284results about How to "Improve classification accuracy" patented technology

The invention discloses a microblog emotion analysis method based on standard dictionaries and semantic rules. The microblog emotion analysis method comprises the following steps: collecting microblog data and manually labeling and marking the emotion value of each microblog; proposing corresponding standard micrblog emotion dictionaries, and establishing an emotion dictionary database; based on the standard emotion dictionaries, adding the semantic rules for assistance, and performing parameter adjustment and optimization on parameters of the semantic rules; based on a real dataset experiment, acquiring the final classification accuracy and precision. The technical scheme provided by the invention is adopted to well analyze the emotion tendency of each microblog user by introducing the standard emotion dictionaries, microblog expression dictionaries and the semantic rules, therefore, higher classification accuracy and precision are achieved.

The invention discloses a multi-mode defect automatic classification method, device and equipment and a storage medium. The method comprises the following steps: acquiring a microscope image, an X-ray image and defect feature information data of a to-be-detected product; first classification processing is preferentially carried out based on the microscope image, when the first classification processing result meets a first preset reliability condition, the first classification processing result is taken as a final classification result, and when the first classification processing result does not meet the first preset reliability condition, the final classification result is taken as a final classification result. Performing feature fusion based on the X-ray image and the defect feature information data, and executing second classification processing; when the second classification processing result meets a second preset reliability condition, the second classification processing result serves as a final classification result, and when the second classification processing result does not meet the second preset reliability condition, defect type judgment is conducted based on key parameters in the defect feature information data, and the final classification result is output; the classification accuracy and efficiency can be improved, and the error recognition rate is reduced.

The invention discloses a wide-spectrum rapid scanning and intelligent identification method, system and device, and the method comprises the steps: firstly, carrying out the rapid frequency sweeping through employing a low-sampling-rate and low-quantization-precision receiver, generating a low-resolution time-frequency graph, and recovering the super-resolution of the low-resolution time-frequency graph into a high-resolution spectrum through a pre-trained deep learning model; then, the enhanced time-frequency image is segmented into time-frequency blocks, global features are extracted through a Transform encoder, and detection and screening of multiple candidate signal areas are achieved; and finally, carrying out directional sampling on the candidate region, respectively extracting time domain and frequency domain features, mapping the time domain and frequency domain features to a unified space for fusion, and completing signal category judgment based on the combined features and a judgment network. According to the wide-frequency-spectrum rapid scanning and intelligent identification method, system and device, through a layered architecture of broadband rapid scanning-frequency spectrum quality recovery-multi-region detection-directional sampling and time-frequency fusion identification, the reliability of unmanned aerial vehicle signal detection and identification in a complex electromagnetic environment is improved while the hardware cost is reduced.

The application discloses a kind of unmanned vehicle multispectral remote sensing water fine classification extraction method, it is related to remote sensing image processing technical field, the joint feature matrix including spectral feature, gray texture feature and elevation difference feature is creatively constructed in the present application, effectively eliminates redundant interference information, provides high-quality input with very distinguishing degree for multilayer perception machine model.Simultaneously, illumination geometry and digital elevation model are deeply coupled in the feature construction process, not only can accurately identify and reverse inhibit the shadow pseudo water body feature projected by complex terrain or building, break through the failure limitation of traditional single elevation filtering in flat shadow area, but also cooperate with the standardization closed operation process based on morphological dilation and corrosion filtering, eliminate the small holes and jagged artifacts in prediction result, realize the high-fidelity restoration of water body boundary, so as to improve the classification accuracy of complex water body such as narrow river, fragmented pit pond and urban waterlogging.

The present application provides a kind of forest tree species classification method, device, electronic equipment and storage medium, belong to artificial intelligence technical field, method includes: forest remote sensing image is input to forest tree species classification model, obtains the output tree species classification result;Forest tree species classification model includes preliminary feature processing module, high-order feature extraction module and tree species classification result output module, high-order feature extraction module is sequentially connected first residual block stack layer, first down-sampling layer, second residual block stack layer, second down-sampling layer, third residual block stack layer, third down-sampling layer and fourth residual block stack layer, stacked residual block embedding dimension rearrangement layer, dimension recovery layer and convolution block attention module.The present application improves the dimension compatibility of CBAM and convolution architecture by embedding explicit dimension rearrangement layer and dimension recovery layer in the residual block embedded with CBAM, effectively improves the classification accuracy of forest remote sensing image for forest tree species classification task.

