Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

171 results about "AdaBoost" patented technology

AdaBoost, short for Adaptive Boosting, is a machine learning meta-algorithm formulated by Yoav Freund and Robert Schapire, who won the 2003 Gödel Prize for their work. It can be used in conjunction with many other types of learning algorithms to improve performance. The output of the other learning algorithms ('weak learners') is combined into a weighted sum that represents the final output of the boosted classifier. AdaBoost is adaptive in the sense that subsequent weak learners are tweaked in favor of those instances misclassified by previous classifiers. AdaBoost is sensitive to noisy data and outliers. In some problems it can be less susceptible to the overfitting problem than other learning algorithms. The individual learners can be weak, but as long as the performance of each one is slightly better than random guessing, the final model can be proven to converge to a strong learner.

Fault prediction method for multi-modal cross-attention enhancement graph neural network

The invention relates to the technical field of fault prediction, and provides a fault prediction method for a multi-modal cross-attention enhancement graph neural network, and the method comprises the steps: collecting the data of equipment; performing adaptive enhancement and normalization processing on the image data, performing sliding window segmentation, standardization and noise suppression on a time sequence numerical signal, and performing semantic vectorization coding on a maintenance log text; extracting low-dimensional spatial features of image data by using the pruned lightweight convolutional neural network, connecting time sequence features of modeling time sequence numerical signals in series, extracting context semantic expressions of maintenance log texts, integrating the features into multi-modal data, alternately taking each modal feature as Query and the other modal features as Key and Value, and obtaining multi-modal data; calculating attention weight and performing weighted fusion; constructing a modal node weighted graph, and performing inter-node feature propagation through a multi-layer graph attention network; and a residual service life regression prediction module and a degradation level classification module are deployed in parallel, and fault early warning is completed through multi-task joint optimization.
Owner:GUANGDONG UNIV OF TECH

Streaming query semantic map adaptive enhancement method and system based on cognitive calculation

The invention provides a streaming query semantic map adaptive enhancement method and system based on cognitive computing, and relates to the technical field of semantic maps, comprising the steps of computing node affinity through a map attention mechanism, identifying knowledge clusters by using a community discovery algorithm, performing knowledge deduction by taking the knowledge clusters as a basic unit, and predicting and complementing potential semantic relationships. And after multi-agent reinforcement learning optimization verification, outputting an enhanced semantic map and a credibility score table. And deploying the enhanced atlas to an edge network, carrying out parallel semantic understanding and query optimization suggestion generation, integrating optimization suggestions through federal learning, updating the central cognitive model, and distributing the central cognitive model to the edge network. According to the method, the semantic map is enhanced through cognitive calculation, so that more accurate semantic understanding and more efficient query optimization are realized.
Owner:北京科杰科技有限公司

Personalized batch and streaming speech-to-text transcription of audio

Techniques for personalized batch and streaming speech-to-text transcription of audio reduce the error rate of automatic speech recognition (ASR) systems in transcribing rare and out-of-vocabulary words. The techniques achieve personalization of connectionist temporal classification (CT) models by using adaptive boosting to perform biasing at the level of sub-words. In addition to boosting, the techniques encompass a phone alignment network to bias sub-word predictions towards rare long-tail words and out-of-vocabulary words. A technical benefit of the techniques is that the accuracy of speech-to-text transcription of rare and out-of-vocabulary words in a custom vocabulary by automatic speech recognition (ASR) system can be improved without having to train the ASR system on the custom vocabulary. Instead, the techniques allow the same ASR system trained on a base vocabulary to realize the accuracy improvements for different custom vocabularies spanning different domains.
Owner:AMAZON TECH INC

Wind resource assessment report generation method based on large model technology

