155 results about "Sample Weight" patented technology

The invention discloses a hyperspectral image classification method based on frequency domain denoising and element gradient correction, and the method comprises the following steps: carrying out the preprocessing of all hyperspectral image data, and dividing an overall training sample set formed by the processed hyperspectral images into a training set and a verification set; constructing a sample weighting model based on frequency domain denoising and element gradient correction; in the training process, a parameterization frequency spectrum gating sensing transformation module is utilized to map features to a frequency domain through discrete Fourier transform, a learnable frequency spectrum response function is utilized to adaptively suppress spectrum jitter noise, and finally pure features are reconstructed. And automatically constructing a high-confidence pseudo-clean verification set based on a Gaussian mixture model and time domain consistency. According to the method, a time domain momentum updating mechanism is introduced, the variance of statistical estimation is effectively smoothed, random interference caused by training fluctuation is resisted, and the accuracy of pseudo clean set construction and the convergence stability of overall model training are further improved.

The invention discloses an uncertainty guided few-sample harmful speech detection method (U-GIFT). According to the method, a pre-training language model is finely adjusted based on a small number of labeled samples, and a semi-supervised self-training and uncertainty guiding strategy is combined. Monte Carlo Dropout is started in the reasoning stage, multiple times of random forward propagation are carried out to obtain sample posterior distribution, prediction entropy and information gain are calculated, pseudo-label samples are sorted and screened, and only high-confidence samples are selected to be added into a training set. And in order to reduce the influence of a pseudo labeling error, designing a stability weighting mechanism, giving a sample weight according to a prediction variance, and constructing a joint loss function, so that the model preferentially learns a stable sample to improve the detection performance. According to the method, the semantic and attention mechanism of the pre-training model is utilized, the detection effect is remarkably improved under the conditions of few samples, imbalance, multiple languages and cross domains, models such as BERT, RoBERTa, XLM-R, LLaMA2 and DeepSeek-R1 are compatible, and the method is suitable for content auditing and risk prevention and control.

The invention discloses a crop disease and insect pest detection algorithm fusing self-attention and a sample weighting mechanism. A YOLOv8 network is used as a basic model; through a two-branch self-attention DF-MSA architecture, the ability of the model to acquire pest target position information is enhanced; a cross-layer feature fusion module is introduced into the feature pyramid network structure, and multi-scale information is fused; and a sample weighting function is adopted to reduce the influence of difficult sample imbalance on a detection result, so that the detection accuracy is improved. And inputting the trained IP-YOLO by using a test set sample, and outputting a result. The method has high stability and robustness, and an effective means is provided for improving the performance of a crop disease and pest detection system.

The invention discloses a federated backdoor defense method based on decoupling contrast learning, and the method comprises the steps: training a backdoor model based on a backdoor sample, and immediately stopping training after the backdoor model converges on the backdoor sample; respectively extracting a penultimate layer vector of the backdoor model and the local model from a sample pair held by the malicious client as a backdoor feature and a clean feature; comparing and learning the separated back door features and the clean features, and learning the clean features for the local model by using a sample weighting strategy to train the local model to obtain a trained local model; and sending local model parameters of the trained local model to a global server, and generating model parameters of a new global model based on the local model parameters through an aggregation function. The method aims at reducing information dependence between backdoor features and clean features through comparative learning, so that local model learning is free of backdoor representation, and the robustness of a global model is improved.

The invention provides a water supply network water leakage abnormity identification method based on NMF dimension reduction, and relates to the technical field of water supply network abnormity identification, and the method comprises the steps: embedding hydrophone sample data containing expert labeling information into a sample weight matrix as a row vector, and constructing a sample dimension loss item; hydrophone sample data containing industry feature priori are mapped to the feature basis matrix to serve as rows, and feature dimension loss items are constructed; combining the two loss items to construct a total loss function and solving the total loss function to obtain an optimal sample weight matrix; and performing clustering analysis based on the optimal sample weight matrix to obtain a clustering affiliation result of the hydrophone sample data so as to judge whether the water supply network to be identified has water leakage abnormity or not. According to the method, the double-constraint NMF framework fusing the expert knowledge of the sample dimension and the industry priori knowledge of the feature dimension is constructed, the accuracy and interpretability of hydrophone feature dimension reduction are considered, and the problems that an existing method is poor in interpretability, less in priori knowledge utilization and the like are solved.