This invention relates to a graph node classification method based on a graph feature self-attention mechanism using ensemble learning. First, the original graph network data is input, including the node feature matrix H and the graph adjacency matrix A. The LightGBM method is used to preprocess the dataset to obtain model parameters. Finally, the expanded node feature matrix H is obtained by summarizing the tree model parameters. new ; Combine the graph adjacency matrix A and the expanded node feature matrix H new The input graph features are trained on an attention network, and the network's preference information for nodes and features is obtained after training. Finally, the trained model is used to predict the classification of the graph node dataset on the validation and test sets. This invention utilizes an ensemble learning method and incorporates node attention preferences for features, which not only efficiently leverages the high interpretability of tree models but also enriches the model's expression, allowing node features to contain more information, thus contributing to higher performance on node classification tasks.

The application discloses a foreground target migration method for unsupervised domain adaptation, and the method comprises the following steps: obtaining labeled source domain samples and unlabeled target domain samples as training samples, inputting the source domain samples and the target domain samples into a deep neural network for training to obtain a classification model, inputting data to be classified in the target domain into the classification model, and obtaining a classification result. The application further provides a foreground target migration device for unsupervised domain adaptation. The foreground target migration method and device for unsupervised domain adaptation provided by the application can improve classification precision and classification efficiency.

The application relates to a memristor-based electroencephalogram sleep staging processing system and method, which comprises a preprocessing module, a control module and an inference module, the preprocessing module is used for feature extraction of input electroencephalogram signals, analog domain operation is realized through a memristor array, the control module is used for data scheduling and overall control of the system, controls electroencephalogram signal input and data flow direction, coordinates read and write operations of the RRAM array, and realizes neuron membrane potential updating; the inference module is used for executing a sleep staging classification task, event-driven pulse coding is used for Level-Crossing coding of envelope signals, a pulse is generated when the signals cross a threshold, a positive and negative pulse sequence is generated, data redundancy is effectively reduced, and event-driven computing is realized. Through the combination of a memory-computing integrated architecture, an SKVM precision maintaining mapping strategy, event-driven pulse neural network inference and other technologies, the target of high precision, low power consumption and end-side on-chip processing is realized.

The application discloses a movie classification system based on multi-modal deep representation collaborative federated learning, and the method comprises the following steps: firstly, initializing local model parameters of each client with public model parameters; then, the client updates the local model parameters according to the total loss on the local movie multi-modal data, obtains the local multi-modal deep representation, and uploads the local multi-modal deep representation and the local model parameters to the server; the server calculates the global multi-modal deep representation, obtains the initialization local model parameters of each client in the next global round through personalized parameter aggregation, and distributes the local model parameters to each client; finally, each client replaces the local model parameters. Except for the initialization, the above training process is repeatedly executed until the local model parameters of each client converge. For the to-be-recognized movie data, only the category thereof is recognized in the local client. While protecting the privacy, the application effectively improves the classification accuracy of each client on the movie multi-modal data.

This invention discloses an industrial material inspection method and system based on feature extraction and contrast enhancement, belonging to the field of image inspection technology. It includes: S1, acquiring the transmitted signal using a digital flat panel detector and generating an original digital image based on the differences in X-ray absorption by different materials or defects; S2, performing uniformity correction and normalization enhancement on the original digital image, and achieving preliminary differentiation of different material regions; S3, dividing the original image data into processing domains based on the preliminary differentiation results, and performing differentiated enhancement processing based on the local feature attributes of each processing domain to generate a binary feature image. By integrating X-ray penetration imaging, multi-dimensional image enhancement, and a deep learning-driven intelligent rating system, this invention fundamentally solves the key technical bottlenecks in traditional industrial material inspection, such as inconsistent image quality, lack of material identification, and strong subjectivity in rating, achieving an automated, intelligent, and objective upgrade in industrial material defect detection.