The invention discloses a wind resource assessment report generation method based on a large model technology. The method comprises the following steps: processing multi-source data, and constructing a domain knowledge base and a fine tuning database; field adaptive RAG enhancement is carried out, professional literatures, historical cases and industry specifications in a field knowledge base are retrieved by adopting a retrieval enhancement generation technology, and wind resource assessment contents meeting technical standards are generated through a multi-modal fusion word vector technology; performing large model fine tuning, and optimizing the generative large model through a gradient-free optimization algorithm Wind-DFO on the basis of a fine tuning database by adopting a field self-adaptive fine tuning strategy; and automatically generating a report, arranging and matching multiple templates through an AI workflow, embedding a data visualization chart, executing verification of a grammar layer, a logic layer and a compliance layer, and outputting a standardized wind resource assessment report. The accuracy, specialty and efficiency of report generation are remarkably improved, and the problems that a traditional method depends on artificial experience, the data utilization efficiency is low, and standardization is insufficient are solved.
Owner:CHONGQING UNIV

Water quality prediction method and system based on gating residual enhancement and feature fusion

The invention relates to a water quality prediction method and system based on gating residual enhancement and feature fusion, and belongs to the technical field of water environment intelligent analysis and deep learning. Taking each water quality index as a node of the graph, and constructing two complementary variable relation graph structures by utilizing a Pearson's correlation coefficient and mutual information; respectively inputting the two graph structures into a graph convolutional network, extracting deep dependency features among indexes, and splicing and fusing the deep dependency features. A multi-head attention mechanism is used as a trunk to extract global time dependence, a GRU network is introduced to extract local time sequence features, GRU output is used as an adjustable residual term to be injected into the attention trunk through a residual gating mechanism, self-adaptive enhancement of local dynamic features is achieved, and finally a self-adaptive fusion mechanism is introduced to generate comprehensive representation. According to the method, the complex dependency relationship between the water quality indexes and the time dynamic evolution process can be modeled in a collaborative manner, the response capability to key local change and sudden change events is remarkably enhanced, and the accuracy and robustness of water quality prediction are improved.
Owner:SHANDONG FENGSHI INFORMATION TECH CO LTD

Pipeline residual strength prediction method and system based on artificial intelligence algorithm

The invention discloses a pipeline residual strength prediction method and system based on an artificial intelligence algorithm, and the method comprises the steps: constructing a CNN-BiLSTM-Adaboost model; the CNN-BiLSTM-Adaboost model comprises a CNN feature extraction module, a BiLSTM time sequence module and an Adaboost optimization module, wherein the CNN feature extraction module is used for extracting features of the corroded pipeline according to parameter data of the corroded pipeline, the BiLSTM time sequence module is used for obtaining a feature time sequence of the corroded pipeline by utilizing a bidirectional LSTM propagation mechanism, and the Adaboost optimization module is used for adjusting sample weights in an iteration process to generate a strong predictor; and during prediction, the residual strength of the pipeline is predicted through the trained CNN-BiLSTM-Adaboost model. The method is high in prediction precision and wide in adaptability.
Owner:NANJING FORESTRY UNIV

Task scheduling and monitoring method for teacher console based on data analysis

The invention relates to the technical field of intelligent teaching, in particular to a teacher console task scheduling and monitoring method based on data analysis, and the method comprises the steps: collecting task execution data, including participation degree, task completion progress and response time, of students, and combining machine learning models such as an adaptive enhancement algorithm, a long-short-term memory network and a random forest; according to the method and the system, personalized task scheduling of students is realized, a real-time data monitoring and dynamic adjustment strategy is adopted, optimal configuration of task difficulty and time length is generated according to student performance data, task risks are identified through a support vector machine model, and multi-level early warning and intervention suggestions are provided. Performing long-term trend analysis and grouping on historical data by using a K-Means clustering algorithm, and supporting a personalized optimization scheme of task allocation; according to the invention, the problem that the task allocation is not matched with the actual learning state of the student in the prior art is effectively solved, the flexibility of task scheduling and the learning effect of the student are improved, and a more accurate and efficient teaching management tool is provided for a teacher.
Owner:CHINESE PEOPLES LIBERATION ARMY NAVAL SPECIALTY MEDICAL CENT

Multi-band high-voltage power supply control system and normalization control and protection method thereof

