15 results about "Early stopping" patented technology

This invention discloses a deep learning-based method for predicting the phenological synchronization of specialized butterflies and their host plants, belonging to the interdisciplinary field of biodiversity conservation, ecological prediction, and deep learning technology. The method includes: collecting environmental climate variables, butterfly occurrence data, and phenological time-series data of their host plants; preprocessing the data to create training and validation sets; constructing a dual-label system with the day of year (DOY) of butterfly occurrence peaks (e.g., emergence peak, egg-laying peak) as the primary label and the normalized value of synchronization deviation as the secondary label; building a deep learning model with ecological weights, including an embedding layer, an LSTM layer, and a fusion layer; inputting a vector concatenated from daily or weekly climate time-series features and ecological dynamic features; and outputting the primary and secondary labels through a dual-output layer; designing a hybrid loss function that integrates the main regression loss, ecological synchronization constraint loss, and small-sample regularization loss; training the model using the Adam optimizer and implementing an early stopping mechanism; and validating and evaluating the model using regression accuracy and ecological synchronization accuracy indicators. The method includes modules for data acquisition, preprocessing, label construction, model training, prediction evaluation, and storage. This invention improves the accuracy of phenological synchronous prediction by embedding ecological dynamic feature weights and dual-label constraints, adapts to small sample scenarios, and provides technical support for the monitoring and protection management of rare butterfly species (such as the Golden Birdwing and the Chinese Tiger Swallowtail).

The application discloses a kind of fusion attention mechanism and the industrial bearing vibration time series signal fault prediction method and system of LSTM.This method includes: collecting bearing vibration signal and carrying out filtering, noise reduction and normalization preprocessing;BiLSTM and coordinate attention mechanism combined deep learning model is constructed to extract bidirectional time series features and enhance key fault features;Multi-objective composite loss function and Adam optimizer are used for model training, and early stopping mechanism is introduced to prevent overfitting;Real-time vibration signal is used to identify fault type and degree evaluation using the trained model, and multi-scale spectral kurtosis features and nonlinear dynamics parameters are used for quantitative analysis;Finally, output fault diagnosis report, and trigger multi-level early warning based on adaptive threshold value.The application can realize high-precision, high-reliability bearing fault prediction and health state evaluation, and is suitable for industrial equipment intelligent operation and maintenance.

The application relates to a SO4 based on deep cross network (DCN V2) feature enhancement and integrated learning 2‑ The concentration driving factor analysis method comprises the following steps: collecting time series data of atmospheric pollutant concentration and meteorological parameters in a target area, and performing pretreatment and quality control; a DCN V2 model integrating a linear cross network, an exponential cross network and a deep neural network is constructed to realize nonlinear high-order cross feature enhancement of original features; a two-layer Stacking integrated learning model taking XGBoost, LightGBM and CatBoost as heterogeneous base models and linear regression as a meta model is constructed, and global optimization is performed through Bayesian optimization; and the SHAP method is applied to quantify the marginal contribution and direction of each feature, and identify the key driving factors of SO4 2‑ concentration. The application integrates optimization strategies such as GPU acceleration, early stopping mechanism, automatic task detection, parallel training and backup training, realizes the automation, high efficiency and reproducibility of the analysis process, and guarantees the physical interpretability of the driving factor analysis, thereby providing scientific and technological support for atmospheric pollution prevention and decision-making.

The application discloses a kind of big model fine-tuning systems and methods based on multimodal gradient coordination, the method contains: the gradient similarity cosθ is calculated, and its with two-stage alternating optimization process determines update direction;With differentiable structure search and Gumbel-Softmax automatically determine LoRA insertion layer position;With Top-K gate and dynamic sparsity rate pruning cross-modal prompt unit;Based on convergence curvature κ analysis and adjust early stopping threshold, prevent invalid training;With cosθ, Kt, κ closed-loop feedback, unified correction gradient, structure, sparse and termination condition, realize ≤5 round global convergence verification.The application solves the problems of gradient conflict, structure fixation and early stopping failure in the prior art, basic DGC-LoRA, 1000 samples 5 rounds of convergence, 0.1% parameters reach 93.1% accuracy, invalid training is reduced by 40%, A100 throughput increases by 88.3%, and extreme conflict is self-healed within 3 rounds.

