Patents
Literature
45 results about "Misclassification error" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Quantum adversarial attack method based on momentum
PendingCN119443148Astrong computing powerFast convergenceQuantum computersNeural architecturesLocal optimumOriginal data
The invention discloses a quantum adversarial attack method based on momentum, which refers to an object momentum mechanism, and designs a quantum adversarial attack method to efficiently generate adversarial samples. In order to solve the problem that an existing quantum countermeasure attack method excessively fits a specific model to cause a poor local optimal solution, the invention provides a novel quantum countermeasure attack method based on momentum (Q-MIFGSM). According to the method, a loss function of a quantum neural network classifier and momentum accumulation gradient information of a sample are defined, a momentum iteration updating mode is adopted, momentum accumulation is carried out on a loss function gradient value, the optimization direction is dynamically adjusted in combination with current and historical gradients, and a local optimal solution is effectively jumped out; the loss function value of the quantum classifier is increased to cause classification errors of the classifier, so that attack resistance is realized, and an adversarial sample is efficiently generated. Simulation experiment results show that the Q-MIFGSM algorithm can effectively execute adversarial attacks on the quantum neural network classifier and generate adversarial samples close to original data. A new strategy is provided for quantum attack resistance, and the method has potential application value in the aspects of quantum neural network security evaluation and defense strategies.
Owner:GUILIN UNIV OF ELECTRONIC TECH
Multi-target particle swarm feature selection method and system based on chaotic population
PendingCN119202646Aincrease diversityincrease vitalityChaos modelsNon-linear system modelsEffective solutionData set
The invention discloses a multi-target particle swarm feature selection method and system based on a chaos population, and belongs to the technical field of data processing. The method comprises the following steps: acquiring a data set, and preprocessing the data set by using a chaos strategy; performing classification extraction on the preprocessed data by using a multi-target particle swarm algorithm; the feature correlation in the extracted data subset is analyzed, and the system comprises an initialization module, a feature extraction module and an updating module. According to the method and the system, the multi-target particle swarm optimization algorithm is optimized through the chaos strategy, the vitality of the population is improved, the classification error rate is effectively reduced, meanwhile, the number of features is remarkably reduced, a practical and effective solution is provided for solving the problem of high-dimensional data feature selection, and the method and the system have good application prospects. And challenges faced by high-dimensional data analysis are overcome successfully.
Owner:LIAONING UNIVERSITY OF TECHNOLOGY
Code generation and repair method and device based on multi-round feedback of large language model
The invention discloses a code generation and restoration method and device based on multi-round feedback of a large language model, and the method comprises the following steps: 1, converting problem description into a structured tetrad (target, input, output and constraint) through a two-stage task demand deconstruction mechanism, and generating a pseudo-code frame according to the structured tetrad; 2, generating a plurality of candidate code schemes in parallel based on different implementation strategies; 3, selecting an optimal code implementation scheme through multi-dimensional evaluation; 4, generating an extended test case through boundary condition analysis and public test reasoning, and expanding a verification range; 5, classifying error types in combination with static analysis and dynamic execution information, and applying a special repair strategy; 6, providing detailed repair reasons and ideas by an interpretable repair mechanism; and 7, establishing a multi-round feedback repair verification iteration mechanism composed of testing, analysis, repair and verification. According to the method, the performance of an existing large language model in processing a complex programming task is effectively improved.
Owner:WUHAN UNIV +1
Optical machined part defect detection method based on image technology
PendingCN119205644Aefficient separationAccurately definedImage enhancementImage analysisFeature extractionOptical processing
The invention discloses an optical machined part defect detection method based on an image technology, and belongs to the technical field of optical machined part detection, in the method, a defect edge in an image is extracted through a Canny edge detection algorithm, a defect area can be effectively separated from a background area, and a foundation is laid for subsequent feature extraction and defect recognition. The segmentation technology has the advantages that the contour of the defect can be accurately defined, and high detection precision can be kept even under the background of complex textures or uneven illumination. In addition, the non-maximum suppression and double-threshold detection mechanism of the Canny algorithm is helpful for reducing false detection and missing detection, and the detection reliability is improved. And extracting shape, texture and statistical features from the segmented defect region, wherein the features are keys for distinguishing different types of defects. Different types of defects can be effectively distinguished through feature extraction, and classification errors are reduced. The calculation amount of subsequent model training and recognition can be reduced, and the efficiency of the whole detection process is improved.
