48 results about "Bayes classifier" patented technology

The embodiment of the invention relates to the technical field of bank risk control, and provides a bank network risk control optimization method and system based on flow behavior analysis, and the method comprises the steps: obtaining a bank network flow behavior data package set, and carrying out the flow behavior feature extraction processing of the bank network flow behavior data package set, obtaining a traffic behavior feature set of each traffic behavior data packet, and inputting the traffic behavior feature sets into a preset deep learning model for traffic behavior classification processing to generate traffic behavior classification results corresponding to the traffic behavior data packets; based on the traffic behavior classification result, calling a corresponding Bayesian classifier to carry out risk classification processing to generate a risk classification result corresponding to the traffic behavior data packet; and generating a bank network risk control optimization instruction set according to a risk classification result, and distributing the bank network risk control optimization instruction set to a corresponding bank network risk control execution node to trigger a risk control operation, thereby improving the accuracy and real-time level of bank network risk prevention and control.

The invention discloses a substation primary and secondary equipment communication prefabricated optical cable online monitoring method and system, and belongs to the technical field of communication prefabricated optical cable monitoring. The system comprises an optical cable parameter acquisition module, a communication quality evaluation module, a physical parameter analysis module, a first-aid repair path planning module and a fault database. The method comprises the following steps: optical cable parameter acquisition: acquiring data in real time, and converting high-dimensional data into low-dimensional data through a principal component analysis algorithm; communication quality evaluation: identifying communication characteristics in the low-dimensional signal parameter matrix based on a fuzzy comprehensive evaluation algorithm, and outputting a communication quality score; the physical parameter analysis module extracts physical deep features of the optical cable by using a deep belief network DBN, and inputs an improved Bayesian classifier to output a state classification result; according to the first-aid repair path planning, OTDR detection parameters are dynamically adjusted, and an optimal first-aid repair path is planned in combination with the position of the inspection robot; according to the invention, optical cable communication quality evaluation, accurate physical state classification and efficient fault repair planning are realized.

The invention discloses a voiceprint recognition-based power transmission line defect recognition method and system, and the method comprises the steps: firstly installing a sound collection system on a power transmission line, collecting sound signals transmitted by the power transmission line and equipment thereof, and then carrying out the preprocessing and feature extraction of the sound signals; and finally, classifying the collected sound signals by adopting a Bayesian classifier to achieve the purpose of identifying different types of defects. According to the invention, an effective technical means can be provided for determining the defect type of the power transmission line, early warning when the power transmission line has defects and saving the cost of power transmission line inspection.

The invention discloses a small sample crack recognition method and system based on transfer learning, and the method comprises the steps: constructing an innovative and deep-coupled neural network architecture, and enabling a self-adaptive crack perception attention module integrated with a parallel asymmetric convolution kernel to recognize the linear geometric features of a crack, and generating an attention graph; then, the attention map is adopted to carry out pixel-by-pixel signal pre-modulation on an original input image, the enhanced image is sent to a pre-training MobileNetV4 backbone network integrated with a feature-level linear modulation layer, and channel-level dynamic adaptation of feature flow in the network is realized by learning affine transformation parameters; and finally, the extracted depth features are sent to a Gaussian naive Bayes classifier for classification, and depth geometric analysis is carried out on the attention map so as to realize interpretable fracture severity evaluation. According to the method, the accuracy, robustness and interpretability of crack identification are remarkably improved, and the technical bottleneck in a small sample scene is effectively solved.

The invention provides an electronic warfare equipment relation extraction method based on BERT and a Bayesian classifier, and belongs to the technical field of knowledge graph relation extraction. The method comprises the following steps: S1, preprocessing text data, and adding a label based on a classification result; s2, constructing an embedding layer, and converting the Chinese data into vector representation by using the embedding layer; s3, constructing a bidirectional encoder, and extracting context features by using the bidirectional encoder; s4, a naive Bayes classifier is constructed, and classification is carried out; and S5, carrying out model training and testing to obtain a relation extraction result. According to the method, the accuracy and practicability of electronic confrontation text relation extraction can be improved.