The invention discloses a multivariable time sequence anomaly detection method based on spatial-temporal feature fusion, and the method comprises the steps: outputting time sequence features through employing a series structure of a multi-scale TCN and a lightweight Transform network; constructing an adjacency matrix through a static graph learner and a dynamic graph learner, processing by using a multi-order GCN based on the adjacency matrix, and outputting spatial features; performing weighted fusion on the time sequence features and the spatial features by using a gating mechanism, and outputting a predicted value in combination with multiple residual connection; in a training process, dynamically calculating a sample weight according to a predicted residual error and calculating a weighting loss; and according to a residual error between a predicted value and a real value, generating an abnormal score through a reconstruction error calculation mechanism based on principal component analysis, and comparing a threshold value to complete abnormal detection.

The invention relates to a discrete industrial agent-based production management method and system, and relates to the field of production management, and the method comprises the steps: collecting a production prediction sample data set and a quality inspection decision sample data set, carrying out the data weight division of the two data sets, and obtaining two sample weight sets; obtaining a production prediction and quality inspection decision path array, a first prediction accuracy rate set and a decision accuracy rate set after integrated training; combining the two path arrays to obtain a discrete industrial agent array, carrying out joint optimization training, and testing to obtain a second prediction and decision accuracy set; obtaining current production basic data, inputting the current production basic data into the agent array, outputting a predicted production yield and a decision quality inspection parameter, performing compensation according to an error between the second prediction and decision accuracy set and the first prediction and decision accuracy set, and obtaining a predicted production yield and decision quality inspection parameter interval for production management. The technical problem that data interaction and business collaboration of a plurality of complex and independent scenes in the discrete manufacturing industry are difficult to realize in production management is solved.

The invention discloses a wind power prediction covariable offset adaptive method based on a conditional energy model. According to the method, the wind power generation power prediction model is constructed by utilizing the gated cycle unit network, and offline training of the wind power generation power prediction model is completed by adopting a sample weighting mechanism, so that the robustness of the wind power generation power prediction model to distribution change is enhanced. A conditional de-noising score matching strategy is adopted to learn the distribution difference of data in a training stage and a prediction stage through a conditional energy model, and a sample weight used for measuring the covariable offset degree is obtained based on the model. Data samples flowing in real time are stored in a replay buffer area, incremental learning is carried out on a condition energy model and a wind power generation prediction model through an online updating mechanism, and the prediction performance is kept stable. The method can effectively improve the power prediction precision and operation scheduling capability of the wind power plant under complex meteorological conditions, and has good engineering practical value and deployment flexibility.

The utility model discloses a static weighing device for a sintered ore sample, and relates to the technical field of weighing devices. The feeding device comprises a feeding machine, and a conveying belt is arranged below a discharging port of the feeding machine. In the conveying direction, a hopper is arranged below the front end of the conveying belt, the outer side of the upper end of the hopper is connected with a horizontally-arranged fixing support, a weighing sensor is installed at the bottom of the fixing support, and a supporting base is arranged at the bottom of the weighing sensor. A gate plate is arranged at the lower end of the hopper, the gate plate extends out of the hopper and is connected with a push rod for driving the gate plate to move horizontally, the push rod is connected with a push rod bracket, and the other end of the push rod bracket is mounted on the hopper. According to the utility model, the weight of a sintered ore sample can be accurately measured, and the accuracy of sample data is ensured, so that the precision and the reliability of a drum strength test are improved, and the problem of weighing deviation caused by factors such as vibration of a batching electric vibration feeder, powder residue and the like in the traditional feeding and weighing process is solved.

The present application relates to the field of electric digital data processing, and particularly relates to a joint training method and system based on real data and synthetic data, the method comprising: obtaining a mixed sample set composed of real data and synthetic data; constructing a global correlation graph based on the mixed sample set, extracting global authenticity and global closeness, and adaptively determining an optimal number of neighbors for synthetic sample quality evaluation; for each synthetic sample, constructing a neighbor subgraph by K-neighbor method using the optimal number of neighbors, extracting subgraph authenticity and subgraph closeness, and obtaining a quality score by a fusion algorithm; giving a fixed weight to real samples and a corresponding quality score to synthetic samples as a weight, constructing a weighted loss function based on sample weights, and completing joint training of the model. The present application improves the model training effect through adaptive number of neighbors, multi-dimensional quality evaluation and weighted differentiated training.

