160 results about "Hypersphere" patented technology

The invention discloses a communication interference signal open set identification method, system and device and a medium. The method comprises the following steps: carrying out short-time Fourier transform on a communication interference signal to obtain a time-frequency graph; performing multi-scale feature representation on the time-frequency diagram by using a Res2Net-based multi-scale feature extraction network; constructing a projection layer to carry out hyperspherical embedding on the multi-scale features, carrying out modeling by utilizing vMF distribution, and designing a compactness and dispersity loss function; multi-scale features after modeling are input into an OpenMax layer for open set recognition, output of a projection layer is used as an activation vector to improve OpenMax, Euclidean distance is replaced with cosine distance, input sample unknown is calculated based on an extreme value theory, category probability distribution is adjusted, and some abnormal samples can be classified into unknown categories; the Res2Net more flexibly captures multi-scale information than the convolutional network; the separation of inter-class features and the compactness of intra-class features are effectively enhanced through the hyperspherical vMF distribution; the OpenMax layer endows the network with unknown category identification capability; the method has better performance and wider universality; the system, the equipment and the medium are used for realizing the communication interference signal open set identification method.

The invention discloses a network information security detection method and device, equipment and a storage medium, and the method comprises the steps: obtaining network flow data, network log data and user behavior data, and carrying out the data preprocessing operation, and obtaining multi-dimensional network time sequence data; according to the multi-dimensional network time sequence data, performing multi-scale feature extraction through a pre-training model to obtain multi-scale feature data, and inputting the multi-scale feature data into a multi-scale normalized stream model to obtain multi-scale normalized stream data; inputting the multi-scale normalized stream data into a hyperspherical support vector machine model, and performing multi-dimensional time series data anomaly classification to obtain classified time series data; according to the time sequence data, abnormal score calculation of the time sequence data is carried out, and a real-time abnormal score of each time sequence data is obtained; and when it is judged that the real-time abnormal score is greater than a preset abnormal threshold value, generating an early warning signal, and sending the early warning signal to a user side. According to the method, real-time detection and accurate early warning of network information security can be realized.

The invention discloses a hyperspectral image open set classification method based on prototype similarity distribution modeling. The method comprises the following steps: acquiring a training sample set and a test sample set; initializing a category prototype on the unit hyper-sphere and forming uniformly distributed prototype spaces through iterative optimization; training a deep learning network based on a joint loss function, guiding the samples to form high-discrimination similarity distribution in a prototype space, and calculating similarity vectors of the samples and prototypes of each category; training the OCSVM by using the similarity vector of the known class sample to learn the distribution boundary of the known class in the prototype space; in the test stage, a test sample is input into the deep learning network, the similarity vector of the test sample is calculated, and whether the test sample belongs to a known class or not is judged by the OCSVM; and if the class is a known class, determining the fine-grained classification according to the class prototype of the maximum similarity component in the similarity vector. According to the method, the interpretability and generalization of the open set classification model are enhanced, and the misrecognition risk between similar categories is reduced.

The invention discloses a universal domain adaptive image classification method based on distance entropy weighting, and the method specifically comprises the steps: 1, obtaining source domain data and target domain data, 2, building a model, and carrying out the pre-training; step 3, mapping the source domain data and the target domain data to a hypersphere; 4, setting all prototypes of the source domain as 0; step 5, calculating a source domain category weight # imgabs0 # and a target domain sample weight # imgabs1 #; step 6, performing adversarial training by using a weight weighting training model and a domain discriminator D, and determining whether the data is from a source domain or a target domain; obtaining weighted confrontation loss; and 7, screening a target domain sample to obtain a target domain auxiliary domain, and outputting an image for classification. According to the universal domain adaptive image classification method based on distance entropy weighting disclosed by the invention, the problem that image classification is not clear due to the fact that a model in the prior art cannot effectively distinguish and recognize private categories of a target domain is solved.