The invention discloses a lung cancer cell brain metastasis prediction system and method, and belongs to the field of computer image processing.The lung cancer cell brain metastasis prediction method comprises the steps that a primary lung cancer CT image sequence, a same-period pathological examination result and a brain nuclear magnetic report are collected; preprocessing the primary lung cancer CT image sequence, and marking the preprocessed CT image sequence as a first image sequence; obtaining a prediction classification result according to a lung cancer brain metastasis sniping model BM-Sniper; the aggregation feature vector is analyzed and processed, linear classification is executed, a classification prediction result is obtained, and linear classification is obtained through a support vector machine model or a Bayesian classifier. Through primary lung cancer CT image sequence processing, feature extraction of a lung scanning image is carried out according to an image feature extraction mode to obtain an aggregation feature vector, and the aggregation feature vector is input into a classification module of a prediction model to output a classification result, so that whether a detected object is subjected to lung cancer brain metastasis is predicted; and an intermediate result with high accuracy is provided for auxiliary diagnosis of a doctor.

The application discloses a homomorphic encryption method and application thereof to a privacy protection classifier. The specific steps of the method comprise generating a public key pk and a private key sk by using a key generation algorithm KeyGen, encrypting a plaintext Q, and decrypting a ciphertext c. Compared with the prior art, the application avoids the disadvantage that in a fixed-point representation system, a number must be represented as a shared integer to perform multiplication, achieves a good balance between calculation efficiency and communication interaction, reduces expected misclassification loss in application to privacy protection classifier encryption, and maintains the same accuracy as an original minimum Bayes risk Bayes classifier.

The application discloses an analysis method and system for noninvasive prenatal screening, and the method comprises the following steps: obtaining target high-depth sequencing data of a target sample; performing data preprocessing on the target high-depth sequencing data to obtain depth information and SNP site information of a target region; obtaining a test result through global Z test based on copy number information, obtaining a first analysis result through local microdeletion / microduplication analysis by using a forward-backward search algorithm, and obtaining a classification result through a Bayesian classifier; obtaining a second analysis result through SNP analysis based on the SNP site information; and finally comprehensively judging to obtain a target analysis result. The application can effectively reduce the complexity of experimental operation, reduce the complexity of the diagnosis process, reduce the sample error probability caused by multiple sampling, significantly improve the efficiency of clinical testing, has high practical value and application prospect, and can be widely applied to the technical field of data processing.

The invention discloses a fault diagnosis method based on integrated empirical mode decomposition and a manifold structure, and aims to research an algorithm model capable of realizing effective fault diagnosis for an early fault with weak characteristics. The main core of the method is to integrate eigenmode function components obtained by empirical mode decomposition, judge the sensitivity of the eigenmode function components to early faults so as to provide a variable reconstruction strategy more sensitive to the early faults, and meanwhile, extract local features and manifold structures by using a neighborhood preserving embedding algorithm so as to improve the robustness of the early faults. And high-order statistical features more sensitive to early faults are constructed in combination with a statistical local algorithm, so that the high-order statistical features are input into a Bayesian classifier, and finally early fault diagnosis is realized. Compared with a traditional method, the method can more effectively distinguish different types of early faults, obtains higher accuracy, and is a more excellent early fault diagnosis method.

The embodiment of the application relates to an algorithm and a device of a Bayesian classifier of a non-uniform background, which are applied to an underwater active sonar system, the algorithm comprising: obtaining underwater data to be measured and auxiliary data through the active sonar system; the number K of the auxiliary data is greater than 0; modeling classification of the unknown covariance matrix structure into a binary hypothesis testing problem; hypotheses of the binary hypothesis testing problem comprise H i Wherein i=0, 1, H0 is a case that the unknown covariance matrix is a complex conjugate symmetric matrix; H1 is a case that the unknown covariance matrix is a real symmetric matrix; a Bayesian model is set, the Bayesian model comprising a complex inverse Wishart random matrix and a real inverse Wishart random matrix; a classifier for distinguishing the two hypotheses is obtained by using a minimum error probability criterion.

