20 results about "Class discrimination" patented technology

The invention discloses a double-channel confrontation and progressive self-training driven cross-working-condition open set domain adaptive fault diagnosis method. In order to suppress an interactive negative migration effect, a three-stage two-way adversarial progressive self-training network DAPN is designed, separation of unknown target samples and feature aggregation of known samples are realized through cooperation of a gradient inversion layer and a two-way adversarial discriminator, and inter-class discrimination and intra-class aggregation are obviously enhanced. When the performance of the DAPN is evaluated in two open set domain adaptive scenes, for open set proportions of different intensity domain offsets and changes, the method always keeps high classification accuracy and unknown class detection rate, and the performance is obviously superior to that of a comparison baseline. According to the method, two-way confrontation and a progressive self-training mechanism are combined, so that accurate classification of known faults and effective identification of unknown faults are realized.

The invention discloses a rotating machine intelligent diagnosis method based on structured pruning and knowledge fusion distillation, and the method comprises the steps: training a teacher network through a training set, carrying out the structured pruning of a percentile threshold value on the teacher network based on the L2 norm calculation and normalization of a convolution filter, and generating a student network with a consistent structure. A KFD strategy including feature-level distillation and logit-level distillation is utilized to carry out deep supervision on a student network, and two types of distillation losses are weighted and fused, so that a student model still keeps relatively strong feature characterization capability and category discrimination capability under a high pruning rate. Asymmetric integer quantization is adopted for the trained student network, so that the reasoning overhead is reduced, and the embedded adaptability is improved. A general neural network operator IP core is arranged on an FPGA, efficient deployment of a quantitative student model is achieved, and low-power-consumption and low-delay real-time fault diagnosis is achieved. The method has the advantages of being high in precision, light in model weight, easy to deploy and the like, and is suitable for on-line monitoring of industrial field rotating machinery.

The application discloses a feature extraction method and system based on difficult sample mining and multi-granularity division, which is used for a cross-view geographical image retrieval task. The method first preprocesses cross-view street view images and satellite images, and uses a generative model to generate cross-view images, reducing the visual difference between different view images. Then a two-stage difficult sample mining model is constructed, including a sampling strategy based on geographical location and visual similarity, mining difficult negative samples in different ranges, and enhancing the inter-class discrimination ability. Then a multi-granularity feature division module is introduced, the image features are extracted through a ResNet50 backbone network, and the features are divided and fused according to different granularities to obtain rich and robust view-invariant feature representation. Finally, the satellite image to be retrieved is input into the trained feature extraction model, the features are extracted, and similarity matching is performed with the street view image library to obtain the cross-view retrieval result.

The application belongs to the technical field of open set identification, and discloses an open set identification method based on a hierarchical visual semantic attribute space. The application can not only accurately identify whether a target belongs to a seen class or an unseen class, but also can explicitly determine the coarse-grained class to which the target belongs and the specific attributes possessed by the target. Compared with the traditional open set identification technology, the open set identification method based on the hierarchical visual semantic attribute space has significant advantages, greatly improves the explainability of the model, and enables the model to not only give a simple unknown class discrimination when facing unknown targets, but also provide more valuable information, thereby providing solid technical support for the effective deployment of the model in complex real-world scenarios.

The invention discloses a high-resolution remote sensing building extraction method. The method comprises the following steps: acquiring multi-scale feature data and shallow enhancement feature data; obtaining deep enhancement feature data; obtaining fusion features; and generating a building extraction result. According to the method, a shallow feature enhancement module is constructed in a shallow spatial information representation stage, so that a network can more accurately highlight building related channels in a complex scene, redundant background information is inhibited, and the category discrimination capability and the positioning reliability are improved; according to the method, a deep feature enhancement module is constructed in a deep semantic information representation stage, the continuity and semantic integrity of a building boundary are improved, the perception and extraction capability of a small-scale building is enhanced, and false detection and missing detection are reduced; according to the method, a lightweight edge feature reconstruction decoder is designed in a decoding stage, so that boundary blur and artifacts caused by traditional interpolation up-sampling are effectively suppressed, and decoding stability and boundary recovery quality are improved on the premise of reducing parameter quantity and calculation overhead.

