141 results about "Bayesian formulation" patented technology

A method for structuring video by probabilistic merging of video segments includes the steps of obtaining a plurality of frames of unstructured video; generating video segments from the unstructured video by detecting shot boundaries based on color dissimilarity between consecutive frames; extracting a feature set by processing pairs of segments for visual dissimilarity and their temporal relationship, thereby generating an inter-segment visual dissimilarity feature and an inter-segment temporal relationship feature; and merging video segments with a merging criterion that applies a probabilistic analysis to the feature set, thereby generating a merging sequence representing the video structure. The probabilistic analysis follows a Bayesian formulation and the merging sequence is represented in a hierarchical tree structure.

The invention relates to a method for tracking a moving target in a complex scene. The method comprises the following steps of: obtaining a statistical histogram by adopting a component H background weighting method in an initially designated image area; creating a colour updating probability distribution graph with an adaptive background by utilizing a Bayes formula for each image of a video stream in the tracking process, updating target colour probability in a search region in real time, iterating the adaptive background updating colour probability distribution graph to obtain a position of the center of mass by utilizing a Camshift algorithm; and carrying out motion prediction by adopting a greedy prediction method in the tracking process, and continuously repeating the tracking step. By applying the method in the invention, the problem that the tracking on the moving target is not ideal enough in the complex scene can be solved, and the accuracy and the robustness are better.

Methods and apparatus are described for monocular 3D human pose estimation and tracking, which are able to recover poses of people in realistic street conditions captured using a monocular, potentially moving camera. Embodiments of the present invention provide a three-stage process involving estimating (10, 60, 110) a 3D pose of each of the multiple objects using an output of 2D tracking-by detection (50) and 2D viewpoint estimation (46). The present invention provides a sound Bayesian formulation to address the above problems. The present invention can provide articulated 3D tracking in realistic street conditions.The present invention provides methods and apparatus for people detection and 2D pose estimation combined with a dynamic motion prior. The present invention provides not only 2D pose estimation for people in side views, it goes beyond this by estimating poses in 3D from multiple viewpoints. The estimation of poses is done in monocular images, and does not require stereo images. Also the present invention does not require detection of characteristic poses of people.

The invention discloses an image acquiring method for removing image blurring and an image acquiring system. The method comprises the following steps: obtaining a depth image acquired by a depth camera and a color image acquired by a color camera; obtaining a depth value of each point on each color image based on the depth of each point on the depth image; blocking the color image to estimate a fuzzy core of each image block, determining a confidence weight value of the fuzzy core of each image block based on the depth value of each point on each image block; obtaining the initial distribution of the movement of the color camera within exposure time in a high-dimensional movement space based on the confidence weight value and the fuzzy core; substituting the initial distribution in a Bayes' formula to serve as a prior distribution of the camera movement, thus obtaining an image which maximizes the corresponding posterior distribution and serves as a sharp image. The method and system provided by the invention are suitable for the image acquiring and deblurring application in a large-depth range scene without insufficient lights, and can be used for improving the convergence rate and robustness of the algorithm.

The invention relates to an evaluation model for evaluating the operation risk of the electrical network on the basis of a Bayesian network modeling method, and belongs to the technical field of scheduling automation of the power system. The method comprises that (1) a Bayesian formula based network model is established; and (2) the risk early-warning evaluation index and model are calculated. The evaluation model has the advantages that the electrical network risk early-warning evaluation model is based on the Bayesian network, the Bayesian network model has unique bidirectional inference technology, the operation risk of the electrical network is evaluated, influence of components on the operation risk of the electric network can be analyzed, weak links of the system are obtained, requirements for risk early-warning evaluation and analysis in practical electrical network service are met, and basis is provided for improvement of the system.

