1822 results about "Mutual information" patented technology

A method and apparatus are provided for segmenting words into component parts. Under the invention, mutual information scores for pairs of graphoneme units found in a set of words are determined. Each graphoneme unit includes at least one letter. The graphoneme units of one pair of graphoneme units are combined based on the mutual information score. This forms a new graphoneme unit. Under one aspect of the invention, a syllable n-gram model is trained based on words that have been segmented into syllables using mutual information. The syllable n-gram model is used to segment a phonetic representation of a new word into syllables. Similarly, an inventory of morphemes is formed using mutual information and a morpheme n-gram is trained that can be used to segment a new word into a sequence of morphemes.

A system and method are described for dynamically adapting the communication characteristics of a multiple antenna system (MAS) with multi-user (MU) transmissions (“MU-MAS”). For example, a method according to one embodiment of the invention comprises: transmitting a training signal from each antenna of a base station to each of a plurality of wireless client devices, each of the client devices analyzing each training signal to generate channel characterization data, and receiving the channel characterization data at the base station; computing a plurality of MU-MAS precoder weights based on the channel characterization data, the combined MU-MAS precoder weights comprising a MU-MAS channel matrix; determining instantaneous or statistical channel quality (“link quality metric”) for the wireless client devices using mutual information of MU-MAS links or singular values of the MU-MAS composite channel matrix; determining a subset of users and a MU-MAS transmission mode based on the link quality metric; precoding data using the MU-MAS precoder weights to generate precoded data signals for each antenna of the base station; and transmitting the precoded data signals through each antenna of the base station to each respective client device within the selected subset.

The present invention is intended to allow a user to easily and precisely extract related terms through use of mutual information without requiring morphological analysis or syntax analysis, by constituting a related term extraction apparatus from preceding-and-subsequent term extraction means for extracting a preceding term occurring prior to a specified term or a subsequent term occurring subsequent to the same in text data; a frequency calculation means for calculating the occurrence frequencies of the specified term, the preceding terms, and the subsequent terms; probability-of-occurrence calculation means for calculating the occurrence probabilities of the preceding and subsequent terms together with the occurrence probability of the specified term; probability-of-concurrence calculation means for calculating the probabilities of the preceding and subsequent terms cooccurring with the specified term; order-dependent degree-of-association calculation means for calculating an order-dependent degrees of the preceding and subsequent terms cooccurring with the specified term; order-independent degree-of-association calculation means for calculating an order-independent degrees of occurrence of the preceding and subsequent terms with the specified term; and term group extraction means for extracting from the text data a group of terms related to the specified term, on the basis of the degree-of-association information calculated by the order-independent degree-of-association calculation means.

The invention relates to an intelligent battery management system of an electric car. In the invention, a core control module is connected with N battery data collecting modules via a K bus and is connected with a charging module, a battery pack monitoring module and a touch screen display system; the battery management system comprises a database management module, the battery pack monitoring module, a self-checking control module and an abnormal control module; the battery data collecting modules are provided with a plurality of battery data collecting control chips; and the core control module is connected to computer control software by utilizing a universal serial bus (usb) interface. The battery management system provided by the invention has the advantage of solving the problems that real-time and dynamic comparison cannot be carried out, a corresponding fault processing function and a mutual information platform are lacked and the like in the past. The invention realizes that data such as voltage, current, temperature and the like of a battery are subjected to acquisition, SOC (State of Charge) estimation, real-time communication, equalization and insulation monitoring and compared with each standard datum in a database, so that a dynamic contrast model is established; and due to the adoption of a layered pattern, the control modules are used for controlling the voltage, the current and the temperature. The interaction with users and the warning are carried out through a touch screen.

A method provides guidance to the physician during a live bronchoscopy or other endoscopic procedures. The 3D motion of the bronchoscope is estimated using a fast coarse tracking step followed by a fine registration step. The tracking is based on finding a set of corresponding feature points across a plurality of consecutive bronchoscopic video frames, then estimating for the new pose of the bronchoscope. In the preferred embodiment the pose estimation is based on linearization of the rotation matrix. By giving a set of corresponding points across the current bronchoscopic video image, and the CT-based virtual image as an input, the same method can also be used for manual registration. The fine registration step is preferably a gradient-based Gauss-Newton method that maximizes the correlation between the bronchoscopic video image and the CT-based virtual image. The continuous guidance is provided by estimating the 3D motion of the bronchoscope in a loop. Since depth-map information is available, tracking can be done by solving a 3D-2D pose estimation problem. A 3D-2D pose estimation problem is more constrained than a 2D-2D pose estimation problem and does not suffer from the limitations associated with computing an essential matrix. The use of correlation-based cost, instead of mutual information as a registration cost, makes it simpler to use gradient-based methods for registration.