A lithium battery data reconstruction and classification method driven by adversarial learning and feature distribution alignment, relating to the field of lithium battery state monitoring technology, mainly includes the following steps: constructing a feature recognizer to capture the temporal correlation features of lithium battery data throughout its entire life cycle; integrating the feature recognizer into an adversarial training framework, aligning the features of the data generated by the feature extractor with those of the real data through adversarial learning between real lithium battery data and simulated data generated by the feature extractor; constructing a feature transfer-based data reconstruction network based on the feature extractor and combining it with the Unet network to reconstruct battery data consistent with the features of the real data, forming an expanded dataset with the original data; and building a battery state classification network based on the feature recognizer, training it with the expanded dataset to complete the state classification of lithium batteries. This method ensures the effectiveness of the reconstructed data through feature distribution alignment, significantly improving the generalization ability and recognition accuracy of the classification model.

The invention relates to a spatial analysis single cell state modeling method and system based on domain self-adaption and layered fine tuning, and the method comprises the steps: obtaining multiple immunofluorescence images and single cell segmentation masks, and constructing a no-label data set; constructing a mask auto-encoder composed of a ViT encoder and a linear decoder, adding a classification token in front of the image, carrying out field adaptive training on the mask auto-encoder based on the unlabeled data set, learning the classification token, and obtaining a field adaptive weight of the ViT encoder; obtaining a labeled data set; constructing a state embedding generation model, wherein the state embedding generation model comprises a shared ViT backbone network and a two-stage classifier; a classification token is added in front of an image feature sequence in the labeled data set, hierarchical training is carried out on the state embedding generation model, and the classification token is learned; and inputting the cell image blocks into the trained state embedding generation model, outputting a classification result and cell state embedding, and carrying out interpretability analysis. Compared with the prior art, the method has the advantages that accurate cell classification can be realized, and cell state representation with biological interpretability can be generated.

The application provides an attack detection method and device for an electric power private network and a public network interaction node, pre-processes each piece of traffic data obtained from a node to obtain target traffic data containing feature information, classifies all the target traffic data to obtain multiple category data sets, samples and optimizes the target traffic data in each category data set to obtain an optimized category data set, selects features for each feature information in the optimized category data set by using a mutual information feature selection algorithm to obtain a feature selection result, updates the optimized category data set according to the feature selection result, reduces the redundancy of the data in the optimized category data set, obtains a more refined to-be-detected traffic data set, shortens the time required for an attack detection classification model to detect the to-be-detected traffic data set, and improves the classification accuracy of the attack detection classification model.

The invention discloses a lithology identification method based on a neural network, and the method comprises the steps: obtaining a logging curve, recognizing a missing value in the logging curve, taking the parameter data in the logging curve as sequence data, inputting the sequence data into an established neural network model, carrying out the prediction through the neural network model, obtaining the complementation data corresponding to the missing value, and obtaining the lithology of the logging curve. Filling missing values in the logging curve by using the completion data to obtain a complete logging data set, namely a first data set; based on the first data set, performing equalization processing on lithology classification samples in the first data set to obtain an equalization logging data set, namely a second data set; a whale optimization algorithm is adopted to optimize hyper-parameters of the classification model, target hyper-parameter configuration is obtained, and the classification model is configured; and inputting the second data set into the classification model, and identifying and outputting the lithology category. The method is high in missing value filling precision, excellent in sample equalization effect, remarkable in model performance optimization and high in system practicability.

This invention relates to an unsupervised domain adaptation method for source-domain data. The method involves training a model with labeled source-domain samples to obtain a pre-trained source-domain model; initializing a target-domain model using the source-domain model; approximating the feature distribution of the source domain with the statistical information stored in the Batch Normalization (BN) layer of the source-domain model, explicitly aligning it with the feature distribution of the target-domain samples, minimizing the distribution alignment loss, and bringing the feature distribution spaces of the source and target domains as close as possible; performing fuzzy clustering of the target-domain samples' features based on the predictions of the classifier from the source-domain model, using the cluster membership degree as the soft label for the target-domain samples, calculating the cross-entropy loss between the soft label and the model classifier's predictions for the target-domain samples, and maximizing the information loss for the target-domain samples; and training the target-domain model using all loss functions to achieve unsupervised domain adaptation for source-domain data, correcting some initially misclassified target-domain samples by the classifier, and improving classification accuracy.

