63results about How to "Reduce feature dimension" patented technology

The invention discloses a marine diesel engine vibration fault early warning method based on an improved VMD, and the method comprises the steps: improving the VMD through combining a frost ice algorithm RIME, carrying out the hyper-parameter optimization, carrying out the VMD signal decomposition of an optimized data set based on an optimal combination, and obtaining a plurality of IMF values, so as to reconstruct vibration signal sequence data. Performing time domain and frequency domain feature extraction on the reconstructed vibration signal sequence data to obtain a time domain feature parameter and a frequency domain feature parameter; calculating and acquiring a Pearson coefficient between each feature parameter in the mixed domain feature set and the early warning value, and selecting the feature parameter of which the Pearson coefficient meets a preset Pearson coefficient threshold as an optimized feature parameter; and obtaining a residual error between a predicted root-mean-square value and an actual root-mean-square value based on the optimal BiGRU algorithm model so as to obtain a residual error threshold range under the condition of fault-free operation of the marine diesel engine, building an RIME-VMD-BIGRU model for vibration fault early warning of the marine diesel engine, and realizing automatic prediction of the vibration fault of the marine diesel engine. According to the method, sailors can be reminded of possible faults of the ship, the dependence on expert experience is reduced, and meanwhile, compared with other early warning algorithms, the method has higher diagnosis precision.

The invention relates to the technical field of condition prediction, and particularly discloses a condition score prediction method for Alzheimer's disease, which comprises the following steps: S1, acquiring longitudinal multi-time-point MRI image data and corresponding clinical score data of a target subject; s2, processing to obtain a feature matrix of the brain region and brain region data and clinical scores at different time points; s3, performing sparse representation on the feature matrix by using a dictionary learning algorithm to obtain a sparse representation matrix; s4, constructing an SLSTM, taking the sparse representation matrixes of the baseline moment and the M06 and M12 time points as input, and training a model to predict clinical scores of subsequent time points M18, M24 and M36; according to the method, sparse representation is performed on MRI image data through dictionary learning, redundant features are removed, features highly related to disease change are extracted, and a long-term dependency relationship in a longitudinal time sequence is captured in combination with a double-layer stacked LSTM structure, so that the model can more accurately predict clinical scores of future time points.

The invention relates to a network modeling method based on GNN and Transform models, and the method comprises the steps: firstly carrying out the generation and preprocessing of a data set, and constructing a message passing neural network; the message passing neural network comprises three parts, namely a GNN cascade module, a Transform cascade module and a specific index reading module; and then training the network, finally inputting the preprocessed test set image into a trained network model to obtain a prediction map, comparing the prediction map with a truth value, and calculating each evaluation index. According to the method, the global dependency relationship can be better captured, so that more comprehensive data representation is obtained, and meanwhile, the model generalization ability and the calculation efficiency are improved.

The invention relates to the technical field of medical information extraction, in particular to an image feature selection method for a schizophrenia medical record Spark model. The method comprises the following steps: acquiring brain magnetic resonance image data and resting state functional magnetic resonance imaging data of a plurality of subjects; performing multi-scale layered segmentation on the brain image of each subject by using a preset layered brain region template for the brain magnetic resonance image data to obtain brain region positioning data including a local level, a regional level and a global level; and performing adaptive hierarchical noise reduction processing on the resting state functional magnetic resonance imaging data in a Spark distributed environment to obtain brain function time sequence data after noise reduction. According to the method, the brain magnetic resonance image data is accurately divided into a local level, a regional level and a global level by using the preset layered brain region template, so that local structure details and global network characteristics of the brain region are considered, and effective integration of multi-scale information is realized.

