259 results about "Overfitting" patented technology

The invention provides a preference alignment optimization method based on reward-driven selective punishment, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining intelligent question and answer training data, and constructing an intelligent question and answer training sample set which comprises a plurality of intelligent question and answer training samples; taking a to-be-optimized large language model as a strategy model and a reference model; and training the strategy model by using the intelligent question and answer training sample set, and measuring the offset amplitude of the strategy model before and after training by using the reference model to obtain an optimized large language model. According to the method, implicit reward signals in the model are introduced, preference data are divided into multiple categories according to implicit reward distribution generated by the model, a dynamic weight function is designed, differential weighted optimization is carried out on different categories of samples, reinforcement learning of high-quality samples and suppression of low-quality samples are achieved, and the method has the advantages of being high in robustness and high in robustness. Weight of low-quality or conflict samples is reduced while high-quality sample learning is enhanced, noise interference is suppressed, and overfitting is prevented.

The invention discloses a data deep learning and intelligent analysis method based on an AI artificial intelligence technology, and relates to the technical field of basic AI models, and the method comprises the steps: employing a multi-modal data preprocessing module to carry out the expansion of small sample data through a generative model, and combining with meta-learning to extract prototype features, meanwhile, an epsilon-differential privacy budget is dynamically allocated based on the data sensitivity level so as to inject dynamic noise; establishing a layered federated learning architecture, training a model by local training nodes through a loss function containing a self-adaptive regularization item, and performing sparse processing and gradient disturbance before uploading parameters; the global aggregation node adopts a weighted federated average algorithm to aggregate parameters, and dynamically adjusts the communication frequency according to the loss convergence speed; and a target model is obtained through iterative training, and a decision interpretation report containing the attention thermodynamic diagram and the desensitization identifier is generated when a result is output. According to the method, the problems of small sample overfitting, data islands and privacy disclosure are effectively solved, and the accuracy and practicability of the model are improved.

The invention discloses a corroded oil and gas pipeline residual strength prediction method considering a physical constraint loss function, and the method comprises the steps: collecting multi-source feature data of a corroded oil and gas pipeline, obtaining a residual strength measured value as a label, and constructing a training data set; an XGBoost regression model is combined with an SHAP interpretability analysis technology, and the influence degree and the influence direction of each feature on the residual intensity are quantified; constructing a neural network model, and determining an optimal architecture of a neural network by adopting a hyper-parameter optimization method; constructing a physical constraint term based on the influence degree and the influence direction of each feature, introducing the physical constraint term into a loss function of a neural network model, and forming a comprehensive loss function together with a data-driven loss term; and training the optimized neural network model by using a comprehensive loss function to obtain a final residual intensity prediction model. The method has the advantages that the prediction precision is improved, the model interpretability is enhanced, overfitting is prevented, and multi-source feature data are effectively integrated.

The invention relates to the technical field of program repair, in particular to an executable invariant and differential signal combined automatic program repair method, which comprises the following steps of: receiving a to-be-repaired program and a test set, and calling a large language model to generate a plurality of candidate patches; forming an entry behavior specification list according to the repair intention description; generating a plurality of executable invariant assertions and injecting the executable invariant assertions into the target function or the calling point, and generating an invariant assertion injection record table; generating a test case covering the boundary condition and the abnormal scene based on the large language model; collecting an execution signal when the candidate patch is operated; converting the patch difference into semantic editing features, calculating an editing stability index, and calculating an overall semantic consistency score of the candidate patches according to the support degree of the standard bar; and calculating an overall comprehensive score of the candidate patches, and outputting an optimal patch according to the overall comprehensive score of the candidate patches. According to the method, the proportion of overfitting patches can be effectively reduced, the patch repairing accuracy is improved, the interpretability is high, and the universality is good.

The invention discloses a three-dimensional magnetotelluric deep learning inversion method, and relates to the technical field of three-dimensional magnetotelluric inversion in electromagnetic exploration, and the method comprises the steps: constructing a three-dimensional layered underground resistivity theoretical model, and forming a sample pair through the structure data of the underground resistivity theoretical model and the corresponding visual parameter data; the method comprises the following steps: constructing a three-dimensional neural network based on a Swin Transform module and jump connection; a forward modeling sub-network is trained for the multiple visual parameters, and the weight of the forward modeling sub-network is frozen to serve as a fixed forward modeling operator, so that rapid forward modeling is achieved; after each fixed forward operator is migrated and spliced to the inversion sub-network, each fixed forward operator is used as an additional loss constraint term, and physical driving of neural network simulation is realized; and end-to-end mapping from each apparent parameter to the underground resistivity is established by fitting the inversion sub-network, and quasi-physics and data dual-drive three-dimensional magnetotelluric deep learning inversion is realized. The three-dimensional magnetotelluric inversion method has high practical value and popularization value in the technical field of three-dimensional magnetotelluric inversion with crossing of deep learning and electromagnetic exploration.