The invention provides a remote sensing image registration method of a multi-source sensor, relating to an image processing technology. The remote sensing image registration method comprises the following steps of: respectively carrying out scale-invariant feature transform (SIFT) on a reference image and a registration image, extracting feature points, calculating the nearest Euclidean distances and the nearer Euclidean distances of the feature points in the image to be registered and the reference image, and screening an optimal matching point pair according to a ratio; rejecting error registration points through a random consistency sampling algorithm, and screening an original registration point pair; calculating distribution quality parameters of feature point pairs and selecting effective control point parts with uniform distribution according to a feature point weight coefficient; searching an optimal registration point in control points of the image to be registered according to a mutual information assimilation judging criteria, thus obtaining an optimal registration point pair of the control points; and acquiring a geometric deformation parameter of the image to be registered by polynomial parameter transformation, thus realizing the accurate registration of the image to be registered and the reference image. The remote sensing image registration method provided by the invention has the advantages of high calculation speed and high registration precision, and can meet the registration requirements of a multi-sensor, multi-temporal and multi-view remote sensing image.

A system and method are described for dynamically adapting the communication characteristics of a multiple antenna system (MAS) with multi-user (MU) transmissions (“MU-MAS”). For example, a method according to one embodiment of the invention comprises: transmitting a training signal from each antenna of a base station to each of a plurality of wireless client devices, each of the client devices analyzing each training signal to generate channel characterization data, and receiving the channel characterization data at the base station; computing a plurality of MU-MAS precoder weights based on the channel characterization data, the combined MU-MAS precoder weights comprising a MU-MAS channel matrix; determining instantaneous or statistical channel quality (“link quality metric”) for the wireless client devices using mutual information of MU-MAS links or singular values of the MU-MAS composite channel matrix; determining a subset of users and a MU-MAS transmission mode based on the link quality metric; precoding data using the MU-MAS precoder weights to generate precoded data signals for each antenna of the base station; and transmitting the precoded data signals through each antenna of the base station to each respective client device within the selected subset.

A system architecture is disclosed that facilitates rapid execution of 3D registration or alignment algorithms. A first image module (e.g., RAM) is included to store data corresponding to images to be registered. A processor coupled to the first storage module accesses the data and determined mutual histogram (MH) values which are then used to compute mutual information (MI) between the images. The processor accumulates the MH values in a second image module. The second storage module is accessible so that registered images can be displayed. The architecture is scalable facilitating distributed calculations to speed-up the registration process.

The invention discloses an internet-facing filtration system of unhealthy information and a method thereof. The unhealthy information filtration system comprises a user data submission module, a user service management system, an auditing platform for user mutual information, an operation platform for purifying service, a knowledge base, and at least an indexing engine. The user data submission module is connected with the user service management system that is connected with the operation platform for purifying service. The operation platform for purifying service is connected respectively with the auditing platform for user mutual information and each indexing engine. The indexing engine is connected with the knowledge base. A plurality of intelligent technologies including word segmentation, keywords matching, and vector model as well as a plurality of processing algorithms with high performances are applied in the invention to process data. According to the invention, indexing services of information including sensitive information, erotic information, vulgar information, junk information, and commercial advertisements and the like are provided for the internet community, so that a high-efficient information management mean is provided for the client.

A method and system for electronic content storage and retrieval using Galois Fields and information entropy on cloud computing networks. Electronic content is divided into plural portions and stored in plural cloud storage objects based on determined information entropy of the electronic content thereby reducing location guessing of the electronic content using information gain and mutual information. Storage locations for the plural cloud storage objects are selected using a Galois field. The plural cloud storage objects are distributed across the cloud network. The Galois filed and information entropy providing various levels of security and privacy for the electronic content.