Owner:YANGZHOU HONGBOYING OPTOELECTRONICS TECHNOLOGY CO LTD
VerilogA code automatic error correction method based on classification error library and large language model
The invention discloses a VerilogA code automatic error correction method based on a classification error library and a large language model, and the method comprises the steps: constructing a classification system of the error types of VerilogA codes, starting from an MTJ device, carrying out the statistics of 84 common errors in the VerilogA codes of MTJ based on the system, and developing an automatic training sample generation system according to the 84 common errors; the method comprises the following steps: selecting a DeepSeek-R1-7B model as a basic model through a benchmark test, and carrying out fine tuning training by utilizing a classified error data set generated by scripting to form a special error correction model for the field. The processing process comprises the steps that VerilogA codes to be corrected are received, error types and reasons are positioned through a trained model, correction codes are generated, and verification of eight types of typical circuits is passed. An error classification-model training-simulation verification system is established, verification and error correction of VerilogA codes are achieved, and time and resources in the development process are saved.
Owner:SOUTHEAST UNIV
Table-to-text generation method based on multi-agent collaboration
The invention discloses a table-to-text generation method based on multi-agent collaboration, which is characterized in that model training comprises two stages of supervised fine tuning and stylized preference optimization, enhanced training data is constructed through table replacement invariance, a large language model is efficiently fine-tuned by using PEFT, and the model is optimized; and a SimPO algorithm is adopted to carry out positive and negative sample contrast learning to generate a text conforming to a golden standard style. In error correction, through a multi-agent cooperation mechanism, table data is coded by using a BERT model and stored in a Faiss vector database, an agent is generated to generate a text based on a large language model, the agent is retrieved to construct a minimum related table, the agent is verified to compare unit declarations and classify errors, and the agent is scheduled to trigger an error correction strategy. And errors such as numerical values, knowledge missing and table conflicts are accurately corrected. The whole process is iteratively generated and verified, it is ensured that the generated text is loyalty to facts, consistent in style and free of illusion, and the quality and accuracy of table-to-text generation are remarkably improved.
Owner:ZHEJIANG UNIV
Video classification and identification method based on Video Swin Transform
The invention discloses a video classification and identification method based on Video Swin Transform. The method comprises the following steps: preparing a data set to be identified; the data set is preprocessed, feature map information enters a network block, and a feature map is subjected to a multi-scale fusion module; the model uses an I3D classification head to carry out final classification on eight categories; and drawing a confusion matrix according to a classification result of the model, and reclassifying samples with model classification errors or adjusting classification boundaries. According to the method, the model adopts a sliding window design of Vdio Swin Transform, so that the model can learn feature information in a cross-window manner, and the parameter quantity in calculation is greatly reduced; moreover, the hierarchical model can process super-resolution picture information, and consumption of computing resources is also reduced; a time dimension T is added to the model, the time dimension is used for capturing continuous time frame information of an incoming video, and the action range of windowed attention is expanded to the space-time field from the space field.