The invention relates to the technical field of data processing, in particular to a BN-based UHPC mix proportion data analysis method and a strength prediction system.The intelligent level of ultra-high performance concrete mix proportion design is improved by introducing a Bayesian network model and a multi-objective optimization algorithm, and the method comprises the steps that firstly, an enhanced feature set is generated through feature engineering; a nonlinear relationship and a cross-level interaction effect among material parameters are fully excavated, and the characterization capability of the model on a complex material system is enhanced; secondly, the Bayesian network model is combined with causal reasoning and a hierarchical regularization strategy, so that the overfitting risk is reduced while the compressive strength prediction precision is ensured; in the multi-objective optimization link, through dynamic weight adjustment and Pareto frontier search, carbon emission and strength requirements are effectively balanced, and candidate schemes with low carbon and excellent mechanical properties are output; and finally, dynamic evaluation and risk analysis are carried out to further screen out a mix proportion with high stability and strong feasibility, and a reliable decision basis is provided for engineering practice.

The invention belongs to the technical field of communication, and particularly relates to a multipath channel DOA estimation method based on a heterogeneous attention double-branch neural network, and the method comprises the steps: constructing a training set, a verification set and a test set through stratified sampling; introducing a multi-head attention mechanism to construct a heterogeneous attention double-branch neural network for realizing intelligent DOA estimation; designing a frequency weighted loss function as a loss function of neural network model training; a dynamic attention mechanism and an early stop mechanism are designed in a model training process to prevent an overfitting phenomenon. According to the method, the problem of serious DOA estimation model overfitting in a small sample and data non-uniform real acquisition data scene is effectively relieved, and the DOA estimation accuracy is improved.

The invention relates to the field of fault diagnosis methods, in particular to a fault diagnosis method based on multi-modal deep learning, and the method comprises the specific steps: S1, carrying out the processing of an original vibration signal of a bearing through continuous wavelet transform, and converting the original vibration signal into a time-frequency image; s2, constructing a multi-scale Mamba network model, and capturing a long-term dependency relationship in the time sequence data; s3, constructing a high-efficiency network model for extracting time-frequency features; s4, introducing a cross attention mechanism, and dynamically splicing the two modal features; and S5, verifying by using an MEF-Net model, and comparing the performance of the MEF-Net model with other reference models, thereby solving the problems that the integrity, accuracy and reliability of data are influenced due to the introduction of noise in the data acquisition process at the present stage, and the accuracy, accuracy and reliability of the data are influenced due to the inaccuracy, gradient disappearance, overfitting and the like of the data. Therefore, the problems of poor model training effect and low accuracy are solved.

The invention discloses a sand permeability coefficient prediction method based on Bayes and a physical information neural network, which comprises the following steps: constructing a physical-data hybrid driven enhanced data set which comprises actually measured anchor point data and physical enhanced data generated based on a seepage physical mechanism; constructing a dual-channel feature decoupling fusion neural network, extracting gradation morphological features and soil compaction features through a particle size channel and a structure channel, and performing fusion in a deep layer; introducing a multi-physical constraint embedding mechanism and a physical constraint activation layer, constructing a total loss function, and performing posterior inference on network parameters through an HMC algorithm to obtain a parameter sample set; and performing permeability coefficient prediction based on the parameter sample set. According to the method, the problem of overfitting caused by small samples in geotechnical engineering is effectively solved through a two-channel architecture and a data enhancement strategy, generation of non-physical prediction values is avoided through two aspects of network architecture and physical loss embedding, cooperation of high-precision prediction and uncertainty quantification is realized, and engineering adaptability is greatly improved.

The invention provides a hydrological flow long sequence prediction method and system of an improved state space model. The method comprises the steps of collecting multi-source data of a drainage basin to be predicted; constructing a time sequence sample pair by the processed multi-source data through a sliding window method, wherein the time sequence sample pair comprises an input sequence and a target sequence; a HydroMama model is constructed according to the time sequence sample pair, a HydroMama prediction model is trained, and an optimal hyper-parameter combination is searched for; based on the trained HydroMama model, traffic prediction and result restoration are realized by adopting an autoregression mechanism; the calculation efficiency is high, and the continuous state equation discretization of the state space model is utilized, so that the long-distance meteorological-hydrological hysteresis effect which is difficult to capture by a traditional cycle model can be captured; according to the method, skewed distribution of hydrological data is processed through logarithmic transformation, and an anti-overfitting objective function is combined, so that the prediction performance of the model on unseen data is remarkably improved, and the practical application value is high.