The invention discloses a discrete dynamic graph link prediction method based on a self-adaptive product space, and the method comprises the steps: obtaining a dynamic relation network, and dividing the dynamic relation network into a plurality of discrete graph snapshots; combining the Euclidean space, the hyperbolic space and the hyperspherical space to construct a product space, and determining parameters of each space; node features are projected to a product space through exponential mapping, and initial node embedding is generated; executing message passing in the product space to obtain node embedding containing geometric structure information; aggregation node embedding is carried out by using an attention mechanism, and historical node embedding is generated; the current snapshot embedding and historical information is dynamically updated through the HyperGRU; calculating a link prediction probability of any two nodes by using a Fermi-Dirac decoder, and optimizing parameters through cross entropy loss; dynamically adjusting each space parameter by using a reinforcement learning mechanism; and calculating the link prediction probability at the next moment based on the optimized product space and parameters. According to the method, the complex geometric characteristics and the time evolution law of the dynamic graph can be efficiently captured, and accurate prediction is realized.

The invention provides a large language model generation code detection method and system, which is applied to the technical field of artificial intelligence, and comprises the following steps: obtaining a to-be-detected code; a to-be-detected code is input to a trained shared encoder, a code feature vector is obtained, the shared encoder is obtained through multi-target joint training, and the multi-target joint training is used for optimizing classification loss, domain confrontation loss, comparison loss and difficult sample loss at the same time; l2 normalization is carried out on the code feature vector, and the code feature vector is mapped to a hyperspherical space to obtain spherical embedding; the sphere is embedded and input into a sphere category classifier based on sphere logistic regression for classification processing, a detection result of the to-be-detected code output by the sphere category classifier is obtained, the detection result comprises AI generation and human writing, and a decision boundary of the sphere category classifier is an intersection line of a hyperplane and a hypersphere for classification. According to the invention, the AI generation code and the human compiled code can be accurately distinguished.

The invention discloses a single-classification industrial control system anomaly detection method based on double-view information bottleneck fusion, which belongs to the technical field of industrial control system anomaly detection and comprises the following steps of: in a training stage, simultaneously constructing a time sequence view and a pseudo image view; respectively extracting characterization through a time dynamic encoder and a pre-trained visual backbone; performing cross-view compression in the variational information bottleneck fusion module and establishing projection branches only depending on sequence representation; a normal subspace is learned around a center vector, an accurate hypersphere is established to describe normal data, and a center distance is used as an abnormal score and a quantile threshold is used to complete discrimination; in the detection stage, online recognition can be performed only by inputting a time sequence view. According to the method, dual-view prior and variational information bottleneck are fused, end-to-end collaborative optimization is carried out on the dual-view prior and the variational information bottleneck and deep support vector data description, an accurate decision boundary can be established under the condition of a small number of samples, and a solution for industrial control system anomaly detection under the condition that the samples are limited is provided.

The invention provides an incomplete vibration data damage identification method and system fusing comparative learning and self-supervised learning, and aims to solve the problems of data scarcity and unbalanced and incomplete data sets in civil engineering structure damage identification, structure acceleration data is acquired through a vibration sensor, data enhancement is performed after preprocessing, and the structural acceleration data is acquired through a vibration sensor. Comprising random mask enhancement and white noise enhancement, a neural network model based on an auto-encoder is constructed, and the neural network model comprises an encoder, a reconstructor, a classifier, a predictor and a dimension rising device. Low-dimensional features are mined through self-supervised learning, feature distribution is optimized in combination with comparative learning, the similarity of similar features and the distinction degree of different types of features are maximized, and finally the health state, known damage, unknown damage and fuzzy damage states of the structure are judged through the hyper-sphere boundary of a high-dimensional decision space. According to the method, the accuracy and robustness of damage identification are remarkably improved, and particularly, the method has excellent performance in the aspect of slight damage identification.