Owner:CHANGCHUN INST OF TECH
Multi-station defect classification accuracy improvement method and system, electronic device, and storage medium
The application discloses a multi-station defect classification accuracy improvement method and system, an electronic device and a storage medium, which comprises setting at least two detection stations with different detection conditions, controlling the detection stations to synchronously collect original images of products to be detected; detecting defects in the original images collected by each detection station, determining the position coordinates of the defects, and marking the defects with the same position coordinates in different detection stations as associated defects to be classified; respectively extracting feature parameters of the associated defects to be classified in the images of the detection stations, obtaining feature differences of the associated defects to be classified under different detection conditions; judging the types of the associated defects to be classified according to the feature differences, and outputting classification results. The application can effectively solve the problem of classification errors caused by similar features of different types of defects in single-station detection, improve the accuracy of defect classification, has the advantages of strong adaptability, flexible adjustment and the like, and is suitable for surface defect detection in electronic manufacturing, thin film production and the like.
Owner:ZHONGJIA MICROVISION (SHENZHEN) SEMICONDUCTOR TECHNOLOGY CO LTD
Simulation training personalized recommendation analysis method, system, equipment and medium
The invention discloses a simulation training personalized recommendation analysis method, system and device and a medium, and relates to the technical field of computer platform load balancing, and the method comprises the steps: collecting user behavior data, carrying out the preprocessing, and carrying out the feature marking and grading of a user; quantizing user behavior characteristics by using a distributed machine learning platform, and dynamically adjusting user groups through a clustering algorithm; and generating personalized recommendation by adopting collaborative filtering and reinforcement learning algorithms, and dynamically adjusting task difficulty based on real-time feedback to optimize recommendation weight. According to the method, multi-dimensional behavior characteristics are clustered through a K-means + + clustering algorithm, and dynamic user grouping is realized in combination with a dynamic threshold adjustment mechanism; by designing a recommendation algorithm architecture, not only can the new user be ensured to quickly adapt, but also individuation and dynamic adaptation of the recommended content are realized, and the classification error rate is reduced.
Owner:GUANGXI POWER GRID CORP
A method for underwater target classification considering the robustness of deep learning models
ActiveCN114565831BImprove robustnessEasy to liftCharacter and pattern recognitionMachine learningAlgorithmMisclassification error
A method for underwater target classification considering the robustness of a deep learning model. In order to solve the problem of low accuracy of underwater target classification by existing deep learning models, the present invention comprises the following steps: using a trained original model to predict a collected underwater target data training set to obtain a set of all correctly classified samples and a set of all incorrectly classified samples; inputting the set of all incorrectly classified samples into the trained original model, clustering and feature compensating the features of the incorrectly classified samples, and obtaining feature compensation for the incorrectly classified samples; inputting the feature compensation into the trained original model to obtain the feature-compensated original model; inputting the underwater target data training set into the feature-compensated original model, and outputting the incorrectly classified samples; establishing an adversarial training model to obtain a trained adversarial training model; and weightedly combining the adversarial training model with the feature-compensated original model to generate a deep learning model. The method belongs to the field of underwater target classification.
Owner:HARBIN ENG UNIV
Enhancement Method, Device, Computer Equipment and Storage Medium for Training Data
This application relates to the field of model training, and particularly to a method, device, computer device, and storage medium for enhancing training data. The method includes: obtaining a training data set; inputting the training data set into a classification model for pre-training to obtain original images with classification errors and classification data; inputting the original images into a preset residual network to obtain the features of the original images; calculating the mutual information of the features according to the classification data, and screening out false features in the features with an influence degree greater than a preset value according to the mutual information; performing data enhancement on the original images according to the false features to obtain target images; generating an enhanced training data set according to the target images, so as to retrain the classification model based on the enhanced training data set. This application can trace the errors of the model, find features correlated with the prediction results, and enhance the original data set to improve the robustness of the model.
