1420 results about "Characteristic space" patented technology

A separation surface set storage part stores information defining a plurality of separation surfaces which separate a feature space into at least one known class region respectively corresponding to at least one known class and an unknown class region. Each of the at least one known class region is separated from outside region by more than one of the plurality of separation surfaces which do not intersect to each other. A data classification apparatus determine a classification of a classification target data whose inner product in the feature space is calculable by calculating to which region of the at least one known class region and the unknown class region determined by the information stored in the separation surface set storage part the classification target data belongs. A method and apparatus for data classification which can simultaneously perform identification and outlying value classification with high reliability in a same procedure are provided.

The invention provides a voiceprint identification method based on a Gauss mixing model and a system thereof. The method comprises the following steps: voice signal acquisition; voice signal pretreatment; voice signal characteristic parameter extraction: employing a Mel Frequency Cepstrum Coefficient (MFCC), wherein an order number of the MFCC usually is 12-16; model training: employing an EM algorithm to train a Gauss mixing model (GMM) for a voice signal characteristic parameter of a speaker, wherein a k-means algorithm is selected as a parameter initialization method of the model; voiceprint identification: comparing a collected voice signal characteristic parameter to be identified with an established speaker voice model, carrying out determination according to a maximum posterior probability method, and if a corresponding speaker model enables a speaker voice characteristic vector X to be identified to has maximum posterior probability, identifying the speaker. According to the method, the Gauss mixing model based on probability statistics is employed, characteristic distribution of the speaker in characteristic space can be reflected well, a probability density function is common, a parameter in the model is easy to estimate and train, and the method has good identification performance and anti-noise capability.

The present invention provides, among other things, automatic identification of near-redundant units in a large TTS voice table, identifying which units are distinctive enough to keep and which units are sufficiently redundant to discard. According to an aspect of the invention, pruning is treated as a clustering problem in a suitable feature space. All instances of a given unit (e.g. word or characters expressed as Unicode strings) are mapped onto the feature space, and cluster units in that space using a suitable similarity measure. Since all units in a given cluster are, by construction, closely related from the point of view of the measure used, they are suitably redundant and can be replaced by a single instance. The disclosed method can detect near-redundancy in TTS units in a completely unsupervised manner, based on an original feature extraction and clustering strategy. Each unit can be processed in parallel, and the algorithm is totally scalable, with a pruning factor determinable by a user through the near-redundancy criterion. In an exemplary implementation, a matrix-style modal analysis via Singular Value Decomposition (SVD) is performed on the matrix of the observed instances for the given word unit, resulting in each row of the matrix associated with a feature vector, which can then be clustered using an appropriate closeness measure. Pruning results by mapping each instance to the centroid of its cluster.

This patent concerns novel technology for detection of zero-day data classes for domains with high-dimensional mixed continuous/discrete feature spaces, including Internet traffic. Assume there is a known-class database available for learning a null hypothesis that a given new batch of unlabeled data does not contain any data from unknown/anomalous classes. A novel and effective generalization of previous parsimonious mixture and topic modeling methods is developed. The novel unsupervised anomaly detector (AD) acts on a new unlabeled batch of data to either identify the statistically significant anomalous classes latently present therein or reject the alternative hypothesis that the new batch contains any anomalous classes. The present AD invention can be applied in an on-line setting. Labeling (by a human expert or by other means) of anomalous clusters provides new supervised data that can be used to adapt an actively learned classifier whose objective is to discriminate all the classes.

A method for unsupervised anomaly detection, which are algorithms that are designed to process unlabeled data. Data elements are mapped to a feature space which is typically a vector space . Anomalies are detected by determining which points lies in sparse regions of the feature space. Two feature maps are used for mapping data elements to a feature apace. A first map is a data-dependent normalization feature map which we apply to network connections. A second feature map is a spectrum kernel which we apply to system call traces.

