44results about How to "Improve classification effect" patented technology

The invention provides a valve leakage diagnosis method and system based on an improved Hereum algorithm optimized SVM (Support Vector Machine), and relates to the technical field of valve leakage diagnosis. Decomposing the collected original signal to obtain a limited number of IMF components; calculating a fuzzy entropy, and constructing a feature vector; taking the feature vectors as data samples, and dividing the data samples into a training set, a verification set and a test set; using the training set to train the SVM model, and according to the classification error rate of the verification set on the trained SVM model, performing iterative optimization on the parameters of the SVM model based on an improved He-Ma algorithm to obtain an optimized SVM model; inputting the test set into the optimized SVM model to obtain a valve leakage diagnosis model; and acquiring a new acoustic emission signal, and inputting the new acoustic emission signal into the valve leakage diagnosis model to obtain a diagnosis result. The method not only can improve the classification accuracy and generalization ability of the diagnosis model, but also can enhance the stability of the model under different working conditions and environmental noise.

The invention belongs to the technical field of hydraulic engineering, and provides a sediment particle size distribution measuring system and method.The method comprises the steps that images of sediment particles in a water body are collected, and a first sediment particle image is obtained; processing the first sediment particle image to obtain a sediment grayscale image; a K-means clustering algorithm is adopted to carry out clustering analysis on the sediment gray level image, and an image with a first-level clustering result is obtained; carrying out clustering analysis on sediment particles with particle sizes smaller than a preset threshold value in the image with the first-level clustering result by adopting a DBSCN clustering algorithm to obtain an image with a second-level clustering result; and carrying out edge detection on the sediment particles in the image with the secondary clustering result, and then sequentially carrying out binarization processing, equivalent circle diameter transformation and statistics on the particle size distribution of the sediment particles to obtain a particle size distribution result. The problem that an existing sediment particle size measurement system is low in measurement precision in a complex underwater environment with dense sediment and more fine particles is solved.

The invention relates to a medical image processing technology, and discloses a pan cancer species histopathologic full-slice classification method and device, which is a trained multi-modal pan cancer species classification model based on histopathologic full-slice image data and full-slice diagnosis report pairing data of various tissue parts and various cancer species, and has the advantages of wide application range and high efficiency. And full slices of various pathological tissues can be classified. For classification tasks of different tissue parts, only text prompts (prompts) are used, i.e., a candidate cancer species list is set, and zero-sample full-slice classification can be realized without training. And for rare cancer species, full-slice classification can be carried out. Besides, the model has high expansibility, in order to better adapt to downstream tasks, better classification performance can be achieved by combining slice embedding with a linear classifier for use, freezing a slice embedding part and only finely adjusting the linear classifier, and the requirement for the training data size is low.

The invention relates to a noise feature vector classification model construction method, a speech enhancement method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: coding penalty parameters and kernel function parameters of a support vector machine; taking the penalty parameter and the kernel function parameter as optimization variables of a genetic algorithm, setting an initial population, and constructing a fitness evaluation function based on classification accuracy; performing selection operation, crossover operation and mutation operation on the initial population, and updating an iterative population according to a fitness evaluation function to obtain an optimal penalty parameter and an optimal kernel function parameter; and training a support vector machine through the optimal penalty parameter and the optimal kernel function parameter, and constructing a noise feature vector classification model. In a noisy environment, the classification effect of the noise feature vector is improved under the condition that nonlinear and non-stationary noise exists, and the noise feature classification requirement in a complex sound signal processing scene is met.

The invention discloses an unmanned aerial vehicle image multi-crop plot identification and productivity prediction method based on DeeplabV3 +, and the method comprises the steps: obtaining an unmanned aerial vehicle image of a research region, and carrying out the splicing processing of the image; preprocessing and labeling the images, and dividing the images into a training set and a verification set; training, verifying and testing the improved DeeplabV < 3 + > deep learning network model by using the data set to obtain a final unmanned aerial vehicle image plot recognition and crop classification model based on DeeplabV < 3 + >; carrying out land parcel identification and crop classification on the preprocessed to-be-detected image by using the trained land parcel identification and crop classification model, and carrying out splicing processing; and the spliced prediction segmentation map is further processed by using envi and ArcGis software to obtain a productivity prediction map of various crops. According to the invention, the dependence on manual field investigation is reduced, the method is less limited by topographic factors, the method is faster and more accurate, and the efficiency of agricultural asset checking is improved.

