61results about How to "Reduce data dimensionality" patented technology

The invention discloses an SCL field safety accident analysis and early warning method and system, a medium and a program product, and the method comprises the steps: carrying out the distributed cleaning and feature extraction of multi-source heterogeneous monitoring data, and obtaining a multi-dimensional time sequence feature flow; constructing a dynamic association network of a security state; identifying a key influence factor chain, and establishing a semantic analysis model; constructing a safety threshold system; evaluating the multi-dimensional time sequence characteristic flow by using a safety threshold system; when the multi-dimensional time sequence characteristic flow triggers early warning, performing tracing analysis by using a semantic analysis model to obtain a root event triggering the early warning, and simulating the development trend of the root event based on a preset evolution model; determining a predicted risk range and a risk type according to the tracing cause analysis result and the accident development trend; and the corresponding accident early warning scheme is matched in the preset database according to the risk range and the risk type, and the accident early warning scheme is sent to the monitoring terminal, so that the accuracy of judgment and classified early warning of different types of safety accidents is improved.

The invention discloses a power equipment fault prediction method based on support vector regression, and aims to improve the prediction accuracy. The method comprises the following steps: firstly, collecting multi-dimensional operation parameter data of power equipment, and constructing an original monitoring data set; a data set is segmented through a sliding time window, wavelet transform is used for noise reduction, and then a normalization method is applied to generate a standardized data set. Time domain and frequency domain features are further extracted, a feature vector space is constructed, an optimal feature subset is screened through a mutual information method, and a training data set is generated; performing preliminary training on a support vector regression model by using the training data set to generate candidate support vectors, and screening a support vector set with the maximum contribution through an optimization algorithm; a grid search method is adopted to adjust kernel function parameters and penalty factors, and a support vector set is further optimized. And evaluating the performance of the model through cross validation, applying the optimized support vector regression model to power equipment fault prediction, and generating a fault occurrence probability prediction value.

The invention relates to the technical field of intelligent scene recognition, and discloses an intelligent scene recognition method and equipment for an intelligent interaction control unit, and the method comprises the steps: carrying out the collection and preprocessing of an operation sequence, video content and audio data of the intelligent interaction control unit in a digital set-top box, and obtaining a standard multi-mode data set; inputting the standard multi-modal data set into a multi-branch deep neural network model, and extracting time sequence, visual and audio features through parallel processing to obtain a fusion scene feature vector; carrying out dimensionality reduction and semantic mapping on the fused scene feature vector to obtain a compressed semantic feature vector; performing similarity calculation on the compressed semantic feature vector and a predefined scene query vector to obtain a scene matching score; and based on the scene matching score, integrating the output of the plurality of sub-classifiers to obtain a target scene classification result, and the method can be efficiently operated on the digital set top box with limited resources to realize real-time scene recognition.

The invention provides an anomaly detection and response method and system based on intelligent perception driving, and is particularly applied to cloud service information security monitoring. The method comprises the following steps: acquiring multi-type data in real time and fusing the multi-type data through Kalman filtering and weighted average; constructing a self-encoding network to carry out feature extraction and dimension reduction, detecting abnormity through a reconstruction error and setting a dynamic threshold value; a reinforcement learning optimization algorithm is introduced, a dynamic response strategy is designed, and a reward mechanism is defined, so that the response effect is improved; designing an automatic response process, including alarm, isolation and repair measures; migrating the optimized self-encoding network knowledge to a new scene by adopting a transfer learning technology; a cloud-edge collaborative architecture is constructed, and data are analyzed in a centralized manner and synchronized in real time. According to the method, the real-time performance and accuracy of information security monitoring are effectively improved, potential threats can be quickly responded, the security risk is reduced, and the method is suitable for various information security monitoring scenes.

The invention relates to an enterprise park meteorological fire risk assessment method based on an adaptive random forest model, and the method comprises the steps: building a risk assessment model and a visual early warning platform, enabling the risk assessment model to collect alarm data, meteorological data, enterprise data and park division data, and forming a risk assessment data set, and integrating internal characteristics and external data of the park into a data set, inputting new data into the self-adaptive random forest model by means of a real-time data flow technology, updating and evaluating a fire risk index value of the park in real time, and optimizing a model decision tree to automatically adjust a risk evaluation model and adapt to changes of environment and operation. Accurate early warning information is provided for a visual early warning platform, the risk level of the park is displayed in real time, and a risk alarm is given out in time.