The invention discloses a circRNA (Ribonucleic Acid) and miRNA (Micro Ribonucleic Acid) interaction prediction system and a circRNA and miRNA interaction prediction method of a graph Fourier pulse neural network. The method comprises the following steps: on the basis of high-throughput sequencing omics data of complex diseases, constructing a heterogeneous biological information network containing drugs, diseases, proteins, circRNA, miRNA and lncRNA; converting the topological features of the entities into a unified feature space by using a graph convolutional network; designing a pulse graph neural network in combination with Fourier coding and a pulse neural network, and extracting a topological structure and high-order semantic features in the network; fusing sequences, topologies and semantic features of circRNA and miRNA through a gate multilayer perceptron to obtain embedding features of circRNA and miRNA; and finally, the interaction of circRNA and miRNA is predicted by adopting a Bayesian classifier. According to the method, heterogeneous biological information is modeled from the perspective of network science, Fourier coding, spiking neurons and graph embedding learning are utilized, the action mechanism of circRNA and miRNA in complex diseases can be disclosed, and the method has good practicability and application prospects in the fields of artificial intelligence, life science, clinical medicine and the like.

The invention relates to the technical field of edge calculation, in particular to a garbage collection and transportation vehicle remote monitoring method and system based on edge calculation, and the method comprises the following steps: a vehicle-mounted weight sensor collects a real-time weight difference to obtain a weight increment, a tilt angle sensor collects a tilt angle and derives to obtain a change rate, and a loading or disturbance state is paired, compared and marked; after monitoring that the dip angle peak value falls back to the difference, Kalman filtering generates an unloading instruction, weight monitoring is started to calculate the mean value and the tail end difference to confirm unloading completion, the operation state is updated, the position time is packaged, the loading and unloading record is input into a Bayesian classifier, and remote monitoring data is output. Loading and disturbance state distinguishing is achieved through vehicle weight increment and dip angle change rate joint analysis, dip angle peak value falling stage continuous monitoring is combined with filtering to weaken noise, unloading is accurately confirmed through the weight falling trend, position and time information is classified and then is synchronously output with the loading and unloading state, and it is guaranteed that recording in the whole process is continuous and credible. And the remote monitoring track is complete and traceable.

The invention discloses a high-orbit non-cooperative target intention recognition and behavior prediction method, which comprises the following steps: establishing and based on a high-orbit non-cooperative target generalization description model, calculating maneuvering sequences under various intentions, and constructing a target maneuvering behavior sequence library; the maneuvering condition of the target is recognized, the maneuvering condition is matched with the target maneuvering behavior sequence library through a Bayesian classifier, and the probability of each type of intention is obtained through calculation; and taking the probability of the previous intention as the prior probability of the next Bayesian classifier processing until the probability of a certain intention is greater than a specified threshold value, completing intention recognition, and extracting a target subsequent maneuvering behavior prediction result from the target maneuvering behavior sequence library. The defect that an existing intention recognition method only aims at a non-maneuvering target is overcome; and high-precision intention identification and behavior prediction for the maneuvering non-cooperative target are realized.

The invention provides an attack detection method using a naive Bayes classifier in a honeypot. The method comprises an active trapping honeypot and an active verification cloud sandbox. The active trapping honeypot is realized by an active trapping honeypot system; the active trapping honeypot system comprises a host layer, a service layer, an event layer, a data model layer and a detection layer. The active verification cloud sandbox is used for analyzing and discriminating 0DAY and NDAY vulnerabilities widely adopted in network attacks by using codes and special Trojan horses, and discovering intrusion behaviors. By applying the technical scheme, the attack detection capability of the naive Bayes classifier in a honeypot environment can be improved, so that a more effective protection means is provided for network security.