The invention relates to a hyperspectral image classification method, in particular to a hyperspectral image classification method based on a greedy strategy guided graph self-attention network. The invention provides a hyperspectral image classification method of a graph self-attention network based on greedy strategy guidance in order to solve the problems that in existing HSI classification, samples are limited, GAT tends to only consider directly-connected nodes, indirectly-related relations are insufficiently considered, and the classification effect is affected. The method comprises the following steps: step 1, constructing a graph self-attention network based on greedy strategy guidance; the greedy strategy guidance-based graph self-attention network comprises a data preprocessing stage, a super-pixel-based graph self-attention branch stage, a pixel-based multi-attention fusion branch stage, a classification stage and a greedy training strategy stage. And step 2, classifying the hyperspectral image to be measured based on the trained greedy strategy guided graph self-attention network to obtain a classification result. The method is applied to the field of hyperspectral image classification.

The invention relates to the field of text classification, in particular to a BiLSTM and mixed attention ResNet-based text classification network, a Bi-Hybrid Att-ResNet text classification network model comprises a BiLSTM, mixed attention and ResNet, the BiLSTM of the model is used for establishing a long-term dependency relationship, context representation before and after access and a mixed attention mechanism, key information in BiLSTM output can be captured more effectively, and the text classification network model can be applied to the field of text classification. The method comprises the following steps of: firstly, extracting a sentence by using ResNet, facilitating feature extraction, increasing network depth, accelerating network convergence and capturing n-gram features in the sentence, and finally, classifying the processed context information by using a full connection layer. And the Bi-Hybrid Att-ResNet can be used for capturing the local features and the global semantic information of the text.

The invention belongs to the technical field of information recommendation, and particularly relates to an intelligent image recognition and commodity classification system. Comprising an image acquisition module, an image processing and feature extraction module, a deep learning model training module, a commodity classification and identification module, a user interface module, a database module, a system integration and deployment module, an update and maintenance module and a security module. The invention provides an intelligent image recognition and commodity classification system, and a multi-layer perceptron is adopted as a feature representation unit in the intelligent image recognition and commodity classification system, so that the system can capture a more complex nonlinear relationship in an image. Therefore, abstract features in the image can be better expressed, and the recognition capability of the system on complex modes is improved.

The invention discloses an epilepsy detection method combining uncorrelated multi-linear discriminant analysis and deep metric learning, and belongs to the technical field of epilepsy detection.The epilepsy detection method comprises the steps that S1, original electroencephalogram signals are collected and preprocessed; s2, forming a third-order electroencephalogram tensor by using the electroencephalogram signals subjected to the improved S-transform time-frequency decomposition processing, and extracting electroencephalogram features through uncorrelated multi-linear discriminant analysis; s3, performing epilepsy disease classification by using a triple network metric learning classifier; s4, a Softmax function is used for outputting probability distribution of the test data, and a detection label is obtained; s5, a moving average filter is used for eliminating burst noisy points and isolated abnormal values, and a classification result and post-processing are output; according to the epilepsy detection method combining uncorrelated multi-linear discriminant analysis and deep metric learning provided by the invention, the workload of doctors can be effectively reduced, the efficiency and accuracy of epilepsy detection are improved, and the epilepsy detection method has a remarkable promotion effect on clinical diagnosis and treatment.

The present invention belongs to the field of target detection technology, and specifically is a target detection method applied to smart construction site security, the method comprising the following steps: constructing a YOLOV8 target detection original model; using historical images collected on the construction site to train the YOLOV8 target detection original model to obtain a trained target detection model; inputting the real-time to-be-detected images collected on the construction site into the trained target detection model, detecting target violations on the construction site in real time, and classifying and locating the detected behaviors, while triggering an early warning system and outputting violation images. The present invention also discloses a target detection system applied to smart construction site security. The target detection model provided by the present invention is applied to a smart construction site, and can monitor various behaviors on the construction site in real time, discover potential safety hazards in a timely manner, and issue alarms or take corresponding preventive measures in a timely manner. This method greatly improves the efficiency of construction site safety management.

