81 results about "Invariant feature" patented technology

The invention relates to the technical field of artificial intelligence, and discloses an unmanned aerial vehicle flight control-oriented intelligent obstacle recognition method, which comprises the following steps of constructing an adaptive wind disturbance fuzzy kernel based on unmanned aerial vehicle attitude data, and synthesizing a degraded image for training; a specific obstacle recognition model integrating a frequency domain and space domain joint feature decomposition module, a turbulence invariant feature enhancement module guided by physical prior information and a double-branch anti-fuzzy feature extraction network is adopted, and a fuzzy robustness contrast loss function is combined to carry out progressive training so as to learn feature representation insensitive to fuzziness; after the trained model is deployed, the wind disturbance fuzzy intensity of a real-time input image is estimated on line, the internal workflow of the model is dynamically adjusted according to the wind disturbance fuzzy intensity, the attention weight is adaptively adjusted, and the output of a trunk or an anti-fuzzy branch is selected. According to the invention, through coupling of the physical model and deep learning, the recognition robustness, accuracy and stability of the model in a dynamic wind disturbance environment are improved.

The invention relates to the technical field of multi-modal data processing, and discloses a multi-modal sentiment analysis method and system based on feature decoupling and variational optimization, and the system comprises a feature decoupling module, a modal variational alignment module, an adversarial representation module and a multi-path interactive fusion network. According to the system, modal features are separated into modal specific features and modal invariant features through a feature decoupling technology, uncertainty modeling and re-parameterization processing are carried out on exclusive features by adopting a single-modal uncertainty perception fusion technology, and robustness of feature learning is enhanced by adopting an adversarial training mechanism for shared features. Model optimization is carried out by combining a cross-modal attention mechanism modeling inter-modal interaction relationship and a multi-level loss function, so that efficient feature extraction, robust feature fusion and accurate emotional intensity prediction of multi-modal data are realized.

The invention provides a multi-source domain invariant acoustic feature extraction method and system for an equipment operation state, and belongs to the technical field of equipment maintenance, and the method comprises the steps: constructing a multi-source domain invariant acoustic feature extraction network based on a DANN model, and the network comprises a feature extractor, a classifier, a domain discriminator and a multi-domain acoustic feature class boundary constraint module; the feature extractor extracts high-dimensional features of sound signals, the classifier carries out fault mode recognition, and the domain discriminator realizes domain prediction. The multi-domain constraint module generates an embedding space, and calculates the maximum mean value difference, the local maximum mean value difference and the Euclidean distance among different source domain features. The network constructs a loss function by taking minimization of inter-domain difference and classification loss and maximization of inter-domain distance and domain discrimination loss as targets, and carries out adversarial training through multi-source tagged acoustic data. According to the method, domain invariant features are extracted by using adversarial learning and hidden space constraint alignment of multi-source domain acoustic features, so that the influence of feature offset under a cross-working-condition condition is effectively reduced, and the fault mode recognition accuracy is improved.

The invention discloses a training and online diagnosis method and system for a ship fault diagnosis model. The method comprises the following steps: generating a dynamic weight based on multi-source domain and target domain data; using the weight to guide a feature extractor and a domain discriminator to carry out adversarial training so as to learn domain invariant features; fusing the weighted supervision loss and domain adversarial loss, and combining a target domain regularization item optimization model; screening a target domain high-confidence sample through a dynamic threshold value to generate a pseudo label and performing iterative training; and finally, performing real-time fault diagnosis by utilizing the trained model, and adaptively updating model parameters according to online data distribution change. According to the method, the problem of negative migration in multi-source domain fusion is effectively solved, and the generalization ability, the diagnosis precision and the long-term operation stability of the model in the target domain are improved.