The invention discloses a multiband high-voltage power supply control system and a normalization control and protection method thereof, and relates to the technical field of power supply control, and the method comprises the steps: collecting multi-mode signals of S, C and Ku band high-voltage power supply systems and a cooling system; an SDAE deep network and an integrated learning AdaBoost framework are combined to construct a fault diagnosis model, and a fault type and confidence are obtained according to signal features; when a fault occurs, high-voltage output of a corresponding power supply unit is cut off and reported through an isolation interface, and a deep reinforcement learning agent is used for carrying out protection action intelligent decision making; a digital twinborn model of a power supply unit is constructed, an improved grey wolf optimizer is used for multi-task collaborative optimization, optimized system parameters are acquired and issued to a PLC for execution, and waveband output stability is ensured. According to the invention, high reliability, rapid response and intelligent operation and maintenance of the multi-band high-voltage power supply system are realized through deep integration of multi-source signal acquisition, intelligent fault diagnosis, adaptive protection decision and digital twinning optimization.
Owner:合肥博雷电气有限公司

Experimental platform and method for applying multi-modal large model digital circuit and medium

The invention relates to the field of digital circuit experiment teaching, in particular to a digital circuit experiment platform and method applying a multi-modal large model and a medium, and the method comprises the steps: inputting experiment task description, analyzing and extracting structured semantic information, and forming task representation; retrieving a circuit function block from the electronic component knowledge base, constructing a context enhancement cue word, guiding a multi-modal large language model to generate a Verilog HDL code, and outputting the Verilog HDL code after grammar check and function verification; a Yosys tool is used for carrying out logic synthesis on the codes to generate a standard JSON netlist, and then the standard JSON netlist is converted into an SVG-format circuit diagram through a Netlistsvg tool; and an electronic component knowledge base updating mechanism is constructed to realize knowledge cyclic evolution and adaptive enhancement, so that the intelligent level and practical training efficiency of circuit experiment teaching are remarkably improved.
Owner:JIEYANG VOCATIONAL & TECH COLLEGE

Multi-modal sentiment analysis method and system based on main modal two-stage guidance

The invention provides a multi-modal sentiment analysis method and system based on main modal two-stage guidance, and relates to the technical field of sentiment analysis. Inputting the multi-modal data into a multi-modal sentiment analysis model, and extracting language, visual and acoustic features from the multi-modal data through a feature extraction module; semantically decoupling the multi-modal features into modal invariant features and modal unique features through a feature space distribution alignment module, and realizing feature distribution alignment dominated by language modals through alignment reconstruction constraints; performing self-attention modeling on the modal invariant feature through an attention enhancement module to obtain a first enhanced feature, and adaptively enhancing the visual and acoustic unique features through a cross-modal attention mechanism by taking the language unique feature as a dominant feature to obtain a second enhanced feature; the first enhanced feature and the second enhanced feature are fused through the emotion prediction module, an emotion intensity prediction result is obtained through regression prediction, and the accuracy and robustness of emotion analysis in a complex scene are improved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

Authority hierarchical control method based on dynamic desensitization and real-time monitoring and operation and maintenance bastion host system

The embodiment of the invention discloses an authority hierarchical control method based on dynamic desensitization and real-time monitoring and an operation and maintenance bastion host system.According to the embodiment of the invention, by integrating a database firewall and a dual-mode desensitization engine and combining authority hierarchical control and real-time semantic analysis, the data security and operation compliance in an operation and maintenance scene are remarkably improved, and the operation and maintenance security is improved. The dynamic desensitization rewrites a query statement in real time according to a user role, and limits exposure of original data; static desensitization is performed to pre-generate an isolated copy, so that direct access to a production library is reduced; based on semantic analysis and a rule engine, the response time is shortened to be within 1 second; the static desensitization library supports direct use of development and testing, and the permission application process is reduced; a rule base is dynamically updated through an Attention-GRU-Adaboost model, and the adaptability to a novel attack mode is improved.
Owner:CENTURY LONGMAI TECH