The utility model discloses a kind of high-efficiency catalyst material grading equipment, it is related to catalyst material processing technical field.The utility model includes equipment frame, and grading box is movably connected in the equipment frame inner chamber, and grading box one side is equipped with discharge port.The utility model is equipped with discharge assembly, using the linkage structure of slide bar, receiving block, sealing plate and extruding block, the automatic switching of grading box between screening and discharging state is realized, when screening, spring pushes receiving block to make sealing plate tightly clamped discharge port, ensure sealing, after screening is completed, cylinder drives grading box to rotate, extruding block compreses receiving block to drive sealing plate to separate discharge port, realize automatic discharge, this design cleverly uses equipment self-motion as power source, without additional driving device, both solve the problem of material leakage in traditional vibrating screening, and also ensure the accurate opening and closing of discharge port through mechanical linkage, significantly improve material recovery rate and equipment reliability.

The utility model relates to the technical field of new energy automobile production equipment, in particular to a waste treatment device for new energy automobile battery production, which comprises a sorting treatment box and a negative pressure suction pump, and two obliquely-arranged second conveying rollers are rotationally connected to the positions, located below the first conveying rollers, in the sorting treatment box, a second conveying belt of a strong magnetic structure is in transmission connection between the exteriors of the two second conveying rollers, and a sorting baffle used in cooperation with the diaphragm discharging groove and the plastic discharging groove is fixedly connected to the interior of the sorting treatment box. The waste material sorting device has the advantages that battery waste materials generated in production are collected through the negative pressure suction pump, comprehensive collection of the waste materials is achieved, then different types of waste materials can be accurately separated through the sorting unit composed of the first conveying belt, the second conveying belt and the sorting baffle in a matched mode, the waste material sorting efficiency and accuracy are improved, and the production cost is reduced. And a foundation is laid for subsequent treatment and resource recovery.

The application discloses a kind of based on double filtering cooperation's remote sensing image scene classification method and system, in the method, for the problem that existing technology is difficult to give consideration to background noise suppression and key feature edge structure preservation when processing remote sensing image, a kind of double filtering cooperation optimization module is presented.The module in this paper introduces Gaussian filter smoothing channel to suppress unstructured high-frequency background noise, while introducing Gaussian Laplace edge enhancement channel to accurately capture and strengthen key geometric structure information such as feature contour;Through feature fusion, position coding, state space model and double activation gating mechanism, the multi-scale feature map is optimized and reconstructed to generate high signal-to-noise ratio and clear structure scene representation.The module is integrated into the remote sensing image scene classification model, and trained using focal loss, which can significantly improve the classification accuracy and robustness in complex texture interference scene.

The invention relates to the technical field of earth space information, in particular to a super-resolution land coverage mapping method coupled with a large language model knowledge base. Comprising the following steps: acquiring a remote sensing image and geoscience text data of a target area and constructing a geoscience knowledge system; mining geoscience knowledge from the geoscience text data based on a large language model, constructing a structured geoscience knowledge base, and further generating a geoscience knowledge graph; obtaining a deep feature graph of the remote sensing image based on a convolutional neural network, and inputting a knowledge graph into a graph attention network to extract a regional geoscience semantic embedding vector; realizing geoscience semantic embedding vector and deep feature map fusion based on a global-local attention fusion mechanism; and performing up-sampling on the fused feature map to obtain a high-resolution depth feature map, and generating a super-resolution land coverage map of the remote sensing image by adopting a nonlinear activation function. According to the method, dynamic modeling and computable expression of regional global knowledge can be realized, and the problems of surface feature boundary fuzziness and category confusion are remarkably improved.

The invention discloses a training data balance processing method and device, equipment, a medium and a product. The invention relates to the technical field of data processing. The method comprises the following steps: when a user in a user set is associated with an object in an object set, generating associated data according to the associated user and object, and adding the associated data into an associated data set; acquiring other users of the same category as the target user corresponding to the to-be-supplemented data of the associated data set; obtaining a target object associated with the target user in the associated data set; according to each target object, determining candidate objects of the target user in other objects associated with the other users in the associated data set; and generating associated data according to the target user and each candidate object, and adding the associated data into the associated data set. The embodiment of the invention can balance the training data of the model.