The invention discloses a flue-cured tobacco maturity classification method and device, and relates to the technical field of flue-cured tobacco classification. The method comprises the following steps: respectively manufacturing upper, middle and lower flue-cured tobacco maturity samples by a tobacco leaf grading expert, acquiring spectral data of the flue-cured tobacco maturity by an imaging system, and eliminating noise in the spectral data of the flue-cured tobacco maturity by using a moving average filtering method and a multivariate scatter correction method; the method comprises the following steps: integrating a spider bee intelligent optimization algorithm into a 1D-ResNet model to establish an SWO-ResNet model, using SWO to intelligently optimize batchsize and epochs parameters in the 1D-ResNet model, using the SWO-ResNet model to extract a spectral characteristic wave band of flue-cured tobacco maturity, and using an LDA classifier to establish a flue-cured tobacco maturity classification model. The flue-cured tobacco maturity classification method capable of being described is established, and classification of the flue-cured tobacco maturity is completed through spectral characteristics.

The invention relates to an intelligent insurance agent face visit log text repetition detection device and a method thereof.The device comprises an input module, a preprocessing module, a similarity calculation module and a post-processing module which are connected in sequence, and the method comprises the steps that a current log to be detected and a historical log are obtained, text pair data are constructed, the historical log comprises customer visit log records in N historical days; performing text cleaning processing on the data for the text to obtain a processed current log text and a historical log text; for the current log text and the historical log text, respectively calculating character similarity and semantic similarity between the current log text and the historical log text; and based on the character similarity and the semantic similarity, performing comparative judgment in combination with a preset corresponding threshold, and outputting to obtain a repetition detection result. Compared with the prior art, the method has the advantages that the character similarity and the semantic similarity are combined, efficient and accurate log repetition detection can be carried out from the aspects of character similarity and semantic repetition, and the log quality is effectively improved.

The present invention is applicable to the technical field of graph structure data, and provides a graph node classification method based on a new graph neural network, comprising the following steps: reading graph data; calculating feature similarity between nodes, and setting a similarity threshold, adding edges between node pairs when the similarity between nodes exceeds the preset threshold; dividing neighbors of different relationships for nodes and adding relationship attributes to the edges of nodes, obtaining a new graph structure after neighborhood reconstruction; inputting the reconstructed graph into MRN‑GNN, aggregating neighbors of the same type with the central node first, and during the aggregation process, calculating the attention coefficient of neighbors and central node features under each spatial relationship, and weightedly aggregating the attention coefficient with neighbor features; splicing the obtained multi-relation features with the central node features, and finally outputting the classification prediction of the node. The present invention can effectively capture the features of distant nodes without deepening the network, and effectively distinguish the relationship structures of different neighbors.

The application provides a video classification method and device, an electronic device and a storage medium, wherein the method comprises: encoding a first video to obtain a plurality of corresponding image frames, wherein the first video is any video in a plurality of videos to be classified; determining the complexity of the first video based on a target image frame in the plurality of image frames, wherein the complexity comprises spatial complexity and temporal complexity; and classifying the plurality of videos based on the complexity. Through the application, the technical problem that the prior art classifies by using the bottom features of a video and needs to rely on strong prior knowledge, resulting in poor video classification effect and weak robustness, is solved.

The invention provides a shale oil and gas reservoir multi-scale pore structure characterization method based on machine learning. The shale oil and gas reservoir multi-scale pore structure characterization method specifically comprises the following steps of obtaining a shale sample image and performing image segmentation; clustering the images by using a K-means clustering algorithm; classifying the segmented images into N classes through three features of gray vectors, variances and information entropies; and calculating a gray average value of the images in each category, and evaluating an image classification effect by using the gray average value. According to the technical scheme, the problem that in the prior art, comprehensive understanding and characterization of multi-type and multi-scale micro-pore structures of heterogeneous shale cannot be achieved at the same time is solved.