A method for selecting a relay mode depending on channel status of relay links in a multihop relay broadband wireless communication system and a Relay Station (RS) apparatus for supporting the method. When signals are received from a Base Station (BS) and a Mobile Station (MS), channel status values (e.g., eigenvalue, mutual information, and probability error) of relay links (BS-RS link and RS-MS link) are estimated using the received signals. The estimated channel status values are compared with a preset reference value. According to a result of the comparison, the relay mode for relaying the received signals is selected. Accordingly, the reliability of the relayed signal can be enhanced and the capacity of the signal link can be increased.

A method for extracting key terms and associated key terms for use in text mining is provided. The method includes receiving unstructured text documents, such as emails over a customer service system. Term candidates are extracted based on identifying consecutive word strings satisfying a context independency threshold. Term candidates are weighted using mutual information to generate a list of weighted terms. The weighted terms are then recounted. Terms are associated based on Chi-square values. Associated terms can then be used for information retrieval. A user interface can be personalized with individual user profiles.

The invention discloses a short-term load prediction method of a variational mode decomposition and deep belief network. The method comprises the following steps of 1) using a variational mode decomposition method to decompose original historical load data into a series of mode functions with different characteristics; 2) using an approximate entropy to calculate each modal function complexity, merging the modal functions whose approximate entropy values are similar into a new component, and carrying out characteristic analysis on each component; 3) in order to calculating correlation of an influence factor and an output variable, carrying out normalization processing on data; 4) combining a period characteristic of a load, and using a mutual information theory to select an input variable set from aspects of a historical load, a meteorology factor, a date type and the like; and 5) constructing the short-term load prediction method based on the deep belief network (DBN), and verifying method validity through a load prediction scene before 24h. By using the method, short-term load prediction precision is effectively increased and an electric power system load prediction problem can be well solved.

The invention provides a safe fingerprint verification method and a system, and a safe fingerprint verification system is constructed by using an image acquisition unit, a verification characteristic extraction unit, an assisted characteristic extraction unit, a template encryption unit, a template storage unit, a registration parameter computing unit, a template decryption unit and the like. The method and the system provided by the invention take a fuzzy safety box method as a basic framework, adopt the number of ridge lines between the position of a fingerprint detailed point and the adjacent three detailed points thereof as verification characteristics, extract stable reference points from fingerprints and blocking direction fields of the peripheral specific neighborhoods thereof as assisted characteristics, use a method based on the direction field mutual information to evaluate the coincidence degree of the fingerprint registration, and search the optimum parameters by a searching strategy from roughness to refinement, namely, the optimum parameters are the registration parameter for the template fingerprint and the querying fingerprint. The registration parameters are used to convert the querying fingerprint characteristics, and encryption and verification operation are carried out on the template fingerprint by using the converted querying fingerprint verification characteristics.

A 2D image supplied from an image input unit including a wide view lens is sampled into a discrete form by an array sensor, and then mapped to a multi-resolution space by a 2D filter. The feature of the supplied image is detected, and then the mapped image is transformed to a local pattern about the detected feature, and then the coordinates of the position of the feature and the code word of the local pattern are formed into a set which is then encoded. The code is supplied to each cell of a stochastic automaton. The quantity of visual information is calculated in accordance with the quantity of mutual information between different cells of the stochastic automaton consisting of cells in blocks, the coordinates of the position of the feature and the distance from the feature to the optical axis so as to control the optical axis of the image input unit in such a manner that the quantity of visual information is maximized.

Apparatus and methods for plasticity in spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). Plasticity mechanism may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and / or mutual information determined over an activity window. Several similarity estimates, corresponding to different unit-to-unit pairs may be combined. The combination may comprise a weighted average. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green).

Generally, the present invention determines and uses spectral peak information, which preferably augments feature vectors and creates augmented feature vectors. The augmented feature vectors decrease errors in pattern recognition, increase noise immunity for wide-band noise, and reduce reliance on noisy formant features. Illustratively, one way of determining spectral peak information is to split pattern data into a number of frequency ranges and determine spectral peak information for each of the frequency ranges. This allows single peak selection. All of the spectral peak information is then used to augment a feature vector. Another way of determining spectral peak information is to use an adaptive Infinite Impulse Response filter to provide this information. Additionally, the present invention can determine and use incremental information. The incremental information is relatively easy to calculate and helps to determine if additional or changed features are worthwhile. The incremental information is preferably determined by determining a difference between mutual information (between the feature vector and the classes to be disambiguated) for new or changed feature vectors and mutual information for old feature vectors.