A method and system for medical analytics implemented on a computer and designed to aid a medical professional in diagnosing one or more diseases afflicting a patient. In contrast to prior art, the present method is based on using clinical data (m) that excludes subjective qualities of and also excludes prevalence of the one or more diseases (i). The method uses a knowledge base that contains disease (i) models exhibiting clinical data (m). Clinical data present (j) in the patient are input into the computer. Then, clinical data present (j) are matched with clinical data (m) in the knowledge base to enable the computer to compose a differential diagnosis list of ruled in diagnoses (k), where k=1 . . . n, for each of the disease (i) models that exhibits at least one clinical datum (m) that matches at least one clinical datum present (j) in the patient. In a key step, the computer computes a probability P(k) for each of the ruled in diagnoses (k) with the aid of a mini-max procedure that overcomes prior art limitations of the Bayes formulation and permits the analytics method to consider concurrent and competing diagnoses (k). Furthermore, the method composes pairs of clinical data present (j) and absent (r) in the patient to aid the medical professional in evaluating diagnoses and determining the most cost-effective clinical data to collect for conducting an effective and rapid diagnostic quest.

The invention discloses a Bayesian algorithm-based content filtering method. Content filtering is performed for text information in a 3rd generation mobile communication core network, text classification is performed by using a double threshold-based Bayesian algorithm, C1 is set to be normal information, C2 is set to be junk information, a classifier estimates the probability that a characteristic vector X which represents a data sample belongs to each class Ci, and a Bayesian formula for the estimation is that: P(Ci / X) = P(X / Ci) P(Ci) / P(X), wherein i is more than or equal to 1 and less than or equal to 2, the maximum value of a posterior probability is called the maximum posterior probability, for an error (a reference source is not found) of each class, the error (a reference source is not found) only needs to be calculated, a characteristic vector X of an unknown sample is assigned to the Ci class of the error (a reference source is not found) with the minimum risk value. Characteristic selection is performed by adopting document frequency (DF), and classification is performed by using minimum risk-based double threshold Bayesian decision. In a time division-synchronous code division multiple access (TD-SCDMA) mobile internet content monitoring system, the algorithm has higher controllability and can realize real-time high-efficiency classification of mass text information.

A Bayesian formulation for coupled surface evolutions in level set methods and application to the segmentation of the prostate and the bladder in CT images are disclosed. A Bayesian framework imposing a shape constraint on the prostate is also disclosed, while coupling its shape extraction with that of the bladder. Constraining the segmentation process improves the extraction of both organs' shapes.

The invention discloses a method for realizing angular super-resolution imaging of forward-looking sea surface targets in a sea clutter background. According to the convolution characteristic of azimuth dimension echoes of scanning radar, echo signals of the scanning radar are rearranged into a form of the product of an azimuth dimension target vector and a convolution measurement matrix in the distance dimension order. Then a maximum posterior target function for solving original scene distribution is constructed on the basis of the Bayes formula according to characteristics that sea clutter obeys Rayleigh distribution and the sea surface targets obey Laplace, original sea surface target distribution is inverted by the aid of an acquired maximum posterior deconstruction iterative equation, and angular super-resolution imaging is realized. According to the method, the Rayleigh distribution is used for representing sea clutter characteristics, the Laplace distribution is used for representing the target characteristics, an iteration expression of the convolution inversion problem is derived in the Bayes principle, reconstruction of original imaging scenes is realized, and azimuth high-definition pictures of the forward-looking sea surface targets are acquired.

The invention discloses an IaaS (Infrastructure as a Service) cloud platform network fault positioning method and system based on log analysis. The IaaS cloud platform network fault positioning system comprises a fault injection module, a log acquisition and analysis module, a knowledge generation module and a fault detection and positioning module. Firstly, by injecting various typical network faults, various corresponding fault logs are formed; then aiming at various faults, log information related to network faults of each layer of physical resources, an operation system, a virtual machine, an OpenStack and the like is respectively acquired, and fault feature mining is carried out on the acquired network fault log information by using an Apriori algorithm; on such basis, according to a maximal frequent item set and parameters, such as a supporting degree, a confidence degree and the like, association rules and knowledge, which correspond to the specific network faults, are generated by utilizing a bayes formula; and finally, when a system has a network fault again, the network fault can be compared with the association rules of a knowledge base and analyzed according to an acquired fault log, so that the layer on which the network fault occurs is positioned.