Remote sensing time-space spectrum fusion method for water body chlorophyll concentration inversion

The invention belongs to the technical field of remote sensing information processing, and particularly relates to a water chlorophyll a concentration inversion-oriented remote sensing time-space-spectrum fusion method, which realizes improvement of spatial resolution of a chlorophyll a concentration inversion sensitive wave band by fusing complementary information of different sensors on time-space-spectrum resolution. The method comprises the following steps of: establishing a water body chlorophyll a concentration inversion-oriented MSI and OLCI space-time spectrum fusion deep learning network, embedding a time sequence dynamic adjustment module, and establishing a water body chlorophyll a concentration inversion-oriented MSI and OLCI space-time spectrum fusion deep learning network for water body chlorophyll a concentration inversion. According to the method, the network can intelligently combine time and space features to generate a more accurate prediction image, an Adaboost machine learning joint inversion model is constructed based on time-space-spectrum fusion data and corresponding limited ground station data, and high-precision remote sensing inversion of the concentration of chlorophyll a is realized.
Owner:ANHUI UNIV +1

Diffusion-driven channel adaptive point cloud semantic communication method

The invention provides a diffusion-driven channel adaptive point cloud semantic communication method, which belongs to the technical field of wireless communication, and comprises the following steps: obtaining a training point cloud data set, constructing a point cloud feature extraction network based on a hypergraph convolutional neural network as a semantic encoder, and constructing a channel adaptive enhancement module as a channel decoder, a channel adaptive recovery module is constructed at a receiving end as a channel decoder, a diffusion reconstruction network is constructed as a semantic decoder, end-to-end joint training is performed on the point cloud feature extraction network, the channel adaptive enhancement module, the channel adaptive recovery module and the diffusion reconstruction network, the diffusion reconstruction network predicts original point cloud distribution, and the point cloud feature extraction network and the channel adaptive enhancement module are subjected to end-to-end joint training. And a loss function is constructed based on the chamfering distance between the predicted point cloud distribution and the original point cloud. In the communication process, the reconstructed semantic features are input into the diffusion reconstruction network to reconstruct an original point cloud structure. The high-order semantic features of the point cloud can be effectively extracted so as to improve the adaptive capacity of the method to the incomplete point cloud.
Owner:南宁桂电电子科技研究院有限公司 +1

Adaptive enhanced staged graph representation learning method based on citation information

The invention relates to the technical field of data processing, and provides an adaptive enhancement staged graph representation learning method based on quotation information, which adopts a data enhancement method and comprises a topological structure level adaptive enhancement method, which comprises the following steps: calculating the centrality of an edge based on a node centrality measurement function, generating a first sampling probability through a truncation probability, and generating a second sampling probability through a truncation probability; taking the first sampling probability as an edge deletion probability, and reserving the topological structure based on the edge deletion probability; the node attribute level adaptive enhancement method comprises the following steps: respectively calculating a corresponding first weight and a corresponding second weight based on discrete node features and continuous node features; and generating a second sampling probability through the truncation probability, taking the second sampling probability as a feature shielding probability, and retaining the feature dimension based on the feature shielding probability. According to the method, topological structure level adaptive enhancement and node attribute level adaptive enhancement are introduced on the basis of the GRLWPT to produce the comparison graph, so that the accuracy in a node classification task and the robustness of an algorithm are improved.
Owner:SSE INFORMATION NETWORK LTD

Improved Adaboost-based single-three-phase series-parallel micro-grid group island detection method