The embodiment of the invention provides a learning embedding method and device for a double-view knowledge graph, electronic equipment and a storage medium. The method comprises the following steps: carrying out global mapping conversion processing on entity embedding features of a triple to obtain entity global features; performing local mapping conversion processing on the entity global features to respectively obtain entity hypersphere features, entity hyperbolic features and entity Euclidean features; inputting the entity hypersphere feature, the entity hyperbolic feature and the entity Euclidean feature into an attention fusion model to obtain an entity fusion feature; according to the entity global feature and the entity fusion feature, obtaining a score value about the triad; and updating the relationship between the entities in the initial knowledge graph according to the score value to obtain a target knowledge graph. According to the method, modeling can be carried out on embedding of the entity through the global view angle and the local view angle, and the learning accuracy is improved.

The invention belongs to the technical field of multi-view clustering, and discloses an end-to-end multi-view clustering method and system for dynamic cross-view node interaction. The method comprises the following steps: constructing graph structure information according to node features in a multi-view data set; and inputting the graph structure information and the node features into the multi-view graph neural network model to obtain a clustering result. The multi-view graph neural network model comprises an encoder, a multi-layer perceptron, a decoder and a hyperspherical clustering module with regularization constraint; the encoder comprises a plurality of encoder layers, and each encoder layer comprises an in-view representation learning module and a cross-view representation learning module. According to the method, an unsupervised end-to-end node-level cross-view message transmission mode is provided, direct information interaction between cross-view nodes is established, complementary information propagation and consistent semantic information learning are effectively promoted, clustering is carried out by adopting a hypersphere with regularization constraint, and the clustering efficiency is improved. Balanced distribution and good separability between different categories can be ensured.

The invention relates to the technical field of fault positioning, and discloses a fault position positioning method and device based on multiple acquisition devices, equipment and a medium, and the method comprises the steps: obtaining a plurality of device positions of the acquisition devices of a plurality of traveling wave signals, the time difference of arrival of the traveling wave signals acquired by every two acquisition devices, and the propagation speed of the traveling wave signals; a plurality of hypersphere equations are established according to the positions of every two devices, the time difference of arrival and the propagation speed, and the hypersphere equations are used for reflecting the difference value relation of the distances between the positions of every two devices and the positions of the fault points corresponding to the traveling wave signals; and using a preset particle swarm optimization algorithm and a hyperspherical equation to carry out fault point position positioning processing to obtain an optimal fault point position. Through the above mode, a plurality of acquisition devices can be adopted to capture traveling wave signals, then the hyperspherical equation is established, and finally, the particle swarm optimization algorithm and the hyperspherical equation are used to carry out fault point position positioning processing, so that the optimal fault point position is obtained, and the fault positioning precision is improved.

The invention discloses a rapid yield analysis method based on xgboost proxy model truncation sampling, and the method comprises the following steps: generating a first random sample point set, and obtaining a training set through simulation; constructing a proxy simulator, and training the proxy simulator by using the training set; generating a second random sample point set, and inputting the second random sample point set into the proxy simulator to obtain a pseudo data set; establishing a filter, determining two hyperspherical surfaces based on the pseudo data set, dividing a process parameter space, evaluating a safety coefficient and the probability that a sample point enters a real simulator, and simulating the sample point of the process parameter space according to the probability to obtain a real sample set; iteratively optimizing the hyper-spherical surface and the proxy simulator by using the real sample set until convergence to obtain a final safety coefficient; and generating a third random sample point set, carrying out truncation sampling and failure discrimination by combining a real simulator and an agent simulator, and carrying out statistics on the final yield. According to the method, the xgboost network is adopted as an agent model to reduce the simulation cost, the sample size is reduced through truncation sampling, and rapid and accurate prediction of the yield of the integrated circuit is realized.