Owner:PING AN TECH (SHENZHEN) CO LTD
Automatic express classification system based on RFID technology
The invention relates to the technical field of image recognition, in particular to an automatic express classification system based on the RFID technology, and the system comprises a tag and image reading module, an error verification and signal decoding module, an execution adjustment and target orientation module, and a performance evaluation and adjustment module. According to the invention, through information reading and error checking mechanisms of the RFID and the camera, the accuracy and efficiency of the express automatic classification system are remarkably improved, after the tag information is read preliminarily, the consistency of the image and the RFID data is checked, classification errors caused by tag damage or information errors are effectively reduced, and when the classification errors are found, the accuracy and efficiency of the express automatic classification system are improved. The system can automatically trigger the re-classification operation, ensures that each parcel is correctly classified, reduces the requirement of manual re-classification, improves the automation level of operation, and can adapt to different operation environments by continuously monitoring the processing speed and the correct rate and optimizing the operation parameters according to the evaluation result; and the stability and reliability of the whole system are improved.
Owner:HUNAN CENTURY BOSI SCIENCE & TRADE CO LTD
Near-infrared nonlinear discrimination method for fruit sorting
ActiveCN119577663AAddress imbalancesImprove generalization abilityNeural learning methodsData setAlgorithm
The invention discloses a near-infrared nonlinear discrimination method for fruit sorting, and relates to the technical field of artificial intelligence, and the training process of a classification discrimination model comprises the steps: obtaining a spectral data set of fruits, carrying out the preprocessing, carrying out the moving smoothing of the preprocessed spectral data set, and carrying out the classification discrimination. Mixing the preprocessed spectral data set with the spectral data set after moving and smoothing to serve as a sample data set; performing random sampling on the sample data set by using a Monte Carlo method so as to divide a training set and a first test set, training the discrimination model based on the training set, obtaining a classification result of random sampling, and performing statistics on a classification error rate of each sample; constructing a sample weight coefficient based on the probability density value corresponding to the chemical value of each sample and the classification error rate of each sample; constructing a non-linear discrimination model by using the sample weight coefficient, and optimizing the non-linear discrimination model; according to the near-infrared nonlinear discrimination method, the accuracy and reliability of fruit sorting are improved.
Owner:HEFEI INSTITUTE OF PHYSICAL SCIENCE CHINESE ACADEMY OF SCIENCES +1
A gesture recognition method based on MPE-YOLOv5
ActiveCN116052266BCharacter and pattern recognitionNeural learning methodsMedicineMisclassification error
A gesture recognition method based on MPE-YOLOv5, belonging to the field of computer vision. This invention solves the problems of low detection accuracy and high classification error rate for small targets in existing lightweight network models. The main technical solutions adopted by the method of the present invention are: Step 1, collecting gesture images and constructing a training dataset based on the collected gesture images; Step 2, building an MPE-YOLOv5 network and training the MPE-YOLOv5 network using the constructed training dataset; Step 3, using the trained MPE-YOLOv5 network to detect a single frame of video image to be detected, and obtaining a gesture target positioning result and classification result in the image to be detected. The method of the present invention can be applied to gesture recognition.
Owner:HARBIN INST OF TECH
A small sample-based target detection method
ActiveCN116071660BInternal combustion piston enginesCharacter and pattern recognitionData setSmall sample
The application discloses a kind of target detection methods based on small sample, comprising the following steps: S1: image acquisition;S2: image pre-processing;S3: construct small sample target detection model;S4: respectively using base class data set and new class data set to small sample target detection model is trained in two stages;S5: the network model obtained using step S4 is tested.This method reduces the dependence of target detection algorithm on a large number of training data, alleviates the problem of difficult data acquisition and high cost of manually labeled data, alleviates the contradiction between different modules that affect each other and reduce performance, improves the detection performance without increasing the training cost;Reduce the detection result error caused by classification error, improve the classification performance of the model.