ActiveCN119128454AFully understand the operation statusimprove accuracyData processing applicationsBiological modelsMicrogridAlgorithm
The invention discloses a single three-phase series-parallel micro-grid group island detection method based on improved Adaboost, and the method comprises the following steps: collecting sample data of different electrical characteristic quantities in a single three-phase series-parallel micro-grid group, which are measured at a point of common coupling (PCC); based on partial least squares (PLS), correlation analysis is carried out on various electrical characteristic quantities measured at a common coupling point, strong correlation electrical characteristic quantities are screened out, and a training set and a test set are formed; according to the method, an Adaboost learning device is improved on the basis of a mucus optimization algorithm (SMA) and a GSN weight learning mode, so that the classification capability is improved, the disturbance influence is weakened, and the detection time consumption is shortened. And constructing an island detection model of the microgrid group based on the improved Adaboost learner, and outputting an island detection result according to the real-time test set data at the PCC. According to the method, accurate island detection can be carried out without being affected by disturbance signals and the three-phase unbalance degree of the system, and the method has high anti-interference performance, accuracy and generalization ability.
Owner:CHINA THREE GORGES UNIV

CART-integrated Adaboost photovoltaic power generation power prediction method, readable storage medium and equipment

The invention discloses a CART-integrated Adaboost photovoltaic power generation power prediction method, a readable storage medium and equipment, and relates to the technical field of photovoltaic power generation power prediction. Firstly, historical data of photovoltaic power generation needs to be collected, then effective photovoltaic power generation data are obtained through data cleaning, and then key parameters influencing power generation power are determined through Spearman rank correlation coefficients. And constructing a photovoltaic power generation standardized database, dividing a data set, and constructing an AdaBoost photovoltaic power generation power prediction model integrated with CART by using a training set. And inputting the test set into the trained model, and testing and evaluating the model. And finally predicting the photovoltaic power generation power by using the model. According to the method, rapid and accurate prediction of the photovoltaic power generation power can be realized, and reliable reference is provided for power grid dispatching and management of photovoltaic power generation utilization.
Owner:POWERCHINA BEIJING ENG CORP

Annular DC micro-grid fault positioning method based on local data driving

The invention relates to an annular DC micro-grid fault positioning method based on local data driving, and provides an accurate positioning method based on local fault data driving aiming at the fault positioning problem under the characteristics of few fault samples and weak positive current so as to provide a basis for maintenance work after fault isolation. In order to solve the problem of insufficient fault samples, a fault data enhancement method based on an attention mechanism and a gated circulation unit neural network is provided, and training data required by intelligent fault positioning is expanded by predicting fault voltage and current dynamics after fault isolation. In order to solve the problems of high resistance and negative grounding fault positioning caused by weak positive current characteristics, a fault positioning method combining discrete wavelet transform, an extreme learning machine and an adaptive enhancement algorithm is provided, implicit fault position information is extracted and learned from a fault sample with weak characteristics, and the line fault positioning precision is improved.
Owner:CENT SOUTH UNIV

Method for predicting performance parameters of oil-based drilling fluid

The invention discloses an oil-based drilling fluid performance parameter prediction method, and relates to the technical field of oil-gas field development. According to the method, firstly, multiple training sets are obtained, each training set comprises a drilling fluid formula and temperature which serve as input and drilling fluid performance parameters which serve as output, then the training sets are used for training an Adaboost-BP prediction model, and the trained model can be used for prediction; the Adaboost-BP prediction model takes a three-layer BP neural network as a sub-model, and meanwhile, a feature enhancement-fusion module is arranged on a hidden layer of the sub-model. According to the method, multiple key indexes of the oil-based drilling fluid can be predicted at a time, and compared with a traditional method, the prediction efficiency is improved, and the application range is widened.
Owner:SOUTHWEST PETROLEUM UNIV

Deep-buried TBM rock machine parameter fusion prediction method and system based on CNN-LSTM-Adaboost model

