33 results about "Markov transition" patented technology

The invention discloses an autism detection method based on multi-mode collaborative embedding, and belongs to the technical field of medical image analysis and artificial intelligence. The method comprises the following steps: firstly, obtaining resting state functional magnetic resonance imaging data and non-imaging data of a subject; a Markov transition field is utilized to encode the time sequence into an image so as to retain dynamic features, and feature extraction is carried out through an efficient multi-scale attention module; then realizing effective fusion and semantic alignment of multi-modal information by adopting a three-level fusion architecture and a joint loss function; and then adaptively constructing a graph structure based on the fusion features, dynamically learning a node relationship by using a graph attention network, and completing a classification decision. According to the method, the defects of a traditional method in the aspects of dynamic feature modeling, multi-modal fusion and heterogeneous graph structure processing are effectively overcome, the autism detection accuracy and robustness are remarkably improved, and a reliable tool is provided for clinical intelligent diagnosis.

The invention provides an optical access network PON port fault prediction and operation and maintenance support method and system, and the method comprises the steps: collecting real-time multi-index sequences of optical power, bit error rate, temperature, frame loss rate, business load and the like, automatically extracting a long-term trend based on variational mode decomposition, constructing a residual sequence, generating a state transition map through employing a Markov transition field algorithm, and carrying out the fault prediction and operation and maintenance support of the PON port. And future operation state distribution prediction is realized through the LSTM neural network. And after an abnormal threshold is dynamically adjusted in combination with quantile regression, a time sequence prediction result and a threshold response are fused to output a comprehensive fault probability score, and an early warning signal is triggered through exponential smoothing and continuity check, so that the progressive fault detection accuracy and advancement can be improved, and an efficient and steady prediction and early warning basis is provided for intelligent operation and maintenance of the PON port.

The invention provides a river trajectory data protection method based on differential privacy, and belongs to the field of environmental data privacy protection. According to the method, river flow velocity and flow direction data are discretized into a two-dimensional grid, spatial-temporal characteristics are extracted by using a graph convolutional network (GCN), and a Markov transfer matrix is established; and according to the grid access frequency and the spatial density, privacy budget is adaptively allocated through a dual attenuation factor model, and differential privacy protection is realized. In the trajectory generation stage, dynamic privacy budget is combined, noise is injected into direction and time features by adopting an index mechanism and a Laplace mechanism, and a synthetic trajectory conforming to physical constraints is generated; and finally, evaluating and optimizing the track quality by using Savitzky-Golay filtering and multiple indexes (such as Frechet distance, access frequency error and KL divergence). According to the method, the privacy leakage risk is effectively reduced while the space-time continuity of the trajectory is kept, the data privacy and availability are considered, and the method is suitable for hydrological monitoring, ecological analysis and environmental data sharing.

The invention discloses a ferromagnetic resonance fault overvoltage identification method and system, computer equipment and a medium. The method comprises the following steps: acquiring a three-phase voltage and zero-sequence voltage time sequence in a power distribution network; according to the time sequence, coding the time sequence into a two-dimensional image by using a Markov conversion field so as to reserve a time sequence dynamic characteristic; inputting the two-dimensional image into a pre-trained dual-channel graph neural network model, extracting image features by the model through a space view angle channel and a time view angle channel, and performing feature fusion by using a cross-modal attention mechanism; and outputting a classification result of the ferromagnetic resonance overvoltage according to the fused features. The method is high in identification accuracy and strong in anti-interference capability, can effectively distinguish fundamental frequency, frequency division and high-frequency ferromagnetic resonance, and has good adaptability to nonlinear and non-stationary overvoltage faults in a power distribution network.

The application discloses an omnidirectional guiding interaction multi-model positioning method and system for a motorized mother ship to recover an underwater robot and a storage medium, the method obtains the state information and distance data of the mother ship by integrating a water acoustic ranging and a water acoustic communication device, constructs an interaction multi-model singular value decomposition unscented Kalman filtering algorithm fusing a uniform straight line and a uniform bow turning model, and realizes real-time estimation of the position of the mother ship under a mouth-shaped maneuvering track. An event-triggered communication mechanism is designed, information is broadcast only when the turning state of the mother ship changes, so as to reduce the communication load and maintain real-time performance; meanwhile, a Markov transition matrix is updated, the turning model weight is enhanced, and the estimation accuracy and model matching are improved. According to the model probability and the estimation result, a LOS guiding law with an adaptive look-ahead distance is constructed, and the autonomous guiding recovery of the underwater robot to the motorized mother ship is realized. The method provided by the application can realize dynamic estimation and guiding based on the measurement data of a single water acoustic device under the conditions of the mother ship maneuvering and communication limitation.