The invention relates to the field of brain image processing, in particular to an image analysis processing system and method based on thought control, and the system comprises an electroencephalogram signal collection system which is used for collecting and preprocessing electroencephalogram signals of a user; the thought analysis system is used for extracting features from the preprocessed electroencephalogram signals and then carrying out thought classification and instruction mapping; the image acquisition and processing system is used for acquiring image information according to the mind control instruction of the user and performing image processing; the VR display system is used for converting the processed image into a format suitable for VR equipment display and providing interactive feedback; and the control and communication system is used for converting the mind state into a control instruction and realizing data transmission and communication among the systems. The EEG signals and the fNIRS signals are acquired through the multi-mode signals, the defect of a single signal in the aspect of reflecting the brain activity is overcome, and therefore brain activity information corresponding to the thought is more accurately interpreted.

The application relates to an automatic text classification method based on a car community, which comprises the following steps: obtaining a data set of car community texts; obtaining word vectors and text feature vectors as input values of a double-layer clustering model; performing clustering calculation on the word vectors and the text feature vectors to generate word classification and text classification respectively, so as to form the double-layer clustering model. When a new text enters: calculating the word vectors and the text feature vectors of the new text; calculating the word classification of each word vector of the new text and the word frequency under each classification; calculating the text classification of the new text; performing dynamic analysis according to the word classification, the word frequency and the text classification of each word vector of the new text; when the number of words and the word frequency of the new text generated outside the existing word classification reach a threshold value, the double-layer clustering model is updated. Therefore, the application can realize automatic classification of car community texts in the whole process, improve the classification accuracy and efficiency, and form a closed-loop management.

The invention discloses a multi-extended target joint tracking and classification method based on star convex RHM and LMB filters, and belongs to the field of radar target tracking. According to the method, an LMB parameter set is initialized by using target prior information, and then a sensor measurement set is divided through a mean shift algorithm; then, state prediction is achieved by combining survival target parameter updating and new target parameter sampling, and then measurement updating is completed through LMB-to-GLMB, GLMB updating and GLMB-to-LMB; and then trimming and fusing the LMB parameter set, estimating the number of targets, extracting state information, and circularly executing until observation is finished. According to the method, a star convex RHM modeling expansion state is adopted to reduce dimensions, the low detection probability / high clutter scene performance is improved based on an LMB framework, the tracking classification effect and the real-time performance are both considered, and the engineering application value is high.

The invention relates to the technical field of medical information, and discloses a lung transplantation patient clinical bacterial infection factor prediction model and a construction method, and the method comprises the following steps: S1, selecting a hospital needing research, and determining a research object according to an inclusion standard and an exclusion standard; s2, selecting a proper number of variables as candidate predictive factors; s3, clinical bacterial infection patients are defined as typical symptoms, signs and sputum characters; laboratory inspection: inflammation indexes are increased, and pathogens can be determined by bacteria detected by sputum culture; s4, if missing values exist in part of variables, simple interpolation processing is adopted, mean interpolation is adopted for continuous variables, and mode interpolation is adopted for classified variables; s5, sample size analysis; and S6, model establishment: firstly carrying out description analysis, and then carrying out Lasso regression and model prediction. A method for respectively establishing prediction models by applying various machine learning and deep learning is adopted, and multi-aspect comparative analysis is carried out on lung transplantation patient clinical bacterial infection influence factor prediction models.

The invention relates to the technical field of data classification, in particular to an intelligent data sharing method for construction of an intelligent sharing system. According to the method, each condition attribute is used for splitting total historical service data to obtain different sub-data sets, and the index characteristics of the index attributes in the total historical service data and the sub-data sets of each condition attribute are analyzed according to the difference of confusion degrees of the index characteristics of the index attributes in the sub-data sets of the condition attributes. Obtaining an initial priority index of each condition attribute according to the change trend of the historical business data of each condition attribute and the change trend of the historical business data of the attention attribute, and adjusting the initial priority index in combination with the influence degree of each condition attribute on the attention attribute and the correlation degree of each condition attribute and other condition attributes so as to construct a decision tree; and classifying and sharing the total historical business data. According to the method, the decision tree is constructed by combining the information gain and the importance degree brought by the condition attributes during data set segmentation and the correlation degree of the different condition attributes, and the classification effect of the decision tree based on the attention attributes is improved.

