33 results about "Likelihood-ratio test" patented technology

The invention discloses a method for estimating the safety communication rate of a near-earth satellite by using an SDFS cooperating with a GLRT. The method comprises the following steps: constructing a communication system model between the near-earth satellite and a ground terminal; analyzing the signal and channel characteristics, and obtaining the distance between the nodes, the channel gain and the received signal distribution; under the condition that the transmitting power of each monitoring party is unknown, estimating the transmitting power by adopting generalized likelihood ratio test, and independently executing the generalized likelihood ratio test based on the observation data of each monitoring party; the superior manager performs joint judgment based on a soft decision fusion scheme in combination with the generalized likelihood ratio test result of each monitoring party and a joint threshold so as to estimate the detection error probability of the monitoring party; a joint optimization strategy of the transmitting power and the number of continuous transmission time slots is constructed, and the total throughput of the system is maximized under the condition that the cooperative concealment constraint is met; according to the invention, an innovative solution is provided for reliable communication of the near-earth satellite in a complex monitoring environment.

The invention relates to the technical field of robot navigation, and discloses a multi-sensor fusion navigation method and system of a robot. The method comprises the following steps: collecting point cloud data of a laser radar sensor and motion data of an IMU six-axis sensor; executing generalized likelihood ratio test and sliding window interval search on the point cloud data and the motion data to obtain a zero-speed abnormal interval, and creating a detection threshold value for the current ground environment according to the zero-speed abnormal interval; performing spatial superposition on the position coordinates of the zero-speed abnormal interval and a laser radar scanning blind area to obtain an obstacle distribution map; cleaning control parameters are adjusted based on the detection threshold value, a re-planning cleaning path is generated based on the obstacle distribution map and the cleaning control parameters, the method can actively identify the potential trapped area and re-plan the cleaning path, and the autonomous navigation ability and cleaning efficiency of the intelligent cleaning robot are improved.

The invention discloses a sea target coherent detection method based on knowledge assistance, which considers introduction of prior information of a radar sea clutter covariance matrix, adopts a two-step generalized likelihood ratio test (GLRT) criterion, constructs an adaptive coherent detection framework under a CG-LN clutter background, and improves robustness and effectiveness of sea detection radar target detection.

The invention discloses a method, device and equipment for directly and qualitatively evaluating a media structure type based on logistic regression and a storage medium, and the method comprises the steps: obtaining logging data of a plurality of wells in a research range, carrying out the standardization processing of the logging data, and obtaining the standardized logging data, the plurality of wells in the research range comprise a reference well and a key well; the reference well is selected, and the coal body structure of the reference well is divided; evaluating the effectiveness of the standardized logging data of the reference well in the aspect of distinguishing coal body structure types by utilizing likelihood ratio test, and screening the standardized logging data according to an evaluation result; the screened standardized logging data are extracted, and a coal body structure evaluation model is constructed through logistic regression analysis; and substituting the standardized logging data of the prediction well into the coal body structure evaluation model, and evaluating the coal body structure type of the prediction well. According to the method, the defect that a single logging index cannot truly reflect the coal body structure can be overcome, and the calculation method is simple, direct, effective, high in accuracy and high in objectivity.

The invention discloses a weak cyclostationary signal detection method based on an unmanned aerial vehicle-mounted passive radar network, and the method comprises the steps: firstly building an active radar transmitting signal and unmanned aerial vehicle passive radar receiving signal model, and then building a binary hypothesis model based on cyclostationary generalized likelihood ratio detection through block cyclic matrix approximation; and constructing generalized likelihood ratio test detection statistics and obtaining local detection results of the unmanned aerial vehicles under a colored noise background by using the cyclostationary characteristic of target echoes, finally fusing the local detection results of the unmanned aerial vehicles based on a Bayesian minimum risk criterion at a fusion center, and outputting global detection judgment. And a detection process of cyclostationary generalized likelihood ratio test-Bayesian minimum risk fusion is formed. According to the method, the detection statistics are constructed by using the cyclostationary characteristics of the target echoes, the global detection accuracy and robustness can be improved under the conditions of low signal-to-noise ratio and complex colored noise, and the method is suitable for a multi-unmanned aerial vehicle cooperative passive radar detection scene.