The invention discloses an unmanned aerial vehicle radio frequency fingerprint extraction method based on multi-dimensional feature field coding, and belongs to the field of wireless signal identification. In order to solve the problem that a traditional time-frequency diagram mainly represents signal energy distribution and is difficult to explicitly express a signal state transition relation, the invention provides an F-FD-A (instantaneous frequency-frequency difference-instantaneous amplitude) multi-dimensional feature coding strategy which can effectively extract information such as a frequency hopping rule and envelope deformation of a signal. The method comprises the following steps: firstly, extracting instantaneous frequency, frequency difference and instantaneous amplitude of a radio frequency signal; further, the Markov transfer field is utilized to encode the first two sequences, and the Gramer angle difference field is utilized to encode the amplitude sequence; and finally, fusing the feature images into an RGB image, and inputting the RGB image into a ResNet-50 network for identification. Experiments show that the method has excellent recognition precision in a mixed data set covering DJI multi-series and multi-brand universal models, and fine-grained and high-robustness recognition of similar models of unmanned aerial vehicles in a complex environment is realized.

The invention discloses a multi-view fusion cloud native malicious software detection method and system based on high-speed introspection of a virtual machine, and the method comprises the steps: 1), deploying a high-speed introspection module in a monitoring layer of the virtual machine, capturing an API call sequence of an internal process of a target virtual machine from the outside in a safe and low-invasion manner, and structuring the API call sequence into a runtime log; (2) the API calling sequence is regarded as a sentence, and a Word2Vec model is used for training to generate a structure embedding vector of the API; then, constructing a directed heterogeneous graph containing a file, a thread and API calling for each sample, taking the structure embedded vector as an initial feature of an API node, encoding the graph by using a graph attention network, and extracting a structure context feature vector; 3) extracting an API official function description text by utilizing the pre-training language model to generate a semantic embedding vector; constructing a directed heterogeneous graph for each sample, replacing the initial features of the API nodes in the graph with the semantic embedding vector, coding the graph by using the graph attention network again, and extracting a functional semantic feature vector; 4) firstly performing function classification on the APIs, and performing dimensionality reduction on the complete API calling sequence to obtain a limited function state sequence; constructing a Markov transition probability matrix for the state sequence of each sample, and selectively stacking a multi-order transition matrix to form a multi-channel feature tensor; inputting the feature tensor into a convolutional neural network for coding, and extracting a macroscopic behavior evolution feature vector; 5) splicing the structure context feature vector, the function semantic feature vector and the behavior evolution feature vector to form a final comprehensive feature vector; and inputting the comprehensive feature vector into a multi-layer perceptron classifier, and training the classifier in an end-to-end manner to enable an output sample of the classifier to be a classification result of malicious software or benign software.

This invention discloses a memory-based dynamic event triggering control method for a single-link robotic arm system based on spoofing attacks. The method first establishes a Markov model of the single-link robotic arm system based on Markov jump system theory, considering a system model with a general transition rate. Next, a mode-dependent memory controller is designed to overcome the influence of spoofing attacks and external disturbances on the system. A memory-based dynamic event triggering mechanism is also designed to reduce communication transmission frequency. Compared with existing memoryless event triggering schemes, this scheme utilizes a series of recently released signals and introduces a threshold function and an internal dynamic factor, which can automatically adjust according to the triggering error. Finally, vertex separator processing is introduced to address the uncertainty in the Markov transition rate. A mode-dependent state feedback controller is designed to control the stochastic stability of a single-link robotic arm system. When applied to a single-link robotic arm system, this method ensures the normal operation of the system under spoofing attacks and disturbances.