The invention provides an orthognathic surgery risk assessment system based on machine learning and data driving, and relates to the technical field of medical and artificial intelligence systems.The orthognathic surgery risk assessment system comprises a data acquisition module used for acquiring orthognathic surgery data of a to-be-assessed patient, and a risk assessment system, the data expansion module is used for inputting the preprocessed orthognathic operation data of the patient into a risk classification model, and in the risk classification model, a generative adversarial network based on circulation consistency is adopted to carry out data expansion on the orthognathic operation data; performing feature extraction on the expanded data by adopting a neural network based on dynamic adaptive oscillation; inputting the extracted high-dimensional features into an auto-encoder based on potential space mapping for feature dimension reduction; and inputting the dimensionality-reduced feature representation into a support vector machine based on fuzzy constraint, processing uncertainty and noise in the orthognathic surgery data feature representation through a fuzzy membership function and an adaptive quantization perturbation mechanism, and outputting a final orthognathic surgery risk assessment auxiliary classification result.

The invention provides a night small target detection method based on an improved YOLOv9c model, and the method comprises the steps: constructing a night small target detection model which takes a YOLOv9c model as a reference network, a backbone network comprises a comprehensive feature extraction module and an SPD-ADown down-sampling module, and a head comprises an FBM-CBAM attention module; performing iterative training on the night small target detection model to obtain a trained night small target detection model; and detecting a to-be-detected target by using the trained night small target detection model to obtain a detection result. According to the method, the comprehensive feature extraction module improves capture of fine features in a night image, and the down-sampling module SPD-Aown retains more key information while reducing feature dimensions, so that the feature fusion effect is improved; the FBM-CBAM attention module more accurately strengthens the expression of important features through a channel and a space attention mechanism; the improvements effectively improve the detection performance of the small target under the low illumination condition at night.

The invention relates to a network security situation awareness method and system based on big data analysis, and belongs to the technical field of network security. The method comprises the steps of collecting original network data which comprises original network data flow and original protocol data in broadband service, training a network security situation awareness model based on a preset network security situation awareness standard set, the network security situation awareness model comprises a network flow analysis model and a protocol analysis model, generating a network state label through the network security situation awareness model, and evaluating a network security level through a rating rule according to the network state label. And outputting a network security situation awareness instruction through an instruction control script according to the network security level, generating a network security situation report through an automatic reporting tool according to the original network data, the network state label and the network security level, and displaying the network security situation report through a data visualization tool.

The invention discloses a grape wine production place identification model training method and system based on a BP neural network, and relates to the technical field of grape wine production place identification, and the method comprises the following steps: collecting a large amount of sample data, including various chemical and physical indexes capable of reflecting the characteristics of different production places of grape wine, carrying out the preliminary cleaning and preprocessing of the data, and carrying out the training of a grape wine production place identification model; and obvious errors and abnormal values are removed. According to the method, the multi-collinearity problem caused by the high correlation between the features is solved through correlation evaluation and classification processing, and the feature data set is reasonably divided by using the Pearson's correlation coefficient matrix and the overall correlation coefficient. Feature selection and dimension reduction processing are carried out on a high-correlation data set, the stability of the training process is ensured, numerical instability and weight updating fluctuation risks are reduced, the stability and convergence of the model are improved, meanwhile, the training efficiency and resource utilization are improved, feature independence is enhanced, and finally the precision and generalization ability of the model are improved. And rapid and accurate wine producing area identification is realized.

The invention belongs to the technical field of natural language processing, and discloses a natural language processing platform and method based on deep learning, and the platform comprises a data collection module which is used for collecting font data, text data, image data and environment data; the data processing module is used for preprocessing the collected font data, text data, image data and environment data and obtaining a comprehensive feature data set; the character recognition module is used for predicting character recognition results through a character recognition model and judging whether the character recognition results are consistent or not; the semantic recognition module is used for generating corresponding character paraphrases through a semantic recognition model; collecting character recognition results and corresponding character paraphrases through the software terminal; the voice output module is used for converting the character recognition result and the paraphrases of the corresponding characters into natural voices and outputting the natural voices by adopting a TTS technology; through the implementation of the technology, students can be helped to better learn and understand.