The invention discloses a human body action recognition method based on decoupling and structured modeling of CSI (Channel State Information). The method comprises the following steps: 1, collecting CSI action sample data; 2, preprocessing the collected CSI data; 3, completely integrated empirical mode decomposition, adaptive noise and Hilbert transform are introduced to carry out action-environment component dual decoupling on the preprocessed CSI data; 4, constructing a human body action recognition model based on the capsule network; and 5, generating unified action characterization insensitive to position change from the decoupled action signals by using capsule network vectorization coding and a dynamic routing mechanism, and constructing an enhancement path and a reconstruction path to respectively improve inter-class discrimination and structural consistency. According to the method, position-independent human body action recognition is realized based on modal decomposition and structured modeling technologies, action recognition under different position conditions can be effectively adapted, and high accuracy is achieved during new position testing.

The invention discloses a family dangerous object identification method and system based on improved YOLOv8, and belongs to the technical field of computer vision and edge computing. Aiming at the problems of long tail distribution of dangerous objects in a family scene, missing detection of small targets, false alarm of similar objects and limited computing power of edge equipment, three improvements are carried out on a YOLOv8s model: a class prototype adaptive mechanism is introduced, and the long tail class discrimination capability is enhanced; a multi-scale feature enhancement module is added, and the small target feature extraction effect is improved; a coordinate attention mechanism is embedded, and the target positioning precision is enhanced. Furthermore, the detection result is subjected to semantic review by using a lightweight multi-modal large model, so that false alarms are inhibited. And efficient deployment of edge equipment is realized through a model quantification technology. Experiments show that the mAP50: 95 is improved by 2.84% on a self-built data set, and the recognition accuracy and the system reliability are remarkably improved while low delay is kept.

This invention relates to the fields of network security and deep learning, specifically a Tor website fingerprinting method for satellite internet. It achieves this by constructing a self-supervised contrastive learning framework to generate multi-view augmented samples; extracting temporal-granularity feature matrices; generating synthetic negative samples based on linear interpolation, which are then compared with positive samples to form contrast pairs; extracting trajectory representations; and jointly optimizing the results using cross-entropy loss and mask reconstruction loss. Compared to traditional website fingerprinting methods, this invention enhances the model's robustness to satellite-borne inherent noise caused by the Doppler effect. The weakly and strongly augmented views of this invention provide multi-scale semantic features, while the synthetic negative samples improve inter-class discrimination and reduce the false positive rate. The joint loss optimization framework allows the model to consider both global statistical characteristics and local burst features, significantly improving the accuracy and adaptability of website fingerprinting under the conditions of highly dynamic topology and limited annotation in satellite internet constellations.

The invention relates to the technical field of cerebral infarction risk prediction, and discloses a PCIS early risk prediction system driven by multi-modal data, and the system comprises a data obtaining module which obtains PCIS-related multi-modal data; the feature extraction module is used for extracting features of the images and the multi-omics data; the feature reconstruction module reconstructs missing features; the adversarial generation module is used for generating pseudo-omics features and pseudo-image features for eliminating heterogeneity among different modes through an adversarial learning network; the intra-modal comparison module is used for enhancing the category distinguishing capability of the pseudo-omics features and the pseudo-image features by using comparison learning; the cross-modal alignment module is used for aligning semantic consistency between cross-modal features through cross-modal comparison learning; the feature fusion module is used for fusing features by using an attention mechanism; and the prediction module is used for generating a PCIS early risk prediction result according to the fused features. According to the method, the reconstruction of the multi-modal missing features and the effective extraction of the interaction relationship between the features can be realized, and the accuracy and robustness of PCIS early risk prediction are improved.

The invention discloses a power grid equipment aging state prediction method and device, equipment and a storage medium, and relates to the technical field of equipment aging prediction, a first loss function and a second loss function are constructed based on logit tensors of a teacher network and a student network, and specialized loss is constructed by taking logit as an object, so that the aging state of power grid equipment is predicted. Refined constraint on target class discrimination information and non-target class time sequence residual information can be realized, and a dynamic temperature module is driven by statistical characteristics of a teacher network in a training process to generate a first instance-level temperature and a second instance-level temperature so as to respectively adjust two classes of losses. According to the method, the capabilities of adaptively smoothing or sharpening soft labels according to sample difficulty and gradually releasing distillation weights according to a curriculation strategy are realized, and finally, a model obtained by training is used for reasoning real-time operation data of target equipment and outputting an aging degree grade, so that real-time grading diagnosis and early warning can be realized under an online working condition, and the working efficiency is improved. And the power grid equipment aging state prediction precision is improved.