The application provides a dual-mode feature fusion power quality disturbance analysis method for a power distribution network, which comprises the following steps: 1, using a Markov transition field to perform mode transformation on a power quality time sequence signal collected and processed on site to obtain an aggregated image of dynamic transition probability; 2, using a convolutional neural network to extract features from the aggregated image of dynamic transition probability to obtain a first feature vector; 3, using a gated recurrent unit to extract features from the power quality time sequence signal collected and processed on site to obtain a second feature vector; 4, using a deep learning feature fusion-based method to fuse the first feature vector and the second feature vector to obtain a fused power quality disturbance feature of the power distribution network; and 5, classifying the power quality disturbance feature of the power distribution network through a power quality disturbance classifier.

This invention discloses a personalized location trajectory privacy protection method based on mutual information, belonging to the field of crowdsourced sensing technology. It includes: Step 1: Data preprocessing; Step 2: After generating the Markov matrix in Step 1, the matrix is ​​normalized, and a location privacy protection mechanism is established by setting a distortion threshold and regularization parameters; Step 3: Measuring the effectiveness of location privacy protection. This method generates a Markov transition matrix by merging user location trajectory data, analyzes implicit privacy information and adds distortion perturbations, and uses mutual information to measure the degree of privacy leakage, achieving a trade-off between privacy and usability. It solves the problem that existing technologies cannot effectively overcome the risk of location information privacy leakage.

This invention relates to the field of equipment operation status monitoring technology, and discloses a method for early warning of photovoltaic terminal sealing failure based on mechanical fingerprint features, including the following steps: A simulated strain signal is acquired using a microelectromechanical system strain gauge, and a basic mechanical fingerprint is output using a preprocessing module; a gateway module calculates an instantaneous reward value to generate a global timestamp, sends the basic mechanical fingerprint and the global timestamp to a cloud server, and stores a pending tuple containing the instantaneous reward value and the global timestamp in a buffer module; the cloud server uses parameterized quantum circuits to map the basic mechanical fingerprint to a quantum state input quantum support vector machine, outputs a sealing failure probability distribution, calculates the quantum state measurement entropy value to generate a delayed reward value for distribution; the gateway module extracts the pending tuple using the global timestamp, merges the reward values ​​to generate a Markov transition tuple, updates the deep Q-network model, and issues control commands; the cloud server calculates a failure risk index for early warning.

The application relates to the fields of machine vision and fault diagnosis, and particularly relates to a bearing fault diagnosis method based on a light-weight neural network and dimension expansion, which comprises the following steps: acquiring a historical bearing vibration signal, performing polar coordinate coding on the acquired bearing vibration signal after normalization; converting the bearing vibration signal subjected to the polar coordinate coding into a two-dimensional bearing vibration signal based on a Grahm angle field, a Grahm angle difference field and a Markov transition field; constructing a light-weight neural network, and training the neural network by using the two-dimensional bearing vibration signal; converting a bearing vibration signal to be detected into a two-dimensional bearing vibration signal, inputting the two-dimensional bearing vibration signal into the light-weight neural network which has been trained, and obtaining a diagnosis result; the application can effectively realize the visualization of the vibration signal, provide an RGB three-channel for neural network learning, and thus realize the accurate identification and diagnosis of rolling bearing faults through a relatively small sample machine vision method.

The present application relates to the technical field of hydroelectric unit control optimization, and discloses a method, system, device and medium for determining the starting mode of a hydroelectric unit by fusing multi-modal features, which comprises the following steps: collecting original vibration signals under different starting modes; preprocessing the original vibration signals to obtain two types of time-series vibration signals during the starting process; extracting frequency domain features of the first type of signals by Markov transition field, i.e. structural reparameterization large core network; extracting time domain features of the second type of signals by bidirectional gate recurrent unit and global attention mechanism; obtaining vibration features under different starting modes and vibration feature reference vectors under the original starting state by using global average pooling layer and weighted fusion mode; and obtaining the optimal starting mode based on the distance between the vibration feature vectors and the reference vectors. The present application extracts richer and more essential features from multiple dimensions, calculates the dynamic characteristics of the starting process, and makes the quantitative determination of the starting mode more accurate, so as to quickly respond to the demand.