The invention discloses a fast method for HEVC (High Efficiency Video Coding) block size partition based on a Bayes decision. The fast method comprises the following steps: first of all, dividing a video sequence into an online learning stage and a fast partitioning stage by employing scene change detection based on an average gray scale difference; then, for the online learning stage and a video frame which occurs a scene change, in each partitioning depth, respectively extracting Jinter and Jintra of a CU (Coding Unit) as characteristic values, thereby establishing a mixed Gaussian model, wherein specific parameters of the model are determined according to an EM algorithm initialized by a K-Means algorithm; and for a to-be-partitioned CU in the fast partitioning stage, extracting the characteristic values and finding a conditional probability on whether to partition according to the mixed Gaussian model, and at last, finding the decision with a relatively small risk by employing a Bayes formula of a minimum risk to take as a judgment basis on whether the current CU is partitioned. According to the fast method disclosed by the invention, the algorithm complexity is reduced, and the coding time can be greatly reduced.

The invention discloses a combined estimation method for a road junction dynamic steering proportion based on Bayes weighting. According to the method, three sub algorithms of an improved Kalman filtering algorithm, an improved back-propagation neural network algorithm and a genetic algorithm are designed to solve the road junction dynamic steering proportion by utilizing road segment traffic detected by all inlet roads and outlet roads of road junctions, historical data are combined based on the road junction dynamic steering proportion, correction on historical and current estimation deviation is considered comprehensively, calibration is carried out by utilizing a Bayes formula and weight is updated dynamically, and obtained results through the three sub algorithms are weighted to obtain the dynamic steering proportion estimated by the combined method. Aiming at different traffic flow situations, the dynamic steering proportions estimated by existing methods all have advantages and disadvantages in the aspects of precision and efficiency, the combined estimation method can embody the advantages of all the methods on the whole, local oversize deviation is avoided, the combined estimation method has the advantages of being strong in adaptability, high in precision, good in stability and optimal in entirety, and can provide basic data supporting for signal control and other real-time traffic management and information service systems.

Methods and apparatus are described for monocular 3D human pose estimation and tracking, which are able to recover poses of people in realistic street conditions captured using a monocular, potentially moving camera. Embodiments of the present invention provide a three-stage process involving estimating (10, 60, 110) a 3D pose of each of the multiple objects using an output of 2D tracking-by detection (50) and 2D viewpoint estimation (46). The present invention provides a sound Bayesian formulation to address the above problems. The present invention can provide articulated 3D tracking in realistic street conditions.The present invention provides methods and apparatus for people detection and 2D pose estimation combined with a dynamic motion prior. The present invention provides not only 2D pose estimation for people in side views, it goes beyond this by estimating poses in 3D from multiple viewpoints. The estimation of poses is done in monocular images, and does not require stereo images. Also the present invention does not require detection of characteristic poses of people.

The invention belongs to the technical field of network security, and particularly relates to a network security domain knowledge graph construction method and device for dynamic threat analysis, andthe method comprises the steps: describing a threat transfer relation caused by a system vulnerability and a network service; constructing a network dynamic threat analysis knowledge graph model by utilizing graph theory knowledge; calculating a threat transfer probability by combining a general vulnerability evaluation standard and Bayesian; and generating a network threat knowledge map by utilizing association rules among threats, vulnerabilities and services, and carrying out loop resolution. According to the invention, network attacks, system vulnerabilities and business applications influence each other; the network threat transfer probability is analyzed in combination with the general vulnerability scoring standard and the Bayesian formula, the constructed knowledge graph is corrected, the threat transfer loop among multiple nodes is eliminated, the attack full view can be completely displayed, the network evidence obtaining efficiency is improved, and a basis is provided for threat clue discovery and traceability evidence obtaining.