Owner:GUANGXI NORMAL UNIV
Method and device for realizing financial text business opportunity mining based on large model, processor and computer readable storage medium thereof
The invention relates to a method for realizing financial text business opportunity mining based on a large model. The method comprises the following steps: acquiring basic information of announcement data and news data; carrying out preliminary screening on the announcement type data in combination with the label content according to a regular rule; performing content analysis on the announcement data of which the original text information is in the PDF format to obtain text content; performing label identification on different types of text contents in combination with a business target, and outputting corresponding business opportunity labels; and calling the large model to identify entities mentioned in the text, and extracting the relationship and related business opportunity attribute information according to the context related to the subject. By the adoption of the method and device for achieving financial text business opportunity mining based on the large model, the processor and the computer readable storage medium of the processor, the multi-label processing capacity is enhanced, and the hierarchical label classification error rate is remarkably reduced. The noise robustness is improved, and the anti-interference capability of a resistance sample enhancement model is generated.
Owner:GUOTAI JUNAN SECURITIES CO LTD
Method for establishing a defect detection model and electronic device
ActiveCN115730242BElectrical apparatusTesting/monitoring control systemsMisclassification errorEngineering
A method for establishing a defect detection model and an electronic device. A first classification model is established based on a training sample set, wherein the training sample set includes a plurality of training samples. The training samples are respectively input into the first classification model to obtain respective classification results of the training samples. A plurality of outlier samples with classification errors are obtained from the training samples based on the classification results. Part of the outlier samples with classification errors are deleted from the training samples, and the remaining training samples are used as an optimal sample set. A second classification model is established based on the optimal sample set, so that a defect detection is performed by the second classification model.
Owner:WISTRON CORP
Model training method for embodied intelligence perception, image classification method and device
This application relates to the field of artificial intelligence, providing a model training method, image classification method, and apparatus for embodied intelligent perception. The method includes: constructing a hierarchical input sequence containing global category labels, local category labels, and patch labels; inputting the hierarchical input sequence into a visual Transformer backbone network; combining local mask multi-head attention and Hungarian matching cross-image voting to determine foreground and background local category labels; performing region semantic self-supervised pre-training, triplet conditional feature interaction, and label-level feature enhancement on the visual Transformer backbone network to obtain an image classification model. This application can extract discriminative local region features of targets under small sample conditions and enhance semantic consistency between similar samples, completing the training of the image classification model, thereby reducing background interference and image classification error rate in complex scenes and improving classification accuracy.
Owner:FUDAN UNIVERSITY
Method and system for probably robust classification with detection of adversarial examples
A computer-implemented method for training a machine-learning network includes receiving an input data from a sensor, wherein the input data includes a perturbation, wherein the input data is indicative of image, radar, sonar, or sound information, obtain a worst-case bound on a classification error and loss for perturbed versions of the input data, utilizing at least bounding of one or more hidden layer values, in response to the input data, train a classifier, wherein the classifier includes a plurality of classes, including an additional abstain class, wherein the abstain class is determined in response to at least bounding the input data, outputting a classification in response to the input data, and output a trained classifier configured to detect the additional abstain class in response to the input data classifier with a plurality of classes, including an additional abstain class.
Owner:ROBERT BOSCH GMBH
A table-to-text generation method based on multi-agent collaboration
The application discloses a table-to-text generation method based on multi-agent cooperation, wherein model training includes two stages of supervised fine-tuning and style preference optimization, enhanced training data is constructed through table replacement invariance, PEFT is used for efficiently fine-tuning a large language model, and SimPO algorithm is adopted to generate text conforming to the golden standard style through positive and negative sample comparison learning. Error correction is performed through a multi-agent cooperation mechanism, BERT model is used to encode table data and store in a Faiss vector database, an agent generates text based on a large language model, a retrieval agent constructs a minimum concern table, a verification agent compares unit statements and classifies errors, a scheduling agent triggers an error correction strategy, and numerical values, knowledge loss and table conflicts are accurately corrected. The whole process is iteratively generated and verified to ensure that the generated text is faithful to the facts, the style is consistent and there is no illusion, and the quality and accuracy of table-to-text generation are significantly improved.