The invention discloses a load identification method, system and device based on Radon transformation and deep learning and a storage medium, and the method comprises the steps: intercepting load measurement data, and converting the load measurement data into a load image through a Markov transfer field; de-noising processing is carried out on the load image containing noise by using wavelet transform; extracting image features of the de-noised load image by using Radon transform; dividing the image features into a training set and a test set, and performing normalization processing on the training set and the test set; and constructing a convolutional neural network, inputting the training set after normalization processing into the convolutional neural network to train the model to obtain a load identification model, testing the load identification model by using the test set after normalization processing, and performing load identification by using the tested load identification model. The method has the advantages of being easy to implement and high in recognition precision, and can be applied to the field of load regulation and recognition.

The present application relates to the technical field of industrial intelligent monitoring and fault diagnosis, and particularly relates to an unbalanced fault diagnosis method based on attention perception and decision coupling. The technical scheme comprises the following steps: obtaining a one-dimensional vibration time series observation signal of a target industrial equipment in a running state, and pre-processing the signal; and inputting the pre-processed time series signal into a Gram angle field sine transformation, a Gram angle field difference transformation and a Markov transition field for parallel coding. The present application can autonomously capture weak fault fingerprints submerged in strong background noise without relying on manual resampling or prior threshold setting, can guarantee the reliability of the diagnosis of majority class samples, can significantly improve the upper limit of the recognition of a small number of key fault patterns, and can provide an intelligent diagnosis solution with high sensitivity, strong robustness and without manual intervention for complex industrial scenes such as wind power, aviation and rail transportation which have high reliability requirements and difficulty in obtaining fault data.

This invention discloses a disturbance-free sliding mode control method for a multimodal Boost converter circuit, belonging to the field of automation technology. Based on a discrete implicit stochastic semi-Markov transition system model, a disturbance-free transfer sliding mode control strategy based on an observer is designed. Since real-world modal information is difficult to obtain in actual environments, an implicit semi-Markov transition system is used to describe the system, which has lower conservatism than a semi-Markov transition system with fully known system modes. To better match the system modes, a mode-dependent sliding surface is selected. Expressions for the disturbance-free transfer performance during operation and at transition moments are also provided. By integrating the sliding mode controller with the disturbance-free transfer performance, disturbances and impacts in the control input are effectively suppressed. This invention can accurately describe the dynamic characteristics of a multimodal Boost converter circuit under conditions of mismatched system and observed modes, effectively suppressing the effects of disturbances and jolts in the control input, and improving the fast response speed and dynamic performance of the Boost converter circuit.

The present application relates to the technical field of fault diagnosis, and discloses a current transformer fault diagnosis method, device, equipment and storage medium.The method comprises: current signal acquisition and complementary ensemble empirical mode decomposition are performed on the current transformer to obtain a plurality of intrinsic mode function components; time alignment and weighted reconstruction are performed on the intrinsic mode function components to obtain a current signal prediction sequence; Markov transition field conversion is performed on the current signal prediction sequence to generate a two-dimensional Markov transition field feature image; the two-dimensional Markov transition field feature image is input into a stripe pooling convolutional neural network, remote spatial features are extracted through a stripe pooling module, and then the feature channels are adaptively adjusted in weight through an SE attention mechanism module to obtain a fault type and a fault degree.The present application effectively solves the non-linear and non-stationary characteristics of signals and improves the fault diagnosis accuracy of the current transformer.

This invention belongs to the technical field of lead-bismuth cooled reactor control system design, and specifically relates to an interactive multi-model weighted fusion method for core power control. The invention includes the following steps: S1, constructing a core model and performing lead-bismuth heat transfer calculations; S2, constructing transfer functions, building four power step transfer functions to characterize the lead-bismuth reactor model, converting the transfer functions into state-space form to obtain a linearized model; S3, dynamically mixing the initial states of each model using Markov transition probabilities, independently calculating the predicted values ​​and residuals of each model using Kalman filtering; updating the model weights in real time based on residual covariance and Bayes' theorem, and weighting and fusing the outputs of each model. This invention obtains the system's transfer function from input to output based on the constructed core model, fuses real-time measurement data through a Markov transition mechanism, and weights and fuses the outputs of each model, ultimately achieving real-time matching of the optimal model to support core power control in lead-bismuth reactors.