The invention discloses an Android malicious application detection method and system based on multi-feature fusion. The method comprises the following steps that: carrying out decompilation on an Android application sample to obtain a decompilation file; extracting static features from the decompilation file; operating the Android application sample in an Android simulator to extract dynamic features; carrying out feature mapping on the static features and the dynamic features by the text Hash mapping part of a locality sensitive Hash algorithm, mapping to a low-dimensional feature space to obtain a fused feature vector; and on the basis of the fused feature vector, utilizing a machine learning classification algorithm to train to obtain a classifier, and utilizing the classifier to carry out classification detection. By use of the method, the high-dimensional feature analysis problem of a malicious code rare sample family can be solved, and detection accuracy is improved.

The invention discloses a gesture identification method and a gesture identification system, wherein the method comprises the following steps: step S1, a gesture detecting step: detecting a gesture in video stream in real time, marking a region in which the gesture is detected as an interested region; step S2, a gesture segmenting step: processing the interested region by utilizing skin color segmentation, and then performing edge detecting and outline extracting to obtain a point sequence of a hand-shaped outline; step S3, a gesture identifying step: firstly extracting a Fourier descriptor of the hand-shaped outline and then mapping the Fourier descriptor to a new vector of a characteristic space by utilizing PCA (principal components analysis), comparing the distance between the new vector and a gesture clustering center obtained by training, and judging a gesture type represented by the vector. The gesture identification method and the gesture identification system disclosed by the invention can improve the gesture identification accuracy and the gesture identification efficiency, and can effectively avoid background color interference.

The invention discloses a multi-operating process monitor method based on principal component analysis and support vectors data. The method establishes a uniform PCA model to various operating mixed data firstly, puts score vectors of principal component space and residual space to high dimension characteristic space. Two new statistics are established in the characteristic space for monitoring the principal component space and residual space. When the process goes wrong, a fault reconstruction method based on SVDD identifies fault. The method establishes two SVDD statistics monitor model to various operating based that the principal analysis method is used for reducing process variable dimension, reduces statistics limit of processing monitor, increases sensitivity of processing monitoring. In addition, the invention provides a fault reconstruction and identifying method aiming at detected process fault which can locate source of fault commendably, is benefit to removing fault as soon as possible, returns process to normal operation.

The invention discloses a model parameter training method based on federal learning, a terminal, a system and a medium, and the method comprises the steps: determining a feature intersection of a first sample of a first terminal and a second sample of a second terminal, training the first sample based on the feature intersection to obtain a first mapping model, and sending the first mapping modelto the second terminal; receiving a second encryption mapping model sent by a second terminal, and predicting the missing feature part of the first sample to obtain a first encryption completion sample; receiving a first encrypted federal learning model parameter sent by a third terminal, training a to-be-trained federal learning model according to the first encrypted federal learning model parameter, and calculating a first encryption loss value; sending the first encryption loss value to a third terminal; and when a training stopping instruction sent by the third terminal is received, takingthe first encrypted federal learning model parameter as a final parameter of the federal learning model to be trained. According to the invention, the characteristic space of two federated parties isexpanded by using transfer learning, and the prediction capability of the federated model is improved.

An input signal is converted to a feature-space representation. The feature-space representation is projected onto a discriminant subspace using a linear discriminant analysis transform to enhance the separation of feature clusters. Dynamic programming is used to find global changes to derive optimal cluster boundaries. The cluster boundaries are used to identify the segments of the audio signal.

The invention discloses a multi-examples-learning-based method for identifying a horror video scene. The multi-examples-learning-based method comprises the following steps of: carrying out shot segmentation and key frame selection on a video scene, wherein the video scene corresponds to a multi-examples learning bag, and a shot corresponds to the examples in the bag; respectively extracting visual characteristics, audio characteristics and color affective characteristics on the basis of the shot and a key frame to form a characteristic space; training a corresponding multi-examples learning classifier in the characteristic space; structurally analyzing a video sample to be tested, and extracting related characteristics; and predicting the category, namely horror or non-horror, of the video sample through the trained classifier. According to the invention, the novel color affective characteristics are provided and applied to the method for identifying the horror video scene, and the multi-examples-learning-based method has wide application prospect.