The application discloses a database training method and device for regional energy consumption prediction and path optimization, an optimization method and system. The STIRPAT model is trained through the standardized multivariate time series data set; the standardized multivariate time series data set is divided to obtain the batched LSTM training data, the batched early stop verification data and the hyperparameter verification set; the LSTM time series prediction model is trained through the batched LSTM training data, the batched early stop verification data and the hyperparameter verification set to obtain the trained LSTM time series prediction model; the optimal fusion weight is solved according to the trained STIRPAT model and the trained LSTM time series prediction model in combination with the hyperparameter verification set, and the STIRPAT-LSTM fusion prediction scheme is constructed. The Pareto optimal solution set finally generated by the application has both the causal logic support and the accurate time series prediction basis, and the optimality and the feasibility are taken into account, thereby providing reliable technical support for regional energy planning.

The application discloses a database logical topology construction method based on a large language model, which comprises the following steps: obtaining target database Schema information, using a large language model to complete the semantic metadata of a missing service to generate enhanced metadata; based on the enhanced metadata, performing multi-stage reasoning arrangement to construct a global logical topology network, using an adaptive partition strategy and an early stop mechanism to solve the context limitation problem of the large language model; performing information entropy determination on key data fields to identify feature types, using an orthogonal boundary synthesis method to construct a virtual sample set covering global feature values to obtain an enhanced topology network; establishing a Schema change monitoring mechanism, triggering an incremental adsorption algorithm to integrate change elements, and maintaining the validity of the correlation relationship through a timeliness confidence decay model to obtain a dynamic global logical topology. The application realizes automatic correlation mining and topology dynamic maintenance of a foreign key-free database, and improves the SQL generation accuracy of an intelligent query scene.

The application discloses a container throughput prediction method based on stacked ensemble learning, and relates to the technical field of intelligent ports. In the system operation, multi-source data is collected from a port operation system, an economic statistics platform and a shipping database, a comprehensive feature system containing throughput, freight rate, transportation time, policy variable, seasonal characteristics and macroeconomic indicators is constructed, and serialization and standardization processing are performed, and an improved model is constructed. The improved CNN-LSTM model introduces a deep separable convolution, a bidirectional LSTM and an improved attention mechanism to enhance the representation ability of key time steps, adopts Bayesian optimization to automatically search for hyperparameters, combines an early stopping strategy to control overfitting, simultaneously realizes multi-model integration based on inverse error weighting and meta-learning linear regression model, adaptively adjusts the rolling prediction window size according to the data coefficient of variation, generates future multi-period throughput prediction results through multi-step rolling prediction, and performs denormalization output.

This invention discloses an adaptive early-stopping generation method and system for language models based on dynamic confidence and domain reinforcement, applied to the inference process of large-scale language models based on autoregressive generation. During model generation, this method performs real-time confidence assessment on the generated text and constructs a multi-factor coupled dynamic confidence threshold function by combining task domain features, generated content structure, and quality constraints. When the generated text meets the pre-set confidence conditions and passes the final quality check, the generation process is terminated early, thereby reducing redundant generation. This invention does not require modification of the original model parameters or structure, is applicable to various inference service frameworks, and can effectively reduce generation latency and computational resource consumption while ensuring generation accuracy and completeness, thus improving the overall efficiency of large-scale model inference systems.

This invention discloses a multi-resolution end-to-end and online parameter update method for depth perception. It includes: (1) constructing a multi-view vision acquisition system to obtain left and right view images and depth information and completing calibration and alignment; (2) constructing a progressive multi-resolution end-to-end disparity inference network to achieve staged disparity prediction and support dynamic early stopping output; (3) converting depth information into disparity form to construct sparse supervision signals; (4) constructing an asynchronous online adaptive mechanism decoupled from the inference process and the model update process to complete model parameter optimization; (5) introducing a supervised quality assessment strategy to control update triggering and improve online learning stability; and (6) converting the disparity results into a depth map as the final output. This invention, through decoupling inference and learning, progressive computation, and a quality-gated update mechanism, achieves continuous adaptive optimization of the model while ensuring real-time performance, significantly improving perception accuracy and robustness in complex environments.

The application relates to the technical field of electromagnetic compatibility (EMC) key parameter optimization, in particular to an optimization method for key parameters of impedance characteristics of an electric drive filter, which improves a genetic algorithm by adding early stop mechanism, dynamic convergence control, Gaussian variation, range clipping and mixed crossover strategies in the iteration process of the genetic algorithm, and optimizes a key parameter combination affecting the impedance characteristics of the electric drive filter by using the improved genetic algorithm, so that subjective deviation of traditional manual parameter adjustment can be avoided, a global optimal solution can be quickly located in a continuous hundred-billion-level parameter space, and repeated manual operation and calculation resource consumption in the research and development process can be effectively reduced.