The invention discloses a discrete element simulation method for slope unstable seepage, effectively solves the problem of nonlinear flow simulation distortion caused by excessive simplification of a traditional seepage model, and improves the calculation precision of transient processes such as rainstorm infiltration. The dynamic porosity feedback mechanism can reflect the influence of the internal structure change of the slope on the seepage field in real time, and more reliable pore water pressure prediction data is provided for landslide early warning. The establishment of a multi-scale coupling framework provides a new technical approach for unstable seepage analysis under complex geological conditions, a physical information neural network effectively avoids the overfitting risk of a pure data driven model, and an improved multi-objective optimization algorithm can quickly position an optimal parameter combination under complex constraint conditions. A dynamic updating mechanism can automatically adjust model parameters according to slope state changes, and the timeliness and accuracy of landslide early warning under the unstable seepage condition are remarkably improved.

The invention belongs to the technical field of financial science and technology, and discloses a multi-agent collaborative document-driven quantitative research and transaction self-evolution system and method. The system adopts a layered architecture, comprises a data and factor service layer, an execution engine layer, an agent layer, an interface service layer and a front-end control layer, and aims to solve the core problems that research and engineering implementation are separated in quantitative strategy research and development, code generation lacks interface constraints and strategies lack self-evolution ability. According to the system, through cooperative work of a research agent, a factor agent and a coding agent, a strategy idea described by a natural language is automatically converted into a standardized document, configuration and executable code; through a closed loop formed by self-monitoring, self-diagnosis and self-improvement intelligent agents, automatic diagnosis and optimization of problems of strategy overfitting, factor attenuation and the like are realized, continuous self-evolution of the strategy is driven, and full-life-cycle automatic management from strategy conception, factor design, automatic coding and real disk back-testing to feedback autonomous optimization is realized.

The invention discloses a GNN-MAPPO task unloading method based on dominant value noise addition, which is characterized in that an MLP is changed into a GNN on the basis of the existing MAPPO framework, a multi-agent system can be directly modeled into a graph structure, an interaction relationship among multiple agents can be better established, Gaussian noise is added on the dominant value, the exploration capability of a model is enhanced, and overfitting is reduced. According to the method, the powerful graph structure learning ability of GNN is combined with an innovative dominant value noise adding mechanism, and the mixed reward function is elaborately designed, so that the MAPPO algorithm can more effectively learn a cooperation strategy between agents and optimize time delay and energy consumption in the aspect of edge computing task unloading, and the efficiency of the MAPPO algorithm is improved. And the exploration capability of the strategy and the avoidance capability of the communication risk can be obviously enhanced, so that a more robust and efficient intelligent task unloading scheme adapting to a dynamic environment can be obtained.

The invention discloses an expressway differential settlement prediction and regulation system based on machine learning, and belongs to the technical field of intelligent traffic infrastructure construction and maintenance. According to the system, a closed-loop system including multi-source data fusion acquisition, spatial-temporal characteristic engineering, physical constraint spatial-temporal diagram network prediction, reinforcement learning reverse regulation and control and visual decision early warning is constructed for solving the problem of differential settlement control in alluvial plain deep and thick soft soil area highway reconstruction and extension projects. According to the system, Biot consolidation theory constraints are embedded in a geological weighted graph network, so that the problems of over-fitting and physical consistency deficiency of a pure data driven model under complex geological conditions are effectively solved; meanwhile, the reinforcement learning strategy network is used for replacing artificial experience, and global optimization regulation and control of construction parameters are achieved on the premise that the differential settlement control requirement is met. The method is mainly used for precise settlement prediction and intelligent construction management of highway reconstruction and extension projects.

The invention provides a scenarized abnormal behavior classification method and system, equipment and a storage medium, radar features are migrated to generate images and six-axis cross-modal features through a feature mapping technology, the problem of insufficient multi-modal training data is effectively solved, the training sample scale is expanded, associated knowledge of radar and other modals is constructed, and the classification efficiency is improved. Model training data are richer, feature representation is more comprehensive, and model overfitting caused by single modal data is avoided. With the help of a multi-level knowledge distillation composite loss function, a scenarized radar student model accurately learns multi-modal decision knowledge (including probability distribution, key feature attention weight and feature contribution degree) of an expert model through collaborative constraints of distillation loss, attention loss, attribution loss and classification loss; the multi-modal classification capability can be reproduced only by inputting scene radar data, and the defect of radar single-modal information is made up.