The invention discloses a deep-buried TBM rock machine parameter fusion prediction method and system based on a CNN-LSTM-Adaboost model, and belongs to the field of intelligent data algorithms, and the method comprises the steps: S1, building an initial CNN-LSTM-Adaboost surrounding rock grade prediction model; s2, establishing an evaluation index and effect index model; s3, optimizing the model; s4, predicting tunneling parameters under different surrounding rock grades by using the optimized model; and S5, outputting a prediction result. The model provided by the invention combines the LSTM model and the CNN model, and can cope with relatively complex stratum conditions. The CNN-LSTM model overcomes the problems that the LSTM is poor in space processing capability and the CNN is insensitive to a time sequence. Compared with the single use of LSTM or CNN, the prediction accuracy of the model is improved by 10%; the prediction relative error rate of the data is within 10%, the root mean square error is within 5, the average absolute percentage error value is within 10%, and the goodness of fit value is 0.9 or above; according to the model, the recognition accuracy of the tunnel surrounding rock grade based on the tunneling parameters is high, and the comprehensive accuracy reaches 90%.
Owner:YANKUANG ENERGY GRP CO LTD +1

Fine-grained feature matching vehicle re-identification method for license plate shielding scene

The invention discloses a fine-grained feature matching vehicle re-identification method for a license plate shielding scene, and the method comprises a vehicle detection stage based on illumination perception and adaptive prediction, and a fine-grained Transform feature matching stage based on implicit semantic prototype perception. Comprising an illumination sensing module and an adaptive prediction module. The illumination sensing module is used for realizing image adaptive enhancement under different illumination conditions; the adaptive prediction module suppresses a redundant prediction frame through a self-attention weight mechanism; in the fine-grained Transform feature matching stage based on implicit semantic prototype perception, an implicit semantic prototype learning module and a fine-grained Transform matching module are included; the implicit semantic prototype learning module unsupervised decouples vehicle structural components through a group of learnable semantic prototypes to generate a soft semantic distribution diagram; and the fine-grained Transform matching module is used for introducing semantic affinity bias in cross attention. According to the method, the accuracy and stability of vehicle detection and identity matching in a complex environment can be improved.
Owner:CHINA UNIV OF MINING & TECH

Method and device for generating high-dimensional security boundary of power system adaptive to online state

The invention discloses a power system high-dimensional security boundary generation method and device adaptive to an online state, and the method comprises the steps: carrying out the calculation through a historical data driving strategy and a least square fitting strategy, obtaining a low-dimensional security boundary of a set branch of a whole network, and generating a security boundary set; an AdaBoost.M2 classifier is trained through historical data and the security boundary set, and an out-of-limit risk prediction model is generated; inputting a set online operation state into the out-of-limit risk prediction model for prediction processing, and outputting a possible out-of-limit boundary and a corresponding out-of-limit risk value; and inputting the possible out-of-limit boundary and the corresponding out-of-limit risk value into a generative adversarial network for training processing, and outputting a comprehensive high-dimensional security boundary. According to the method, the high-dimensional security boundary generation efficiency can be greatly improved on the premise of ensuring the accuracy, and efficient and reliable technical support is provided for real-time monitoring, scheduling and decision making of a power grid.
Owner:TIANJIN UNIV

Landslide susceptibility evaluation method based on category type feature improvement

The invention provides a landslide susceptibility evaluation method based on category-type feature improvement, and belongs to the field of landslide prediction.The method comprises the steps that obtained various types of data of a landslide disaster research area are preprocessed, evaluation factor original values corresponding to landslide points are exported, an original data set is obtained, a category-type feature improvement algorithm is trained, and a landslide susceptibility evaluation result is obtained; performing grid search to obtain a category-type feature improvement algorithm with optimal parameters, and performing adaptive enhancement integration by using the adaptive enhancement model as a meta-learner and using the category-type feature improvement algorithm with the optimal parameters as a base learner to obtain an integrated model; substituting the training set into the integrated model to perform training simulation, importing the grid points into the trained integrated model to perform landslide disaster susceptibility evaluation, and outputting a landslide disaster susceptibility prediction map; according to the method, the problems of low adaptability of existing different machine learning models to complex data and low accuracy of susceptibility evaluation are solved.
Owner:TIBET UNIV

Customer carbon footprint prediction method based on electric energy supply and demand prediction and electric power transaction contract