The present application provides a kind of inference time control method based on reflection trigger signal word, belong to natural language processing and logic calculation technical field.The method of the present application introduces the dynamic monitoring and sampling control mechanism based on reflection trigger signal word in reasoning phase, introduces probe mechanism in reflection trigger position, uses intermediate answer consistency check as early stop determination basis, combines single track self-consistent early stop mechanism and group consistency early stop mechanism, controls and independently suppresses multiple reasoning tracks in parallel.The present application identifies redundant reflection behavior in mathematical derivation in real time during the generation process of large language model, adaptively suppresses the generation probability of corresponding word element, effectively reduces invalid or repeated derivation content, thereby significantly shortens the length of reasoning thought chain and reduces the computing resource overhead, and at the same time improves the stability and reliability of mathematical solution result;With the advantages of low implementation cost, strong universality, easy to deploy, etc., suitable for various reasoning tasks and application scenarios.

This invention provides a method for removing artifacts from photoacoustic B-scan images based on deep learning ResUNet. The method includes normalizing and augmenting the original photoacoustic B-scan images to construct a paired training dataset; employing an encoder-decoder network structure containing residual convolutional blocks, achieving multi-scale feature fusion through downsampling, upsampling, and skip connections, and outputting artifact suppression results of the same size as the input; during model training, adaptively determining the principal structure position based on reference labels, constructing principal structure preservation bands, deep weighting, and out-of-band distance increasing weights, and combining structural similarity constraints with out-of-band TopK anomaly response suppression terms to form a composite loss function; and using adaptive learning rate decay and early stopping strategies to complete network training, thereby achieving end-to-end artifact removal of photoacoustic B-scan images during the inference stage, while effectively suppressing artifacts and ensuring the integrity of tissue structure information.

This invention discloses a method for predicting the water content of tunnel rock mass based on a multi-scale residual denoising network, belonging to the field of tunnel geological prediction technology. It includes the following steps: a dataset construction stage, constructing a transient electromagnetic method water content sample dataset; a sample dataset partitioning stage, dividing the dataset into a training set, a validation set, and a test set, and performing randomization during partitioning; a model construction stage, constructing a multi-scale sampling residual denoising network model based on a self-attention mechanism; a model training stage, using the training set for model training, employing an early stopping strategy and the Adam optimizer during training, and using the signal-to-noise ratio as an evaluation metric to optimize the model; and a water content prediction stage, using the trained model to predict water content, validating the model's imaging effect through tunnel data in a real-world scenario, and further optimizing the model based on the validation results. This invention can achieve high-precision inversion of tunnel rock mass water content under complex noise environments.

The application discloses a kind of robust pose estimation methods under complex crowd scene based on end-to-end deep learning, comprising: 1) using CrowdPose dataset as the data source of model training, the dataset is divided into training set, verification set and test set;2) construct deep convolutional neural network, including preprocessing part, backbone network part, feature enhancement part, feature fusion part and head part;3) set training parameters, including batch size, learning rate and early stopping strategy, and train the deep convolutional neural network accordingly until the model converges;4) input the image containing the person into the trained deep convolutional neural network, and the deep convolutional neural network outputs the key point coordinates of the person in the image, and the corresponding human pose graph is obtained according to the connection relationship of key points.The technical scheme of the present application can improve the pose estimation accuracy and robustness in complex scene, and is suitable for further popularization and application.

This invention discloses a method for predicting automotive drag coefficients based on the XGBoost algorithm, comprising the following steps: collecting the design range of various components of the aerodynamic exterior trim of the project vehicle, and generating a sample space using Latin hypercube sampling; calculating the drag coefficient of each corresponding sample data; adding feature engineering, dividing the dataset into training, validation, and test sets, and performing min-max data normalization; obtaining the optimal XGBoost model through multi-stage hyperparameter tuning combined with early stopping method; and outputting feature importance scores. This invention, by constructing an XGBoost-based drag prediction model, achieves rapid and efficient prediction of automotive drag coefficients at the component level, significantly improving computational efficiency and reducing data acquisition costs.