classification accuracy and can be used for complicated image classification.

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.

The invention provides a human body behavior identification method based on an inertial sensor. The method comprises the steps of acquiring human body behavior data of testees by means of the inertial sensor, conducting sliding window segmentation on the acquired human body behavior data, conducting feature extraction on a triaxial accelerated speed subsequence and a triaxial angular speed subsequence which are obtained after sliding window segmentation, conducting feature fusion on a feature vector to form a sample set of the human body behaviors of the testees, conducting feature selection on the sample set by means of the least correlated maximum redundant algorithm and the Bayes regularization sparse polynomial logistic regression algorithm, obtaining the classification feature vectors of all human body behaviors of all the testees, obtaining a classifier model of each human body behavior by means of a fuzzy least square support vector machine, and obtaining a human body behavior identification result after the human body behavior data are tested by means of the fuzzy least square support vector machine. By means of the human body behavior identification method, self-adaptation and identification efficiency can be improved.

A solution of the invention discloses a multi-feature-fusion Chines-text classification method based on Attention neural network, and belongs to the field of natural language processing. In order to further improve accuracy of Chinese-text classification, the method fully exploits features of text data under three different sizes of convolution kernel granularity through fusing three CNN paths; interconnections among the text data are manifested through fusing an LSTM path; and in particular, relatively important data features are enabled to play a greater role in a Chinese-text class recognition process through merging a provided Attention algorithm model, and thus recognition ability of a model on Chinese text classes is improved. Experiment results show that compared with a CNN model, an LSTM structure model and a combined model of the two parts under the same experiment conditions, the model provided by the invention is significantly improved in Chinese-text classification accuracy, and can be better applied to the Chinese-text classification field with high requirements on the classification accuracy.

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.

Mobile device (102) comprising a number of sensing entities (230) for obtaining data indicative of the context of the mobile device and / or user thereof, a feature determination logic (230) for determining a plurality of representative feature values utilizing the data, and a context recognition logic (228) including an adaptive linear classifier (234), configured to map, during a classification action, the plurality of feature values to a context class, wherein the classifier is further configured to adapt (236) the classification logic thereof on the basis of the feature values and feedback information by the user of the mobile device. A method to be performed by the mobile device is presented.

The invention discloses an attention mechanism relationship comparison network model method. An attention relationship comparison network model for small sample learning under a small amount of labeled sample data is constructed. Based on a relational network architecture, the model is divided into a feature coding part, a feature combination part and a relational coding part, the feature coding module is used for extracting image feature information, and the feature combination part is used for recombining the extracted query image feature information with the training image feature information of each group to form a new combined feature map. The relation encoding module performs nonlinear metric learning of the network; by introducing an attention mechanism and a spectrum normalizationmethod into an end-to-end deep convolutional neural network model, the model has higher classification accuracy under the condition of small sample learning, the stability of a final training result of the model is improved, and the image classification accuracy of an existing model in small sample learning is improved.

The invention, which belongs to the technical field of remote-sensing image classification, relates to a multi-mode-characteristic-fusion-based remote-sensing image classification method. Characteristics of at least two modes are extracted; the obtained characteristics of the modes are inputted into an RBM model to carry out fusion to obtain a combined expression of characteristics of the modes; and according to the combined expression, type estimation is carried out on each super-pixel area, thereby realizing remote-sensing image classification. According to the invention, the characteristics, including a superficial-layer mode characteristic and a deep-layer mode characteristic, of various modes are combined by the RBM model to obtain the corresponding combined expression, wherein the combined expression not only includes the layer expression of the remote-sensing image deep-layer mode characteristic but also includes external visible similarity of the superficial-layer mode characteristic. Therefore, the distinguishing capability is high and the classification precision of remote-sensing images is improved.

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.

The invention provides an image quality evaluating method based on a support vector machine. The method comprises the following steps: first, a preprocessed image sample is selected and extracted according to characteristic value, a processed sample set is respectively divided into a training set and a testing set; secondly, the training set is used for training the support vector machine, the number of the support vector machine is ensured according to a certain level which is required by a system, thus ensuring each support vector machine to be trained, wherein, an input sample is the characteristic value of the image and an output sample is the level of the image quality; thirdly, the trained support vector machine is used for adjusting and optimizing correlation parameters with the testing set and determining the parameter of the decision function of the optimal hyperplane of the support vector machine model; and finally, the support vector machine model which is trained and optimized is used for evaluating the quality level of the image sample. The invention has the advantages of little required sample, fast arithmetic speed, high precision, good performance, strong popularization, etc.

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.

The invention relates to a hierarchical classification method for internet flow, comprising the following steps: firstly, coarse grained classification is conducted as follows: a flow statistical property method based on machine learning is adopted for quickly classifying network flow, the network flow is divided into applied categories with different characteristics, if the flow distinguished by the coarse grained classification needs to be used, the flow can be output directly, and if the flow needs further classification, next step is conducted; and secondly, fine grained classification is conducted as follows: classification is further conducted on the applied categories distinguished by the coarse grained classification, the network flow can be intelligently, accurately and effectively identified in real time, good integrity and expandability are realized, and the requirements on the internet flow classification with different application targets and classification grain size can be met.