The present application relates to the field of distributed optical fiber sensing-based intrusion event classification and identification, in particular to a distributed optical fiber fence monitoring feature learning method. The present application improves the learning efficiency and recognition performance of the network through feature learning, and proposes a vibration recognition method based on MTF-NMF and 2-D CNN. The one-dimensional phase time domain signal without denoising is converted into a Markov transition field (MTF) matrix, then the base matrix is extracted from the MTF through non-negative matrix factorization (NMF) and saved as an RGB image, and finally the feature learning and recognition are performed by the 2-D CNN network, so as to realize the classification of different types of intrusion events on the optical fiber fence. The present application effectively solves the problems of low learning efficiency of the intrusion event recognition model and high construction cost of the recognition network training data set in the current Φ-OTDR monitoring field.

The invention provides a data intelligent calculation method for a 6G cloud-edge-end edge intelligent satellite internet in combination with a low-orbit communication satellite, and belongs to the field of 6G satellite internet. The method comprises the following steps: deploying a laser emission device in a'air-space-ground-sea 'converged communication network, establishing three laser inter-satellite links of GEO-GEO, GEO-LEO and LEO-LEO, processing data by adopting a laser communication ranging integrated structure, and performing staged fine adjustment by combining a Markov transfer matrix method with a large model to predict and quantify the emission power of each network management and control instruction; and meanwhile, a cloud-edge-end edge intelligent framework is constructed, massive satellite data form grids for storage by an optimal model segmentation method, and the grids are distributed to the edge or the cloud for operation according to needs. The problems that satellite communication power management and control are difficult, regional coverage is limited, and mass data processing resources are insufficient are solved, and 6G satellite internet communication stability and data processing efficiency are improved.

Disclosed herein are scientific instrument support systems, as well as related methods, computing devices, and computer-readable media that can be employed to construct in silico mass spectra of compounds. In various embodiments, a system can comprise a processor that can execute computer-executable components stored in a non-transitory computer-readable memory, wherein the computer-executable components can comprise a matrix computation component that can compute a Markov transition matrix and a mass spectrum component that can construct a mass spectrum for a molecule based on the Markov transition matrix.

The invention discloses an emergency situation evolution simulation method based on a multi-source data-driven dynamic Bayesian network, and belongs to the technical field of maritime emergency emergencies. According to the invention, a general accident emergency scene evolution framework is constructed based on a public safety triangle theory; identifying ship accident emergency scene elements and establishing an emergency scene evolution path; constructing a DBN model based on the path; the method comprises the following steps: determining DBN parameters by combining statistical analysis, a Markov transfer model and a Leaky Noisy-OR model; and simulating the natural environment change by using an evidence reasoning method, and evaluating the influence of the ship-end emergency, the shore-based emergency and the ship-shore cooperative emergency on the scene state evolution. According to the method, the dynamic evolution rule of different types of accident emergency situations on the north pole sea is disclosed, a scientific basis is provided for emergency management and decision making, and the emergency response capability of emergencies on the north pole sea is improved.

The invention relates to a blueberry sugar degree prediction method based on feature coding and a double-branch network, and belongs to the technical field of blueberry sugar degree prediction. The method comprises the following steps: screening an obtained original hyperspectral data set of blueberries by using a Pearson correlation coefficient, and respectively carrying out coding processing by using a GASF, a GADF and an MTF to obtain a two-dimensional coding data set; constructing a double-branch network comprising a 1D network branch and a 2D network branch, extracting spectral features of an original hyperspectral data set by using the 1D network branch, extracting visual features of a two-dimensional coding data set by using the 2D network branch, performing cross-modal fusion on the spectral features and the visual features to obtain fusion features, and performing fusion on the fusion features to obtain a fusion result; and inputting the fusion features into a constructed blueberry sugar degree prediction model to obtain a blueberry sugar degree prediction result. The method aims at solving the technical problems that an existing blueberry sugar degree prediction method is insufficient in feature expression, insufficient in inter-modal information utilization and poor in model stability.