The invention discloses a photovoltaic power station ultra-short-term irradiation prediction method based on a single-photon laser radar, belongs to the technical field of laser radar signal processing, and solves the problem of how to use the laser radar to obtain cloud layer information and realize ultra-short-term irradiation prediction of a photovoltaic power station under different weather conditions. An echo signal profile of the laser radar is inverted through an improved differential zero crossing algorithm, a cloud parameter data set is obtained, based on a volume scanning mode of the radar, the condition of clouds in the sky can be inverted, feature parameters of more clouds are obtained, and the integrity and accuracy of data are ensured; the method comprises the following steps: calculating a sun path, segmenting an effective scanning area so as to extract cloud layer features and reduce feature dimensions, finally combining meteorological features and historical irradiation data to construct a feature matrix, adopting a CNN-LSTM hybrid model to predict irradiation, and showing relatively high precision and stability in prediction of different weather types.

The invention discloses an unsupervised industrial abnormal sound detection method and system based on time-frequency feature selective learning, and the method comprises the following steps: 1, extracting log-Mel spectrogram features from a training set sound signal, executing a spectrogram frame selection strategy, and obtaining a spectrogram frame of each sound sample; step 2, inputting the spectrogram frame in the step 1 into a frequency domain feature selection auto-encoder model for training, wherein a loss function is LAEFS; step 3, extracting log-Mel spectrogram features from the collected unknown sound samples, and selecting a plurality of frames from a log-Mel spectrogram according to a spectrogram frame selection strategy; step 4, inputting the spectrogram frame obtained in the step 3 into the trained frequency domain feature selection auto-encoder model in the step 2, and taking the reconstruction loss LRec as an abnormal score S; and step 5, comparing the abnormal score S obtained in the step 4 with a threshold value A theta, if the abnormal score S is greater than the threshold value A theta, indicating that the input sound signal is abnormal, otherwise, indicating that the sound signal is normal.

The invention discloses an electric tool fault type identification method and system based on data driving, which are used in the field of fault identification, and the method comprises the following steps: collecting operation data of an electric nail gun under different environment conditions and operation states; processing including time domain analysis and frequency domain analysis is executed on the operation data, and a waveform index and a rough principal component analysis method are used for extracting a feature set for distinguishing fault types in an analysis processing result; constructing a fault type identification model by using a support vector machine combination of K neighbors; performing fault type detection and recognition on the electric nail gun by using the trained fault type recognition model; and obtaining the fault type of the electric nail gun according to the analysis result. According to the invention, fault type detection and identification are carried out by using the model to quickly and accurately determine the fault type of the electric nail gun, the efficiency and accuracy of fault diagnosis are improved, and the cause and the feature of the fault are obtained by comparing the difference between different fault types.

The invention discloses an obstetrical complication prediction system and method based on AI, and relates to the technical field of complication prediction. The obstetrical complication prediction system based on the AI comprises a data acquisition module, a data preprocessing module, a feature engineering module, a complication prediction module, a prevention measure module and a result display module. According to the method, the psychological state data of the pregnant woman is taken into consideration, that is, the psychological state data of the pregnant woman is also taken as partial data of model input and training, so that the obstetrical complication prediction model can more comprehensively understand the health state of a patient, thereby helping the model to make more accurate prediction, and improving the accuracy of the obstetrical complication prediction. Meanwhile, the model is optimized through an incremental learning method, so that the model can be gradually corrected by introducing psychological state data, overfitting of historical data is avoided, computing resources can be saved, computing cost and time expenditure can be reduced, a large amount of historical data does not need to be stored, only necessary parameters and statistical information need to be reserved, and the method is suitable for large-scale popularization and application. Therefore, the storage requirement is reduced.

The invention relates to the technical field of data processing, in particular to a user portrait prediction method based on a sparse auto-encoder and K-means. According to the user portrait prediction method based on the sparse auto-encoder and the K-means, the limitation that a traditional user portrait generation and prediction method mainly depends on artificial feature engineering can be overcome, and the user feature dimension is reduced by using the sparse auto-encoder, so that similar user features and invalid user features are eliminated; the method comprises the following steps: firstly, inputting data into a server, and introducing a sparsity penalty term to better capture important features of the input data so as to automatically extract useful features, finally, dividing the obtained useful features into different categories by using K-means clustering, and constructing a user portrait after analysis.