The invention provides a mixed precursor chemical gas identification method based on feature construction, and relates to the technical field of mixed gas identification, and the method comprises the steps: determining a division criterion of a transient response stage and a steady-state response stage through a working mode of fixed temperature modulation as an inverted step wave; and taking the average value in the steady-state response stage as the characteristic of the structure, establishing a sample library of the structure characteristic and the mixed gas concentration, and fitting the relationship between the structure characteristic and the mixed gas concentration by using a regression model with a simple structure, so that the function of identifying the mixed precursor chemical gas by using the simple model is realized. The current situation that the model for identifying the mixed precursor chemical gas is more complex and the algorithm scale is more huge is changed, and the working efficiency of mixed gas detection is improved.

The invention relates to the technical field of tumor patient management, in particular to a tumor patient hospitalization full-period management system, which acquires and manages personal information, physiological data and treatment data of tumor patients through a data management module and ensures the real-time performance and integrity of the data. The data processing module improves the accuracy of the data by supplementing missing values and screening out abnormal values, optimizes the calculation efficiency through dimension reduction processing, retains main information features, and provides high-quality data input for intelligent prediction. The intelligent prediction module is based on a neural network algorithm, the future physiological parameter change trend of the patient is accurately predicted, the physiological anomaly occurrence probability is calculated, the prediction accuracy and timeliness are remarkably improved, and medical staff are helped to recognize potential risks in advance and provide personalized treatment. And the full-cycle visualization module displays patient data through a timeline and generates a risk object attention set, so that key monitoring of high-risk patients is realized, and the safety management level during hospitalization is enhanced.

The invention relates to an airport aid-to-navigation light inspection method based on an unmanned aerial vehicle technology, and relates to the technical field of aid-to-navigation light inspection, and the method comprises the following steps: S1, setting standard parameters; s2, the unmanned aerial vehicle executes a flight task, and images are collected from multiple angles; s3, obtaining the mass center of the navigation aid lamp; s4, calculating actual geographic coordinates of the navigation aid lamp; s5, comparing the position coordinate information of the navigation aid lamp; s6, brightness attenuation detection of the navigation aid lamp; and S7, carrying out statistical feedback, and carrying out the step S2. The airport navigational light inspection method has the effects of reducing and improving the airport navigational light inspection cost and improving the airport navigational light inspection efficiency.

The invention belongs to the technical field of network security, and discloses an Internet of Things attack detection method based on deep learning, which eliminates redundant features through feature selection, enhances inter-class difference and intra-class similarity of selected feature subsets, solves the problem of class imbalance in an attack detection data set by utilizing EQLv2, and improves the attack detection efficiency. And meanwhile, constructing a space-time model to extract space-time information of the sample. According to the method, multi-classification performance evaluation is carried out on an Internet of Things attack detection reference data set NSL-KDD and a CIC-IDS-2017, the advantages of the method are verified from five indexes including the accuracy rate, the precision rate, the recall rate, the F1 score and the false alarm rate, and the effectiveness and feasibility of the method are reflected when the method is compared with a plurality of methods.

The invention relates to an intelligent industrial data clustering and grouping method, system and device and a medium, and the method comprises the steps: carrying out the standardization preprocessing of collected original industrial data, obtaining standard industrial data, and constructing a high-dimensional feature space according to the standard industrial data; performing industrial feature extraction and dimension reduction on the high-dimensional feature space to obtain a low-dimensional feature vector; performing preliminary grouping on the low-dimensional feature vectors according to a preset clustering algorithm to obtain a first clustering result; performing secondary adjustment on the first clustering result to obtain a second clustering result; and performing industrial scene simulation verification on the second clustering result to obtain a verification result, and performing optimization adjustment on the second clustering result according to the verification result to obtain a target clustering combination. According to the method, a more reasonable clustering result can be obtained, and the accuracy and applicability of the clustering effect are improved.