This disclosure provides a security detection method, apparatus, storage medium, and electronic device based on a large model, relating to the field of network security technology. The method includes: acquiring training sample emails to train a Bayesian classifier, determining the trained Bayesian classifier; using the trained Bayesian classifier to detect emails to be detected, determining a first detection result; if the first detection result is in a first detection interval, determining structured prompt words based on the first detection result; inputting the structured prompt words into a locally deployed large language model, determining the output result of the large language model; and performing either allow or block actions on the emails to be detected based on the first detection result and the output result of the large language model. This achieves accurate email identification.

The present invention relates to a method and system for spatial reconstruction of sparse trajectories based on a probability distribution model, and belongs to the technical field of spatial reconstruction of automatic vehicle identification trajectories. The method comprises the following steps: S1, constructing a trajectory network through GPS trajectory data, wherein the trajectory network includes all possible roads that a vehicle may pass through when traveling on urban roads; S2, when a vehicle travels in the trajectory network, using a Bayesian classifier to calculate the probability of the vehicle taking each path, and selecting the path with the highest probability as the vehicle's trajectory; S3, using the overall model to reconstruct the trajectory of a test set, and evaluating and analyzing the prediction error based on the prediction results and actual data. The present invention can more accurately reconstruct the spatial trajectory of a vehicle while reducing data dependence, has higher efficiency and higher accuracy than existing methods, and has a broad application prospect.

The invention relates to the technical field of electric appliance operation mode identification, in particular to a non-intrusive electric appliance operation mode identification method and system, and the method comprises the steps: calculating an active power signal according to the collected voltage and current signals at a power utilization inlet of a user; using an unsupervised clustering method to complete load mode mining; extracting load characteristics according to each group of detected load modes; constructing a classification model to perform electric appliance mode identification; according to the invention, the active power signal is calculated by collecting the voltage and current signals at the power utilization inlet of the user, so that the detection of the load event is completed, and the non-intrusive identification of the operation mode of the electric appliance is realized; the calculation of the local density is completed according to the Euclidean distance of the elements in the power characteristics, so that the accuracy and efficiency of load mode recognition are improved; the Gaussian naive Bayesian classifier is constructed, and the Gaussian naive Bayesian classifier is utilized to complete the identification of the electric appliance mode, so that the identification of the electric appliance mode is more reliable.

The invention relates to an underground water environment risk assessment method based on big data, and relates to the technical field of underground water monitoring and pollution risk assessment. According to the method, water quality parameter data filling is carried out based on a big data pre-trained water quality parameter filling model, a Bayesian classifier or a K nearest neighbor mean value through adaptive missing rate and data type selection, and the calculation efficiency and prediction precision of different missing rates are balanced; a similarity function is defined by considering sampling sites and water quality parameters, repeated data screening is carried out, and data with similar water quality parameters and non-similar sites are prevented from being deleted. Clustering and quartering anomaly mixed detection is utilized to consider univariate statistical anomaly and multivariate structure anomaly, and true pollution data is prevented from being deleted by mistake. A groundwater monitoring data set is utilized, and a composite groundwater environment evaluation model is trained through a differential evolution optimization fusion weight mode to estimate a groundwater environment index value. Model complementation is utilized to reduce deviation; and the integration benefit of the model is maximized by optimizing the weight through differential evolution.

The invention discloses a transformer risk assessment method and device based on multi-index fusion, relates to the technical field of electrical performance test and electrical fault detection, and mainly aims to solve the problem of low accuracy of existing transformer risk assessment. The method mainly comprises the steps that comprehensive risk values of different transformers are calculated according to static risk indexes of the transformers, static risk levels are determined according to the comprehensive risk values, and real-time monitoring data in the operation process of the transformers are obtained according to data monitoring frequencies determined according to the static risk levels; according to the real-time monitoring data, identifying a first state evaluation result of each transformer through a pre-constructed Bayesian classifier, and identifying a second state evaluation result of each transformer through a pre-constructed fuzzy evaluation model; and for any transformer, performing cooperative verification according to the first state evaluation result and the second state evaluation result of the transformer to obtain a risk evaluation result of the transformer. The method is mainly used for evaluating transformer risks.