The invention provides a modeling method of the characteristics of population space-time dynamic moving based on multisource data fusion. The modeling method comprises: A. inputting map data, mobile phone locating data and floating vehicle data into a system and managing data organization according to requirements; B. establishing a spatial analysis model of the characteristics of population moving based on the mobile phone locating data and the floating vehicle data; C. applying the spatial analysis model of the characteristics of the population moving to carry out multisource data fusion of the map data, the mobile phone locating data and the floating vehicle data to obtain integrated information of the characteristics of the population moving; and D. analyzing the characteristics of various population moving according to the integrated information of the characteristics of the population moving and publishing an analyzed result by the geographic information system. The modeling method can acquire data of urban population space-time dynamic distribution and moving characteristics with large data amount, high quality and space-time characteristics, obtain basis of accurate population distribution and population moving characteristics, and provide decision-making supports for urban planning, land use planning, transportation planning and the like.

The invention discloses a rapid image retrieval method based on supervised topology keeping hash. The method includes the steps of S1, extracting features of obtained training images and inquiry images, converting feature spaces into new nuclear spaces, and obtaining nuclear space representation of each image; S3, conducting binary coding on the training images and the inquiry images; S4, conducting image retrieval through binary codes. For solving the rapid image retrieval problem, hash coding is studied in the nuclear space with higher expression capacity, supervise information and topology keeping information are added in the hash mapping matrix studying process, a studied mapping matrix has higher semantic expression capacity and higher within-cluster variation expression capacity, and therefore the studied binary codes are more suitable for image retrieval tasks, retrieval accuracy is improved, and retrieval result sequencing is optimized.

The invention discloses a network hot event detection method based on text classification and clustering analysis. The method solves the problem that the efficiency and accuracy rate of the existing network hot event detection method based on clustering analysis need to be improved. The method comprises the steps that feature words are respectively selected for various classes of files through feature extraction and feature selection by utilizing a training corpus; each training text and test text are represented as vectors in all of the feature spaces by utilizing a vector space model method, and the weight of each dimension of the vectors is determined by utilizing a TF-IDF (term frequency-inverse document frequency) method, and then each test text is classified; the classified test texts in different classes are respectively subjected to clustering analysis, so the hot cluster of each class is obtained, the feature word representing the hot event is obtained through further analysis, and then the word property and other aspects of each feature word are analyzed; the description of each hot event is generated by utilizing relevant language knowledge and necessary linguistic organization. With the network hot event detection method based on text classification and clustering analysis, the detection efficiency and accuracy rate of hot events can be effectively improved.

A method for graph-based spatiotemporal video segmentation and automatic target object extraction in high-dimensional feature space includes using a processor to automatically analyze an entire volumetric video sequence; using the processor to construct a high-dimensional feature space that includes color, motion, time, and location information so that pixels in the entire volumetric video sequence are reorganized according to their unique and distinguishable feature vectors; using the processor to create a graph model that fuses the appearance, spatial, and temporal information of all pixels of the video sequence in the high-dimensional feature space; and using the processor to group pixels in the graph model that are inherently similar and assign the same labels to them to form semantic spatiotemporal key segments.

The present invention includes a method for analyzing an image wherein elements defining a path within a two-dimensional image are received from a prescreener. A Sobel operator may be applied to the region around each of the elements of the chain to obtain a corresponding array of gradient directions. An angle correction may be applied to any of the gradient directions that goes beyond the highest value (in radian measure; the Pi −Pi transition), to obtain an array of gradient directions free of any artificial jumps in value. The gradient direction array (Sobel chaincode) can have its bandwidth taken to determine a single number of straightness so as to identify extremely straight edges, (manmade objects) from less straight edges (natural objects). A similar process can be used to analyze contours for straight sections, which are also parallel. These two and other filters applied to the gradient array can be part of a feature suite, for feature space analysis.