The invention discloses a deep learning-based pipeline structure stress proxy model construction method, which belongs to the field of engineering mechanics, energy transmission and artificial intelligence, and comprises the following steps of: firstly, establishing a numerical model of a pipeline, simulating different environmental conditions by applying different loads, and solving to generate a large amount of simulation data; then, feature unit extraction is carried out on the simulation data so as to compress feature dimensions; then, a deep learning initial proxy model of pipeline stress is constructed, and initial training is carried out through finite element simulation data; and finally, transfer learning is carried out based on the initial agent model, the transfer learning is divided into two stages, enhanced actual measurement sample data is used for training in the pre-training stage, and accurate actual measurement samples are used for further training and fine adjustment in the strengthening stage, so that the generalization ability of the model is improved. According to the method, the stress distribution can be rapidly and accurately solved by constructing the stress agent model, the generalization ability is high, and the problem that a traditional physical modeling method is insufficient in real-time performance and precision in stress monitoring and prediction can be solved.

The invention discloses an efficient intelligent data compression and feature extraction method and system. The method comprises the following steps: S1, data preprocessing: performing data cleaning, denoising and standardization processing on to-be-processed data; s2, data compression and storage: determining a compression algorithm according to the type of the data, and uploading a compressed data file to a database; s3, feature extraction: deploying a machine learning model, and extracting representative features from the compressed data; and S4, data post-processing: further processing and optimizing the extracted features. According to the method, the data compression technology and the feature extraction technology are combined, the most representative information is extracted from the original data, meanwhile, the data storage and transmission cost is reduced, key features in the data are automatically recognized and reserved through an intelligent algorithm, and therefore efficient data compression and feature extraction are achieved.

The invention provides an industrial control protocol abnormal behavior analysis and detection method and device, a medium and a program product. The method comprises the steps of network flow collection, network flow analysis, data preprocessing, behavior baseline model construction, real-time flow access and detection and dynamic optimization of a baseline model. According to the invention, the process service behavior baseline model can be established for specific process service communication links and industrial protocols, and automatic construction and dynamic adjustment of the process service baseline model can be realized; the problems that in existing industrial control protocol abnormal behavior analysis and detection, a model is not established for a specific process service communication link, when the service changes, real-time dynamic adjustment cannot be achieved, and the abnormal detection rate is low are solved. The abnormal condition of each device in the industrial network traffic can be rapidly detected by performing abnormal behavior analysis detection on the industrial control protocol transmission traffic by using the process business behavior baseline model.

The invention relates to the technical field of energy storage, and discloses an energy storage power station abnormity alarm method, device and equipment based on multi-modal data, and the method comprises the steps: obtaining the original sampling data of an energy storage power station, and carrying out the sampling frequency alignment processing of the original sampling data based on the resampling frequency, so as to obtain the multi-modal data; performing feature extraction and fusion processing on the multi-modal data to obtain a comprehensive feature vector, and performing dimension reduction processing on the comprehensive feature vector to obtain a key feature vector; and inputting the key feature vector into a pre-trained anomaly monitoring model, and generating an alarm signal under the condition that the energy storage power station is monitored to run abnormally according to an output result of the anomaly monitoring model. The method has the beneficial effects that the multi-modal data of different data sources are kept consistent in the sampling time dimension, the availability of the multi-modal data is improved, and the accuracy of subsequent feature extraction and analysis is also ensured.

The invention relates to the technical field of intelligent manufacturing, in particular to a fault prediction method and system for factory manufacturing equipment based on data driving, and the method comprises the steps: collecting vibration signal data and tool wear data, carrying out the preprocessing of the collected data, carrying out the time-frequency domain feature extraction of the collected vibration signal data, and extracting the wear features of a tool; fusing the extracted tool wear features, vibration signal data features and cutting parameter features to form a high-dimensional feature vector, selecting first k feature vectors through principal component analysis (PCA), and reducing the dimension of the high-dimensional feature vector; constructing and training a numerical control machine tool fault prediction model based on a support vector machine SVM model; and performing fault prediction on the numerical control machine tool, namely factory manufacturing equipment. Potential faults of the numerical control machine tool can be predicted, maintenance and overhaul can be arranged in advance, the equipment reliability is improved, the accidental shutdown time caused by the faults is shortened, and the production continuity is guaranteed.