The invention discloses an intelligent avalanche susceptibility assessment method fused with a deep residual network, and relates to the technical field of geological disaster risk assessment. According to the method, the spatial precision is high, the 12.5 m high-resolution DEM and 10 multi-source evaluation factors are adopted, the influence of the microtopography on the stability of accumulated snow can be accurately recognized, and the avalanche point hit rate reaches 82.5% and is far higher than that of a traditional method (generally lt: 70%); the model is excellent in performance, the interpretability of a shallow model is reserved through a two-stage framework of an integrated learning primary model and a residual network, nonlinear interaction among factors is captured through a deep network, and AUC of ResMLP is equal to 0.8496 and is improved by more than or equal to 4% compared with the primary model; the method is high in generalization stability, the prediction variance is reduced by about 12% on the premise that the training cost is not increased by introducing a TTA mechanism with Gaussian noise added, the method is particularly suitable for a high-altitude small sample area, and the overfitting problem is effectively relieved.

The invention belongs to the technical field of Internet of Things. The invention provides a large-scale infrastructure network link dynamic prediction method based on nonlinear reserve pool calculation. According to the embodiment of the invention, by combining nonlinear reserve pool calculation and regularization regression technologies, the dynamic, efficient and accurate prediction of a complex network link is realized, and the method is particularly suitable for state inference and stability analysis of a key link in an infrastructure network. A reserve pool calculation framework is adopted, and the core advantage of the method is that only the linear weight of an output layer needs to be trained, and the internal connection of a huge reserve pool is kept random and fixed. A large amount of iterative computation and GPU resources required by back propagation are avoided, and the training complexity and the time cost are remarkably reduced. A Tikhonov regularization item is introduced, so that the overfitting problem under limited training data or noise interference is effectively prevented, and the generalization ability and prediction stability of the model are improved.

The invention discloses a method for intelligently evaluating the susceptibility of a landslide disaster in combination with deep learning, and relates to the technical field of geological disaster evaluation. According to the method, data processing is more accurate, standardized processing of multi-source geographic space data is achieved through the GIS technology, coordinate deviation, resolution difference and magnitude influence are eliminated, a high-quality and high-consistency data basis is provided for model training, and interference of data noise on an evaluation result is effectively reduced; model fusion is efficient, the advantages of RF and KNN basic models (the RF is high in anti-overfitting capacity, and the KNN is sensitive to local features) are fused, the prediction result serves as the input feature of the deep learning model, cooperation of machine learning and deep learning is achieved, the utilization efficiency of the model on the landslide influence factors is remarkably improved, and the method is suitable for the landslide prediction of the landslide. The evaluation precision is improved by 15%-20% compared with that of a single model (AUC value verification shows that the AUC value of the model is larger than 0.85).

The invention discloses a five-axis numerical control finish machining tool path approximation error calculation method based on an Optuna optimization BiLSTM-TCRA (BiLSTM, Bidirectional Long Short Term Memory Network, a Bidirectional Long Short Term Memory Network, a Temporal-Channel Residual Attention, a Time-Channel Residual Attention mechanism) neural network, and relates to a tool path approximation error calculation method based on an Optuna optimization method of a BiLSTM-TCRA (BiLSTM, Bidirectional Long Short Term Memory Network, a Bidirectional Long Short Term Memory Network, a Time-Channel Residual Attention Mechanism) neural network and a tool path approximation error calculation method based on the BiLSTM-TCRA neural network. The method comprises the following steps: firstly, acquiring core parameters required by calculation of a neural network model, and mapping the parameters to the same scale by using mean variance normalization to eliminate the influence of dimensional difference between different features on the performance of the model; then, each hyper-parameter of the BiLSTM model is optimized by using an Optuna hyper-parameter optimization framework; a TCRA attention mechanism module is introduced to dynamically distribute different time step feature weights, so that the model can pay more attention to effective information which greatly influences an approximation error, the learning ability of the model is enhanced, and the training precision is improved; dropout mechanism sparsity is added to optimize a network structure, and part of neurons are randomly discarded in each iteration process, so that interference of non-core knife contacts on an approximation error value is reduced, and model overfitting is avoided; finally, the effectiveness of the method is verified in combination with actual curved surface model data, and efficient and accurate prediction of the five-axis machining approximation error is achieved.