The application discloses a kind of adaptive data enhancement methods based on diffusion model, comprising:1 constructs knowledge tracking network, by embedding layer student interactive triple is mapped into vector, and output the predicted probability of next question;2 construct conditional diffusion model, and by Markov conversion original interactive sequence is converted into noise sequence, combine the context condition extracted by bidirectional converter to generate positive / negative interactive sequence, to be discretized output by rounding step;3 construct contrast learning network, mix original sequence and generated sequence to construct enhanced view, based on question similarity and response consistency calculation adaptive weight to mine difficult sample;4 jointly optimize knowledge tracking loss, diffusion model loss and contrast loss, end-to-end training network.The application generates enhanced data in line with knowledge state dependence by conditional diffusion, and improves the robustness of model to sparse noise data by combining adaptive weighting strategy, can significantly improve prediction accuracy and representation quality.

This invention provides a robot localization method based on background pulse Kalman filtering, comprising: constructing a linear dynamic system with multiple motion states and a Markov transition probability matrix; applying an interactive multi-model Kalman filter algorithm based on the linear dynamic system and the Markov transition probability matrix to obtain the estimated values ​​of the state vectors of the motion models and the model probabilities of the motion models; obtaining the estimated values ​​of the state vectors based on the estimated values ​​of the state vectors of the motion models and the model probabilities of the motion models; applying the background pulse Kalman filter algorithm to each motion model to obtain the estimated values ​​of the state vectors of the robot's motion models and the covariance matrix of the state vectors of the motion models; and iteratively solving to obtain the estimated values ​​of the state vectors of the motion models and the covariance matrix of the state vectors of the motion models at the next time step, thereby achieving high-precision localization of the robot.

The invention relates to the technical field of power systems, and discloses a load sequence generation method, system and device and a medium. The method comprises the following steps: dividing an obtained original load sequence into a first reference load sequence and a first dynamic load sequence through screening and clustering; combining a joint probability distribution model and a Markov transfer matrix to reconstruct a daily load curve of a simulated typical day, and generating a second reference load sequence; inputting the screened target external factors influencing the first dynamic load sequence into a neural network model fusing a bidirectional time sequence convolutional network, a gating circulation unit and a double-stage attention mechanism to carry out load prediction, and generating a second dynamic load sequence; and correspondingly superposing the second reference load sequence and the second dynamic load sequence according to the time dimension to obtain a target load sequence. According to the invention, high-quality load simulation data support is provided for refined operation of a power system.

The application relates to the technical field of power consumption anomaly detection, and specifically provides a Markov model-based improved power consumption anomaly detection method for clustering, which comprises the following steps: for power data preprocessing, a symbolic aggregate approximation method is used to reduce the dimension and symbolize the power consumption time sequence, and a Markov state transition probability model is constructed to represent the power consumption behavior mode of a user; for the problem that a traditional density peak value clustering algorithm relies on manual experience to select a truncation distance, a clustering anomaly detection model is provided; the relative distance is used to measure the difference in the Markov transition probability distribution of the user; a mycoparasitism optimization algorithm and a Bonferroni index are introduced to automatically optimize the truncation distance parameter; and the density peak value is used to identify the clustering center to complete user clustering and identify abnormal points. The application improves the precision and efficiency of power consumption anomaly detection, and provides technical support for power consumption safety management and anti-electricity stealing.

The invention discloses a vibration event classification method and device based on multi-modal features and a double-branch network, and relates to the technical field of structural health monitoring and safety early warning. The method comprises the steps that original vibration signals are collected and preprocessed, and normalized signals are obtained; extracting multi-scale time-domain features through empirical mode decomposition, extracting sub-band frequency-domain features through wavelet packet decomposition, screening optimal sub-band frequency-domain features in combination with information entropy, integrating the optimal sub-band frequency-domain features with the multi-scale time-domain features, and obtaining dimensionality-reduced features through principal component analysis; converting the normalized signal into a two-dimensional image matrix by using a Markov conversion field; constructing a back propagation algorithm-multilayer perceptron and self-attention transformation network encoder double-branch network, and respectively extracting local multi-scale features and global time sequence features; and fusing the local multi-scale features with the global time sequence features to obtain a fused feature vector, and outputting a final classification result through a classification module. According to the invention, the accuracy and robustness of ship collision event classification can be improved.