Owner:ZHEJIANG UNIV
Guided workflow for deep learning error analysis
A model management system performs error analysis on results predicted by a machine learning model. The model management system identifies an incorrectly classified image outputted from a machine learning model and identifies using the Neural Template Matching (NTM) algorithm, an additional image correlated to the selected image. The system outputs correlated images based on a given image and a selection by a user through a user interface of a region of interest (ROI) of the given image. The region is defined by a bounding polygon input and the correlated images include features correlated to the features within the ROI. The system prompts a task associated with the additional image. The system receives a response that includes an indication that the additional image is incorrectly labeled and including a replacement label and instruct that the machine learning model be retrained using an updated training dataset that includes the replacement label.
Owner:LANDINGAI INC
Image recognition method based on deep reinforcement learning and evolutionary algorithm
ActiveCN116152572BInternal combustion piston enginesNeural architecturesAlgorithmMisclassification error
The application discloses an image recognition method based on deep reinforcement learning and an evolutionary algorithm, and comprises the following steps: S1, collecting image data and performing standard processing on the image; S2, defining an optimization target and an optimization target function; S3, solving a multi-target optimization function F based on deep learning and the evolutionary algorithm; S4, performing optimization training on the model based on the deep learning and the evolutionary algorithm; and S5, classifying image data by using the optimized image recognition model. The application can be applied to image recognition, and the model structure is optimized, so that the image recognition precision is effectively improved, and the image classification error rate is reduced.
Owner:ANHUI UNIV
A Weighted Bayesian Classifier and Ontology Mapping Method for Semantic Ontology
The present invention claims protection for a weight Bayesian classifier and an ontology mapping method for semantic ontology, which comprises the following steps: S1: Parsing the ontology: Parsing the ontology participating in the ontology mapping through the Jena package in Java, extracting concepts, and using the WordNet semantic dictionary to complete the expansion of concepts; S2: Determining weights using the harmony search algorithm: Introducing a dynamic weight mechanism to reduce the impact brought by its assumption of conditional independence of attributes; S3: Constructing a weight Bayesian classifier: Establishing a weight Bayesian classifier through the weights obtained in the previous step, converting the ontology mapping problem into a classification problem, calculating the maximum posterior probability to complete the classification; finally, saving the output classification result into the AllergoGraph database. The present invention adopts the harmony search algorithm, uses the classification error rate as the objective function, calculates the global optimal weight and assigns it to the weighted naive Bayesian classifier; the present invention proposes a new way of generating solutions to improve the optimization ability of the harmony search algorithm.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
System and method for error detection in dental imaging
PCT designated stageWO2025191278A1Image enhancementImage analysisComputer graphics (images)Misclassification error
A system and method for error detection in dental imaging. The method for detecting errors in a dental panoramic image, comprising converting a dental panoramic image into a byte array. Identifying and extracting critical features from the byte array. Generating a plurality of feature map layers. Generating region proposals for potential errors within each feature map layer. Extracting fixed sized features from the region proposals. Classifying features within each region proposal. Regressing bounding boxes around classified error. Outputting the image with bounding boxes indicating errors within the image, and outputting an indication whether image is viable based on the errors.
Owner:VOXEL3DI LTD
Prototype network feature reconstruction and classification method, device and equipment
The application provides a prototype network feature reconstruction and classification method, device and equipment, comprising: obtaining N prototypes of a prototype network; determining the Euclidean distance between the feature vectors of the i-th prototype in any two prototypes is less than a preset threshold; determining the to-be-inserted feature vector in the prototype according to K feature vectors in the two prototypes; inserting the to-be-inserted feature vector into the set position of the two prototypes respectively, reconstructing the feature of the to-be-identified object through the above method, performing three spline interpolations on the two prototypes after feature reconstruction and the feature of the to-be-identified object after reconstruction, and deriving the two prototypes and the feature of the to-be-identified object after three spline interpolations, and determining the category of the to-be-identified object according to the similarity between the derivative of the feature of the to-be-identified object and the derivative of the two prototypes. The problem that the prototypes in the prototype network are too far away from the target and cause classification errors is solved, and the classification accuracy is improved.