The invention discloses a tunnel engineering construction drawing design risk event safety assessment and standardized prevention and control method, which comprises the following steps: constructing a sample library matrix containing risk sources, risk events and risk prevention and control technologies at the same time, training a random forest model, and extracting risk source parameter weights; weighting the risk source parameters of the tunnel to be built by using the weight, inputting the weighted parameters into the model, and predicting the risk event probability; carrying out binaryzation by adopting a self-adaptive threshold algorithm based on F1-score to obtain a risk event prediction result; calculating multi-dimensional similarity with a sample library in combination with a Gaussian kernel function, normalizing to obtain a sample weight, and recommending an excavation method and an advanced pre-reinforcement measure according to the sample weight; and finally, a field implementation result is fed back to the sample library, and the bandwidth and the threshold are optimized by using gradient descent to realize closed-loop updating. The method reduces human intervention, improves risk assessment objectivity and prevention and control scheme standardization level, and is suitable for safety risk assessment in a complex geological tunnel construction drawing design stage.

This invention discloses a method and system for defending against big data poisoning attacks, belonging to the field of information security technology. The method includes the following steps: collecting a raw big data dataset to be labeled, and adding a credibility label column to the data to obtain a labeled big data dataset; calculating the credibility value corresponding to each sample in the labeled big data dataset, and removing samples whose credibility values ​​are less than a preset credibility threshold to obtain a high-credibility big data dataset; using the credibility values ​​corresponding to each sample in the high-credibility big data dataset as sample weights, and calculating the total loss value in combination with the loss function of the big data model to be trained; optimizing the parameters of the model to be trained based on the total loss value to obtain a big data model resistant to poisoning attacks, and using the big data model resistant to poisoning attacks to defend against big data poisoning attacks. This invention can solve the problem of training data pollution caused by data poisoning in current big data systems.

The application discloses a meter box line loss compensation method and system based on a neural network. The method first collects voltage, current, power supply end electric energy and power supply end electric energy, and calculates the abnormality degree and line loss rate of the meter box accordingly; then a data point set is constructed, DBSCAN clustering based on abnormality density weighting is performed, and multiple clustering clusters are formed; based on the abnormality distribution proportion vector similarity in each clustering cluster, the abnormality degree level is adaptively divided, and the variance of the line loss rate in each level is calculated as the line loss sensitivity; a long short-term memory neural network model is constructed, and an adaptive sample weight based on the line loss sensitivity is introduced into the loss function for training; finally, line loss compensation is performed according to the model output. The application retains key sparse samples through weighted clustering, adaptively divides abnormal levels and quantifies compensation difficulty, and combines sensitivity weighting training, so that the precision and robustness of line loss compensation in a complex scene are significantly improved.

The application discloses a long video understanding-oriented adaptive key frame sampling method and system based on a video hierarchical structure, which comprises the following steps: performing hierarchical structure splitting on a long video to be processed; calling a video large language model component to generate summaries of semantic event segments, scene segments and shot segments; calling the large language model component according to a task text to calculate similarity scores of each level and comprehensive similarity scores of each shot segment; screening top K shot segments as candidate sampling units; under the constraint of a preset total sampling frame number, calculating sampling weights and frame quotas of each candidate sampling unit; and performing adaptive key frame sampling in the corresponding candidate sampling unit. The application solves the problems of poor performance of existing long video understanding methods in key frame selection tasks and consumption of a large amount of computing resources, and is suitable for video content labeling, summary generation and question and answer tasks driven by a video large language model.