This invention provides a method, apparatus, device, and storage medium for fault diagnosis of rotating components of a crane, relating to the field of mechanical fault diagnosis technology. The method includes: processing source and target domain data of the crane's rotating components in a unified format to output a normalized vibration signal; aligning feature distributions through a shared encoder and adversarial training to output domain-invariant features; constructing conditional embedding vectors based on the domain-invariant features and generating target domain fault data using a diffusion model; combining the generated fault data with real data to form a diagnostic dataset, extracting multimodal features, fusing them, and outputting the fault diagnosis result through a classifier. This invention effectively solves the problem of scarce crane fault data through a diffusion model and, combined with multimodal feature fusion technology, improves the accuracy, robustness, and cross-domain generalization ability of fault diagnosis.

The application discloses a hyperspectral wetland image classification method based on a graph capsule neural network, which comprises the following steps: S1, learning feature transformation is performed on an adversarial domain self-adaptive framework, so that source domain samples and target domain samples of a hyperspectral wetland image are matched in features; S2, a graph capsule neural domain self-adaptive network structure is constructed, domain-invariant features and domain-related features are extracted, and transferable features are discovered and shared across domains; and S3, a coupling structure two-classifier is designed, the two-classifier is trained by using the source domain samples, classification differences of the target domain samples are maximized, and precise classification of the hyperspectral wetland image is realized by identifying a classification boundary. Meanwhile, the application discovers transferable knowledge and realizes cross-domain sharing, enhances effective discrimination of a class boundary, and finally realizes precise classification of the hyperspectral wetland image under conditions of unknown regions, complex scenes, and lack, deficiency and imbalance of data types.

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 embodiment of the invention discloses a weld defect intelligent detection method and device based on multi-modal feature fusion. The method comprises the steps that an excitation unit is controlled to apply standardized mechanical knocking excitation to a target weld joint, and response signals generated by the weld joint are collected; transforming the time domain signals corresponding to the acoustic signal and the vibration signal based on Lie group transformation to obtain an invariant feature vector so as to construct a multi-modal feature vector; the weight of each feature in the multi-modal feature vector is determined based on the physical parameters of the target welding seam, and the weighted distance between the multi-modal feature vector and each clustering center in a standard database is calculated based on the weight, so that a target clustering center is determined; and in response to the fact that the target weighted distance corresponding to the target clustering center is larger than a distance threshold value, determining the defect type of the target weld joint based on the similarity between the multi-modal feature vector and each defect feature vector. In the embodiment of the invention, higher-precision and more reliable weld defect identification can be realized, and the whole process can be automatically carried out without manual operation.

A method and system for explainable classification of a target point cloud may include receiving a target point cloud comprising N points in a multidimensional space, applying a feature extraction model to extract, for each point, a permutation-invariant feature vector comprising local feature entries, applying a bottleneck function on the feature vectors to produce a global feature vector having F global feature entries, applying a classification model on the global feature vector to classify the target point cloud according to classification criteria, for one or more points, applying an aggregation function over the local feature entries of the respective feature vector, prior to the bottleneck function, to obtain an aggregation value, and indicating importance of the points in the classification based on their aggregation values.

The invention discloses a recognition method of a reversely-installed fastener, a storage medium and equipment, and the method comprises the steps: firstly obtaining an original image of a track, carrying out the data enhancement and domain extension of the original image, inputting the enhanced track image and a domain extension image into a fastener recognition model, and carrying out the iterative training, thereby obtaining a trained fastener recognition model; inputting a track image to be recognized to obtain a fastener recognition result of the track image; the fastener identification model is based on Faster R-CNN and comprises a backbone network, a region candidate network, a domain comparison module and a detection head, the domain comparison module introduces a class-level domain comparison learning mechanism to encourage a detector to understand correlation and difference between fasteners in different fields on the class level, the model is guided to mine fastener class-level domain invariant features, and the detection head is used for identifying the fasteners in the class-level domain. According to the method, the problem that the reversely-installed fastener is difficult to recognize in multiple scenes is solved, the generalization and accuracy of track fastener recognition are greatly improved, the cost is saved, and the method has important practical application significance.