The invention discloses an information retrieval method based on a Bayesian classification algorithm in the technical field of information processing, which comprises the steps of: selecting a data sheet from a relationship database, establishing an information retrieval model; deriving a sample set from the information retrieval model, dividing the sample set into a training data set and a testing data set; selecting relevant fields from the information retrieval model to be used as a classification attribute of the sample set, determining the class of the classification attribute and calculating the prior probability of the class of the classification attribute; calculating the posterior probability of samples; calculating the class probability of the samples according to the Bayesian formula; classifying the samples according to the class probability of the samples, and generating a data classification set; and making the information retrieval operation in the data classification set by a user. The invention applies the Bayesian classification algorithm to the actual information retrieval, thereby effectively improving the accuracy of the information retrieval.

The invention discloses a soil moisture site data upscaling method based on the Bayesian theory. The soil moisture site data upscaling method includes steps of estimating prior probability density distribution function pre_pdf of a target variable on the basis of sparse site observation data in an upscaling area; inversing MODIS ATI into SM by establishing nonlinear regression relation between the SM and the MODIS ATI, estimating an estimated confidence interval of the soil moisture nonlinear regression and probability distribution as soft data in a probability form; integrating the prior distribution of the target variable and auxiliary information of the probability form from the MODIS ATI through the Bayesian theory, and acquiring posterior probability density distribution function post_pdf of the target variable; calculating the value of the target variable in the maximum probability through maximization of the posterior probability distribution function. By the soil moisture site data upscaling method, uncertainties caused by scale difference between soil moisture remote sensing products and ground site authentication data are effectively reduced. The soil moisture site data upscaling method can be applied to upscaling application of other ground surface parameters.

The invention belongs to the sub-field of the learning theory and application in the technical field of computer application, and relates to a CCA and 2PKNN based automatic image annotation method, in order to solve problems of a semantic gap, a weak annotation, and category imbalance that exist in an automatic image annotation task. The method comprises: firstly, for a semantic gap problem, mapping two features to a CCA sub-space, and solving a distance between the two features in the sub-space; for a weak annotation problem, establishing a semantic space for each annotation; for a category imbalance problem, by combining a KNN algorithm, finding out k nearest neighbors of a test image in the semantic space of each annotation, constituting the k nearest neighbors to an image sub-set, and by using a visual distance between the sub-set and the test image, and by combining a Bayesian formula, assigning a few annotations with the highest score to the test image; and finally, optimizing an image annotation result by using correlation between annotations. The method disclosed by the present invention has a greater degree of improvement for image annotation performance.

The invention relates to a pedestrian attribute refined recognition method based on deep learning, and the method comprises the steps: automatically learning the pedestrian attribute features throughimproving a deep learning model frame; inputting the attribute features into classifiers, and training independent pedestrian attribute classifiers, so that the posterior probability that a pedestriansample has the attribute; obtaining the posterior probability of an attribute category through calculating the proportional relationship between the attribute in the pedestrian training sample and the attribute category; and finally obtaining the attribute category of the pedestrian sample according to the Bayesian formula. The method can improve the recognition precision and recognition speed.

The invention provides a comprehensive assessment method of power quality. The comprehensive assessment method of the power quality comprises the steps of acquiring J sample sets corresponding to distributive J data acquiring nodes according to the power quality monitoring data, public information data and power user data; extracting the same user characteristics vectors to obtain the corresponding J training sample sets; conducting data transformation to obtain J data set stored by means of data block; treating K security levels as the type of class of the common classification properties; classifying and counting the J data sets to obtain the corresponding prior probability and condition probability of each class; obtaining the class probability of each class through the bayes formula; and determining the security level corresponding to the class with the maximum probability in the class probability as the security level of the current power quality of a power circuit. The comprehensive assessment method of the power quality has the advantages that a plurality of data are taken into account, a bayes classifying model is trained by mass samples, and then the transient power quality can be quickly assessed and predicted on the basis of the model.