The invention discloses a software deployment compatibility prediction method and system based on a LightGBM algorithm, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring environmental parameters of a historical deployment task and a dichotomy deployment result; performing sample balance and weight distribution processing on the data to construct a full-amount training set; based on the training set, a two-stage LightGBM architecture is adopted to train a prediction model, a first classifier learns a global mapping relation and outputs an initial prediction probability, and after a boundary fuzzy sample set is screened out according to the initial prediction probability, a second classifier learns fine feature differences of the boundary fuzzy sample set so as to determine a final prediction result. According to the method, the problem of unbalanced category distribution is solved through cooperation of SMOTE oversampling and sample weight adjustment, the discrimination capability of boundary fuzzy samples is enhanced by using a two-stage classification mechanism, and the defect of low prediction accuracy of a traditional method in a complex heterogeneous industrial environment is effectively overcome; and the compatibility evaluation automation level and the prediction reliability before the printing industry software deployment are obviously improved.

This invention provides a method for high-speed train bearing fault diagnosis and selection based on multi-model comprehensive evaluation. The method first obtains bearing fault feature vectors, then divides the training and test sets using 8:2 stratified sampling, mitigating sample imbalance bias through a sample weighting strategy. Next, it constructs a diagnostic system comprising five models, including random forest and support vector machine, and employs optimal hyperparameters for parallel training. Subsequently, a multi-dimensional evaluation system for accuracy and efficiency is established, and model reliability is verified using a confusion matrix. Finally, model selection is tailored to specific scenarios: multilayer perceptrons are used for real-time monitoring, gradient boosting trees for high-precision scenarios, and random forests or K-nearest neighbors for lightweight deployment. This achieves scientific multi-model selection, balancing diagnostic accuracy, real-time performance, and stability, adapting to the maintenance needs of high-speed trains, and demonstrating strong engineering practicality.

The invention discloses an unsupervised cross-modal retrieval method based on robust consensus learning, and the method comprises the following steps: extracting image and text features of input data through a pre-training backbone network, and obtaining multi-level feature representation through a three-layer projector; generating a prototype as a pseudo label based on top layer feature clustering, calculating a sample weight by using contour coefficients of three levels, performing optimization through layered consensus prototype comparison loss, and finally obtaining a high-reliability pseudo label; the noise tolerance triple alignment loss and the modal consistency loss are jointly optimized, and the robustness of the model to noise is enhanced; and cross-modal retrieval is realized in the optimized shared semantic space. According to the method, a two-stage training strategy is adopted, the pseudo-labels are generated through top-layer clustering, the sample weight is optimized through multi-layer semantic information, robust learning is carried out based on the reliable pseudo-labels, the problems of pseudo-label noise and semantic granularity mismatch in an unsupervised environment are solved, and the accuracy and robustness of cross-modal retrieval are remarkably improved.

The invention relates to the technical field of data processing, in particular to a processing method for task classification and subclass sample enhancement of a corner plastic data set, which comprises the following steps of: S1, acquiring a label set of the corner plastic data set, judging whether each label in the label set conforms to a classification task or a regression task, and if yes, judging whether each label conforms to the classification task or the regression task; taking samples corresponding to the same label in the corner plastic data set as a label category; s2, a learning model is constructed for the labels conforming to the classification task, the learning model adjusts the sample weight of a sample corresponding to each label category through a dynamic category weight method, and then the sample number of the angle plastic data set is adjusted through a self-adaptive mixed sampling method to form an adjusted data set; s3, adjusting the attention degree of the samples in the adjusted data set; and S4, performing prediction fusion on the adjusted data set processed in the step S3 through a subclass gating fusion method, and further executing a classification task on each sample in the adjusted data set. According to the invention, the sample processing accuracy is improved.

The invention discloses a sample weight real-time adaptive statistical adjustment method for a classification model, and the method comprises the following steps: obtaining the sample data of a current training batch, inputting the sample data into a main classification model, processing the sample data through the main classification model, and generating prediction result data; the real-time statistical tracking module receives the prediction result data and the sample data, and updates a sample level statistical magnitude and a batch level statistical magnitude based on the prediction result data; the weight decision network receives the sample level statistics and the batch level statistics, and calculates a real-time weight value of each sample; updating the parameters of the main classification model by using a weighted loss function, and updating the parameters of the main classification model through a back propagation algorithm; updating parameters of the weight decision network according to updating feedback of the main classification model; therefore, the feature learning of minority class samples and difficult samples can be continuously optimized, and the classification balance among the classes is remarkably improved while the overall high accuracy is kept.