The invention discloses a fault diagnosis method and device for a large die forging press, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining multi-modal sensor data of the large die forging press; the data of the multi-mode sensor are preprocessed; inputting the preprocessed multi-modal sensor data into a multi-modal attention convolutional neural network model for feature extraction to obtain multi-modal features; carrying out fusion processing on the multi-modal features; and inputting the fused multi-modal features into a classifier for classification to obtain a fault diagnosis result.

The invention discloses a time series prediction method of a multi-time scale channel mixed attention mechanism, and relates to the technical field of time series prediction and deep learning. Specifically, weighted processing is carried out on extracted features of time sequence data through a channel mixed attention mechanism. The mechanism can dynamically adjust the weight of the feature according to the importance of the feature, and ensures that the key feature plays a greater role in prediction. Inputting the time sequence data into a multi-time scale convolutional neural network to obtain feature vectors under different time scales; and fusing the weighted features to obtain comprehensive multi-time scale features, and completing the training process of the time sequence prediction model. According to the method, the accuracy and adaptability of time sequence prediction are improved, and complex modes and trends in time sequence data can be captured more accurately. Through the method, the method can play a role in various application scenes needing high-precision prediction.

The invention provides an audio coding method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: performing first-level feature extraction processing on an audio signal to obtain a first-level signal feature; for the ith hierarchy in the N hierarchies, splicing processing is carried out on the audio signals and the signal features of the (i-1) th hierarchy to obtain spliced features, feature extraction processing of the ith hierarchy is carried out on the spliced features to obtain the signal features of the ith hierarchy, N and i are integers larger than 1, and i is smaller than or equal to N; the i is traversed, the signal feature of each level in the N levels is obtained, and the data dimension of the signal feature is smaller than the data dimension of the audio signal; respectively encoding the signal feature of the first level and the signal feature of each level in the N levels to obtain a code stream of the audio signal at each level; according to the invention, the audio coding efficiency can be improved and the audio coding quality can be ensured.

The invention discloses a diabetes mellitus index data classification method and system based on an adaptive heterogeneous differential evolution algorithm, and a terminal. The method comprises the following steps: preprocessing original diabetes mellitus index data; feature selection and hyper-parameter optimization are carried out at the same time by adopting an adaptive heterogeneous differential evolution algorithm, the data dimension is reduced by evaluating the importance and redundancy of feature subsets in the feature selection process, and the model performance is improved by adaptively adjusting key parameters of a learning algorithm in the hyper-parameter optimization process; and inputting the optimized feature subset into a machine learning model for training and prediction. By constructing a hybrid coding mechanism and a differentiated variation strategy, the heterogeneous parameter collaborative optimization problem is effectively solved, algorithm control parameters are dynamically adjusted based on population diversity measurement, self-adaptive balance of global exploration and local development is achieved, and then the accuracy of diabetes index data classification is improved.

The invention discloses a software defect prediction feature selection method based on an improved whale optimization algorithm, and the method comprises the following steps: obtaining traditional features of a single file in a folder where a software source code to be predicted is located, and forming a data set; preprocessing the data set of the to-be-predicted software; dividing the preprocessed data set of the prediction software into a test set and a training set according to a proportion; based on the training set data, an improved whale optimization algorithm is adopted for training, and traditional features corresponding to the to-be-predicted software source code file are screened out; and adopting the screened traditional features to predict the number of defects of the source code of the software based on the test set data. According to the method, the data dimension can be effectively reduced, the calculation complexity is reduced, and the problem of dimension disasters caused by redundant features is avoided, so that the generalization ability and the prediction precision of the model are improved.

The invention relates to the field of image processing, in particular to a human body attribute identification method in a coal mine transportation scene, which comprises the following steps: constructing a danger monitoring model, and collecting data information of coal mine field environment and personnel; preprocessing the data information to obtain corresponding feature information; classifying the danger monitoring models according to the danger types and endowing the danger monitoring models with corresponding risk values; the feature information is processed to obtain action behavior information, road condition information and mineral information, the action behavior information, the road condition information and the mineral information are substituted into a danger monitoring model to obtain corresponding risk values, whether danger occurs or not is judged, and an alarm signal is sent; the danger monitoring model is trained through the detected feature information, the original danger monitoring model is covered, and therefore the problem that in the prior art, the accuracy of judging the danger type and the danger occurrence probability through experience is low, subjective factors are many, and consequently the accuracy of risk judgment during coal mine transportation is reduced is solved.

