39results about How to "Improve discrimination" patented technology

The present application relates to the technical field of wireless communication security, in particular to a radio frequency fingerprint identification method for wireless node identity authentication. The method solves the problems of weak radio frequency fingerprint characteristics in short frame wireless signals, insufficient discrimination ability of lightweight models, and difficulty in rigid alignment and distillation of heterogeneous teacher-student models. The method obtains training wireless signal samples with identity labels and converts them into time-frequency spectrum samples; inputs the time-frequency spectrum samples into a teacher recognition model and a student recognition model to obtain classification results and global features; projects the teacher global features and the student global features, generates a cross-dimensional correlation matrix according to the projection feature component correlation, and normalizes to obtain alignment-free attention weights; constructs an alignment-free feature distillation loss based on the weights, and jointly trains to obtain a lightweight radio frequency fingerprint identification model; the model is used to output the identity category of the wireless node to be verified during inference, which is used for wireless node access authentication and physical layer identity authentication.

The application discloses a kind of education resource sequence recommendation method, device and equipment based on three-view structure distillation and storage medium, the method includes: based on student-course interaction log, the learning sequence of time sequence course index is constructed, three types of view hypergraph are constructed according to semantic, path, concept structure multidimensional feature, three-view course representation matrix is generated by structure coding fusion, and the recommended list is output by inputting education resource recommendation model;Education resource recommendation model generates student state vector by the coding of Transformer, and the total course score is obtained by fusing three-view branch score and predicted;The present application predicts the education resource recommendation by three-view collaborative scoring from multiple perspectives, accurately captures course representation, effectively depicts learning path high-order law, improves the accuracy, explainability and generalization ability of education resource recommendation in sparse interaction and cold start scene.

This invention discloses a supervised multimodal hash retrieval method and system based on label enhancement, belonging to the field of artificial intelligence and multimedia retrieval technology. The technical problem this invention aims to solve is how to better capture the similarity information between multimodal data points and achieve better performance and accuracy in multimodal retrieval tasks. The technical solution includes: data preprocessing: acquiring and organizing public datasets of image and text modalities, and dividing each public dataset into training, testing, and retrieval datasets; extracting deep features: using a pre-trained network model to extract features from the raw data of the public datasets of image and text modalities respectively, obtaining deep features of the image modality and the text modality; offline training; variable update and optimization; and online query. The system includes a data preprocessing unit, a feature extraction unit, an offline training unit, a variable update and optimization unit, and an online query unit.

This invention discloses a method and system for rock mass integrity discrimination based on core image and parameter fusion, comprising the following steps: Step 1: Acquire core images and divide them into multiple image blocks; Step 2: Generate image block structure state vectors; Step 3: Acquire structural parameters and map them into the latent space, perform structural similarity matching discrimination, and generate structural parameter semantic vectors; Step 4: Construct an improved CoFormer model, inputting the image block structure state vectors into the structure state projection branch and the structural parameter semantic vectors into the parameter semantic constraint branch, and outputting a local rock mass integrity score; Step 5: Construct an asymmetric cross-image block inference structure between image blocks; Step 6: Obtain the evolution result of the overall rock mass structure; Step 7: Output the overall integrity level discrimination result of the corresponding rock mass. This invention combines the improved CoFormer model and the asymmetric cross-image block inference structure to achieve intelligent rock mass integrity discrimination.

This invention relates to the field of functional engineered wood products, specifically to an engineered wood product with ultra-long room-temperature phosphorescence characteristics. The engineered wood product includes bonded units and an adhesive layer located between adjacent bonded units. The adhesive layer is formed by an adhesive that, upon curing, can generate room-temperature phosphorescence. Under external light excitation, the adhesive layer can generate ultra-long room-temperature phosphorescence emission, and the emission signal includes at least one of the following: emission color, emission intensity, emission spectrum, delayed emission image, and / or phosphorescence lifetime. The bonded units are selected from at least one of the following: decorative paper, thin wood veneer, engineered wood veneer, wood veneer, wood / bamboo strips, wood / bamboo shavings, wood / bamboo fiber, straw, and biomass fragments. By adjusting the adhesive system, interface structure, and hot-pressing process parameters, the resulting engineered wood product can exhibit different room-temperature phosphorescence characteristics. This invention endows the board with stable room-temperature phosphorescence function without changing the basic manufacturing process of existing engineered wood products, possessing good process compatibility and application prospects. The room-temperature phosphorescence signal can construct material-level optical coding information, realizing the identification and anti-counterfeiting traceability of the engineered wood product.