Methods, apparatus, systems, and articles of manufacture to estimate cardinality through ordered statistics are disclosed. In an example, an apparatus includes processor circuitry to selects a sample dataset from a first reference dataset of media assets and partitions the sample dataset into m mutually exclusive subsets of approximately equal size. The processor circuitry then estimates a ratio of a sample weighted average and empirical cumulative distribution of an approximately largest order statistic from at least one of the m subsets and generates an estimate of a total cardinality of the first reference dataset by multiplying the ratio by approximately m.

The invention belongs to the technical field of communication, and discloses a pruning and fine tuning troposphere waveguide prediction method and system based on multi-granularity evaluation, and the method comprises the steps: calculating edge loss and task loss; fusing edge loss and task loss to construct a channel importance evaluation system, and performing quantitative evaluation and dynamic sorting on the contribution degree of the atmospheric waveguide prediction channel; on the basis of the sorting of atmospheric waveguide prediction channels, redundant channels are gradually eliminated by adopting an iterative pruning algorithm until a preset pruning rate is reached; and calculating the prediction confidence of the atmospheric waveguide prediction model before and after pruning, positioning a high-sensitivity atmospheric waveguide sample of which the prediction result is remarkably reduced, establishing a dynamic sample weighting mechanism, and performing fine adjustment compensation on the residual channel weight by using error back propagation. According to the method, a multi-granularity importance evaluation cutting mechanism and a prediction information guiding method are adopted, lightweight compression and fine adjustment are performed on the model, the effectiveness of the prediction model is improved, and accurate prediction and interaction of the non-uniform atmospheric waveguide are realized.

The application discloses a multi-view clustering method and system based on self-step learning and view weighting, and belongs to the technical field of multi-view data processing. The method comprises the following steps: normalizing a multi-view data set, splicing the multi-view data, initializing each view clustering kernel and distribution matrix by using a kmeans algorithm, and calculating each view weight; each view sample weight matrix, each view clustering kernel and distribution matrix are iteratively updated in sequence through a target function; and when an iteration end condition is met, a final clustering kernel and distribution matrix are output. The clustering system comprises an acquisition module, a preprocessing module, a construction module, an optimization module and a clustering output module. The self-step learning model is used to sequentially learn clustering data and finally obtain a clustering result. Through view weighting, the model can selectively learn information of different views, thereby effectively improving clustering accuracy. The application can be applied to retrieval of an image database, a text database and the like.

An artificial intelligence system performing operations including: an operation of calculating an importance score for data points of a dataset, an operation of calculating an oversampling rate for each of the data points, an operation of calculating a sample weight based on the oversampling rate for each of the data points, and an operation of oversampling the data points in correspondence to the calculated sample weight.

This invention proposes a stable target recognition method and apparatus based on visual feature random partitioning and decorrelation. The method includes: acquiring a visual feature set of a training dataset consisting of industrial images and their defect labels, and performing multiple random partitions; after each partition, all dimensions of visual features are divided into two mutually exclusive feature segments; under each feature partitioning scheme, using the training dataset, learning a set of sample weights to decorrelate the two feature segments in a weighted distribution; weighting the training data using the sample weights, and using the weighted training data to train a base recognition model; inputting the image to be recognized into the trained base recognition model to obtain the corresponding recognition result; and integrating the recognition results from all models to obtain the final stable recognition result. This invention can effectively alleviate the environmental bias problem in industrial production lines and improve the stability and generalization performance of defect detection models with limited training data.

The invention discloses a pulverized coal distribution uniformity control method and device, electronic equipment and a storage medium, and relates to the technical field of thermal power generation, and the method comprises the steps: obtaining a historical operation data set and a current monitoring data set, and carrying out the feature alignment processing; taking the historical operation data set as a source domain and a current monitoring data set as a target domain, training a control model by adopting an integrated transfer learning framework, balancing contribution of the two domains to model training by dynamically adjusting sample weights, and improving model robustness by adopting an integrated learning strategy; predicting key state parameters of the target process by using the trained control model to generate a prediction result; and generating a control instruction according to the prediction result, adjusting the action of an execution mechanism, and feeding back the adjusted process state to a control model to realize online optimization. The method has the technical effects that the pulverized coal distribution uniformity control precision is improved, the adaptability of the model to coal quality fluctuation and working condition change is enhanced, and long-term stable operation of a coal pulverizing system is guaranteed.