The invention provides a hydroelectric generating set fault identification method based on a support vector machine, and relates to the technical field of hydropower station equipment. The method specifically comprises the following steps: acquiring vibration signal data of different parts in the hydroelectric generating set in real time by using a vibration sensor, constructing a hydroelectric generating set vibration signal data set, and preprocessing the hydroelectric generating set vibration signal data set to obtain a time sequence data set; performing dimension reduction processing on the time sequence data set by adopting a principal component analysis method to obtain a dimension-reduced time sequence data set, inputting the dimension-reduced time sequence data set into a support vector machine, and training the support vector machine by adopting a multi-strategy improved sparrow search algorithm to obtain an optimized hydroelectric generating set fault recognition model; vibration signal data of different parts in the hydroelectric generating set are collected again and preprocessed, a new time sequence data set is constructed and input into the optimized hydroelectric generating set fault recognition model for fault recognition, and a fault recognition result of the hydroelectric generating set is obtained. The accuracy and the real-time performance of fault diagnosis of the hydroelectric generating set are effectively improved.

The invention relates to an intelligent prediction method for seepage characteristic parameters of earth and rocks, which comprises the following steps of: primarily selecting and processing an indoor seepage test result data set of the earth and rocks, constructing an interpretable machine learning model to quantify the influence degree of different characteristic parameters on the seepage characteristic parameters of the earth and rocks, and realizing dimensionality reduction and optimization of the data set. And establishing an intelligent combined prediction model fusing the bidirectional long-short-term memory neural network, a sparrow search algorithm and attention mechanism optimization, completing prediction model training based on the optimized data set, and inputting related characteristic parameters to realize intelligent prediction of soil and stone seepage characteristic parameters. According to the invention, engineering technicians can be assisted to complete rapid and intelligent prediction of seepage characteristic parameters (permeability coefficient and critical permeability drop) according to gradation characterization parameters, porosity, dry density and other basic characteristic parameters of soil and stone, and the test cost is reduced.

This application belongs to the field of underwater acoustic array signal processing technology. This application provides a tensor-enhanced azimuth estimation method suitable for high-order acoustic field sensor arrays. The embodiments of this disclosure first construct a received tensor from the received data of the high-order acoustic field sensor array; then, multilinear low-rank modeling is performed on the received tensor, and the optimal first subspace factor matrix in the array dimension and the optimal second subspace factor matrix in the channel dimension are extracted using the HOOI method; next, the received tensor and the angle domain dictionary are synchronously projected into a low-dimensional tensor quantum space; finally, the sparse power spectrum in the angle domain is estimated using a multi-shot sparse Bayesian learning model, thereby obtaining the target azimuth. This method can suppress noise components in each dimension while preserving multidimensional coupling relationships, reducing the data dimensionality of subsequent sparse processing, reducing the influence of dictionary correlation and noise, and obtaining a sharper azimuth spectrum and higher resolution under conditions of low signal-to-noise ratio, low snapshot, and adjacent targets.

The invention relates to the technical field of wind power generation, in particular to a wind turbine generator incoming wind condition prediction method and system based on a meteorological background and wind power plant characteristics, and the method comprises the steps: obtaining historical incoming wind condition data through an anemometer tower, and calculating a historical incoming wind condition sequence affected by an upstream terrain wake flow effect in front of a wind wheel of a wind turbine generator; obtaining weather forecast data and interpolating the weather forecast data of different air pressure layers to a unit target height; constructing a spatial downscaling model, and establishing a spatial mapping relationship between the historical weather forecast data of the unit target height and the incoming wind condition; constructing a time feature extraction model, and extracting time features based on historical weather forecast data and unit operation data; and combining weather forecast data, historical incoming flow wind condition data of the unit and operation data of the unit, and outputting an incoming flow wind condition prediction result by utilizing the spatial-temporal feature extraction model. The objective of the invention is to realize simultaneous prediction of incoming flow wind speed and wind direction and improve the accuracy of incoming flow wind condition prediction.