This invention proposes a method for quality evaluation and multi-class discrimination of yam based on PCA and LDA, belonging to the technical field of agricultural product quality evaluation. The method includes the following steps: A) Constructing a discrimination model, specifically including A1) Data acquisition; A2) Data preprocessing and feature selection; A3) Constructing a linear discriminant model; B) Distinguishing yam categories, B1) Measuring 12 original indicator data of the sample to be tested according to the method described in A1); B2) Calculating the 12 original indicator data x... j Standardized to Z j B3) Z j Substitute the values ​​into the LDA discriminant function to calculate the values ​​for each type of yam; compare them, and the category corresponding to the maximum value is the discrimination result. When users apply the discrimination method of this invention, they do not need to understand the principle of PCA; they only need to perform simple standardization and a single linear combination calculation to complete the classification, which greatly reduces the threshold for using the model and the computational cost.

The invention discloses a class incremental learning method based on feature correlation and space structure preservation, and belongs to the technical field of machine learning. In order to solve the problems that the relieving effect of the disastrous forgetting problem in sample-free class incremental learning is limited and the class discrimination in an embedded space is difficult to maintain, a class incremental learning model based on feature correlation and space structure maintenance is established; training the class incremental learning model by using the incremental task to obtain a trained class incremental learning model; after each increment stage is completed, the trained model is used for testing to obtain a final class increment learning model, and the final model is used for class increment learning, so that the limitation of a traditional classification method in a dynamic learning environment is overcome, effective learning of newly added classes and long-term maintenance of historical knowledge are realized, and the learning efficiency is improved. And a more flexible and robust incremental learning capability is provided for the model.

The application provides a kind of based on visual identification inference and the class incremental learning method and system of data playback, the method includes: S1, the pre-training main stem of visual identification image is frozen, and bottleneck type residual adapter is introduced;S2, the causal latent variable space is constructed, the inter-concept dependency is learned, and the cross-task causal structure is continuously stable through the plastic updating mechanism and sparse constraint;S3, original sample is not stored, only the statistical distribution of historical class in semantic and causal space is saved, and pseudo sample is generated to realize data-free knowledge playback;S4, progressive weight scheduling and inference period uncertainty fusion mechanism are designed, and dynamic balance new and old knowledge is selected reliable branch output to realize stable prediction.The application can simultaneously maintain old class discrimination ability, support new class effective learning and have the class incremental learning method of reasonable forgetting mechanism under the premise of not saving old data.

An information processing method, an information processing apparatus, and a computer program that extract features of an intermediate layer that reflects subtle features of input data and perform class discrimination of discriminated data are provided. The information processing method includes: (a) a process of preparing, for each of a plurality of classes, a known feature spectrum group obtained when a plurality of teaching data is input to a machine learning model of a vector neural network type; and (b) a process of performing class discrimination processing of discriminated data using the machine learning model and the known feature spectrum group. Step (b) includes: (b1) a process of calculating a feature spectrum from input of the discriminated data to the machine learning model; (b2) a process of calculating, for each of the plurality of classes, a class-based similarity of the feature spectrum to the known feature spectrum group; and (b3) a process of discriminating a class of the discriminated data from the class-based similarity.

The invention relates to a waste paper regenerated pulp impurity classification method and system based on multi-modal sensing, and the method comprises the following steps: S1, obtaining an original multi-modal signal set of waste paper regenerated pulp flow through sensing array detection; s2, the collected original multi-mode signal set is preprocessed, and an aligned multi-domain signal set is obtained; s3, based on the aligned multi-domain signal set, features are extracted and normalized, and a multi-modal feature vector is obtained; s4, inputting the multi-modal feature vector into improved multi-category discrimination for feature correlation modeling, and performing multi-category discrimination; s5, determining the specific position and quantity of the impurities in the detection channel by combining a spatial positioning algorithm according to the multi-class discriminant output classification information; and S6, according to the types of the impurities and the specific positions and the number of the impurities in the detection channel, removing the impurities through a linkage execution unit, and purifying the waste paper regeneration pulp flow. According to the invention, accurate removal of waste paper regenerated pulp impurities is effectively realized.