The invention discloses a training method and a prediction device for a multi-class gynecological disease prediction model, and relates to the technical field of gynecological disease prediction, and the method comprises the steps: obtaining a gynecological electronic case data set, and carrying out the preprocessing of the data set; the preprocessed data set is divided into a training set and a verification set according to the proportion of 4: 1, and the training set and the verification set serve as input of training of at least two prediction models; and evaluating the trained prediction model, taking out the model with the best prediction effect as the prediction model, and the like. Compared with the training of the existing gynecological disease prediction model, the method has the advantages that the training time is shortened, and meanwhile, the execution efficiency is improved; 12 gynecological diseases can be predicted at the same time according to gynecological electronic case data, the generalization ability of the prediction model is enhanced, and the method can be practically popularized and used.

The invention discloses an intelligent correction method for a numerically simulated wind field, which belongs to the field of numerical simulation. The method comprises collecting and processing site observed wind field data and multiple characteristic variable data of numerical model simulation, using a random forest model to screen important characteristic variables that have a significant impact on the wind field, dividing the data sets of the observed wind field and the important characteristic variables into a training set, a validation set and a test set, constructing and training a BP (Back Propagation) neural network model, and finding an optimal model by adjusting parameters, evaluating the performance of the optimal BP neural network model, and performing visualization processing. The invention is based on the observed wind field data and the numerical model data, utilizes the random forest model, and combines the BP neural network to construct an intelligent correction method for a numerically simulated wind field. The method can further improve the accuracy of wind field simulation on the basis of a dynamic numerical model simulating a wind field, and provides a new method for correcting a numerically simulated wind field.

The invention relates to the field of carbon emission prediction, in particular to a subway station construction stage carbon emission prediction method and system. Measuring and calculating carbon emission of the subway integrated station at different stages according to a carbon emission coefficient method, and performing data preprocessing to obtain carbon emission monitoring data; performing feature and target variable separation on the carbon emission monitoring data to obtain a feature matrix and a target variable vector; constructing a carbon emission prediction model to perform feature processing on the carbon emission monitoring data to obtain carbon emission feature data; the method comprises the following steps: constructing a carbon emission prediction integrated model based on LightGBM and XGBoost, identifying carbon emission characteristic data through the carbon emission prediction integrated model, and optimizing parameters in the LightGBM model and the XGBoost model by using grid search to obtain a carbon emission prediction amount in a subway station construction stage.

The application provides a kind of foodborne microorganism identification method based on metal omics coupling XGBoost algorithm, belongs to microorganism identification technical field, the foodborne microorganism identification method includes the following steps: 1) with foodborne microorganism strain as research object, ICP-MS is used to analyze each standard strain metal group characteristics, combined with XGBoost algorithm to construct foodborne microorganism classification model;2) the ICP-MS full quantitative analysis is used to detect the bacterial species, and the detection data of the metal elements of the bacterial species to be detected are obtained;3) the obtained detection data is substituted into the obtained foodborne microorganism classification model for analysis, and the bacterial species to be detected is identified.The foodborne microorganism classification model constructed by the application can quickly and accurately identify 18 kinds of foodborne microorganisms, and lays a good foundation for the broad-spectrum and efficient classification and identification of more kinds of foodborne microorganisms in the future.

The present application relates to an image processing method, device, computer equipment and storage medium. The method comprises: obtaining an image to be classified; performing statistical processing on the image features of the image to be classified to obtain at least two image statistical features for the image to be classified; inputting the image statistical features into a pre-trained image classification neural network respectively; and determining the classification result for the image to be classified according to the output result of the pre-trained image classification neural network. The use of this method can improve the accuracy of image classification.

The application provides an RGB-D image feature collaborative fusion method based on transfer learning and width learning, and comprises the following steps: obtaining an RGB-D data set, performing preliminary training through a neural network, and performing retraining in the data set after modifying the structure; after feature extraction, performing correlation analysis and fusion on RGB image features and depth image features; and using width learning to classify and identify the fused features. The application can reasonably fuse the features of RGB images and depth images, ensure that the feature information of color images and depth images can complement each other, improve the running speed of the system by using width learning, and finally make the classification result have higher accuracy and reliability.