The utility model relates to the technical field of metal steel cylinders, and discloses a derusting device for metal steel cylinder production, which comprises a derusting box, a rotating rod is rotatably connected to the center of the inner wall of one side of the derusting box, a connecting plate is fixedly connected to one end of the rotating rod, and a telescopic rod is fixedly connected to one side of the connecting plate. The rust removal device comprises a rust removal box, telescopic rods are rotatably connected to the inner wall of one side of the rust removal box, clamping plates are fixedly connected to the movable ends of the two telescopic rods, a plurality of limiting plates are fixedly connected to the opposite sides of the two clamping plates, a fixing cylinder is fixedly connected to the inner wall of the upper end of the rust removal box, and a driving opening is formed in the lower end face of the fixing cylinder. According to the automatic rust removal device, the rust removal efficiency can be greatly improved through the arranged automatic rust removal structure, better usability and higher efficiency are achieved, meanwhile, chippings generated in the production process can be rapidly treated through the arranged cleaning structure, and therefore better environment friendliness and convenience are achieved.

The utility model relates to the technical field of sorting devices, and discloses an automatic article sorting device which comprises a sorting device body and two sets of visual inspection devices fixedly connected in the sorting device body, a conveying belt assembly is arranged in the sorting device body, and the conveying belt assembly is connected with the sorting device body. The sorting equipment body is provided with an adjusting mechanism, the adjusting mechanism plays a role in pushing workpieces, the adjusting mechanism comprises a heat dissipation box fixedly connected to one side of the sorting equipment body, and the output end of the heat dissipation box is fixedly connected with a servo motor. Through the arrangement of the servo motor, the bevel gear I, the reciprocating screw rod and the contact block, the effect that the position of a product can be adjusted so as to improve the detection effect of visual detection equipment is achieved, use is convenient, and the problem that when an existing sorting device is used for transporting objects, the sorting efficiency is high is solved. Products are often directly placed on a conveying device, and the problem that the product detection effect is affected due to the fact that the placing positions of the articles are not accurate is prone to occurring.

The present invention discloses a multi-label text classification method based on a graph neural network, and relates to the field of natural language processing. The method comprises the following steps: extracting text semantic vectors of text to be classified through a text encoder; establishing a graph G with category labels as nodes; inputting the graph G into a graph convolutional network to obtain a node representation vector of each category label; combining the node representation vector of the category label with an additionally defined category expression vector to obtain a classification layer fusion weight; inputting the text semantic vector into the classification layer, and performing category prediction on the text according to the classification layer fusion weight. The method can improve the performance of the model in multi-label text classification of various text genres, and can be combined with powerful pre-trained text feature extractors such as BERT and Elmo, and can be used in actual multi-label text classification systems to improve classification effects.

The present disclosure belongs to the technical field of natural language processing, and relates to a knowledge base question-answering method and device, a storage medium, and an electronic device. The method includes: obtaining a question statement and a database, and using an improved named entity recognition model to identify a first entity category and a first named entity in the question statement; using a matching model to identify a second entity category and a second named entity in the question statement, and fusing the first entity category and the second entity category to obtain a target entity category; fusing the first named entity and the second named entity to obtain a target named entity, and searching for an answer statement to the question statement in the database according to the target entity category and the target named entity. The present disclosure implements intent classification and named entity recognition through a model, simplifies the processing flow, improves the accuracy of the improved named entity recognition model, improves the accuracy of intent classification, optimizes the classification effect, improves the accuracy of answer search, and reduces the answer screening time.

This application discloses an unsupervised classification method for dedicated power transformer users based on load curves. The method includes: acquiring user load curves; pre-classifying users based on their load curves to determine user types, including horizontal, zero-value regular, annual-cycle, daily-cycle, and random types; and performing secondary classification on annual-cycle and daily-cycle users respectively to obtain the target classification result. This application classifies dedicated power transformer users based on the characteristics of their load curves. This classification method is more suited to the electricity consumption habits of dedicated power transformer users, is highly practical, has good classification results, and can achieve accurate classification.