The invention is suitable for the technical field of carbon emission, and provides a customer carbon footprint prediction method based on electric energy supply and demand prediction and a power transaction contract, and the method comprises the following steps: collecting historical data, training an LSTM-AdaBoost neural network model based on the historical data, and carrying out the prediction of the output of a new energy station and the load of a power distribution and utilization user. Future weather forecast parameters are collected, and the LSTM-AdaBoost neural network model is used to predict the output of the new energy station and the load of the power distribution and utilization user in the future; based on the power transaction contract and the transaction curve, power generation side output and power distribution and utilization client load matching is carried out; and based on the thermal power generating unit carbon emission factor data, carrying out future carbon footprint change trend prediction on the power distribution and utilization clients. According to the method, the change trend prediction of the power consumption carbon footprint of the power distribution and utilization clients in the future one week is realized, enterprises can be guided to preferentially consume new energy for power generation, and power carbon demand response is developed through scientific production arrangement and power utilization behavior optimization.
Owner:内蒙古电力(集团)有限责任公司电能计量分公司

LLM-based emotion classification method and device, electronic equipment and medium

The invention provides an LLMs-based emotion classification method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence. The LLM-based sentiment classification method comprises the following steps: constructing a basic learner of an adaptive enhancement algorithm by using a target LLM set, and initializing initial weight distribution of a training sample; according to the training sample and the initial weight distribution, a basic learning device is finely adjusted to obtain a first weak classifier, and the basic learning device is trained into a second weak classifier according to the error rate and the weight coefficient of the first weak classifier; on the basis of the error rate and the weight coefficient of the second weak classifier, continuously iterating the weight distribution of the training sample, and integrating the weak classifiers into a strong classifier; and based on a to-be-classified text, obtaining a text sentiment category through the strong classifier. Through the technical scheme provided by the invention, the problem of low accuracy when a large model recognizes the emotion category of the text is solved, and the recognition accuracy of the emotion category of the text is improved.
Owner:CHINA MOBILE COMM CORP TIANJIN +1

Sintering furnace temperature control method and system based on BP neural network prediction model

The invention provides a sintering furnace temperature control method and system based on a BP neural network prediction model, and the method comprises the steps: constructing an initial model of a BP neural network based on Adaboost, and training a prediction model through test data and the initial model; the test data comprises the sintering furnace temperature and power of the test sintering target; and on the basis of the prediction model, according to the sintering temperature curve of the target needing to be sintered, the heating power needed by the sintering furnace is predicted and adjusted in real time. According to the sintering furnace temperature control method and system based on the BP neural network prediction model, the Adaboost-based BP neural network is trained by using the test data to obtain the prediction model, and the heating power required by the sintering furnace is predicted according to the sintering temperature curve of the required sintering target and is adjusted in real time; the heating process of the sintering furnace is more timely and more linear, the anti-interference capability is higher, further, the product stability of sintered products is improved, and the defective rate of the products is reduced.
Owner:YANCHENG INST OF TECH

Two-dimensional code image classification method based on double-domain contrast learning and sample adaptive enhancement

The invention relates to a two-dimensional code image classification method based on double-domain contrast learning and sample adaptive enhancement, and belongs to the field of semi-supervised image classification. According to the method, a double-domain contrast learning module (Freq-MOCO) is designed. The module carries out comparative learning in parallel in a feature domain and a frequency domain, the feature domain learning mainly focuses on spatial features of images, and the frequency domain learning focuses on spectrum features and global structure information. Besides, a sample adaptive enhancement module (SAA) is also designed, and the learning effect of the samples is further improved by identifying the simple samples and performing more diversified enhancement on the simple samples. The SAA module selects a simple sample by using historical loss information, and applies a richer enhancement strategy to the simple sample, so as to ensure that the sample which cannot effectively promote model learning originally can generate positive influence on model training through diversified enhancement modes. The algorithm provided by the invention has better performance than several recent algorithms.
Owner:MINJIANG UNIVERSITY