The invention provides a Bayesian Decision Theory foreground extraction method combined with reflected illumination. The Bayesian Decision Theory foreground extraction method comprises the steps of appointing a point light source located on a foreground object by a user, carrying out gray level matching on an image, converting and imitating point light source illumination, strengthening image edge information, obtaining an illumination function according to before-after conversion comparison, filtering waves, reducing noise, dividing the image through a watershed algorithm, calculating a sectional drawing parameter through a Bayes formula, imitating an alpha value function curve through a multi-layer perception device, integrating the illumination function and a color distribution function, and completing extraction of the foreground object. The user is only required to appoint the position of the point light source and not required to preset edge information of a foreground and a background, the requirement for user interaction is reduced, meanwhile, time complexity of the used algorithms is series, and the defects that a common sectional drawing algorithm is large in calculated quantity and low in processing speed are avoided. Due to the facts that the illumination function is introduced and the alpha value is matched by the perception device, an accurate and complete extraction result can be obtained for the foreground object with complicated edges, and particularly for the foreground object similar colors of the edge and the ground.

The invention discloses a diabetes mellitus probability calculation method based on large data of a diabetes mellitus system. The diabetes mellitus probability calculation method comprises the following steps: (1) constructing a diabetes mellitus decision tree model; (2) selecting an optimal branch variable of the decision tree model according to the information gain ratio Gains (Xi) of a training sample S; (3) post-pruning a decision tree from bottom to top; and (4) constructing a diabetes mellitus naive Bayes model, and obtaining the diabetes mellitus probability P (C1|y1.y2.y3.....ym) with C1 serving as an output variable on a rth node by utilizing a Bayes formula. According to the diabetes mellitus probability calculation method disclosed by the invention, a two-layer model method with the combination of the decision tree and the naive Bayes model is designed; by extracting the characteristic attribute of diabetes mellitus from the large data, whether the diabetes mellitus occurs or not is forecasted, the probability of the occurrence of the diabetes mellitus is further calculated, and the prevention and the forecast are combined and are relatively overall and accurate.

The invention relates to a medical X-ray device 5 arrangement for producing three-dimensional information of an object 4 in a medical X-ray imaging medical X-ray device arrangement comprising an X-ray source 2 for X-radiating the object from different directions and a detector 6 for detecting the X-radiation to form projection data of the object 4. The medical X-ray device 5 arrangement comprises: means 15 for modelling the object 4 mathematically independently of X-ray imaging and means 15 for utilizing said projection data and said mathematical modelling of the object in Bayesian inversion based on Bayes' formula p⁢(⁢x⁢m)=ppr⁡(x)⁢p(m⁢x)p⁡(m)to produce three-dimensional information of the object, the prior distribution ppr(x) representing mathematical modelling of the object, the object image vector x, which comprise values of the X-ray attenuation coefficient inside the object, m representing projection data, the likelihood distribution p(m|x) representing the X-radiation attenuation model between the object image vector x and projection data m, p(m) being a normalization constant and the posteriori distribution p(x|m) representing the three-dimensional information of the object 4.

The invention discloses a distribution network fault locating method based on Bayes and complex event processing. The distribution network fault locating method based on Bayes and complex event processing includes the steps: S101, acquiring the power grid topology information, and dividing distribution network fault locating calculating nodes; S102, according to the divided calculating nodes, acquiring the historical fault data and monitoring information of each node, and calculating the Bayes formula prior probability; S103, constructing a processing model of distribution network fault locating complex events; and S104, acquiring the input information, and outputting the fault locating information after operation through the processing model. The technical scheme of the distribution network fault locating method based on Bayes and complex event processing can calculate the probability of fault nodes by means of the Bayes method, can obtain the fault probability by means of the topology information and the historical fault information and then perform probability calculation according to the real-time fault feedback information and the power grid equipment operation information, and finally can obtain the node with the maximum fault generation possibility so as to realize fault locating.

The invention provides a method for determining load effect of a wind-wave coupling design of a long-span bridge structure. The method is an improved load effect determination method. One-dimensional distribution of a structure dynamic load effect extremum replaces two-dimensional joint distribution of a wind and wave environment element extremum, so that design ultimate load effect under the condition of recurrence interval is estimated according to an extremum exceedance probability distribution rule of 10-minute dynamic load effect of the structure. The method comprehensively employs a finite element modelling technology, Monte Carlo numerical modeling, a threshold method (POT), generalized Pareto distribution (GPD) and a bayes formula; for the key section of the structure, the acquired design ultimate load effect takes the dynamic characteristics of the structure into account and further conforms to the reality, so that the wind-wave coupling design of the structure is more reliable.