Embodiments of the present application provide a reservoir pool data processing method and device, electronic equipment and storage medium. The reservoir pool data processing method comprises: in the test verification stage, obtaining input layer data; based on the random weight of the reservoir pool, performing time evolution calculation on the input layer data to generate output layer data; performing ridge regression on the input layer data to obtain input fitting value, and performing the ridge regression on the output layer data to obtain output fitting value; determining a fitting difference value according to the input fitting value and the output fitting value; when the fitting difference value is greater than a preset overfitting threshold, determining that the reservoir pool is overfitting, adjusting the random weight until the fitting difference value is not greater than the overfitting threshold. Through the embodiments of the present application, the output layer of the reservoir pool can be optimized, and the operation efficiency of the reservoir pool is improved.

The invention relates to the technical field of data processing, and particularly discloses a multi-round voting integration method fusing multiple evaluation indexes, which comprises the following steps of: establishing a multi-round voting mechanism, and taking an original data set formed by prediction results of base models as input in the first round of voting; the advantages of different machine learning models are concentrated by screening the combination of several base models with the best performance under each evaluation index, the prediction result of each machine learning model is comprehensively considered, the first round voting integration result of the model combination is used as input in the second round voting, that is, the first round voting result is subjected to the second round voting, and the prediction result of each machine learning model is obtained. The variance and deviation are reduced to obtain a result with higher accuracy, the generalization ability of the machine learning model is improved, the advantages of each machine learning model are integrated, and the problem that a traditional integrated machine learning method based on voting integration only carries out voting integration of various different item adjustment on a single machine learning model, so that the efficiency of voting integration is greatly improved is solved. And an over-fitting risk exists.

The application discloses a hyperspectral sparse unmixing method of a learnable implicit variable iterative unfolding network, and comprises the following steps: constructing an unmixing model by sparse constraint optimization; constructing an alternating direction iteration by variable splitting and an augmented Lagrangian method; modeling an alternating direction iteration step as an implicit unfolding network module, including a learnable layer of abundance variable and multiplier variable; constructing a learnable smooth convolution layer to improve the smoothness of abundance patches; realizing spectral unmixing and reconstruction by a coding-decoding structure; and realizing model training by adopting an unsupervised loss function. The application uses the optimization mechanism of a classical sparse unmixing model to design a learnable network, the network layer is designed based on algorithm iteration steps, the sparsity and patch smoothness of hyperspectral abundance are fully met, and the explainability and transparency are enhanced; an unsupervised training mechanism is introduced, the network availability is enhanced; the model parameter size and overfitting phenomenon are reduced through model driving and network parameter sharing, and the model is lightened.

This invention discloses a method, system, device, and medium for generating and presenting a large-scale modular fact-checking response. The method includes: acquiring user input instructions and decomposing them into information fragments to be checked; retrieving and aggregating evidence sets from a pre-set knowledge base or online information sources; determining the consistency of the information fragments based on the evidence, and outputting the verification conclusion and confidence level; determining the risk level and generating control parameters according to a pre-set risk assessment strategy; and using the control parameters to control or adjust the generation and / or perceptual presentation of the response content. The control or adjustment methods include constraints during generation and post-processing corrections to suppress deterministic assertions and output uncertainty identifiers and evidence summaries when evidence is insufficient or conflicting. This solution improves factual consistency and traceability through decoupling of responsibilities and an auditable evidence chain, and reduces the risk of illusion caused by consistency overfitting. The risk level can be further mapped to decoding parameters of the generation module (such as temperature, top-p, and logit bias masks) or modulation parameters of the perceptual presentation. The response data can be provided to the client via a network interface, allowing the client to control the output presentation.

This provides a machine learning technique that can suppress overfitting of new knowledge when applying IFSL to SaB. [Solution] This disclosure provides a machine learning device 100 that performs continuous learning based on a small number of new class data compared to basic class data, comprising: a pre-training module 30 that learns the weights of a neural network (NN) using basic class data; a pseudo-continuous learning module 40 that learns the weights of the NN learned by the pre-training module 30 using pseudo-data generated based on the basic class data; and a new class learning module 50 that learns the weights of the NN learned by the pseudo-continuous learning module 40 using basic class and new class data.