The invention provides a civil engineering structure apparent damage small sample intelligent diagnosis method and system, and relates to the field of artificial intelligence. Comprising the following steps: S1, inputting a labeled source domain data set and a labeled small sample target domain data set, and carrying out data preprocessing; s2, training an encoder through an adversarial training mode containing domain adversarial loss, and extracting domain invariant features; s3, extracting domain invariant features from the target domain data set by using the trained encoder to obtain a target domain invariant feature set; using the target domain invariant feature set training condition to generate an adversarial network, and obtaining a target domain sample set; combining the target domain data set and the target domain sample set to form a mixed training set; s4, using the mixed training set to finely adjust a diagnosis network; and S5, extracting features of a target domain image to be diagnosed by the trained encoder, and inputting the features into the trained diagnosis network to obtain a damage identification result. According to the invention, high-precision, high-robustness and high-adaptability intelligent structural damage diagnosis is realized.

The embodiment of the application discloses a domain generalization target detection method based on a large model guide and related equipment, a training image set with the same content is obtained, and a foreground enhanced image set is generated in combination with foreground mask guidance, which not only helps to enrich the diversity of data enhancement from the root by means of multiple training data, but also focuses on the target foreground for feature enhancement through the foreground mask, thereby effectively retaining the positioning characteristics of the target while improving the richness of data distribution and avoiding damage to the positioning accuracy of the target. The style of the foreground enhanced image set and the to-be-predicted image is fused to realize feature adaptation, and then a hyper-domain invariant feature encoding is used to obtain a feature map after feature encoding. On the basis of retaining key feature information, the feature map after feature encoding efficiently extracts domain invariant features with strong generalization, thereby avoiding feature information loss and improving feature representation capability, so that accurate target detection results are obtained.

The invention provides a knowledge distillation method for cargo identification model lightweight, and relates to the technical field of knowledge distillation, and the method comprises the steps: constructing a prototype representation learning module and a feature enhancement module, and enabling local semantic prototypes extracted from a large-scale teacher model, such as invariant features of'peel texture ', 'leaf edge' and the like, to be subjected to feature extraction; and the knowledge is migrated to a lightweight student model, so that efficient transmission of the knowledge is realized. The feature enhancement module performs selective enhancement on intermediate features of the student model based on a prototype related attention mechanism, and improves the ability of the student model to discriminate similar goods. Meanwhile, a joint optimization objective including embedded layer distillation loss, prototype consistency loss and classification loss is designed, and the problem of performance reduction caused by cross-task label space difference and data distribution imbalance is relieved.

The invention discloses an unsupervised domain adaptive method based on a cascade learning strategy, and aims to decouple the training process of a source domain and a target domain, prevent semantic information confusion and realize fine-grained adaptation to the target domain. Specifically, the proposed two-stage cascade learning framework mainly comprises two stages of learning processes, in the first stage, a low-rank adaptation fine tuning module is used for performing fine tuning of a source field on a visual language pre-training model so as to learn feature information which is related to categories and invariable in field; and in the second stage, learning knowledge of a target domain by freezing the fine-tuned visual language pre-training model and a low-rank adaptive fine-tuning module and introducing text prompt, and refining a pseudo tag by means of knowledge of a source domain. According to the method, semantic learning and a domain-specific adaptation process are effectively decoupled, so that the performance of the target domain is improved.

The application discloses a water surface target and underwater target classification method based on unsupervised domain adaptation, and belongs to the technical field of underwater acoustic target depth classification. The application solves the problems of poor generalization and target classification performance of traditional deep learning methods under small sample conditions. The classification model constructed by the application introduces sound field elevation angle structure simulation data to assist training, and extracts domain invariant features of simulation data and measured data through adversarial training, so that the classification performance degradation problem caused by the difference in feature distribution between domains is relieved. The application can realize effective classification of water surface targets and underwater targets under small sample conditions, and does not need to know the class labels of measured data, effectively improving the generalization and target classification performance of the model. The method can be applied to the classification of water surface targets and underwater targets.