The invention relates to the technical field of intelligent monitoring and specifically relates to a plant cultivation monitoring system and method. The plant cultivation monitoring system comprises a data collecting device, a terminal and a cloud server, wherein the data collecting device is used for collecting data information; the terminal comprises a user input module used for inputting event information reflecting plant cultivation condition, the terminal sends the data information and the event information reflecting the plant cultivation condition to the cloud server, the cloud server is used for receiving the data information and the event information reflecting the plant cultivation condition, the data information and the event information reflecting the plant cultivation condition are generated into plant cultivation query feedback information after being computed via a Bayes formula, and the plant cultivation query feedback information is sent to the terminal. The data information collected via the data collecting device of the plant cultivation monitoring system can further bring effective help to a user via the terminal to obtain a suitable solution according to local conditions when the user plants exotic plant species such as macadamia nuts and the like, and operation simplicity is realized.

The embodiment of the invention discloses a method for identifying abnormal electricity utilization users. The method includes the following steps that multiple month line-loss rates of each line-loss line are obtained; whether each line-loss line has two month line-loss rates larger than the preset threshold or not is judged; if yes, the actual line-loss line and the line-loss mouth are determined; any time period in one line-loss month of one actual line-loss line is selected to be tested, sample data relevant to electricity utilization of all the users on the line in the test period are obtained, and the prior probabilities and the posterior probabilities of all the users are obtained; the category probabilities of all the uses are obtained with the Bayes formula according to the obtained prior probabilities and the obtained posterior probabilities of all the users, and the user with the largest numerical value in the obtained category probabilities is determined as the suspicion user. The embodiment of the invention further discloses a system for identifying the abnormal electricity utilization users. According to the method and system for identifying the abnormal electricity utilization users, the problems that in the prior art, when the users who steal and leak electricity are identified, a hardware prevention method is large in investment cost and a software prevention method is confined to individual users are solved.

The invention discloses a method for providing network service resources. The method comprises the following steps: firstly, classifying the network service resources; then, providing a retrieval scheme according to the interest of a user, and providing the classified network service resources according to the retrieval scheme; firstly extracting feature vectors of to-be-classified service resources when the network service resources are classified, then, computing the probability of each attribute in each feature vector in each category and the weight of each attribute, then, acquiring the probability that each attribute belongs to each category by utilizing a weighting Naive Bayes formula, and selecting the maximum as the classification category of each service resource. According to the method disclosed by the invention, when the service resources are classified, by utilizing the bayesian classification algorithm and combining the calculation of attribute similarity, the classification accuracy of the service resources is improved, and when the service networks are provided for the user, a user interest-based personalized service resource retrieval is explored under the framework of a vector space model, so that the complexity of time and space in the retrieval algorithm is reduced, and the retrieval efficiency is improved.

The invention provides an emoticon recommendation method and an emoticon recommendation device. The emoticon recommendation method has the advantages that training sentences corresponding to emoticons are clustered, and text training based on clustered paraphrase categories is conducted, so that chaos caused by the fact that one emoticon corresponds to multiple semantically-irrelevant training sentences can be avoided and text training accuracy can be improved; meanwhile, during text training, a first probability corresponding to every paraphrase category and a third probability corresponding to every word in every paraphrase category are obtained through calculation, and target sentences input by a user in real time are subjected to semantic matching probability analysis (precise to every word) by combining a Bayes formula according to the first probability and the third probability, so that the problem of extremely low recommendation triggering probability under an existing recommendation mode can be avoided, the situation that a target paraphrase category determined by final analysis is a paraphrase category the closest in actual meaning of the target sentences can be guaranteed, and recommendation accuracy, emoticon input efficiency and user experience are improved.