The application belongs to the technical field of equipment management, and discloses a nuclear detector fault diagnosis method, device, computer equipment and storage medium. The nuclear detector fault diagnosis method comprises the following steps: acquiring an output signal of the nuclear detector; inputting the output signal into a pre-trained deep belief network for fault identification to obtain a fault parameter corresponding to the output signal; and adopting a generalized likelihood ratio test classification model to perform fault classification on the fault parameter to obtain a fault category corresponding to the output signal, so that the fault of the nuclear detector can be quickly and accurately detected.

The invention relates to a radiation source direct positioning method based on random sampling, belongs to the technical field of radiation source direct positioning, and solves the problem of large calculation amount of radiation source direct positioning in the prior art. Comprising the following steps: receiving radiation source signals from different directions by using dispersedly arranged receiving nodes, and sampling received data to obtain observation sample data at different moments; grid division is carried out on the radiation source sensing area coordinate system; randomly selecting a preset number of grid points according to uniform distribution, and calculating likelihood ratio test statistics subjected to time delay compensation as matrix elements of the positions of the grid points based on observation sample data and the positions of the selected grid points; and completing matrix element completion of the whole radiation source sensing area based on a low-rank matrix completion method to form a sensing area receiving signal synchronization likelihood ratio test statistic matrix, and determining a peak position in the sensing area receiving signal synchronization likelihood ratio test statistic matrix as a radiation source position. The radiation source direct positioning method based on random sampling is realized.

This invention discloses a method for detecting multi-channel constant-mode signals without prior electromagnetic interference, belonging to the field of radar signal processing technology. The method includes modeling multi-shot data received by a multi-channel antenna array to obtain high-dimensional multi-channel data; introducing weight vectors to project the high-dimensional multi-channel data onto a single channel for dimensionality reduction, resulting in single-channel weighted data; constructing a generalized likelihood ratio test detector without prior spatial electromagnetic interference information based on the probability density functions under two assumptions: the presence and absence of multi-channel constant-mode signals; and building an optimization model based on the generalized likelihood ratio test detector without prior spatial electromagnetic interference information. A hybrid optimization framework combining alternating optimization and alternating direction multiplier methods is used to solve the optimization model, obtaining the detection parameters and completing the multi-channel constant-mode detection.

Embodiments of the application disclose a kind of distributed communication signal detection method, device and system based on generalized likelihood ratio, wherein the method is applied to fusion center, comprising the following steps: S1: receiving the observation data transmitted by multiple receiving nodes; S2: under the assumption that radiation source does not exist and radiation source exists, respectively construct the joint conditional probability density function of all observation data of all receiving nodes within the observation time; S3: adopt NP criterion to construct the expression of generalized likelihood ratio test statistic; S4: according to maximum likelihood criterion, estimate the covariance matrix in the joint conditional probability density function under the assumption of two kinds; S5: the estimated value of the covariance matrix under the assumption of two kinds is substituted into the expression of generalized likelihood ratio test statistic, and compared with the decision threshold set according to false alarm probability, to complete distributed communication signal detection. The application can improve the detection probability of communication signal under low signal-to-noise ratio, and has good noise resistance when there is noise fluctuation in different receiving nodes.

The application belongs to the technical field of medical informatics, and discloses a population automatic subdivision method based on a population pharmacokinetic model, which extracts individual core pharmacokinetic parameter full posterior distribution and statistical characteristics, combines clinical data to construct a fusion feature space and complete clinical-oriented feature screening, and then builds a Bayesian non-parametric pre-clustering algorithm incorporating clinical stratification constraints to guide the clustering process to fit the clinical diagnosis and treatment logic, while eliminating ambiguous samples and verifying clinical rationality, so that the population subdivision is supported by data and pharmacokinetic theory, potential pharmacokinetic difference subgroups are found, and the clustering results have clear biological and clinical significance, improving the subdivision objectivity and rigor; a specific population pharmacokinetic model is constructed for each pre-clustering subgroup, subgroup merging and splitting are completed through likelihood ratio test, and the subgroup boundary and model parameters are corrected in reverse in combination with clinical feedback.