Methods, systems, and devices are described for wireless communications at a wireless device. A wireless device may adaptively select a parity check matrix to increase the reliability of signal transmission by adapting to different channel statistics and channel types (e.g., erasure channels, channels with additive white Gaussian noise, and channels with discrete or continuous alphabets). For example, polarization codes (i.e., codes based on rows of a polarization matrix) may be used to construct parity check matrices “on-the-fly” given an estimation of dynamic channel conditions or diverse channel structures. The channel may be decomposed into polarized sub-channels corresponding to the polarization codes, and mutual information profiles may be determined for each of the polarized sub-channels. The parity check matrix corresponding to the polarization codes may be constructed based on the mutual information profile of all polarized sub-channels. The wireless device may encode or decode data based on the constructed parity check matrix.

A system, method, and tangible computing apparatus is disclosed for the detection of anomalies in an integrated data network. Said system, method and apparatus comprises the creation and construction of a mathematical model that utilizes multi-dimensional mutual information to detect interactions and interrelationships between pairs of data streams and among pluralities of data streams. Real-time analysis of the operations of an integrated data network is enhanced and expedited via use of locality sensitive hashing that relies on density determinations of clusters of data.

While decoding a representation, imported from a channel, of a codeword that encodes K information bits as N>K codeword bits, by updating estimates of the codeword bits in a plurality of iterations, the iterations are interrupted upon satisfaction of an interruption criterion that is either an order-dependent interruption criterion or an interruption criterion that includes an estimate of mutual information of the codeword and a vector that is used in the decoding iterations. Either the iterations are terminated or the iterations are resumed after one or more elements of one or more vectors used in the iterations is / are modified.

The invention provides, in some aspects, methods and apparatus for registering 3D image volumes by utilizing a graphics processing unit (GPU) to facilitate maximizing the “mutual information” of the two image volumes being registered. Particularly, the GPU is used to compute a histogram representing a probability that a pixel value in one of the images being registered coincides with a pixel value in a transform of the other image. In one aspect, this histogram is generated by a two-step approach including (i) “drawing” a polygon covering a two-component render target having as many pixels as there are samples, where the value of each pixel in the target includes the intensities of the respective pixels of the first and second images, (ii) interpreting that render target as a buffer of vertex positions and, for each sample, rendering into a new render target, a single vertex using coordinates from that buffer.

A route is selected in a wireless cooperative relay network of nodes. A decoding order is initialized. A set of resources is minimized subject to constraints. The resources are allocated to the nodes in the decoding order. The decoding order is changed iteratively to further minimize the allocated resources, until a minimum is reached. A code word is transmitted when the allocated resources are at the minimum, which can either be determined globally or locally at each node. The method can operate in a centralized or distributed manner.

A system and method for acoustic detection of coronary artery disease (CAD) are provided. The system includes a transducer for acoustically detecting heart signals of a patient and a computer system which executes detection software for processing the detected heart signals to identify the presence of CAD from the heart signals. The software allows for the automatic definition of a diastolic “window” of the acoustic signal for analysis, and automatically edits the sampled acoustic signal to eliminate unwanted artifacts and / or noise in the acoustic signal. The edited signal is then processed by a plurality of signal processing algorithms, including spectral analysis algorithms, time-frequency algorithms, global feature algorithms, kurtosis algorithms, mutual information algorithms, negenthropy algorithms, and principal component analysis algorithms, to generate a disease vector. The disease vector is then classified to determine whether CAD is present in the patient. Classification can be accomplished using linear discriminant analysis or a support vector machine.

The invention belongs to the technical field of computer software and discloses a multi-language-pair neural network machine translation method and system. A plurality of bilingual parallel corpora ofa same language system are utilized and mapped to a same high-dimensional vector space after byte pair encoding, so that multiple languages share a same semantic space, the size of a word list is reduced, model parameters are reduced, and convergence of a model is accelerated. Words of a same language family are in the same vector space, more information can be learned mutually, the information which can not be learned through only certain bilingual parallel corpora can be learnt, and the quality of word vectors is improved. The machine translation system can be used for translation in the language direction without direct bilingual parallel corpora, and the translation quality in the scarce parallel corpus translation direction is greatly improved through mutual information learning. Meanwhile, the same model is used for translation for the translation direction low in utilization rate, occupation of a server is reduced, and the utilization rate of the server is increased.