The utility model discloses a food weighing and grading equipment, including first chain plate conveyer, first chain plate conveyer one side is provided with platform scale, and platform scale one side is provided with material grabbing manipulator, and the both ends of platform scale are provided with qualified grading assembly and substandard product grading assembly respectively, and substandard product grading assembly and qualified grading assembly structure are same, qualified grading assembly includes second chain plate conveyer at first chain plate conveyer one end, and one end of second chain plate conveyer is fixedly connected with fixed frame, and the bottom of fixed frame is installed with visual inspection camera, and the outer wall of visual inspection camera is provided with illuminating lamp, and the bottom of visual inspection camera is provided with placing frame, and the bottom of placing frame swing joint has fixed seat, and the inside fixed seat is installed with third motor, and one end of third motor axle is connected with second connecting frame, and one end of second connecting frame is installed with second motor. The device can realize automatic weighing and ketone body classification after livestock slaughtering, thereby improving classification precision and classification efficiency.

The application relates to the field of workpiece defect detection, and discloses a workpiece end face defect detection method and system based on deep learning, which comprises the following steps: acquiring an end face image of a machined workpiece, performing image enhancement and region marking on the end face image to obtain an end face enhanced image and an end face marked region, querying abnormal points corresponding to the end face marked region, calculating an image offset of the workpiece end face image in a preset direction, querying an image difference frame corresponding to the workpiece end face image according to the image offset, extracting pixel values of the image difference frame, calculating an image difference value of the workpiece end face image, performing classification detection on the workpiece end face image by using a preset end face detection model to obtain a classification image, identifying a defect region in the classification image, extracting region features, and performing defect detection on the workpiece end face image to obtain a defect detection result of the machined workpiece. The application can improve the detection efficiency of workpiece end face defects.

This invention discloses a frequency-domain guided multi-scale deformable alignment method and system for UAV target detection. The method first acquires and preprocesses a dataset of UAV aerial images. Next, it improves the YOLOv8 model, performing target detection based on the preprocessed UAV aerial image dataset and outputting the target detection results. Finally, the improved YOLOv8 model is integrated into a pre-configured training environment, using training and validation images from the UAV aerial image dataset for training and validation. This invention significantly enhances the model's ability to perceive small targets, thereby significantly improving the localization and classification accuracy of small targets, reducing detection errors, and improving overall accuracy.

A direct current partial discharge signal defect classification method, system, device and medium based on time-frequency feature map visualization analysis optimization comprises the steps of performing first preprocessing on partial discharge original signal data, and dividing the data into a training set, a test set and a verification set; inputting the training set and the verification set into a ResNet-18 classification model for training, and screening three types of key samples based on an output prediction result; constructing an incremental data set according to the three types of key samples; respectively inputting the incremental data set and the combination of the incremental data set and the training set into a ResNet-18 classification model in sequence for secondary training; carrying out the second preprocessing of the to-be-detected partial discharge original signal data, inputting the to-be-detected partial discharge original signal data into the ResNet-18 classification model after the secondary training, and outputting a defect classification result; and secondary training of the ResNet-18 classification model is carried out by using an incremental data set constructed by the three types of key samples, so that the model focuses on learning samples with fuzzy features, high inter-class similarity or located near a decision boundary, and the discrimination capability and prediction precision of the model on complex samples are effectively improved.

The embodiment of the invention discloses a communication signal multi-parameter intelligent parallel extraction method. The method comprises the following steps: firstly, acquiring a to-be-measured signal and extracting an I / Q component; processing the I / Q components through a multi-scale feature extraction structure to obtain high-dimensional features; extracting shared features from the high-dimensional features through a plurality of residual block groups, inputting a plurality of parallel task branches, and enhancing the shared features in the branches by using a channel attention mechanism to obtain output features; the output features of all task branches are transformed through a learnable linear layer to form a key matrix and a value matrix, the current task features are transformed through a learnable linear layer to form a query matrix, and the input features are segmented into a plurality of heads by means of a multi-head attention mechanism; each head obtains output of a single head based on zoom dot product self-attention operation, and results of all the heads are integrated to obtain enhanced features of the current task; and determining a communication signal parameter prediction label according to the enhanced features, and realizing multi-parameter efficient parallel extraction.