The invention relates to the technical field of power system protection, in particular to a longitudinal differential protection method and system based on 5G communication self-synchronization likelihood ratio test, electronic equipment and a medium. The method comprises the following steps: acquiring electrical quantity data on two sides of a protected line and executing synchronous preprocessing; calculating according to the electrical quantity data after synchronous preprocessing to obtain a power accumulation break variable; based on a discrimination observation value constructed by the power accumulation break variable, performing statistical hypothesis testing on the discrimination observation value and a currently configured dynamic adaptive threshold to obtain an internal and external fault determination result; and performing longitudinal differential protection on the protected feeder line according to the internal and external fault judgment result. Through the mode, the technical problem that the reliability and adaptability of the protection criterion are insufficient in the existing longitudinal differential protection technology is solved, and rapid, accurate and reliable fault identification and isolation under complex communication conditions and fault characteristics are realized.

This invention discloses a MIMO-OFDM target detection method and system considering clutter interference. Addressing the characteristics of multiple symbols and multiple carriers on an OFDM frame, this invention first combines all received symbols on a subcarrier, dividing all subcarriers into several groups. For each subcarrier and one symbol, a received signal model is established to indicate whether the target is present or absent. Then, using the generalized likelihood ratio test, the clutter covariance matrix of each subcarrier group and the maximum likelihood estimate of the target response channel are calculated. Next, based on the maximum likelihood estimate of the unknown parameters of each subcarrier group, the test statistics for all subcarriers on the OFDM frame are calculated. Finally, based on the detection threshold obtained through offline training, the presence of the target is determined by comparing it with the test statistics. This invention considers the statistical characteristics of clutter interference in MIMO-OFDM target detection, achieving a higher correct detection probability compared to traditional energy detectors, and can achieve ideal results on a hardware platform.

An occupancy detector includes a radar and an occupancy analyzer. The radar is provided to output a radar background signal and a radar detection signal which are time-domain signals. The radar background signal is detected by the radar from an area when a subject is not occupying the area, and the radar detection signal is detected by the radar from the area when the presence of the subject is unknown. The occupancy analyzer is electrically connected to the radar to receive the radar background signal and the radar detection signal, and it is provided to analysis whether a subject is occupying the area based on the radar background signal and the radar detection signal through generalized likelihood ratio test (GLRT).

A method and system for sea surface target recognition based on range-time images, belonging to the field of measurement image recognition and processing, firstly maps the actually observed sea surface RT image into sea surface RT image data with amplitude following a standard Rayleigh distribution. The covariance matrix of the mapped sea clutter data is constructed. A binary hypothesis testing method is used on the mapped sea clutter data to construct a generalized likelihood ratio test statistic. The optimal estimate is substituted into the log-likelihood ratio expression to obtain the standard form of the mapped generalized likelihood ratio detector. The detector is then used to identify whether a target exists in the range cell to be detected. This invention can convert arbitrary non-Gaussian sea surface RT image data into RT image data with amplitude following a standard Rayleigh distribution, thereby achieving unified processing in complex sea clutter environments and effectively improving the accuracy of target recognition under complex non-Gaussian sea clutter backgrounds.

The invention belongs to the technical field of genetic relationship identification methods, particularly relates to a genetic relationship identification method and system based on homologous co-progenitor fragments IBD, and aims to solve the technical problem of identifying genetic relationships of five levels and within five levels. According to the technical scheme, the method comprises the following steps: detecting IBD fragments between two disputed individuals; constructing a likelihood ratio test framework, taking two dispute individuals as irrelevant individuals as an original hypothesis, and taking a specific genetic relationship between the two dispute individuals as a standby hypothesis; solving the probability of IBD fragment data under the original hypothesis; solving the probability of IBD fragment data under the alternative hypothesis; calculating a likelihood ratio gt by synthesizing the probabilities of IBD fragment data appearing under the original hypothesis and the alternative hypothesis; if 1 is less than 1, determining that the individual is an unrelated individual.