Apparatus and methods for plasticity in spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). Plasticity mechanism may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and / or mutual information determined over an activity window. Several similarity estimates, corresponding to different unit-to-unit pairs may be combined. The combination may comprise a weighted average. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green).

The invention discloses a method for 3D reconstruction and texture generation from single-view face based on multi-task learning, belonging to the computer vision field. The method comprises the following steps of: selecting a special viewpoint for rendering a three-dimensional human face model; generating depth map and texture map as truth value data from special viewpoint; designing an integrated learning and coding network based on feature sharing of depth information and texture information; designing the branch decoding network to recover the depth map from the shared features, and recovering the depth map, designing the mutual information with shared features as latent variables to maximize the generation of antagonistic network, and restoring the texture unwrapping map, adjusting the proportion of each task loss function and training the model; interpolating the depth map and using texture map to reconstruct the 3D face mesh model with texture details. The invention utilizes multi-task learning to carry out single-view face three-dimensional reconstruction, texture generation and style migration, and has the advantages of high speed, low cost and the like.

The invention discloses an automatic microblog text abstracting method based on unsupervised key binary word extraction. The automatic microblog text abstracting method comprises the steps of preprocessing a microblog; standardizing a binary word; extracting a key binary word based on a mixed TF-IDF (term frequency-inverse document frequency), TexRank and an LDA (local data area); sequencing sentences based on the intersection similarity and a mutual information strategy; extracting abstract sentences based on a similarity threshold value; generating abstract by reasonably combining the abstract sentences. According to the automatic microblog text abstracting method, the binary word is used as a minimum vocabulary unit, and the binary word has richer text information than words, so that the sentences based on the key binary word is higher in noise immunity and accuracy than the sentences based on key word extraction; meanwhile, when the abstract sentences are extracted, the similarity threshold value is introduced to control redundancy, so that the abstract is higher in recall rate. The abstract generated by the method is accurate, simple and comprehensive; the efficiency and the quality that a user acquires knowledge are obviously improved, and the time of the user is greatly saved.

An image reconstruction algorithm begins with an initial acquisition of a preoperative imaging volume followed by a second imaging sequence subsequent to an applied deformation. A computational domain (model) is generated from the preoperative image series and boundary conditions are derived from a pre-post deformation comparison, as well as from information gathered from deformation source application (i.e., displacement and / or force). Using boundary conditions, a series of model-based image deformations is accomplished while varying model material properties. A calculation of a Jacobian matrix relating the change in regional mutual information is performed with respect to the change in material properties. Upon completion of this process, matrix regularization techniques are used to condition the system of equations and allow for inversion and subsequent delivery of model-property adjustments.

The invention discloses a Chinese domain term recognition method based on mutual information and a conditional random field model. The Chinese domain term recognition method includes the following steps: (1) gathering domain text corpus and marking all the punctuations, spaces, numbers, ASSCII (American Standard Code for Information Interchange) characters and characters except Chinese characters in the corpus; (2) setting character strings and computing the mutual information values of the character strings, (3) computing the left comentropy and the right comentropy of every character string, (4) defining character string evaluation function, setting evaluation function threshold, computing the evaluation function values of every character string, determining that every character string is a word, comparing in sequence the evaluation function value of the former character with the evaluation function value of the latter character in the character string and segmenting character meaning character strings one by one, (5) utilizing conditional random fields to train a conditional random field model and recognizing domain terms with the conditional random field model. When the Chinese domain term recognition method is used to recognize terms, the data sparsity of legitimate terms is overcome, the amount of calculation of conditional random fields is reduced, and the accuracy of the Chinese domain term recognition is improved.

The invention discloses a liver multi-phase CT image fusion method which comprises the steps of firstly performing coarse registering on a source image sequence according to a multi-resolution CT image registering method based on a combined histogram, then realizing automatic liver image dividing according to a region growing algorithm in combination with confidence connection and liver image dividing based on a gradient vector flow snake model, and effectively extracting the edge information of the liver; performing blood vessel extraction based on a directional region growing algorithm on the liver image, performing free deformation transformation based on a B spline and liver non-rigid registering based on space weighting mutual information on a liver essential image, thereby accurately finding an image pair at a same position of a space; and finally performing image fusion based on wavelet transformation. The liver multi-phase CT image fusion method aims at the characteristics of a liver CT image. An image separation process and an image registering process are combined with the image fusion process, thereby greatly improving fusion precision.