The invention discloses an SVDD-based operation condition classification method and system for autonomous shovel loading of a loader, and the method comprises the steps: collecting the autonomous operation data of the loader under different operation conditions, and carrying out the preprocessing of the autonomous operation data, so as to extract a shovel loading operation segment and the characteristics of the shovel loading operation segment; training an SVDD model under each working condition by using the features, obtaining the center and radius of a hypersphere of each working condition grade category, and constructing an SVDD category incremental learning model; when new operation data are input, the model can judge whether the data belong to known working conditions or not; if yes, calculating a support function value to determine a specific working condition grade; and if not, identifying the working condition as a new working condition and updating model parameters. According to the method, by collecting and analyzing the operation data of the loading machine and utilizing the SVDD model and the incremental learning ability of the SVDD model, precise classification and dynamic adaptation of the operation working conditions under all working conditions are achieved, and the autonomous operation efficiency and precision are improved.

The invention provides an electric smelting magnesium oxide production process safety monitoring method based on supervision matrix regression, and relates to the technical field of fault monitoring and diagnose.The method comprises the steps that firstly, a fixed camera is used for collecting furnace body image data of an electric smelting magnesium oxide furnace, and after graying and normalization processing, a furnace body image matrix is obtained; secondly, establishing and training an objective function model of the furnace body image matrix in a low-dimensional space through a public information extraction method, and solving a unique mapping matrix of each piece of sample data in the low-dimensional space; then, establishing a regression model of the mapping matrix of each sample and the corresponding class label vector by adopting a supervised matrix regression method; then, determining a hyper-spherical boundary and an angle boundary according to the category label of the sample; finally, furnace body image data are collected and processed in real time, the category of a new sample is judged according to the hyper-sphere boundary and the angle boundary, and then whether a fault occurs at the current moment or not is judged. According to the invention, the accuracy of industrial fault monitoring classification can be improved.

The invention discloses a memory enhancement action recognition method and system on a Riemannian manifold and a storage medium, and the method comprises the steps: 1, collecting human body action data, and representing the human body action data as a third-order tensor; 2, expanding along three modes to obtain three corresponding matrixes; 3, calculating by adopting a human short-term memory mechanism to obtain a memory enhanced weight matrix; 4, decomposing the weight matrix through a principal component analysis method to obtain a base vector with a weight; 5, recombining, normalizing and mapping to a unit hyper-sphere, and reserving an angle relation; 6, learning modal weight parameters through a Monte Carlo Markov algorithm, and calculating geometric differences between points on the hypersphere; and 7, carrying out human body action classification by adopting a K-nearest neighbor classifier. The method effectively solves the problem of time information loss in a complex scene, and is suitable for various application scenes such as medical health, virtual reality, physical training and the like.

The invention relates to a flight trajectory anomaly detection method based on an LSTM-GBSVDD model, in order to deal with the problem of length change of flight trajectory data, key features in a time sequence are extracted by using an LSTM, and variable-length trajectory data are converted into fixed-length representation, so that anomaly detection can be performed in a fixed-length feature space, and the detection accuracy is improved. And the universality of the model is improved. On the basis of feature extraction, an SVDD algorithm is introduced to construct a multi-dimensional hypersphere classifier, and a normal flight trajectory is modeled. Through the model, potential abnormal tracks can be identified under an unsupervised framework, dependence on data labels is avoided, and the bottleneck that abnormity cannot be identified under an unsupervised environment is solved. According to the invention, joint optimization of LSTM network parameters and an SVDD scoring function is realized for the first time, and a gradient-based training method is provided. According to the method, the anomaly detection precision and the calculation efficiency are remarkably improved, and the detection performance is improved.