This invention discloses a fault diagnosis method for wind turbine turntable bearings based on WDCNN-Transformer, belonging to the field of wind power equipment condition monitoring and intelligent fault diagnosis technology. This invention proposes a novel fault diagnosis method by combining dual-branch time-frequency domain parallel feature extraction with the serial structure of WDCNN-Transformer and time-frequency domain feature fusion. This method effectively improves the accuracy and robustness of wind turbine turntable bearing fault diagnosis. It utilizes both time and frequency domain branches simultaneously, automatically extracting features using deep networks to ensure comprehensive mining of signal information from multiple perspectives. The concatenation of WDCNN and Transformer improves the utilization efficiency of temporal and spatial features. Feature fusion fully leverages the complementary advantages of time-frequency information, enhancing the discriminative power of fault features.

The application discloses a kind of academic question and answer-oriented multi-model paper retrieval method, it is related to natural language processing and information retrieval technical field, including: first, construct unified corpus and training dataset, utilize the model in first model set and second target model respectively encode generation document vector set;Then, based on the initial retrieval result of second model, difficult negative sample is filtered, and the contrast learning sample pair is constructed to fine-tune and re-encode corpus;With the model group of the second target model after fine-tuning and the model in first model set, each model in model group is executed similarity retrieval in parallel respectively, and the corresponding original similarity matrix is obtained, based on the original similarity matrix, the document is filtered, and the first target document list of target query is generated.The application can effectively improve the accuracy and robustness of academic literature retrieval.

This invention belongs to the field of radar signal processing technology and discloses a method for detecting small sea targets based on optimized feature mode decomposition, including: S1: acquiring the signal data to be detected; S2: decomposing the original signal into several modal components using FMD, and selecting envelope spectral entropy as the fitness function; S3: using the SOS algorithm to globally optimize the fitness function in FMD; S4: introducing the PSO algorithm to locally optimize the key parameters of FMD; S5: retaining components with low envelope spectral entropy values ​​and correlation coefficients greater than a threshold; S6: extracting envelope spectral entropy and frequency band energy proportion features from the selected modal components, introducing the Gini coefficient as a weighting factor, and constructing GSEBE joint features; S7: inputting the envelope spectral entropy value into a DELM classifier with controllable false alarm rate, and achieving target detection based on the comparison between the predicted value and the decision threshold. This invention enhances the ability to distinguish between sea clutter and target echoes, achieving more accurate classification and detection.

This invention provides a non-contact, highly anti-interference, and highly accurate wind turbine blade monitoring system and method based on lidar and multi-dimensional data fusion. The method includes the following steps: S1, data acquisition; S2, data preprocessing; S3, feature extraction; S4, data fusion; S5, equilibrium state diagnosis; and S6, dual verification. The system includes a lidar acquisition module (1), a data synchronization module (2), a signal processing module (3), a data fusion module (4), an intelligent diagnosis module (5), and a dual verification module (6). This invention is applied in the field of wind power equipment condition monitoring technology.