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.

The present invention discloses an integrated support vector machine mixed intelligent diagnosis method of machine failure. Said method includes the following steps: respectively adopting and lifting small wave packet, utilizing frequency band and empirical mode decomposition process to decompose vibration signal according to the eigen mode component and extract time domain statistical character of decomposed signal to form total characteristic set; providing characteristic distance evaluation technique and characteristic evaluation index; utilizing said characteristic evaluation index to select most sensitive characteristic set from the total characteristic set; using said most sensitive characteristic set as diagnosis characteristics and creating integrated support vector machine mixed intelligent diagnosis model so as to implement intelligent diagnosis of machine failure state.

The invention discloses an urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud. The method includes: S1) a step of subjecting original point cloud data to road surface segmentation based on wheel path data to obtain road surface point cloud data; S2) a step of subjecting the obtained road surface point cloud data to binarization processing and extracting road marker points; S3) a step of clustering the road marker points and separating independent road marker targets; S4) a step of sorting large road markers and small road markers according to the dimensions of the obtained road marker targets; S5) a step of subjecting the large road markers to sorting processing based on wheel paths and road edge lines; and S6) a step of subjecting the small road markers to sorting processing based on deep learning and principal component analysis. The method rapidly and accurately extracts and sorts urban road markers, largely reduces the time and labor cost for data processing, and effectively guarantees traffic safety and intelligent drive reliability.

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.

The invention provides a method of constructing a text classification model. The method comprises the steps of: constructing a training sample set according to structure features of characters, wordsand sentences of text information, wherein each piece of sample data in the training sample set corresponds to a feature matrix A of a piece of text information about the words and a feature matrix Babout the characters and a category vector O corresponding to the piece of text information, and the dimension number of O is the same as a category number; and using the feature matrix A about the words and the feature matrix B about the characters in the training matrix set as input and the corresponding category vector O as output to train a deep learning model to obtain the text classificationmodel. Classification is carried out according to the classification model constructed by the method, an accuracy rate of text classification can be improved, and the method is particularly suitablefor use in short-text classification.

In one example, a method includes receiving a feature vector that characterizes a call history for a telephone network subscriber, wherein the feature vector comprises respective categorical values for one or more categorical features and respective continuous values for one or more continuous features, and applying, to the categorical values, a first algorithm to determine a categorical score for the feature vector. The example method further includes applying, to the continuous values, an isolation forest algorithm to determine a continuous score for the feature vector, and outputting, in response to determining at least one of the categorical score for the feature vector and the continuous score for the feature vector indicate the feature vector is anomalous, an indication that the feature vector is anomalous.

A call center includes a message playback unit for playing back a prerecorded greeting during an outgoing call while a call classifier unit within the call center processes an audible signal received from a remote party location. A call processing unit places a call to a remote party location via a communication network to attempt to elicit a desired response from the remote party. The call classifier then processes an audible signal received from the remote party location to determine whether or not the call was answered by a live party. The prerecorded greeting is then played while the call classifier is simultaneously processing the audible signal. If the call classifier determines that the call was answered by a live party, the call processing unit completes a talk path between the remote party location and a local agent at the call center who handles the remainder of the call. The call processing unit will normally wait until the greeting has ended to complete the talk path. If the call classifier determines that the call was not answered by a live party, the call processing unit will terminate the call.

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.

The invention relates to a recognition method of digital music emotion, belonging to the field of computer pattern recognition; the recognition method solves the problem that the existing recognition method of digital music emotion can not recognize sampling-based digital music format, the sorting technology based on a multi-class support vector machine is adopted, acoustic characteristic parameters and music theory characteristic parameters are combined, so as to carry out emotion recognition of digital music; the recognition method comprises the following steps: (1) pretreatment; (2) characteristic extraction; (3) training the multi-class support vector machine; (4) recognition. The music emotion is classified into happiness, impassion, sadness and relaxation, the emotion recognition is carried out based on a sampling-based digital music format file, the common acoustic characteristics in the speech recognition field are not only extracted, and a series of music theory characteristics are extracted according to the theory characteristics of music; meanwhile, the sorting method based on the support vector machine is adopted, the leaning speed is rapid, the sorting precision ratio is high and the recognition efficiency is improved.

Disclosed, among other things, is a computer device and computer-implemented method of classifying cells within an image of a tissue sample comprising providing the image of the tissue sample as input; computing nuclear feature metrics from features of nuclei within the image; computing contextual information metrics based on nuclei of interest with the image; classifying the cells within the image using a combination of the nuclear feature metrics and contextual information metrics.

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.