The application discloses a data-driven replay attack detection method based on an equivalent space industrial control system, which comprises the following steps: acquiring input and output data of multiple time points from an industrial control system; constructing a historical data matrix and calculating a zero matrix, solving an optimal weight matrix, calculating an equivalent matrix, generating a system residual, designing a chi-square test and a generalized likelihood ratio test, and designing corresponding thresholds; introducing part of model information to enhance the detection capability of the original system; deploying the obtained detection system, acquiring the input and output of the system online, generating a residual, and using the chi-square test and the generalized likelihood ratio test to judge the system operation; when the test value is greater than the residual threshold, it is judged that the system is subjected to a replay attack, and an alarm is issued. The application can detect the replay attack based on the historical data of the equipment operation of the industrial control network through the input and output of the system without depending on the model parameters of the system, meanwhile, the application is easy to deploy and does not sacrifice the control performance of the system.

The present application relates to spaceflight measurement and control technical field, especially relate to a kind of generalized data detection and simplification method, system and equipment for improving the precision of space target positioning, comprising: obtaining the observation data of space target, construct extended Gaussian-Markov model containing potential modeling error, generate multiple hypothesis set by different combination of modeling error parameter;Utilize likelihood ratio test criterion to construct the test statistic between different hypotheses, according to the observation environment requirement self-adaptive selection executes generalized data detection process or generalized data simplification process;Determine the optimal model hypothesis of current observation by multiple hypothesis testing, based on the optimal model hypothesis parameter adaptive estimation is carried out, and the position parameter of space target is solved.This application guarantees high-precision requirement by forward selection strategy, enhances robustness under complex environment by backward elimination strategy, realizes the effective identification and elimination of multiple modeling error, significantly improves the precision and reliability of space target positioning.

The application relates to a generalized likelihood ratio test method and device based on Bayesian inference. The method comprises the following steps: acquiring reference channel and monitoring channel signals of a transmitting source and a receiving node, and constructing a binary hypothesis test signal model of target presence / absence; modeling unknown channel response coefficients as random variables with a known prior distribution, and modeling a transmitting signal symbol sequence as a deterministic variable, and constructing a joint probability distribution function of two types of hypotheses; obtaining an edge probability function through integral edge processing, maximizing the edge probability function to obtain a deterministic variable estimation value, constructing a Bayesian generalized likelihood ratio test statistic, and comparing the Bayesian generalized likelihood ratio test statistic with a preset threshold to determine whether the target exists. By using the method, channel characteristics and signal structure prior knowledge can be fully fused, detection robustness and sensitivity in a low signal-to-noise ratio and high dynamic environment can be improved, calculation complexity can be simplified, spatial diversity gain can be efficiently utilized, and quasi-optimal detection under the constraint of a constant false alarm probability can be realized.

The embodiment of the invention provides a credit line decision-making method, device and equipment in the credit loan field, and the method comprises the steps: constructing a dynamic network potential space model which is used for representing the change of the operation state of an enterprise and is provided with a change point according to the original transaction data of the enterprise at different time points, the dynamic network potential space model comprises network potential space models at different time points; performing parameter estimation on the dynamic network potential space model to obtain a potential space of the transaction network; based on a likelihood ratio test algorithm, detecting change points of a potential space from each time point; and determining the credit line of the enterprise according to the change point of the potential space and the feature vector centrality of the enterprise. According to the method, a multi-dimensional dynamic network representation model is constructed, fund exchange data among enterprises is converted into a sequential network topology structure, a potential space change point detection mechanism is introduced, a credit line is dynamically adjusted, and the credit line is dynamically and flexibly adjusted according to real-time operation conditions of small and micro enterprises, so that efficient configuration of credit resources is realized.

The application provides a bearing fault automatic detection method and system based on iterative likelihood ratio test, relates to the technical field of bearing fault periodic signal modeling and period automatic detection, and comprises the following steps: S1, collecting a noisy periodic signal from a fault bearing by using a sensor; S2, constructing a constrained linear model, performing parameter estimation and calculating a likelihood function after segmenting the signal by the constrained linear model; S3, obtaining a likelihood function waveform graph by scanning a period parameter; S4, obtaining an accurate period from the likelihood function waveform graph by iterative likelihood ratio test; and S5, performing fault diagnosis on the bearing by using the period estimation result. The application can make the regression model more stable, the period estimation effect more accurate, effectively eliminate false positives and false negatives of the fault period when the signal is long enough through iterative hypothesis testing.