The application discloses a gas classification method and equipment based on pooling aggregation and joint attention enhanced LSTM, wherein the gas classification method first performs low-parameter dimension reduction on original data of a multi-sensor array through a pooling aggregation module; secondly, a joint attention module composed of a channel attention submodule and a time attention submodule is introduced to respectively adaptively weight different sensor channels and time sequence positions, so that the effective gas response features are strengthened and the environmental noise is suppressed, and the signal and noise can be distinguished without relying on baseline calibration; finally, the screened features are input into a single-layer lightweight long short-term memory network module for time sequence modeling, so that an efficient recognition architecture adapting to short sequence data is constructed, the local and global features in a short time sequence are deeply mined, the effective signal and noise are accurately distinguished under the condition of no baseline, the model calculation complexity is greatly reduced, and the rapid reasoning and lightweight deployment requirements of a portable device are met.

This invention discloses a method for evaluating the comprehensive performance of phase change asphalt pavement based on combined weights. The method includes: acquiring multiple evaluation indicators for assessing the comprehensive performance of phase change asphalt pavement; determining the relative importance weights of each evaluation indicator based on the priority graph method; acquiring experimental or measured data corresponding to each evaluation indicator and determining the information entropy weights of each evaluation indicator based on the entropy method; constructing a subjective-objective weight combination optimization model under the principle of minimum deviation to obtain the combined weights of each evaluation indicator; calculating the comprehensive performance evaluation value of the phase change asphalt pavement based on the combined weights, and ranking and evaluating different schemes or samples. This invention overcomes the bias caused by a single weighting method by integrating subjective perception and objective data information, improving the scientific rigor, stability, and discriminative power of the comprehensive performance evaluation results of phase change asphalt pavement, and providing a reliable basis for the design optimization and engineering application of phase change asphalt materials.

The application relates to the fields of molecular biological technology and livestock breeding technology, in particular to a SNP molecular marker related to a total number of piglets character, a detection primer pair, a kit and application of the SNP molecular marker in a method for breeding large white pigs with high number of piglets, the SNP molecular marker is located on a pig 9th chromosome, a physical position is located at chr9:65633096 of a genome version Ensembl Sscrofa11.1, a polymorphism site is C or A, and the C allele is positively correlated with the high number of piglets character; through genotype discrimination, selection breeding can be carried out: an individual with a genotype of C / C is preferentially selected or reserved as a breeding pig, because the total number of piglets has the highest potential, so that the genetic improvement speed of a population breeding performance is accelerated.

This invention belongs to the field of wireless communication and relates to a machine learning-based method for wireless communication channel estimation. The method includes: acquiring pilot signals, antenna array geometric parameters, and multipath propagation parameters from the transceiver end of a millimeter-wave massive MIMO system to construct a three-dimensional propagation structure model; determining candidate regions for the channel sparse support set and generating a prior constraint matrix for the channel sparse support; inputting the prior constraint matrix and pilot observation data into a sparse reconstruction algorithm for channel sparse feature extraction and dimensionality reduction; performing super-oscillatory feature enhancement on the dimensionality-reduced channel sparse features to form an enhanced channel feature vector; inputting the enhanced channel feature vector and the prior support vector matrix into a complex domain deep expansion network to output the channel estimation result; and outputting the final beamforming weights. Its beneficial effects are improved sparse support set matching accuracy and channel estimation precision with low pilot overhead, and enhanced system throughput and interference suppression capabilities.

This invention relates to the field of machine vision, and in particular to a method and system for detecting defects on building roofs based on unmanned aerial vehicles (UAVs). The method involves acquiring grayscale images of building roofs captured by the UAV; calculating morphological gradient maps in multiple directions of the grayscale image; calculating the variance of each pixel across all gradient values ​​to generate a gradient direction consistency map; and weighted fusion of all morphological gradient maps based on the gradient direction consistency map to generate an edge saliency map. Within the neighborhood of each pixel in the grayscale image, the frequency of grayscale pairs is attenuated and weighted according to the Euclidean distance between neighboring pixels and the center pixel, and spatial location-sensitive entropy is calculated based on the weighted co-occurrence probability to generate a texture complexity map. Further, a defect response map is obtained; a local discrimination threshold corresponding to each pixel is calculated; and when the value of a pixel in the defect response map is greater than the corresponding local discrimination threshold, the pixel is determined to be a defect point.