The invention relates to the technical field of electric digital data processing, in particular to a weak supervision event representation learning method and system for aid decision making, and the method comprises the following steps: forming an event sequence through the operation behaviors of a user on an operation and maintenance network, and generating an initial event representation; constructing a normal prototype of the multi-hypersphere; performing first-stage training to obtain a sequence encoder after first-stage parameter optimization and a normal prototype of the multi-hyper-sphere; calculating an abnormal score of each event in the event sequence to obtain a prediction result of the event; carrying out multi-instance learning, and carrying out second-stage training to obtain a sequence encoder after second-stage parameter optimization, a normal prototype of the multi-hypersphere and an anomaly discriminator; abnormal events are screened, and manual decision making of the intelligent operation and maintenance system is assisted. The method and the system provided by the invention provide better assistance for decision making of the intelligent operation and maintenance system.

The invention belongs to the technical field of microservice system anomaly detection, and discloses a Trace anomaly detection method under a microservice architecture based on a graph attention network. A service operation graph (SOG) is constructed to serve as a mesoscopic layer trace representation method, and the graph representation granularity and efficiency of an existing method are balanced. Meanwhile, a group of delay-related features and error propagation modes are extracted as multi-dimensional edge features to be integrated into the SOG, and interaction information between services is fully utilized to improve the accuracy of anomaly detection. In order to capture various index data generated in the service and a calling relation between the services, the characteristics of nodes and edges of SOG are learned through GAT, and a graph embedding vector of a trace is obtained. And a hypersphere loss function training model is utilized to avoid dependence on labels, normal traces are gathered to a hypersphere center, and traces far away from the hypersphere center are regarded as anomalies.

The invention discloses a remote sensing image semantic segmentation method and device based on a hyperbolic neural network, and the method comprises the steps: constructing a hyperbolic space neural network model based on an encoder-decoder structure, obtaining a plurality of earth observation remote sensing images as a training set, and carrying out the training of the neural network model, and the semantic segmentation model is used for carrying out accurate semantic segmentation prediction on the earth observation remote sensing image. According to the neural network, a convolutional layer, batch normalization, nonlinear activation, residual connection, a Softmax function and a deconvolutional layer are mapped to a hyperbolic space by adopting a Lorentz model so as to learn low-distortion remote sensing image representation; pairwise correlation in a hyperbolic space and a Euclidean space is simulated at the same time in a parallel mode, and hyperspherical context dependency and Euclidean affinity are effectively combined. According to the method, the hierarchical structure and the spatial relationship in the remote sensing image can be more effectively captured, so that more accurate semantic segmentation is realized.

The invention discloses an LSTM-SVDD anomaly detection method and system based on rule guidance, belongs to the technical field of industrial nondestructive quality inspection, and aims to solve the technical problems that noise samples are sensitive and excessively depend on annotation of abnormal data, and expert experience and knowledge cannot be effectively introduced. Constructing a feature extraction model based on a bidirectional LSTM network, a rule template engine and a feature projection fusion layer; calculating a hypersphere radius through a quantile method, constructing an SVDD loss function as a basic loss function, introducing a rule penalty term to construct a rule loss function, carrying out weighted summation on the basic loss function and the rule loss function to construct a total loss function, and obtaining a trained feature extraction model and an optimized hypersphere radius through minimizing the total loss function; and inputting a to-be-detected sample into the trained feature extraction model, calculating an Euclidean distance between a fusion feature vector and the center of the hypersphere, and comparing the Euclidean distance with a dynamic detection threshold value.

The invention discloses a unified unsupervised depth forgery detection method based on prototype guidance and double hyperspheres, and the method comprises the following steps: S1, extracting visual artifact features generated by depth forgery, and achieving the generation of pseudo labels through the clustering of a Gaussian mixture model; s2, performing comparative learning through a category prototype of momentum updating; and S3, realizing effective fusion of a feature space and a geometric decision by respectively constructing independent hyper-spheres for real and forged samples, and constructing a dual-depth support vector data description framework. The system has the beneficial effects that the system is composed of three core modules: a visual artifact feature-based pseudo label generator provides a reliable supervision signal, and the visual artifact feature-based pseudo label generator provides a visual artifact feature-based pseudo label description framework; a prototype guided contrast learning (PGCL) module enhances the discrimination capability through a prototype of momentum update, and a dual-depth support vector data description (Dual-DeepSVDD) module constructs a dual-hyperspherical decision boundary of true and false samples, thereby realizing effective integration of feature learning and geometric decision.