The invention provides a target detection method and system suitable for a reverberation edge environment, and relates to the technical field of active sonar detection. According to the target detection method, the detection model can be generated according to the prior information of the covariance matrix in the reverberation edge environment, the prior information of the covariance matrix is fully utilized, and the estimation precision of the covariance matrix is improved. The estimation value of the detection statistic parameter of the detection model is solved based on the two-step generalized likelihood ratio test criterion, the adaptive detector is obtained, the adaptive detector is used for carrying out adaptive detection on the target in the reverberation edge environment, and the target detection performance in the reverberation edge environment is remarkably improved.

A target adaptive detection and position estimation method for a multiple-input-multiple-output system comprises the following steps: acquiring the number of transmitting array elements, the number of receiving array elements and the size of a time delay-Doppler unit of the multiple-input-multiple-output system, and constructing a time delay-Doppler unit echo vector model containing a target, dividing the leakage condition of the target energy in the time delay-Doppler unit into a plurality of scenes; modeling target adaptive detection of the multi-input multi-output system as a binary hypothesis test problem; on the basis of a two-step generalized likelihood ratio test criterion, firstly, it is assumed that a background interference covariance matrix is known, detection statistics of generalized likelihood ratio test are calculated by using an echo vector in a time delay-Doppler window to be detected, and then an estimated value of the background interference covariance matrix is calculated by using a recursive estimation method. And replacing the background interference covariance matrix in the detection statistics with the estimated value to obtain a target adaptive detection method, and estimating the position of the target in the time delay-Doppler unit through two-dimensional lattice search.

The application provides a target detection method and system suitable for a reverberation edge environment, and relates to the technical field of active sonar detection. The target detection method can generate a detection model according to prior information of a covariance matrix in the reverberation edge environment, fully utilizes the prior information of the covariance matrix, and improves the estimation accuracy of the covariance matrix. An estimation value of a detection statistic parameter of the detection model is obtained based on a two-step generalized likelihood ratio test criterion, an adaptive detector is obtained, and the adaptive detector is used for adaptive detection of a target in the reverberation edge environment, so that the target detection performance in the reverberation edge environment is significantly improved.

The invention relates to a generalized likelihood ratio detection method and device based on Bayesian inference. The method comprises the following steps: acquiring reference channel and monitoring channel signals of a transmitting source and a receiving node, and constructing a binary hypothesis test signal model of target existence / absence; modeling an unknown channel response coefficient as a random variable of known prior distribution, modeling a transmitting signal symbol sequence as a deterministic variable, and constructing a joint probability distribution function of two types of hypotheses; and carrying out integral marginalization processing to obtain an edge probability function, obtaining a deterministic variable estimation value after maximization, constructing a Bayesian generalized likelihood ratio test statistic, and comparing with a preset threshold to judge whether a target exists or not. By adopting the method disclosed by the invention, channel characteristics and signal structure priori knowledge can be fully fused, the detection robustness and sensitivity in a low signal-to-noise ratio and high dynamic environment are improved, the calculation complexity is simplified, the space diversity gain is efficiently utilized, and quasi-optimal detection under a constant false alarm probability constraint is realized.

The invention relates to a radar system error detection method based on cooperative targets, and the method comprises the steps: carrying out the calculation in a detection period through employing the obtained position information of a plurality of cooperative targets under a north-east-sky coordinate system, and obtaining a measurement truth value set; acquiring a plurality of actual measurement values of the radar system on the plurality of cooperative targets; calculating difference values between the plurality of actual measurement values and the measurement truth value set to obtain a difference value sequence set; performing data dimension expansion on the difference value sequence set, and performing generalized likelihood ratio test on the difference value sequence after dimension expansion to obtain a first statistical magnitude under the condition that the system error is positive and a second statistical magnitude under the condition that the system error is negative; determining whether a system error exists or not according to a comparison result of the first statistic or the second statistic and a detection threshold; and under the condition that the existence of the system error is determined, the radar system is corrected based on the error estimation value, and the corrected radar system is obtained. The device can maintain the overall positioning precision of the radar system under various error levels.