Credit scoring model modeling method based on transfer learning

The invention discloses a credit scoring model modeling method based on transfer learning, and the method comprises the steps: a data collection stage: dividing a sample into a source domain and a target domain, and dividing the sample of the target domain into a training set and a test set; in the data preprocessing stage, special values and abnormal values are removed, initial weights are given to samples, linearization based on the evidence weight (WOE) is carried out on variables, and then variables suitable for model entering are screened according to the distinguishing capacity of the variables for good and bad samples and correlation between the variables; in the model iteration stage, based on the improved migration adaptive enhancement algorithm (TrAdaBoost.R2) aiming at the regression problem as a basic framework, a generalized linear model is adopted as a reference model, and repeated iteration is carried out on the weight and the model; in the iteration stopping stage, whether iteration is stopped or not is judged based on the model loss function and the expression trend of the model loss function on the test set. According to the method, credit scoring model modeling based on small samples is realized, and the speed of model iteration is greatly improved.
Owner:BANK OF JIANGSU CO LTD

Prediction modeling method of multi-source migration adaptive enhancement network

The invention relates to a prediction modeling method of a multi-source migration adaptive enhancement network, which comprises the following steps of: source domain modeling: after samples of a multi-source domain and a target domain are respectively subjected to deep migration learning based on confrontation, extracting consistency information of the multi-source domain, and inputting the information into a domain discriminator to distinguish whether data is from the source domain or the target domain; inputting the source domain features into a nonlinear regression device to complete a source domain prediction task; simultaneously training an adversarial-based deep transfer learning network, a domain discriminator and a nonlinear regression device based on a domain discrimination error and a regression prediction error, and stopping training when the domain discriminator cannot correctly divide received data into source domain features or target domain features and the nonlinear regression device can predict source domain data; and target domain prediction: performing prediction by using the prediction network trained by the source domain and inputting new information of the target domain, performing transfer learning on data of each source domain, constructing a multi-source transfer prediction model, and better performing accurate prediction by using low-value density data.
Owner:GUANGXI UNIV

Method for rapidly predicting particle rotation of hydrocyclone based on data driving

The invention relates to a method for rapidly predicting particle rotation of a cyclone based on data driving, which comprises the following steps of: carrying out CFD numerical simulation through an Euler-Lagrange coupling model, combining PIV (particle image velocimetry) measurement and high-speed camera experiment data, and dynamically fusing multi-source data by adopting Kalman filtering to construct a mixed data set; in the feature engineering stage, thousand-dimensional flow field data are compressed to 50-dimensional through PCA dimension reduction and an auto-encoder, and key physical quantities such as centrifugal acceleration, shear stress and vorticity are weighted and fused. A multi-model collaborative prediction system (BP / XGBoost / CATBoost / RF / AdaBoost / SVM) is innovatively constructed, and algorithm advantage complementation is realized through dynamic weight fusion (error reciprocal distribution + abnormal weight drop). Classified hyper-parameter optimization (Bayesian optimization tree model depth / learning rate, grid search SVM kernel parameters) is adopted, TensorRT quantization (FP16) and ONNX conversion are combined, and the inference speed of embedded deployment reaches 48 ms. And the prediction result drives the PID controller to accurately adjust the inlet flow in real time. And through data-driven modeling and interpretability analysis, an efficient solution is provided for cyclone optimization control.
Owner:EAST CHINA UNIV OF SCI & TECH

Railway accident type prediction method based on KNN and AdaBoost

The present invention discloses a railway accident type prediction method based on KNN and AdaBoost. Specifically, the method involves calculating the sparsity of attributes in a railway accident history data set and deleting some attribute columns based on a sparsity threshold; encoding character data in the railway accident data; using the KNN algorithm to fill missing values ​​in the railway accident data; normalizing the railway accident data and randomly dividing the normalized data into a training set and a test set; constructing a railway accident type prediction classifier using the AdaBoost method, and testing the classifier performance on the test set. The method disclosed in the present invention effectively preprocesses the railway accident data and uses the ensemble learning method AdaBoost to alleviate the class imbalance problem of the original data, thereby improving the performance of accident type prediction.
Owner:XIAN UNIV OF TECH