The invention is suitable for the technical field of point cloud processing, and provides a small sample point cloud classification model training method, computer equipment and a computer program product, and the method comprises the steps: extracting a first visual feature and a position feature based on a training point cloud data set; carrying out implicit sample expansion based on the first visual feature and the position feature to obtain an expansion feature; updating parameters of the pre-training model based on the first visual features and the expansion features; returning to the first step until a preset ending condition is met; and outputting a target classification model based on the pre-training model. According to the method provided by the invention, the distinguishing ability and the understanding ability of the model for different types of point clouds are improved through the first visual features and the position features, the diversity of training data is effectively enriched through implicit expansion of the first visual features, and the model parameters are jointly updated based on the features after implicit expansion and the first visual features, so that the training efficiency is improved. And the model has better generalization ability and classification performance.

The invention relates to a source code problem classification method and device, equipment, a readable storage medium and a product. The method comprises the steps of obtaining at least one source code problem in a preset time period; for any source code problem, determining an initial classification result of the source code problem according to the problem content of the source code problem; and according to the initial classification result and the problem content of the source code problem, classifying the source code problem to obtain a target classification result of the source code problem. By adopting the method, the source code problems can be better classified.

A hydraulic device fault diagnosis method relates to the technical field of hydraulic device state diagnosis and comprises the following steps: step S01, acquiring sensor data of a hydraulic device; step S02, carrying out dimensionality reduction on the collected data of the hydraulic device sensor through a Barnes-Hut t-SNE algorithm; step S03, improving an artificial bee colony algorithm ABC; and step S04, using SCQ-ABC to train a weight w of an input layer, a hidden layer deviation b and the like of the ELM model. According to the fault diagnosis method, dimension reduction processing is performed on the data through Barnes-Hut t-SNE, and the fault diagnosis method of the extreme learning machine ELM is optimized by using the variant artificial bee colony algorithm SCQ-ABC, so that the diagnosis precision is improved.

The invention relates to a multi-source time series data prediction method fusing spatio-temporal characteristics, and belongs to the technical field of Internet of Things data analysis and artificial intelligence. Time domain alignment and resampling are carried out through a unified time reference, and frequency heterogeneity of multi-source data is eliminated; fusing the time-lag mutual information and the dynamic time warping index, mining time-lag and nonlinear dependence among different data sources, and constructing a sparse multi-source spatio-temporal topological graph; the topological graph is used as a structure prior input self-attention mechanism space-time diagram convolutional network for feature extraction and prediction; an improved grey wolf optimization algorithm is adopted to jointly optimize a composition threshold value and a network hyper-parameter, a population is initialized through a hierarchical anchor point and a reverse learning strategy, an adaptive state-time domain double-control convergence factor is used to balance exploration and development, and a mixed gravitation weight strategy is used to update a population position; and performing multi-source time series data prediction by using the optimized model. The problems of asynchronous response and weak coupling of multi-source data are effectively solved, and reliable support is provided for intelligent decision making.

The invention relates to a multi-dimensional data fusion method and system based on adaptive weight. The method comprises the steps of data acquisition and preprocessing, feature extraction of multi-dimensional data, multi-dimensional data fusion and classification discrimination, feedback learning mechanism and result explanation. A multi-strategy collaborative Harris eagle algorithm is adopted, wherein the multi-strategy collaborative Harris eagle algorithm comprises a mixed population initialization strategy, an optimal solution retention strategy, a cosine decline escape energy operator iteration method and a double-strategy variation optimal solution and adaptive weight factor prey updating strategy; and designing a feedback learning mechanism, and continuously improving the performance of the model in actual data. The multi-dimensional data fusion module combines the main discriminant features and the auxiliary discriminant features of the data; and the support vector machine classification model captures a nonlinear relationship between complex features through a kernel function. The method can effectively cope with noise and isomerism in a multi-dimensional data environment, supports real-time discrimination and result interpretation of multi-dimensional data fusion, and provides more reliable and accurate support for complex data analysis and intelligent decision making.