The present invention relates to a method, device and equipment for designing a high-density memory chip packaging structure. The method: based on the current packaging structure parameter combination, a multi-chip stacking structure of a high-density memory chip is three-dimensionally modeled to obtain a packaging structure model; a finite element analysis is performed to obtain stress distribution data and a stress-strain curve; feature extraction and feature fusion are performed to obtain a fused feature vector; a structure optimization model is obtained based on multi-layer feedforward neural network training; dependency analysis is performed to construct a parameter tree structure and assign corresponding priority values; multiple packaging structure parameters are sorted and optimized one by one using the parameter tree structure and the priority value, and an adaptive penalty function method is used to process constraint conditions to obtain a target packaging structure parameter combination. The implementation of the present invention improves the design efficiency and performance of the high-density memory chip packaging structure.

The application discloses a multi-modal radio frequency authentication method based on a multi-scale signal representation, which comprises the following steps: firstly, pre-processing the original IQ signal of a target device received to obtain an instantaneous envelope signal; carrying out multi-scale decomposition and denoising processing on the instantaneous envelope signal to obtain a denoised envelope signal; constructing a multi-modal data set according to the original IQ signal and the denoised envelope signal; carrying out feature extraction and fusion on the multi-modal data set through a pre-trained target feature extraction network to obtain a fused feature representation; and carrying out classification on the fused feature representation through a pre-trained target classification network to output a classification result corresponding to the target device. The amplitude, frequency and time-frequency energy distribution information can be complementarily fused by constructing the multi-modal data set; the multi-modal features are extracted and fused through the target feature extraction network, so that the information loss is effectively avoided; and the target classification network is used for rapid classification, thereby reducing the calculation cost and ensuring the accuracy of identification.

The invention is suitable for the field of artificial intelligence, and provides a transportation tool matching recommendation method and system based on a knowledge graph, and the method comprises the steps: converting a triple into a text form through employing an improved knowledge graph embedding model KGE, carrying out the coding of an input text through a BERT model, and obtaining the context representation of each Token; capturing global semantic information of the entities and the relationships based on the aggregation representation of the triple to obtain embedded representations of the entities and the relationships; integrating and extracting features of the heterogeneous information, and performing dimension reduction processing on feature data of the heterogeneous information by using principal component analysis (PCA) to obtain embedded representation of the heterogeneous information; the method comprises the following steps: performing feature dimension reduction on entities, relationships and heterogeneous information based on an embedded layer of a recommendation system algorithm NFM model, capturing a second-order interaction relationship between dimension reduction features through bilinear interaction operation, learning high-order feature interaction by using a feed-forward neural network FNN, outputting a matching probability of goods and a transportation tool, and obtaining a matching result of the goods and the transportation tool; and based on the matching probability, performing matching recommendation of the goods and the transportation tool.

The invention relates to the technical field of ultra-precision machining, in particular to an ultra-precision cutting machining surface roughness online measuring method and system. First, a machining process signal is read. Secondly, calculating the weight of the processing process signal; the processing process signals are weighted according to the weights, and the weighted processing process signals are fused to serve as first input data; the machining process signal is used as additional input data. Then, obtaining a first input result and an additional input result according to the first input data and the additional input data, and obtaining a first fusion result according to the first input result and the additional input result; thirdly, inputting a high-dimensional feature fusion branch according to the first fusion result and additionally extracted first high-dimensional feature information and additional high-dimensional feature information to obtain a second fusion result; and finally, obtaining a surface roughness measurement result. According to the method, surface roughness prediction of ultra-precision cutting machining is more accurate.

The invention provides a power data processing method, electronic equipment and a storage medium, and the method comprises the steps: classifying power demand influence feature data, and dividing the data into a first type of influence features and a second type of influence features according to whether the data stability is lower than a set threshold value or not; decomposing the first type of influence features to obtain initial sub-feature data, and screening out key sub-feature data; and then, inputting the key sub-feature data of the first type of influence features and the second type of influence feature data into a preset power demand prediction model, and performing power demand prediction so as to obtain a prediction value. According to the method, the original data characteristics are decomposed into a plurality of sub-characteristic data, so that local characteristics and trend changes in the data can be captured more comprehensively, and the possible modal aliasing problem is solved. Besides, the sub-feature data is screened to extract a variable which contributes to model prediction to the greatest extent, so that the data dimension can be effectively reduced, and the generalization ability of the model is improved.