The application relates to the technical field of EEG emotion recognition, and provides a cross-subject EEG emotion recognition method and system based on decoupled hybrid meta-learning, which comprises the following steps: constructing a backbone network which is decoupled and connected in series by a cross-subject invariant feature encoding module and a sparse dynamic graph topology adaptation module; firstly, pre-training the cross-subject invariant feature encoding module based on a supervised contrast loss and an adversarial loss, fixing the parameters of the cross-subject invariant feature encoding module after training convergence, and outputting general node features; then, constructing a double-path hybrid meta-learning architecture: in the inner loop stage, a classification head is accessed for parameter adaptation, and then a scene semantic memory reasoning module is accessed for memory construction; in the outer loop stage, the prediction results of the parameter optimization path and the memory cognitive path are weightedly fused, and global meta-parameters are updated. Through the method, the accuracy and robustness of cross-subject EEG emotion recognition are improved.

The invention relates to the technical field of machine learning, and particularly discloses a false tooth quality detection method and system based on machine learning. The system comprises a data acquisition and preprocessing module, a multi-source feature fusion and adaptive representation module, a meta-learning driven defect detection core module, an incremental model updating and knowledge distillation module and a decision output and feedback module. In combination with a meta-learning mechanism, small sample rapid adaptation is realized, and the model is continuously optimized by using incremental learning and knowledge distillation, so that the adaptability, robustness and long term evolution capability of the system in diversified scenes are improved.

The invention relates to a line fault reason intelligent identification method based on a recording waveform image, and the method comprises the steps: carrying out the feature extraction of a fault waveform image through employing a scale invariant feature transform (SIFT) feature extraction method, and mining key feature information in the fault waveform image; a clustering method (K-means) is utilized to classify similar feature descriptors according to clusters to form a visual dictionary, and on this basis, an image pyramid technology is utilized to realize multi-scale feature fusion of image vectors; and a support vector machine (SVM) classifier is introduced, and vectorized image features are utilized to carry out accurate identification on fault causes. The line fault reason identification model constructed by the invention can effectively predict various power grid line fault reasons, and improves the accuracy and timeliness of fault reason identification; good robustness is shown in an actual case test, and generalization performance and stability of the model are ensured through cross validation and monitoring of model performance indexes; and powerful support is provided for fault diagnosis and maintenance of a power system.

The invention discloses a cross-domain steganographic text recognition and analysis method and system based on multi-adversarial domain adaptation, and belongs to the technical field of network security. The method comprises the following steps: constructing a feature extractor of double heterogeneous branches, and performing fine-grained semantic feature extraction on a real text and a text in a public data set; constructing a steganography text analyzer based on the combination of a multi-adversarial domain self-adaptive domain invariant feature extractor and a discriminator based on a full connection layer, allocating a unique domain discriminator for each class, realizing cross-domain feature alignment, and updating parameters of the feature extractor and the discriminator; for the trained steganography text analyzer, a mutual learning mechanism and a feature alignment means are further used to optimize the model; and deploying a steganography text analyzer and carrying out real-time detection. Compared with a traditional single-branch method or a method without a mutual learning mechanism, the method has the advantages that the cross-domain knowledge migration efficiency is improved, and stable recognition performance can still be maintained even in a scene with remarkable inter-domain distribution difference.

The invention discloses a method for automatically classifying and identifying the types of floating objects in a coagulating sedimentation process section, and the method comprises the steps: carrying out the preprocessing of an obtained image of the floating objects in the coagulating sedimentation process section of a water supply plant, and carrying out the white balance correction and noise reduction preprocessing; taking the preprocessed floating object image as an input, and constructing an illumination invariant feature channel; constructing a multi-source feature extraction library based on the illumination invariant feature channel; in the multi-source feature extraction library, establishing a corresponding feature sub-library according to an apparent scene of the preprocessed floating object image; and according to the floating object shooting condition, selecting the feature sub-library meeting the floating object shooting condition, and adopting a support vector machine classification model to automatically classify and identify the type of the floating object. According to the method, the dependence on manual inspection can be reduced, the timeliness of floater event discovery and the consistency of type judgment results are improved, and decision support is provided for control of floaters in the process section.