The invention provides a method and device for detecting tumbling. The method provided by the invention comprises the steps of: firstly, collecting behavioral data of a user; secondly, identifying behavior of the user according to the behavioral data of the user; thirdly, segmenting out behavioral switching data from the collected data according to a behavioral identification result, and warping the behavioral switching data into equilong characteristic vectors; and fourthly, performing tumbling detection according to the warped characteristic vectors. According to the method and device provided by the invention, tumbling detection is performed on the basis of behavioral switching, a great amount of normal behavioral data can be filtered, the complexity of a feature space is reduced, the separating capacity of models is enhanced, and the model detection rate is improved.

The invention discloses a face recognition method based on deep transformation learning in an unconstrained scene. The method comprises the following steps: obtaining a face image and detecting face key points; carrying out transformation on the face image through face alignment, and in the alignment process, minimizing the distance between the detected key points and predefined key points; carrying out face attitude estimation and carrying out classification on the attitude estimation results; separating multiple sample face attitudes into different classes; carrying out attitude transformation, and converting non-front face features into front face features and calculating attitude transformation loss; and updating network parameters through a deep transformation learning method until meeting threshold requirements, and then, quitting. The method proposes feature transformation in a neural network and transform features of different attitudes into a shared linear feature space; by calculating attitude loss and learning attitude center and attitude transformation, simple class change is obtained; and the method can enhance feature transformation learning and improve robustness and differentiable deep function.

The invention discloses an optimized face recognition method and a device thereof, which improve the rate of facial image recognition. The technical proposal is that: the method and the device combine principal component analysis and linear discriminant analysis to solve the recognition problem; namely, the principal component analysis is carried out first before the conduction of the linear discriminant analysis so as to obtain relatively low dimensional space, then the space is utilized to carry out the linear discriminant analysis, and therefore, an intra-class dispersion matrix can not be caused and the process of the linear discrimination is effective. The invention firstly adopts the principal component analysis to obtain the best feature description, based on which, optimum identifying features are obtained by adopting the linear discriminant analysis, thereby greatly reducing the space dimension of facial features; finally, a minimum distance method is adopted to carry out classification and identification and therefore the rate of recognizing human faces is evidently increased. The method and the device of the invention are applied to face recognition.

The invention discloses an agricultural drought grade monitoring method based on a temperature vegetation drought index (TVDI). The method comprises the following steps of: 1, data preparation; 2, land surface temperature (LST) data reconstruction; 3, construction of crop plantation area normalized difference vegetation index-land surface temperature (NDVI-LST) feature space; 4, TVDI calculation; and 5, drought grade monitoring based on the TVDI. The invention brings forward an LST data reconstruction method based on multi-year background values and area fluctuation values, a cultivated land area multi-year NDVI-LST feature space is constructed for crops, the TVDI is calculated, a crop drought grade monitoring model based on a supervision classification idea is designed for drought grade remote sensing monitoring, the model can quite accurately reflect drought threat degrees of the crops under difference conditions in real time, and the method has great significance in monitoring, early warning and prevention of agricultural disasters.

The invention discloses a system for automatic classification analysis for websites based on website contents. The system comprises a capture module, a website text content analysis module, a word segmentation module, a feature training extracting module and a website classification module. The feature training extracting module selects a plurality of features words with maximum weights by calculating importance degree, distinction degree and feature keyword weight of every candidate feature word and sorting the candidate feature words according to the feature keyword weights, wherein the feature keyword weights are used as weightings after the normalization of the selected feature words and a website classification vector template is created according to the given sets of the selected feature words and the feature keyword weights. The website classification module is used for generating a feature spatial vector according to the given set of the selected feature words and the weightings which are obtained by the feature training extracting module and identifying the classification of a website by calculating the similarity between the feature spatial vector and the feature spatial vector of the website. The system is capable of effectively solving the problem of network information in a mess and allowing users to searching information for positioning conveniently and accurately.