The application discloses a kind of stone surface image defect intelligent detection and real-time grading method, by the RGB image of the stone surface to be detected, thermal radiation image and depth image are synchronously collected, three modal images are respectively input corresponding feature extraction network and extract multi-scale hierarchical features, with cross-modal gate fusion module Channel inter-attention weight and spatial attention weight of each modal feature map are calculated respectively for each feature level and dynamically weighted fusion, generate unified cross-modal defect representation, then through grading decision network based on four semantic attributes mapping to continuous quality score space, configurable grading threshold output discrete quality level.The application utilizes the complementary characteristics of multi-modal information, solves the problem that single visible light image is difficult to accurately distinguish natural texture from real defect under complex texture background, while completely decouples defect objective attribute description and grading subjective standard application, significantly reduces deployment and maintenance cost.

The application discloses an image semantic segmentation method, an electronic device and a computer readable storage medium, comprising: obtaining a target image and an image gradient map thereof; inputting the target image into a semantic segmentation network to obtain shallow feature maps and deep feature maps through an encoder; the semantic segmentation network comprises a cascaded encoder, a semantic-boundary double-branch decoder and an output layer; the feature fusion of multiple feature maps is performed through the semantic fusion branch of the decoder to obtain a semantic segmentation prediction result; the boundary information is obtained based on the image gradient map and the multiple feature maps through the boundary refinement branch of the decoder, and the feature fusion of the multiple feature maps is performed based on the boundary information to obtain a boundary prediction result; and the semantic segmentation prediction result and the boundary prediction result are fused through the output layer to obtain a semantic segmentation image of the target image. The application can further depict the object boundary in the semantic segmentation prediction result, thereby improving the accuracy and segmentation effect of semantic segmentation.

This invention discloses a visual inspection system and method for transformer tank panels in new energy applications, belonging to the field of transformer tank manufacturing and inspection technology. The system includes a flexible steady-state clamping and conveying mechanism, a transient pulse excitation mechanism, a high-frequency multimodal visual acquisition mechanism, and a data processing and spatiotemporal response judgment module. By applying a controlled transient thermal pulse to the area to be inspected and simultaneously acquiring static three-dimensional reference surfaces and dynamic three-dimensional response surface sequences, spatial registration and differential processing are performed to obtain a transient out-of-plane displacement field. Welding defects are then identified based on preset spatiotemporal continuity anomaly judgment conditions, and the system combines two-dimensional surface texture images to classify and identify internal latent defects and surface penetration defects. This invention is suitable for online inspection of transformer tank panels.

The application provides a method for detecting defects in a steel pipe welding digital radiograph image, comprising the following steps: S1, collecting a plurality of DR images, expanding a sample data set, preprocessing the plurality of DR images, and constructing a training data set; S2, constructing a deep convolution network model based on image reconstruction, wherein the network model comprises at least one convolution network-based encoder and a corresponding decoder; S3, performing model parameter optimization training, using the training data set to optimize network parameters, and obtaining an optimized network model; S4, inputting the collected DR image into the optimized network model for inference to obtain a reconstructed image; performing difference operation on the reconstructed image and the input image, and binarizing the difference result to obtain a final defect position; and through the above scheme, the final defect position is obtained.

The application belongs to the technical field of wireless communication security and signal processing, and discloses a high-reliability device authentication method based on antenna array error characteristics and double-beam transmission, which comprises the following steps: 1, constructing a double-beam, wherein signals received by a user equipment are transmitted through the double-beam; 2, actively tracking the double-beam and adjusting the direction of the double-beam in real time; 3, modeling a statistical analysis model of a radiation mode; 4, defining a radiation mode characteristic extraction target, completing characteristic extraction, and calculating gain error values, phase error values and position error values; 5, calculating signal energy, comparing the signal energy with a preset threshold as an energy detection statistical quantity, judging the legitimacy of a signal source, and completing device authentication. The authentication scheme provided by the application can effectively cope with the influence of array errors, thereby providing a reliable and efficient authentication solution for a millimeter wave communication system and helping to enhance the security of a communication link.