The invention relates to a micro-expression recognition method for cross-domain feature center assisted emotional intensity invariance feature extraction, belongs to the technical field of deep learning and pattern recognition, designs a cross-domain feature center assisted emotional intensity invariance feature extraction network, and fully utilizes an existing macro-expression data set to assist micro-expression recognition. Macro-expression related features are utilized to guide learning of micro-expression features, a neural network is helped to learn more emotion related features, hyper-spherical constraint is carried out on the micro-expression features and the macro-expression features, multiple angle optimization strategies are designed, intensity information of the features is weakened, angle information is focused, and the effect of improving the accuracy of the micro-expression features is achieved. In addition, a macro-expression feature center and a micro-expression feature center are designed to cooperatively guide training of the network, and a model is helped to learn more compact emotional feature distribution.

The invention discloses a robot virtual-real cooperative training decision optimization system and method based on digital twinning, and the method comprises the following steps: collecting state data and disturbance data of an entity robot in a real environment, and carrying out the preprocessing of the data to generate standardized input; joint coding and state perturbation mapping are carried out on the standardized data, and a feature vector sequence embedded in a hyperspherical manifold space is generated; inputting to a virtual twin control body based on a hypersurface neural element structure, executing disturbance direction sensitive activation, and outputting an activated state vector sequence; virtual and entity control action prediction sequences are generated respectively, an embedded space difference vector is calculated, and control body parameters are updated based on a consistency optimization criterion; after convergence, the control body executes reasoning to generate a target control action sequence, the entity robot is driven to complete action execution, and control strategy optimization is achieved. According to the method, high-precision migration and rapid convergence of a robot control strategy are realized, and the execution stability in a complex disturbance environment is improved.

The invention relates to an approximate nearest neighbor search problem in the field of image retrieval, and discloses an image feature retrieval method based on hyper-sphere adaptive filtering, which mainly comprises three stages of candidate set acquisition, hyper-sphere filtering and reordering, and comprises the following steps of: combining an inverted index constructed based on residual quantization to obtain a candidate set; constructing a hyper-sphere taking the query feature vector as a sphere center in an image feature library by using a full-connection neural network, and adaptively acquiring an inverted list to be retrieved by using the hyper-sphere to form a candidate set; according to the spatial position relationship between the hyper-sphere and the query feature vector, filtering the feature vector of which the spatial position is located outside the hyper-sphere from the candidate set to simplify the candidate set; in the result reordering stage, according to the similarity or the Euclidean distance between the query feature vector and the candidate feature vector, the feature vectors in the candidate set are ordered, and the previous feature vector with the highest similarity or the smallest Euclidean distance is used as a final retrieval result. According to the method, the hypersphere model is constructed in combination with deep learning, so that the retrieval efficiency is effectively improved while the retrieval precision is ensured.

The invention discloses a method and a system for monitoring pressure abnormity of a fuel oil common rail pipe of a marine main engine. The method comprises the following steps: acquiring historical operation parameter data and constructing a data set; the historical operation parameter data comprises historical host load data, historical host rotating speed data and historical fuel oil common rail pressure data; historical operation parameter data are preprocessed, an SVDD model is constructed and trained based on the historical operation parameter data, the model obtains a historical normal data hyper-sphere in a three-dimensional feature space, and the center and the radius of the hyper-sphere are obtained; similarly, real-time operation parameter data collected in real time are preprocessed and then input into the model, the distance between the real-time operation parameter data and the center of the hypersphere is obtained, and the value of the distance is compared with the value of the radius of the hypersphere in historical normal data; and when the numerical value of the distance is large, it is judged that the real-time operation parameter data is within an abnormal range, the fuel oil common rail pressure of the ship main engine is in an abnormal state, and an alarm signal is triggered. The method has the effect of low error rate.