This invention discloses a non-intrusive load identification calculation method. To improve the accuracy of load identification, the method first collects data from the target user, obtaining voltage and current data of the electrical equipment. An improved two-dimensional generalized likelihood ratio test is used to perform event detection on the current data. Two false detection filtering algorithms, cluster removal and derivative removal, are used to reduce the occurrence of false detections. The abrupt change points of events are identified and stored in an event list. Reactive current is used to replace the total current in the traditional V-I trajectory. Steady-state data is extracted from the event list to generate a V-reactive-I trajectory diagram. This diagram is then fused with the active and reactive power obtained from the Fourier decomposition of the measured voltage and current to form an image feature matrix. Finally, the image feature matrix is ​​input into an improved fully convolutional network model incorporating residual blocks to output the identification result.

The general problem of pattern change discovery between high-dimensional data sets is addressed by considering the notion of the principal angles between the subspaces is introduced to measure the subspace difference between two high-dimensional data sets. Current methods either mainly focus on magnitude change detection of low-dimensional data sets or are under supervised frameworks. Principal angles bear a property to isolate subspace change from the magnitude change. To address the challenge of directly computing the principal angles, matrix factorization is used to serve as a statistical framework and develop the principle of the dominant subspace mapping to transfer the principal angle based detection to a matrix factorization problem. Matrix factorization can be naturally embedded into the likelihood ratio test based on the linear models. The method may be unsupervised and addresses the statistical significance of the pattern changes between high-dimensional data sets.

The invention provides a test question parameter consistency detection method and system for group knowledge diagnosis. The method comprises the steps that group, student, test question and answer result data are collected and preprocessed to obtain an interaction matrix; individual knowledge distribution is constructed, group knowledge generality characteristics are obtained, and group knowledge generality and dependency are captured based on an attention mechanism; then test question parameters are coded, and the answer correct probability is calculated based on a cognitive diagnosis model; by taking variation lower bound (ELBO) maximization as a target and knowledge distribution KL divergence minimization as a constraint, iteratively updating parameters of an encoder and the like; and finally, outputting a knowledge diagnosis result and completing DIF detection through layered likelihood ratio test. According to the group knowledge diagnosis and test question function difference (DIF) detection method based on the hierarchical variation model, the problem that knowledge dependence of students in a group is ignored in traditional detection is solved, the knowledge point prediction precision of group knowledge diagnosis is improved, objectivity and precision of test question DIF detection are achieved, knowledge state distribution KL divergence is reduced, and inference efficiency is improved.

The invention relates to the field of biological information, and discloses a protein phosphorylation site function evaluation method based on a kinetic model in combination with an artificial intelligence algorithm. Comprising the following steps: S1, acquiring intracellular omics data of cells under N conditions; s2, taking the omics data under each condition as a reference one by one, substituting the data in the S1 into a kinetic model, and estimating model parameters by introducing a Bayesian algorithm; meanwhile, whether a certain protein phosphorylation site has functions or not under the current reference condition is evaluated through likelihood ratio test; and S3, repeating the step S2 for N times until each condition serves as a reference, summarizing the results of a certain protein phosphorylation site under N iterations, and estimating the probability that the potential protein phosphorylation site has a regulation function under N conditions by adopting a maximum likelihood estimation method. According to the method, the model parameter estimation capability of an artificial intelligence algorithm is fully utilized, protein abundance data are integrated, phosphorylation abundance data are also integrated, model solving is more accurate, and false positive occurrence is reduced.

The invention belongs to the technical field of gear wear monitoring, and particularly relates to a non-Gaussian working condition gear wear online monitoring method based on a vibration signal, which realizes real-time automatic monitoring and evaluation of a gear wear state under a complex working condition. The problems that traditional oil and visual analysis depends on off-line detection, and an existing vibration method is difficult to recognize early wear due to non-Gaussian interference are solved. Compared with the prior art, the method has the advantages that cyclostationary analysis is introduced, weak non-stationary features caused by tooth surface microtopography changes can be effectively extracted, and therefore effective recognition of gear early-stage abrasion is achieved; a health index is constructed by combining likelihood ratio test and a generalized Gaussian distribution model, the index still keeps good tendency under a non-Gaussian working condition, interference of non-Gaussian components can be effectively restrained, more stable and reliable wear degradation state monitoring is achieved under a complex working condition, and the method is suitable for popularization and application. And core technical support is provided for predictive maintenance and health management of a high-end equipment transmission system.