The invention discloses a gas detection alarm method, which relates to the field of gas detection, and comprises the following steps: collecting an environmental gas sample at a detection moment, measuring the temperature and humidity of the sample, and obtaining compensation based on temperature and humidity deviation in combination with a coupling compensation model; a double-agent coordination algorithm is used, temperature control equipment and humidity control equipment are respectively regarded as agents to carry out simulation regulation and control training, and temperature control and humidity control actions are determined based on temperature and humidity deviation and compensation after training so as to enable an environment gas sample to reach standard temperature and humidity; extracting the current detection moment, the current detection position and the spatio-temporal characteristics of the gas concentration table by adopting spatio-temporal Gaussian modeling to generate the current probability density, and deciding a current environment state label; the current gas concentration table, the detection moment, the detection position and the environmental state label are classified into leaf nodes of the decision tree through the Bayesian classifier to determine the next detection moment, so that the influence of temperature and humidity on concentration measurement is avoided, and the accurate judgment of the environmental state is realized.

This invention provides a method for detecting battery thermal runaway anomalies and a battery management unit. During detection, operational data for each battery sub-module is acquired. Based on this data, the corresponding Channenzo entropy or Channenzo entropy change rate is obtained and compared with a set target threshold. When the parameter value in the sample to be detected exceeds the target threshold, it is considered thermal runaway anomaly data. Simultaneously, a Bayesian classifier is used for further data processing, and the abnormal data is output and an alert is issued, thereby effectively improving the accuracy of battery operational data detection and ensuring battery usability and safety performance.

The application discloses a seabed soil type automatic identification method based on a naive Bayes algorithm. The method comprises the following basic steps: 1) CPT data acquisition; 2) attribute feature calculation; 3) normalized cone tip resistance fluctuation feature calculation; 4) feature parameter filtering; and 5) using a Bayes classifier to identify the seabed soil type. The method has the advantages of simplicity, small calculation amount, good real-time performance, saving of manpower and easiness in implementation, and is suitable for automatic identification of seabed soil types.

A test apparatus for testing a trained classifier (e.g., neural network, random forest algorithm, naïve Bayes classifier, support vector machine, linear regression machine learning algorithm, etc) tha

An object detection assistant system includes a memory and a processor. The processor is coupled to the memory. The memory stores one or more commands. The processor accesses and executes one or more commands of the memory. One or more commands include inputting a detection result parameter output by an object detection neural network for object detection of an image to an assistant neural network to output a first correction coefficient after processing by the assistant neural network, where the detection result parameter includes object information and a first confidence; inputting the first correction coefficient and detection result parameters to a Bayesian classifier to output a second correction coefficient; and adjusting the first confidence according to the second correction coefficient to obtain second confidence, and the second confidence being taken as the first confidence of the adjusted detection result parameter.

The invention discloses a baby sleeping posture recognition method based on double models. The method comprises the following steps: S1) making a data set with baby sleeping posture pictures; s2) baby sleeping postures on all pictures in the data set are identified through an improved Yolov5 network model; s3) extracting baby skeletons on all pictures in the data set through Openpose; s4) performing sleeping posture recognition on the baby skeleton through a GoogleNet network model; and S5) inputting recognition results of the improved Yolov5 network model and the GoogleNet network model into a Bayesian classifier, and performing final infant sleeping posture judgment. And S6) setting an evaluation index, and evaluating the identification results of the improved Yolov5 network model and the GoogleNet network model through the evaluation index. According to the method, a double-model integration method is adopted, and the robustness and accuracy of classification performance are improved by integrating the output results of the two independent models.