The application discloses a hyperspectral image anti-attack method based on invariant features, which comprises the following steps: step one, constructing a sample set; step two, pre-training a deep convolutional neural network classification model; step three, building an anti-attack model; step four, constructing a loss function of the anti-attack model; step five, iteratively training the anti-attack model; and step six, testing the trained anti-attack model. The anti-attack method can enhance the robustness of a convolutional neural network and improve the classification accuracy of a hyperspectral classification model against an anti-attack.

This disclosure provides a method, device, electronic equipment, and storage medium for HVAC fault diagnosis, relating to the field of fault diagnosis technology. It acquires multi-source time-series operational data of an HVAC system and performs standardized preprocessing. A multi-scale feature extraction network is constructed, containing convolutional branches with different receptive fields set in parallel and achieving adaptive fusion of features from each branch based on an attention mechanism. This network is then optimized using domain adversarial training to align feature distributions on the source and target domain datasets, thereby obtaining a domain-invariant feature extractor. Finally, this domain-invariant feature extractor is combined with a few-sample learning paradigm of metric learning to calculate feature prototypes for each category in the dataset. The fault category is determined based on the distance metric between the fault query data and the feature prototypes. Therefore, this method can solve the problems of poor model generalization and difficulty in accurately diagnosing faults in small-sample scenarios in existing technologies.

The application belongs to the technical field of image processing, and relates to a converter station multi-source heterogeneous image registration method based on feature similar triangles. The method firstly acquires images and extracts scale-invariant feature points, encodes feature vectors to construct initial matching candidate point pairs. The core lies in that feature triangle primitives composed of reference and to-be-tested feature triangles are constructed by randomly sampling from the initial matching set; then, the geometric properties of the primitives, such as internal angles and normalized edge length ratios, are calculated, and topological consistency pre-screening is performed on samples to obtain an effective sample set. Subsequently, the effective sample set is used to estimate a preliminary transformation model and screen a global inlier set; then, an accurate spatial mapping transformation matrix is calculated based on the global inliers, and finally, through coordinate mapping and resampling filling, the aligned heterogeneous image stream is obtained. The application solves the problems of high computational cost and limited registration accuracy caused by high false matching rate when existing registration methods are used to process heterogeneous images of converter stations.

The application relates to a high-resolution range profile (HRRP) increment recognition method based on domain condition feature calibration, which comprises the following steps: collecting an HRRP signal to be recognized; inputting the HRRP signal to be recognized into a trained HRRP increment recognition network to obtain a recognition result of a target category; wherein the HRRP increment recognition network comprises a shared feature extractor, a domain condition feature calibrator, a cross-domain feature aligner and a classifier which are connected in sequence, wherein: the shared feature extractor is used for performing feature extraction on the HRRP signal to be recognized to obtain an HRRP feature vector; the domain condition feature calibrator is used for outputting a domain feature calibration vector; and the cross-domain feature aligner is used for outputting a domain-invariant feature vector which is robust to posture changes, wherein the domain-invariant feature vector is used for recognition by the classifier, so that the recognition result is obtained. The method can significantly improve the generalization ability and memory efficiency in a serialized posture domain.

The application provides a pedestrian re-identification method and equipment based on a mixed attention decoupling re-identification network, so as to enhance the discrimination ability of field-invariant pedestrian features, thereby forming reliable class boundaries and learning the in-class semantic diversity. The design of the mixed attention module in the method is to strengthen the field-invariant feature expression in the form of attention weight decoupling from the spatial and channel perspectives, which forces the network to automatically use the image regions and attribute clues conducive to cross-domain re-identification. In addition, based on the enhanced field-invariant feature expression, a multi-difficult sample memory learning strategy is proposed to improve the in-class diversity of target domain samples. The application optimizes the feature learning process by updating the reliable sample memory library and multiple difficult sample memory libraries, and by considering the relationship between samples in the same class, the application can be used to capture significant in-class semantic changes, and can positively affect the accuracy of pseudo labels.