Owner:HISENSE GRP HLDG CO LTD
Cross-domain long-tail image classification method based on self-supervised learning and self-training mechanism
The application discloses a cross-domain long-tail image classification method based on self-supervised learning and self-training mechanism, comprising the following steps: firstly, acquiring a dataset of cross-domain long-tail images, and dividing the dataset into a training set and a test set; then, training a double-branch network model by using the cross-domain long-tail image data in the training set; for the unsupervised adaptive branch, using a self-supervised learning and global distribution alignment method for representation learning; for the supervised adaptive branch, self-training and mutual information maximization are performed on the classifier; using a dynamic weighted ensemble training strategy to automatically adjust the learning weights of the two branches, so as to realize the simultaneous optimization of the learning objectives of the two branches; finally, classifying the cross-domain long-tail image data in the test set by using the trained model. The application solves the problem that the existing classification method is prone to cross-domain long-tail image classification errors due to insufficient extraction of image discriminative features, model decision boundary deviation, error accumulation in the self-training process and the like.
Owner:YUNNAN UNIV
A system and a method for analysing log data for operational and security anomalies
PCT designated stageWO2026052997A1Hardware monitoringPlatform integrity maintainanceData integrityMisclassification error
A system (100) for analyzing log data for operational and security anomalies is provided. A preparation module (120) prepares log data by determining the necessary volume, evaluating suitability, and categorizing it. A pattern discovery module (125) identifies structures in the log data using a plurality of methods. A patterned-message structure module ( 130) creates a structured format for each log message and computes hashes for data integrity. A processing module (135) stores and validates the structured logs. A message pattern curation module (140) customizes patterned messages and offers suggestions. A log message grouping module (145) organizes log messages into groups based on patterns and binding variables. An error identification module (150) detects and categorizes errors, highlighting operational and security issues. Finally, a log storage module (155) stores configurations, static log data, and variable content efficiently.
Owner:MANVI ANAND
An intelligent classification control system and method for urban garbage recycling
The present application discloses an intelligent classification control system and method for urban garbage recycling, which belongs to the field of garbage recycling. The present application assigns weights to misclassified garbage based on the error analysis results of the misclassified garbage, performs classification effect analysis based on the weight assignment results of the misclassified garbage, classification data of the garbage classification, and classification accuracy data, and issues classification anomaly warnings based on the obtained classification effect analysis results. The present application accurately identifies classification anomalies by performing comprehensive data analysis on classification errors in the garbage classification process, avoids the influence of image recognition factors on the accuracy of judging classification anomalies, and improves the recognition accuracy and efficiency of classification anomalies.
Owner:JIANGXI YAMAGATA ENVIRONMENTAL PROTECTION ENERGY GRP CO LTD
Method and apparatus for object classification
Owner:SHENZHEN IWIN VISUAL TECH CO LTD
Accurate operation area calculation method and device based on classification-clustering bidirectional feedback
ActiveCN121659011AData processing applicationsClimate change adaptationData setMisclassification error
The invention relates to the technical field of agricultural intellectualization, and discloses a method and a device for accurately calculating an operation area based on classification-clustering bidirectional feedback, and the method comprises the steps: determining target trajectory data generated in an operation process of an agricultural machine; based on the target trajectory data, performing operation state classification processing by using a target classification model to determine a target operation data set of the agricultural machine; wherein the target classification model is determined by performing iterative training on the initial classification model by using suspicious trajectory data in the target trajectory data; and performing area calculation based on the effective land parcel units in the target operation data set to obtain a target operation area of the agricultural machine. The target classification model can continuously learn and correct classification errors by performing iterative training on the initial classification model, so that compared with a single classification model, misjudgment and missed judgment can be effectively reduced, the precision of a final operation area calculation result is remarkably improved, and high-standard application requirements can be met.
Owner:ZHEDA ZHENGCHENG TECH CO LTD