The invention discloses a supercavitation vehicle effluent trajectory prediction method based on BO-FNN. The method comprises the following steps: step 1, constructing a CFD basic mathematical model; 2, based on the mathematical model, boundary condition setting and mesh generation are carried out on the external flow field of the aircraft, and a simulation model is obtained; 3, verifying the simulation model to obtain a numerical model of the water outlet process; 4, an orthogonal test is designed, and a water outlet trajectory data set is obtained according to the numerical model; step 5, designing a feedforward neural network, and fitting the water-out trajectory data set to obtain a water-out trajectory prediction model presenting an over-fitting characteristic; and step 6, optimizing the water outlet trajectory prediction model to obtain a supercavitation vehicle water outlet trajectory prediction model based on the BO-FNN. According to the supercavitation aircraft water outlet trajectory prediction method based on the BO-FNN, the problems that the supercavitation aircraft water outlet process is high in nonlinearity, and prediction cannot be carried out under the multivariable coupling condition are solved.

The invention discloses a multivariate time series prediction method and system based on flexible actor-commentator, and the method comprises the steps: obtaining historical data, carrying out the preprocessing of the historical data, carrying out the feature extraction operation, and completing the construction of historical features; defining reinforcement learning elements of multivariate time series prediction, and constructing a flexible actor-commentator model based on the reinforcement learning elements; training the flexible actor-commentator model based on the historical features, and obtaining a multivariate time series prediction model after the training is completed; real-time data to be predicted are obtained, the real-time data are preprocessed, feature extraction operation is carried out, construction of real-time data features is completed, the real-time data features are input into the multivariate time series prediction model, an output result is obtained, and prediction of a future time series is completed. According to the method, efficient learning and optimization can be carried out in a large-scale environment under limited computing resources, the overfitting problem can be avoided, and the stability, robustness and generalization ability of the model are greatly improved.

The application discloses a kind of high-impact weather condition-oriented wind power prediction information filtering method.It realizes the dynamic soft selection and reweighting of different input variables under different weather conditions through instance-level attention recalibration, improves the effective signal-to-noise ratio, and reduces the interference of noise channels on the learning process.At the same time, it removes irrelevant random disturbances from the information flow by variational information bottleneck compression regularization term, alleviates overfitting and noise memory problems caused by relying only on error minimization, and improves cross-condition generalization ability.Compared with the prior art, the present application can effectively filter out random disturbances irrelevant to the prediction task under the condition of strong noise and distribution fluctuation caused by high-impact weather, improve the stability, robustness and cross-scene generalization ability of the wind power prediction model, and have good engineering application value.

Techniques are described for overtraining (e.g., 1002) an ML model over a plurality of game playing videos of individual scenes of a computer game to better configure the model to reconstruct or enhance portions of the computer game at a receiver when the computer game is received over a streamlined network. Individuals of a frame are assumed to be missing of reconstruction (904) of slices (810) such that the frames missing slices do not need to be fully discarded.

The invention relates to the technical field of speed control, in particular to a feed rate control method and system in numerical control machining based on data analysis, and the method comprises the steps: obtaining a vibration signal and a current signal in a machining process; calculating the cutting impact strength at each moment, wherein the cutting impact strength is positively correlated with the kurtosis of the amplitude of the vibration signal in the window corresponding to the moment and the logarithm of the absolute mean value of the current signal; and the instability index of each moment is calculated. According to the method, the penalty factor and the kernel function parameter can be adjusted in real time according to the instability of the machining process, high fitting precision is kept when the signal is stable, overfitting is prevented by reducing the penalty factor in the stage of severe abrasion and large noise, and therefore accurate prediction of the surface roughness is achieved, closed-loop correction is conducted on the feeding rate, and the precision of the surface roughness is improved. And the processing efficiency and the surface quality are effectively balanced.

The invention relates to the technical field of network security, in particular to a hybrid integrated learning-based traceability intrusion detection method and device and an electronic product, and the method comprises the steps: firstly obtaining system audit log data, constructing an initial traceability graph based on the system audit log data, and generating an attribute node embedding vector of the graph through a preset deep learning method; building an incremental training data set by relying on the log data, and training a pre-built explicit expert model by utilizing an attribute node embedded vector of the traceability graph corresponding to the incremental data; and finally, detecting the initial traceability graph node through the trained model to obtain a detection result, and performing integration verification through a preset bagging detection method to obtain a traceability intrusion detection result, thereby solving the problems of relatively low model prediction performance and relatively low robustness caused by over-fitting and excessive forgetting in a long-term model learning process in related technologies, and improving the accuracy of the traceability intrusion detection. The robustness of the system is improved, and the performance of intrusion detection is improved.