The invention discloses an interpretable single-domain generalization method and system for multi-label classification of ophthalmic diseases, and the method comprises the following steps: obtaining the feature representation of an original image sample and an enhanced image sample through double-branch input processing; a feature guiding mechanism is applied, and an interpretable signal is utilized to carry out weighted guiding on features so as to focus a clinical related area; domain invariant features are extracted, masks are generated through similarity calculation, domain sensitive features are filtered out, and feature representation insensitive to distribution changes is reserved; modeling relevance among disease tags, learning relevance among tag vectors through an attention mechanism, and calculating the existence probability of each tag in the image; attention feature alignment is executed, and attention vector consistency of different branches is restrained. Through collaborative design of double-branch feature processing, a feature guide mechanism, domain invariant feature filtering and label association modeling, a multi-label classification system which can be generalized to an unknown domain only through single-source domain training is realized.

The application discloses a single-source domain target recognition generalization method, product, medium and equipment, relates to the field of domain adaptive target recognition, and comprises the following steps: generating a stylized image corresponding to an original image through a style feature space; encoding original image and stylized image features; jointly decoupling the original image and the stylized image features into domain-invariant features and domain-unique features; training a region candidate network using the domain-invariant features, and optimizing the network using orthogonal loss and target recognition loss functions; and inputting a complex unknown weather sea target image into the optimized network to obtain the category and position of the sea target in the complex unknown weather sea target image. The application can overcome the problems of difficulty in extracting domain-invariant features in complex weather data sets, single style generation and data generated being biased towards source domain distribution, and difficulty in method model generalization, improve the generalization ability of the model, and effectively improve the recognition ability of sea targets under different complex unknown weather conditions.

This invention provides a cross-device domain adaptation method based on domain decoupling and class confusion minimization feature alignment. The main steps include: collecting vibration signals from different devices to construct labeled source domain and unlabeled target domain datasets, and dividing them into training and testing sets; constructing a domain decoupling module based on a feature extractor with convolutional channel separation and a decoder reconstructing the input data, and constructing a classifier and domain discriminator on this basis; constraining the model's learning behavior through sample reconstruction loss, conditional adversarial domain adaptation loss, classification loss, and class confusion minimization loss, the model decouples features into domain-specific features and domain-invariant features to enhance the extraction effect of domain-invariant features, aligns domain-invariant features, and simultaneously minimizes inter-class confusion in the target domain; completing model training on the training set, and finally establishing a high-precision fault diagnosis model to achieve fault diagnosis of the target device. This invention enhances the representation performance of domain-invariant features through the decoupling module, improves feature alignment by combining conditional domain adaptation loss and class confusion minimization loss, and optimizes the classifier's classification behavior in the target domain, effectively addressing the problem of completely missing labels in the target device dataset.

This invention discloses a fault diagnosis method for cross-domain migration of transmission chains based on sparse learning and Riemannian metric, comprising the following steps: data acquisition and preprocessing; constructing a feature extraction model based on a sparse autoencoder; processing the extracted features through covariance mapping and Riemannian dimensionality reduction; and inputting the dimensionality-reduced manifold features into a multilayer perceptron classifier to classify the fault type. This invention proposes a feature extraction model based on a sparse autoencoder, which can automatically extract invariant features under various operating conditions and, combined with class discriminant analysis and source-target domain matching strategies, effectively improves the accuracy of fault identification and diagnosis across different operating conditions.

The application provides a large model optimization method and system based on multi-modal information and AI, relates to the technical field of artificial intelligence, and comprises the following steps: by extracting multi-modal parameter features and interaction features, dynamically adjusting a contribution coefficient to realize feature migration and obtain a cross-modal fusion vector; adopting an antagonistic mechanism to align the modal features to obtain domain invariant features; constructing a prompt chain based on modal confidence, and optimizing the prompt chain by using AI reinforcement learning, and iterating to convergence to obtain an optimization result; and finally updating the large model parameters. The application realizes effective fusion of multi-modal information, and improves the optimization effect and generalization ability of the human-computer interaction large model.