This invention provides a method and system for predicting the risk of aortic remodeling after aortic dissection, comprising the following steps: receiving CTA images of the patient's chest and abdomen at multiple time points, such as preoperative and short or mid-operative postoperatively, and obtaining aortic segmentation results based on the CTA images; obtaining the displacement field of each voxel point between the two time points based on the aortic segmentation results, and obtaining vascular deformation mapping results based on the displacement field; extracting multi-dimensional features from the three-dimensional aortic segmentation model and the vascular deformation mapping results respectively; and predicting the risk of adverse aortic remodeling after surgery based on the multi-dimensional features. The beneficial effects of this invention are: by comprehensively utilizing multi-dimensional, dynamic, and static features, the prediction model constructed by this invention theoretically has higher discrimination and calibration than existing single-index models. Therefore, this invention can detect early, local abnormal deformations that cannot be detected by traditional diameter measurement, significantly advancing the risk identification time point.

The application discloses a big data-based equipment operation anomaly detection method and system, relates to the technical field of equipment detection, and comprises the following steps: obtaining historical operation data of a target equipment in a healthy state, and constructing a high-dimensional equipment operation big data pool; constructing and training a deep autoencoder, and establishing an equipment health baseline set for the target equipment; obtaining real-time operation data of the target equipment, and calculating an encoding residual error vector of the real-time operation data relative to the equipment health baseline set; taking the encoding residual error vector as an analysis target, inputting the encoding residual error vector into a pre-trained lightweight classifier for anomaly classification detection, and outputting operation anomaly information according to the anomaly classification detection result. The technical problems of low equipment anomaly detection precision, high false alarm rate and difficulty in adapting to complex working condition changes in the prior art are solved.

An automated scoring system for medial temporal lobe atrophy (MTA) based on YOLO deep learning includes: a coronal slice selection module, an improved YOLOv8 model construction module, an optimal coronal slice automatic selection module, and a medial temporal lobe atrophy detection and automatic scoring module. This invention provides an automated MTA scoring technique that balances accuracy, versatility, and ease of use. By using a lightweight deep learning YOLO object detection framework and combining it with an appropriate loss function, computational overhead is reduced while maintaining algorithm performance. Furthermore, a user-friendly front-end interface improves the efficiency and accuracy of clinical MTA scoring. This invention provides an efficient, accurate, and consistent automated MTA scoring system with significant clinical application value and promising prospects, and is expected to play an important role in the early diagnosis and monitoring of neurodegenerative diseases such as Alzheimer's disease.

This invention discloses a method, apparatus, device, and storage medium for credit assessment of campus card deduction transactions, relating to the technical field of campus card systems. The method includes: acquiring deduction transaction information data of the user to be assessed; constructing a feature matrix of independent variables with multiple dimensions, whereby the deduction transaction information data includes transaction behavior data and user information data; mapping the original feature values ​​in the feature matrix of independent variables to corresponding WOE values ​​according to a pre-constructed feature mapping rule, wherein the pre-constructed feature mapping rule is obtained after optimal binning of historical sample data based on the DFS binning algorithm; inputting the mapped WOE values ​​into a pre-trained logistic regression model to calculate the user's risk quantification score; and generating risk control instructions based on the comparison result between the risk quantification score and a preset threshold. This application can solve the risk of overdue payments and bad debts under the campus card deduction model, realizing accurate assessment and automated hierarchical management of user credit risk.

The present application relates to a kind of based on improved CPD nonrigid point cloud registration mining area surface three-dimensional movement extraction method and system, belong to surface detection technical field, solve the problem of poor adaptability of nonrigid registration in complex sparse area, low computing efficiency in prior art.The specific steps include: obtaining the nonrigid point cloud in the two-period unmanned aerial vehicle laser point cloud data of the mining area to be measured, respectively on the nonrigid point cloud of two periods multi-layer feature point extraction, obtain the first candidate point cloud set and the second candidate point cloud set;According to the set registration window and the moving step on the first candidate point cloud set and the second candidate point cloud set, obtain multiple local unit point cloud pairs;Using direction constrained CPD algorithm, sequentially nonrigid registration is carried out to each local unit point cloud pair, obtain each local unit deformation field;Superimpose each local unit deformation field, obtain global deformation field, significantly improve the efficiency and precision of mining area surface three-dimensional movement extraction.