The present invention discloses a feature selection method, device, computer equipment and storage medium for image samples. The method comprises: obtaining a feature set including image sample features; performing redundant feature screening on the image sample features in the feature set; performing Schmidt orthogonalization processing on each redundant feature subset to obtain N orthogonalized feature subsets, and using a preset Wrapper method to perform feature screening on the N orthogonalized feature subsets, and forming the screened features into a first feature subset; calculating the correlation between each image sample feature in the feature set and a preset target category feature, and screening the image sample features related to the target category feature according to the correlation to form a second feature subset; performing a union operation on the non-redundant feature subset, the first feature subset and the second feature subset to obtain a new feature set. The technical solution of the present invention can improve the training precision and recognition accuracy of the image recognition model.

The invention discloses a software evaluation method and system with high credibility characteristics, and relates to the technical field of computer security, and the method comprises the following steps: obtaining code data; preprocessing the code data to obtain a code text library; performing feature extraction on the code text library, and identifying and extracting high-credibility feature information; constructing a DBN network evaluation model based on the code text library and the high-credibility feature information; and processing and analyzing the code original data according to the DBN network evaluation model, extracting high-credibility characteristics in the code original data, and generating a software evaluation report. According to the method, feature dimensions are greatly reduced through feature selection of code data, a large number of irrelevant and redundant features in the code data are removed through an online logistic regression model, high-credibility feature information is obtained, the high-credibility feature information is used for testing, the testing accuracy is fundamentally improved, and the time consumed by an algorithm is shortened.

The invention discloses a supervised learning-based drug and pathway association prediction method and system, and a medium, and belongs to the technical field of bioinformatics, and the supervised learning-based drug and pathway association prediction method comprises the following steps: obtaining a training sample set associated with a drug pathway; constructing a plurality of drug pathway sample feature representation vectors; constructing a drug pathway association prediction model based on a supervised learning training algorithm at least according to a training sample set associated with the drug pathway and the plurality of drug pathway sample feature representation vectors; and acquiring an actual drug pathway sample feature representation vector, inputting the actual drug pathway sample feature representation vector into the drug pathway association prediction model, and predicting and outputting a drug and pathway association result by the drug pathway association prediction model. According to the method, a potential drug and pathway association result is identified, and valuable information is provided for drug research and development and biological research.

The present invention relates to a method for identifying bird nests in substations based on deep learning, comprising: building and training a recognition model: acquiring a sample image, processing the sample image by using a first feature extraction algorithm, and obtaining a sample feature map; inputting the sample feature map into a recognition model, wherein the recognition model performs several convolution operations on the sample feature map, and obtains several feature maps of different scales, and generates several anchor frames in the several feature maps; using a quantum particle swarm algorithm, determining the ratio value and confidence threshold of positive samples to negative samples; dividing the several anchor frames into positive samples and negative samples according to the confidence threshold; updating the recognition model according to the several positive samples and negative samples; acquiring an image to be inspected; processing the image to be inspected by using a first feature extraction algorithm, and obtaining a first feature map; inputting the first feature map into the recognition model, and obtaining a first recognition result and the confidence of the first recognition result.

The present invention discloses an EEG signal classification method that fuses wavelet scattering transform and differential entropy features, belongs to the technical field of EEG signal classification, and is used for EEG signal classification, including importing collected EEG epilepsy signals, inputting samples into a wavelet scattering transform network, performing scattering transform on channel signals, extracting second-order decomposition scattering coefficients, and obtaining time-frequency domain features of channel signals; performing differential entropy calculation on channel signals, obtaining nonlinear dynamic features of channel signals, performing discriminant correlation analysis on time-frequency domain features and nonlinear dynamic features, and constructing multimodal fusion features; inputting fusion features into a long short-term memory neural network for training and learning, and evaluating the results using average classification accuracy. The present invention reduces feature dimension through feature fusion methods by analyzing the time-frequency domain features and nonlinear dynamic features of signals, thereby improving classification accuracy, better distinguishing EEG signals of epileptic patients from those of normal people, and providing effective assistance for diagnosis and treatment.