The application relates to a kind of industrial equipment control method and related device based on multi-protocol fusion, which comprises: according to dynamic protocol mapping relationship, unified standard data object is generated by parsing multi-source data through zero-copy analysis mechanism;Extracting time series statistical features and physical property features for heterogeneous fusion to construct a multi-dimensional feature vector;Anomaly probability value is calculated using a model based on prior sample weight;When the probability exceeds the dynamic adaptive threshold, trigger the double-channel strategy, and issue a shutdown command directly through the local channel, and report the data synchronously.The application solves the delay accumulation problem under multi-protocol integration through zero-copy analysis and heterogeneous feature fusion technology, and uses double-channel architecture to ensure the real-time and certainty of industrial control response.

This invention relates to the field of medical data mining technology, specifically to an automatic analysis and classification system for pulmonary function test data based on big data. First, it calculates a single-channel weighted evolution index based on the variation deviation of multi-channel data time-series curves, capturing the dynamic evolution characteristics of each dimension within a continuous observation window. Then, it combines the variation trend deviation between multiple channels to accurately assess the feature response sensitivity of each dimension in response to changes in pathological states. Finally, by comparing the differences between current data and historical lesion characteristics, it quantifies the discriminative contribution of each dimension when considering historical data for each lesion type. This allows the weighted discriminative signal intensity obtained based on feature response sensitivity and discriminative contribution to more comprehensively evaluate the sample contribution of each pulmonary function test dimension. This results in higher accuracy in training the classification model using the weighted discriminative signal intensity as sample weights, thereby improving the accuracy of pulmonary function test data classification.

The present application relates to the technical field of chromatographic analysis detection, in particular to a gynecological tuberculosis endocrine disorder typing system based on chromatography-mass spectrometry. The system comprises a memory and a processor, and the processor executes a computer program stored in the memory to realize the following steps: evaluating the compound identification accuracy according to the number of compounds in different reference samples in each specimen source, determining the sample weight of each specimen source in combination with the ideal effect of the specimen source and the proportion of the number of reference samples; evaluating the mixed similarity in combination with the retention time and response intensity of the compounds in the chromatographic data segment in each compound set; obtaining the correction weight by comprehensively considering the number of compounds, the mixed similarity and the sample weight of each compound set in each reference sample, and further determining the gynecological tuberculosis endocrine disorder typing. The present application overcomes the identification deviation problem caused by insufficient reference samples and similar compound structures, and improves the accuracy of gynecological tuberculosis endocrine disorder typing.

To measure powder with high accuracy by an inexpensive constitution.SOLUTION: A weighing device that accommodates a target weight of a sample in a subdivision container from a raw material container includes a movable arm to which a scoop is attached, a leveling plate, a subdivision scale that measures a weight of the sample in the subdivision container, and a control unit, in which the control unit controls the movable arm so as to scoop up the sample from the raw material container by the scoop, level the sample in the scoop using the leveling plate, and accommodate the sample in the scoop in the subdivision container based on the weight of the sample in the subdivision container measured by the subdivision scale.SELECTED DRAWING: Figure 1

The invention provides a width learning medical image recognition method based on global-local feature combination, and the method comprises the steps: firstly generating a feature mapping matrix and a feature enhancement matrix based on a width learning network, and constructing global features and local features; secondly, a sample weight matrix is constructed according to sample prior distribution, and different contribution degrees are given to different samples; using the global features, the local features and the sample weight matrix to establish a width learning model based on global-local feature combination; and finally, performing optimization solution on the model to obtain a closed-form solution, determining the category of a test sample set by using the optimal solution, and performing performance evaluation according to a prediction result. According to the method, the global features and the local features extracted by the width learning network are effectively fused, and the weight distribution of different training samples is adaptively adjusted in combination with a sample weight mechanism based on intra-class and inter-class density information, so that the feature expression ability and discrimination of the model are remarkably enhanced.