The present application belongs to the technical field of information recognition, and particularly relates to a media information recognition feedback method and system based on big data processing. The method analyzes and processes the to-be-recognized media information, and judges whether it is abnormal media information according to a preset abnormality judgment rule. When it is abnormal media information, the abnormal media information is directly sent to a processing end, and only normal media information is subjected to a subsequent step of constructing comparison data, so that the abnormal media information is removed in advance, and is prevented from entering a subsequent complex comparison data construction link, thereby reducing the computing load of the system to improve the overall processing efficiency, and ensuring the purity and reliability of the benchmark data used for constructing the comparison benchmark from the source.

The present application relates to the technical field of electromagnetic compatibility monitoring and transient electromagnetic interference detection, in particular to a static discharge transient signal detection method and device based on software radio, comprising: collecting and digitizing and buffering static discharge transient signals, pre-processing the collected continuous signals, waveform window intercepting and standardizing the burst signals meeting the conditions, sending the standardized data into a double-branch recognition model for recognition processing, splicing the feature vectors of the two branches, and completing signal recognition after processing by a fusion discrimination layer, compared with the prior art, the method can effectively improve the distinguishing ability of ESD signals and interference signals, has high recognition accuracy and good engineering application value.

This invention relates to the field of online detection and condition monitoring technology for power system switchgear, and discloses a method for accurately measuring the opening and closing time of disconnecting switches. By synchronously collecting voltage data on both sides of the disconnecting switch to construct a voltage difference sequence, the action interval is extracted through differential and sliding window energy analysis. Within this interval, differential features are used to determine the action index and convert it into the action time. The average voltage difference before and after the action time is calculated to determine the action type. The stability of the action time is evaluated by combining a reference action time and statistical analysis of multiple measurement deviations. Simultaneously, key data from the entire process are compiled into an identifiable dataset. Through these steps, the measurement of the opening and closing behavior and action time of disconnecting switches is achieved, overcoming the problems of asynchronous single-sided sampling or mechanical triggering, poor reliability of threshold and zero-crossing detection, and difficulty in quantifying time stability, thus providing an improved means for disconnecting switch condition assessment without adding complex hardware.

The application provides a cost entropy information granulation semi-supervised feature selection method for diabetes detection, and belongs to the technical field of intelligent medical treatment, and the technical scheme is as follows: S1, a weighted granular cell is constructed; S2, a hemispherical granulation is performed on each decision class based on covariance matrix principal direction analysis, and a pseudo label is assigned to an unmarked sample; S3, a cost entropy is introduced for feature evaluation according to feature difference, and feature importance is obtained; S4, the feature importance is sorted, and a feature subset is selected; and S5, the optimal feature subset is obtained by aggregating the feature selection results of each subnode. The application improves the classification accuracy of a multi-dimensional feature diabetes data set, reduces the calculation complexity of a classification method, improves the accuracy and efficiency of feature selection, helps doctors to judge whether a patient is suffering from diabetes, and has strong application value.

This invention provides a YOLO-based method for identifying fault types in 10kV distribution network lines, comprising: constructing a fault image dataset and data augmentation; constructing an improved YOLOv8 fault identification model architecture; constructing a multi-task loss function for fault identification; training the line fault identification model; inference detection based on line inspection images; post-processing optimization of fault detection results; and outputting identification results. This invention achieves high-precision, robust, and real-time intelligent identification and classification of various types of line faults in 10kV distribution networks, effectively improving the efficiency of intelligent inspections and the timeliness of fault early warnings, and ensuring the safe and stable operation of the distribution network.