The invention belongs to the technical field of electrocardiosignal detection, and particularly relates to an atrial fibrillation anomaly detection method and system based on multi-mode time-frequency pseudo-anomaly, and the method comprises the steps: carrying out data enhancement on normal time-domain electrocardiosignals to generate atrial fibrillation pseudo-anomaly time-domain electrocardiosignals; features of the normal time-domain electrocardiosignals and the normal frequency-domain electrocardiosignals are extracted through a time-domain encoder and a frequency-domain encoder respectively and mapped to a hypersphere space through a predictor; the atrial fibrillation pseudo-anomaly time-domain electrocardiosignals and the atrial fibrillation pseudo-anomaly frequency-domain electrocardiosignals extract features through a time-domain encoder and a frequency-domain encoder respectively and map the features to a hypersphere space through a predictor; calculating the distance from the normal time domain and frequency domain hyper-sphere mapping to the hyper-sphere center, and training the model to reduce the distance; calculating the distance from the pseudo-abnormal time domain and frequency domain hyper-sphere mapping to the hyper-sphere center, and training the model to expand the distance; the atrial fibrillation abnormity prediction is carried out through the sum of the distances from the hypersphere to the hypersphere center in the time domain and the frequency domain of the electrocardiosignals. The accuracy and efficiency of atrial fibrillation detection are improved.

The invention discloses a hyperspectral image open set classification method and device based on fractional domain information enhancement and a hypersphere prototype learning strategy, and belongs to the technical field of hyperspectral image open set classification. In order to solve the problem that a high misclassification risk exists between a known category and an unknown category in an existing hyperspectral image classification method, the method comprises the following steps: firstly, obtaining fractional domain information of hyperspectral data based on weighted fractional Fourier transform, and then fusing the fractional domain information with spatial spectral domain information; deep feature extraction is carried out on the hyperspectral image through a double-branch network, a hypersphere prototype learning strategy is adopted, utilization of a measurement space is optimized, and features of known categories are restrained to be evenly distributed on a hypersphere; and carrying out identification based on a closed set classifier of a known category prototype, and meanwhile, realizing open set identification by utilizing a hypersphere prototype radius so as to obtain a final open set classification result.

The present application relates to a kind of single class image recognition method based on multiple hypersphere space division, belong to image recognition and machine learning technical field.First, sample is mapped to a latent space by feature extraction network, then according to the similarity of training sample and test sample in space, and the classification identification of test image sample is carried out.The way of introducing threshold radius is used to judge whether the distance of test sample from its nearest neighbor training sample is close enough.The representation of target category in feature space is the space formed by the superposition of multiple hypersphere regions, with threshold as the radius of each hypersphere, if the feature of a test sample is within the space range formed by the multiple hyperspheres, it will be predicted as positive sample, otherwise it will be predicted as negative sample.The prediction accuracy of the present application for test image sample is significantly improved, and the prediction of positive sample and negative sample in test image sample is more balanced.

The application discloses an iris recognition method and device, system and storage medium, and performs preprocessing such as polar coordinate unfolding on an input original iris image in sequence; multi-level image features are extracted through an inverse residual module; subsequently, a global depth convolution GDConv operator is introduced to replace a global average pooling layer, so that spatial structure distribution features of iris textures are retained under the premise of extremely low calculation complexity; finally, an ArcFace loss function is used to optimize the distribution of features in a hyperspherical space, and the class separability of the features is enhanced by introducing an additive angle interval. By using the technical scheme of the application, the technical problems that spatial topological information is lost due to a global average pooling GAP operation in iris feature extraction by using an existing lightweight convolutional neural network, and the feature discrimination is reduced due to network lightweight are solved.