The invention belongs to the technical field of deep learning image classification, and provides a cancer tissue pathology image fine-grained classification method based on SMCNet. Comprising the following steps: S1, setting an SMCNet network model; s2, collecting a cancer pathology image fine-grained classification public data set, training a classification network based on the formed SMCNet network model, and storing training weights; s3, performing network performance evaluation on the training result of the SMCNet model by utilizing the evaluation indexes of the accuracy, the classification precision, the recall rate, the F1 score and the AUC score; and S4, in combination with the training weight and a result visualization program, reporting a classification prediction result of the test set, and visualizing the classification prediction result by using a thermodynamic diagram. The SMCNet model adopted by the invention has stronger feature extraction capability and high discrimination degree for fine-grained categories, space-channel features are subjected to DRA attention of feature extraction by using a self-attention module, and the design thought of model lightweight is considered on the basis of realizing an optimized feature extraction function.

The invention discloses a high-dimensional sparse text-oriented classification method, system and device and a storage medium, and belongs to the technical field of natural language processing. The method comprises the steps of obtaining to-be-classified text data; based on the to-be-classified text data, constructing a candidate redundant feature set by calculating semantic similarity; joint mutual information of candidate redundant features in the candidate redundant feature set is calculated, and key features are obtained through screening according to the joint mutual information; inputting the key features into a pre-constructed text classification model to obtain a classification prediction result; wherein the text classification model comprises a dual-channel gating module, an attention module and a prediction module; the two-channel gating module extracts context features in the key features; the attention module weights the context features to obtain weighted features; and the prediction module obtains a classification prediction result according to the weighted features. According to the method, effective compression of feature dimensions and precise modeling of context semantics are realized.

The invention provides a medical image classification model training method and system, a medical image classification method, equipment and a medium, and the method comprises the steps: carrying out the time-sequence feature extraction of a time sequence of a resting-state functional medical image through an encoder, so as to obtain the multi-scale features of the resting-state functional medical image; performing feature extraction processing on the metabolic network of the functional state medical image to obtain features of the functional state medical image; processing the multi-scale features and the features of the functional state medical image by using an adapter to obtain feature pairs of the resting state functional medical image and the functional metabolism medical image; performing constraint processing on each feature pair by using comparative learning to obtain an aligned feature pair; and training the initial model by using the aligned features, and performing group-level modal distillation processing on the initial model to obtain a medical image classification model. According to the medical image classification model training method, the flexibility and robustness of cross-modal feature fusion can be improved.

The application provides a traditional Chinese medicinal material hyperspectral anomaly detection classification method and system and a computer device, relates to the traditional Chinese medicinal material quality inspection field, and the method comprises the following steps: reading hyperspectral data, performing foreground detection on the hyperspectral data by adopting a multiscale spatial spectrum fusion method to obtain an abnormal area foreground mask; collecting N three-dimensional Patch arrays of the foreground mask area through three-dimensional Patch automatic sampling; setting a three-dimensional convolutional neural network of a wave band self-attention mechanism, inputting the foreground mask and the three-dimensional Patch arrays into the neural network to generate a high-level semantic feature vector; and finally outputting a classification result through a neighborhood spatial spectrum self-supervision aggregation attention module of the high-level semantic feature vector. The traditional Chinese medicinal material hyperspectral anomaly detection classification method, system and computer device are used, a new efficient, accurate and automatic traditional Chinese medicinal material mildew and insect damage detection method is realized, and the detection quality and the practical value of the system are significantly improved.

The application discloses a skin type prediction method for small sample data autonomous learning, and relates to the technical fields of deep learning and medical beauty skin type. The initial model is obtained by a convolutional neural network through a small number of labeled samples, and the subsequent new samples are accepted through the initial model, and whether the new samples have labeling value is judged according to the prediction result of the model, so that only the samples determined to be inaccurate by the model are selected for labeling and retraining. Compared with the existing skin type method, a single model can be used to obtain a more perfect result, the model is continuously iteratively optimized by using the enhanced unit in the actual use process, and the idea of active learning is used to select the samples with greater uncertainty for labeling, so that the number of samples needing expert labeling can be greatly reduced, and the labor cost is reduced. According to the reliability module, when the samples are expanded, the skin type with insufficient reliability is preferred, so that the final typing effect is improved.