An accident explosion source tracing method based on a Bayesian classifier, which belongs to the field of accident explosion damage. The present invention solves the problems of poor real-time performance and low accuracy of existing accident explosion source tracing methods. The method of the present invention first analyzes and constructs the types of accident explosion sources, and then determines the explosion sources for historical accident explosion events, thereby constructing a labeled data set; for the accident explosion event to be traced, a set of similar events is selected from the data set, and explosion source tracing is carried out according to the set of similar events, so as to more accurately identify and track the source and damage impact of the accident explosion event. Compared with the traditional manual explosion source tracing method, the method of the present invention can greatly improve the efficiency of explosion source tracing, and does not require the establishment of a complex physical model, has lower requirements for data, simplifies the explosion source tracing process while improving the accuracy of source tracing, and ensures the feasibility and real-time performance of explosion source tracing. The present invention can be applied to tracing the source of accident explosions.

The application discloses a gas detection alarm method, relates to the field of gas detection, and collects an environmental gas sample at a detection moment and measures the temperature and humidity of the sample, obtains compensation based on the deviation of the temperature and humidity and a coupling compensation model, uses a double-agent coordination algorithm, simulates control and regulates training by taking temperature control and humidity control equipment as agents respectively, determines temperature control and humidity control actions based on the deviation and compensation of the temperature and humidity after training to make the environmental gas sample reach standard temperature and humidity, adopts space-time Gaussian modeling to extract the space-time features of the current detection moment, a detection position and a gas concentration table, generates the current probability density, and decides the current environmental state label, classifies the current gas concentration table, the detection moment, the detection position and the environmental state label to the leaf nodes of a decision tree through a Bayesian classifier to determine the next detection moment, avoids the influence of the temperature and humidity on concentration measurement, and realizes accurate judgment of the environmental state.

The present invention relates to a video target tracking method, which solves the problems of low tracking accuracy and stability and target loss of existing tracking algorithms under target illumination, and includes: 1. Obtain an image M and a target; 2. Set a target gate. If M is the first frame image, execute step 3; otherwise, execute step 6; 3. Generate e positive sample image blocks and d negative sample image blocks within the target gate; 4. Calculate the feature values of each positive sample image block and negative sample image block, and obtain a template feature vector; 5. Initialize the Bayesian classifier and then return to step 1; 6. Draw a search box, select R candidate image blocks within the search box, calculate the template feature vectors of each candidate image block, classify them using the Bayesian classifier, and output the target position of the next frame image; if the tracking requirement is met, end; otherwise, execute step 7; 7. Calculate the template feature vector of the target position, update the Bayesian classifier, and then return to step 1.

The invention provides a method and a system for classifier-based prediction. The method includes: receiving a multivariable input having a characteristic variable; performing prediction based on a coherent independent Bayesian classifier (CIBer) by executing a conditional probability quality function on the feature variables; and outputting the prediction category. Prediction based on the coherent independent Bayesian classifier (CIBer) includes joint coding to manually insert an order in classification features. The joint coding is configured to maintain intrinsic dependencies between the classification features.

The present invention relates to the technical field of packet inspection. Disclosed are a packet inspection and analysis system and method based on deep flow inspection. The system comprises a data acquisition module, a deep flow inspection module, a packet analysis module, a data storage module, and a security module; the data acquisition module is used for acquiring production data stream information transmitted by a packet in a network; the deep flow inspection module is used for performing flow feature extraction on a packet data stream and determining an application type; the packet analysis module is used for determining whether the packet is normal; the data storage module is used for storing packet flow data; and the security module is used for checking packet information and network connection condition. According to the present invention, deep flow inspection technology is used to identify the application type of the data stream, without being affected by encryption of application layer data; and a Bayesian classifier is used for continuing to perform classification in a major category, which only depends on statistical properties of the data, thereby achieving high efficiency and accuracy when determining whether the encrypted packet is normal.