A method for estimating a global uncertainty of output data of a computer-implemented main neural network is described, comprising the steps of: determining (102) a first measure quantifying how much a current input data of the main neural network follows the same distribution as the data used for training the main neural network; generating (103) a second measure quantifying a certainty of the main neural network in its own input data-based prediction, in particular by using at least one Bayesian method, e.g. a Bayesian neural network or an ensemble-based method; determining (104) a third measure based on an estimate of a class discrimination feature in the input data and a comparison of the feature with a class activation probability distribution, in particular wherein the class activation probability distribution is created based on the estimated class discrimination feature during training of the main neural network; determining (105) the global uncertainty based on at least two of the first measure, the second measure and the third measure.

The application provides a document directory error repair method and system based on multi-model cooperation, comprising constructing a document into a graph structure, each paragraph as a node and extracting semantic, format and position features; using a three-layer graph convolutional neural network to process the graph structure to obtain a node representation fused with global information; screening nodes with confidence exceeding a threshold as candidate titles; extracting text and visual features of the candidate titles; performing two-class discrimination on the filtered candidates to form a real title set; detecting title errors and constructing an input sequence containing context, using an adaptive sliding window to process a long document; generating multiple candidates, scoring and selecting the best; matching new and old titles; and minimizing format consistency and serial number continuity cost. The application can accurately identify the title through its structural features in the graph even if the format of the title is not standard or lacks obvious markers, greatly improving the recall rate and accuracy of title identification.

The invention provides a cross-working-condition bearing fault diagnosis method of a prototype comparison network with minimum entropy optimization, and relates to the technical field of intelligent fault diagnosis. In a pre-training stage, an auxiliary domain discriminator is constructed, DA is assisted by discrimination information of a classifier, classification difficulty is evaluated through sample entropy, and performance degradation in a DA process is inhibited; in the training stage, a prototype is found in a learning vector quantization mode; through intra-domain prototype comparative learning, sample features are prompted to closely gather around similar prototypes in a feature space, and meanwhile, the sample features are kept separated from heterogeneous prototypes; further, the intra-class consistency of the features is enhanced, the inter-class distinction degree is improved, and therefore intra-domain accurate alignment is achieved on the feature level; besides, the cross-domain instance-prototype learning aligns the semantic structure in the shared embedding space, and through a fine-grained alignment strategy, the negative migration problem is relieved, and the generalization ability of the model is improved; and the generalization performance of the model in a cross-working-condition small sample scene is improved through pseudo label generation and a weighted loss function.

This invention provides a method, system, and application for interpreting all features of remote sensing images by integrating zoning control and hierarchical extraction. By innovatively introducing a zoning control network constructed from real geographic elements such as roads and waterways, the large-scale image interpretation task is decomposed into multiple independent geographic units, effectively avoiding the problem of extraction results contradicting geographical common sense. Simultaneously, this invention employs a hierarchical extraction mechanism, extracting features class by class within each zoning according to visual saliency. Each dedicated model only needs to learn to recognize a single or a few categories, fundamentally improving inter-class discrimination and overall extraction accuracy. Furthermore, by encapsulating all stages—data preprocessing, zoning generation, hierarchical extraction, and result fusion—into visual, programmable tool nodes, and uniformly scheduling and executing them through a workflow engine, this completely changes the shortcomings of existing technologies, such as fragmented processes and reliance on manual coordination, significantly improving the standardization of production and engineering application capabilities.

This invention provides a method and system for grouping flue-cured tobacco using feature channel weighting and dynamic loss control, relating to the fields of deep learning and flue-cured tobacco grading. The method involves acquiring images of flue-cured tobacco from N main groups using an image acquisition device to establish a flue-cured tobacco grouping dataset, where N is a positive integer. This dataset is then preprocessed to obtain a preprocessed dataset. A flue-cured tobacco grouping classification network (TGNet) is designed and trained on the preprocessed dataset to obtain a flue-cured tobacco grouping classification model. Based on this model, the grouping results are obtained. This invention solves the technical problems of existing deep learning methods for flue-cured tobacco grouping, such as lack of key feature representation in high-scale features, limited inter-class discrimination ability, and a tendency for the model to learn from majority class samples during training. It achieves real-time classification of flue-cured tobacco groups, effectively improving the efficiency of flue-cured tobacco group classification and reducing the cost of manual grading.