The present application discloses a fault diagnosis method based on random walk and machine learning. First, the vibration signal data of the moving parts are collected and preprocessed. For the preprocessed vibration signal, the fault feature extraction algorithm is used to extract the feature parameters, and the obtained feature parameters are subjected to principal component analysis PCA. Then, a random walk optimization algorithm is constructed, and the random walk optimization algorithm is used to optimize the hyperparameters of the machine learning model. Then, the sample data after PCA dimension reduction is divided into a training set and a test set, and the training set is put into the optimized machine learning model for training. The test set is used for fault prediction to obtain the prediction accuracy under different features. Finally, a comparative analysis is performed to select the feature with the highest accuracy as the best feature. This method solves the problem that the traditional algorithm takes too long to find the optimal solution and cannot find the global optimal solution. While ensuring the prediction performance of the model, the prediction accuracy of the model is significantly improved, thereby improving the efficiency of fault diagnosis.

The invention provides an intelligent algorithm for battlefield situation real-time analysis and pilot fire control sensor operation recommendation based on time sequence classification, fire control and sensor operation recommendation are carried out on a pilot in real time in a battlefield, and help is provided for battlefield situation awareness and auxiliary decision making. According to the method, a real-time fire control sensor operation recommendation algorithm is established based on time sequence classification, the algorithm shows high accuracy in fire control sensor key behavior point judgment and has certain interpretability, and the method is called as STMLight GBM in the invention. According to the method, the situation sensing capability of the fire control sensor is remarkably improved, and a method with practical application value is provided for real-time situation analysis.

The present invention relates to the field of data analysis technology, and invents a sales big data analysis method based on cross-border e-commerce ERP, including: extracting enterprise resource data from an enterprise management platform, and extracting an inventory resource feature set from the enterprise resource data; performing clustering dimensionality reduction and correlation dimensionality reduction on the inventory resource feature set to obtain a product resource feature set; performing autocorrelation analysis and time series feature extraction on the product resource features to obtain product time series features; forward propagating the product time series features to obtain analysis product data, and extracting unsalable product inventory from the analysis product data; extracting product sales features corresponding to the unsalable product inventory from the enterprise resource data, and performing sales strategy analysis on the unsalable product inventory according to the product sales features to obtain product sales strategies. The present invention also proposes a sales big data analysis system based on cross-border e-commerce ERP. The present invention can improve the accuracy of sales analysis.

The present invention relates to the field of geographic information data processing technology, and discloses a method for predicting railway disaster trends based on machine learning, comprising the following steps: S1, data collection and data annotation; S2, data expansion, sample generation based on a deep belief generative adversarial network with robust quantum state information to achieve GIS remote sensing data expansion; S3, feature extraction model training; S4, feature dimension reduction model training; S5, classifier model training; S6, railway disaster trend prediction, using the trained model to process new GIS remote sensing samples to predict railway disaster trends. The present invention has the beneficial effect that the use of quantum state information can greatly improve the quality of generated data on the basis of ensuring data authenticity, so that the expanded data is closer to the real scene, thereby improving the effectiveness and accuracy of model training, and further improving the accuracy of railway disaster trend prediction.

The invention relates to a steel rail corrugation degree grading method, device, equipment, medium and program, and the method comprises the steps: collecting the vertical vibration information of a train axle box, and constructing a vertical vibration data set according to the vertical vibration information; performing low-pass filtering on the vertical vibration data set to obtain a filtered data set, and calculating a track impact index corresponding to the filtered data set; judging whether a rail corrugation section exists or not according to the rail impact index and a preset over-limit rail impact index threshold value; if the steel rail corrugation section exists, corrugation information corresponding to the steel rail corrugation section is used for generating a corrugation data set; and extracting signal time domain features corresponding to the corrugation data set, and performing full-connection mapping on the signal time domain features to obtain a disease degree grading result.