86 results about "Classful network" patented technology

The invention discloses an intelligent flow arrangement method based on fusion expert network and deep reinforcement learning, which comprises the following steps: collecting network node and link state data in real time, and constructing a time sequence input vector and a topological graph structure; a time sequence neural network and a graph neural network are used for extracting traffic spatial-temporal features and node topological features respectively, future traffic is predicted through a classification network after fusion, and coarse-grained arrangement of network slices of different service levels is completed; modeling resource scheduling into a multi-agent Markov decision process, and designing a state space, an action space and a reward function; a deep reinforcement learning agent is initialized, and training is carried out through interaction experience; fusing a pre-trained expert strategy network, and constructing a total loss function to optimize network parameters; and finally generating an intelligent strategy capable of dynamically optimizing the flow path and resource allocation according to the real-time state. According to the invention, efficient resource scheduling under multi-service differentiation service quality requirements can be realized.

The invention relates to the technical field of artificial intelligence, and provides a quantum-enhanced multi-scale network intrusion detection method, which comprises the following steps: calculating a covariance matrix for an original traffic feature matrix, and obtaining a feature value and a feature vector through feature decomposition, mapping each sample xi to a quantum Hilbert space to generate an enhanced feature matrix, executing complex field transformation on the enhanced feature matrix to generate an entangled feature tensor, and realizing dynamic feature enhancement through a multi-head attention mechanism based on a quantum probability amplitude; performing space-time attention calculation and gating fusion on the feature tensor after dynamic feature enhancement to obtain a space-time fusion feature; converting the space-time fusion features into a time sequence form, extracting behavior features through a multi-scale convolution branch, and fusing the behavior features to obtain a three-dimensional feature tensor; and calculating a mean value of the three-dimensional feature tensor in a sequence dimension, generating a two-dimensional feature matrix, and performing classification prediction, uncertainty quantification and threat grading evaluation based on a classification network, an uncertainty network and a threat grading network.

The embodiment of the invention discloses a power grid equipment state classification method and device based on multi-scale continuous coherence. The method comprises the steps of obtaining point cloud data and operation environment data of to-be-classified power grid equipment; decomposing the point cloud data into a plurality of point cloud subsets with different scales; an improved continuous coherence algorithm is applied, filtering parameters are optimized in combination with operation environment data, and continuous coherence invariants of point cloud subsets under all scales are calculated; screening high-persistence topological features related to the power grid fault mode from the persistence features; according to the screened high-continuity topological features, constructing a multi-scale topological feature vector; and performing classification by using a machine learning model obtained by pre-training in combination with the operation environment data and the multi-scale topological feature vector to obtain a state classification result of the to-be-classified network equipment. According to the method, a multi-scale continuous coherence algorithm is adopted, so that accurate power grid equipment state classification is realized.

The invention relates to a small sample electroencephalogram signal enhanced soft hybrid generative adversarial network model training method, which comprises the following steps of: 1, constructing an adversarial training framework of a generator G and a discriminator D, and generating a new EEG sample by the generator through a soft hybrid data enhancement mode; 2, introducing a Wasserstein distance to constrain the difference between generation distribution and real distribution, and helping the generative adversarial network to converge; 3, inputting the enhanced sample into a deep network, and extracting time, space and channel features through a multiple attention mechanism; and then corresponding features are enhanced from the aspects of time sequence, channel and space. And through confrontation training of the generator and the discriminator, new data with relatively high quality is obtained. In the classification network part, a multi-attention mechanism is introduced, and the integration of feature extraction and classification is enhanced from the aspects of time, space, channels and the like.

The invention discloses an unknown attack detection method and system for intelligent network security situation awareness, and the method comprises the steps: obtaining multi-dimensional data of a power grid monitoring system, carrying out the data preprocessing, carrying out the network attack preliminary detection of the multi-dimensional data through a pre-built network security situation awareness framework, and outputting suspected attack data, the method comprises the steps of performing data training on historical attack data through an improved OCN open set classification network, identifying attack features of each known attack type, performing semantic similarity calculation on the attack features and suspected attack data, performing attack feature mapping and clustering on the suspected attack data based on semantic similarity, and obtaining an unknown attack feature clustering result. And according to the unknown attack clustering result, carrying out attack type classification on unknown attacks in the suspected attack data to obtain an unknown attack detection result. The method has the effects of detecting unknown attack means in time, effectively reducing the risk that the power grid system suffers from network attacks and guaranteeing safe and stable operation of the power grid system.

The invention discloses a multi-modal dynamic gesture recognition method based on deep learning. RGB image and hand key point features are respectively extracted through a double-branch network: an RGB branch adopts ShuffleNetV2 to extract spatial features, and a time sequence feature is captured in combination with GRU; the key point branch is based on improved ST-GCN modeling space-time correlation. The two branch features are input into a classification network after channel / space fusion, a multi-scale feature fusion module is introduced to enhance the recognition precision, and shallow feature extraction is optimized to improve the small target detection effect. According to six dynamic gestures of left sliding, right sliding, up sliding, down sliding, grabbing and fist clenching, model parameters are compressed to be below 8MB on the premise of keeping precision through technologies of decomposition convolution, frame compression, channel rearrangement and combination and the like, the reasoning speed is increased, and the method is suitable for various embedded devices such as AR glasses and smart home or scenes with low computing power.

The invention discloses an inverter IGBT intelligent fault diagnosis method based on a multi-scale attention network, and relates to the technical field of power electronic equipment fault diagnosis. A three-phase current signal of a three-level NPC inverter is collected and preprocessed; multi-dimension fault features of the current signals are extracted in parallel through multi-scale depth separable convolution; a scale-aware efficient attention mechanism is introduced to carry out weighted optimization on each scale feature, and key fault information is strengthened; and outputting a fault diagnosis result through a feature fusion and classification network, and performing INT8 quantization processing on the model to adapt to an embedded deployment scene. The method has the advantages of being high in multi-scale feature capturing capacity, high in diagnosis precision and light in model weight, and can meet the dual requirements of industrial application for real-time performance and accuracy.

The invention relates to a federal semi-supervised domain adaptive time sequence learning method, which comprises the following steps: aiming at a target classification network formed by a coding feature extraction layer and a classifier head, firstly, executing pre-training by a server based on local label data, freezing the classifier head, and then, respectively executing pre-training by each client based on local label-free data; unsupervised training is carried out on the coding feature extraction layer, federated learning is realized and a mobile behavior recognition model is obtained in combination with fusion of each trained parameter of the local coding feature extraction layer of each client by the server, and each preset mobile perception data acquisition is analyzed and a corresponding mobile behavior label is output, so that mobile behavior perception application is realized. The design method not only can improve the classification accuracy of the target classification network on the client data, but also lays a solid foundation for promoting the wide application of semi-supervised federal learning in a complex real scene.

The invention discloses a few-sample mechanical fault diagnosis method based on a collaborative enhancement generative adversarial network, and belongs to the technical field of mechanical fault diagnosis. Comprising the steps of designing a deep data sampling collaborative enhancement generative adversarial network (DDSAGAN), generating a high-quality fault sample to expand a data distribution range, and relieving a data deviation problem in a few-sample scene; a fault classification network of a multi-view feature extraction and diagnosis architecture (MVFE-DA) is constructed, collaborative extraction of fault signal features from different scales and views is realized, and the ability of the model to capture fault signal multi-scale features is enhanced; a priority embedded reward clustering depth deterministic policy gradient (PERC-DDPG) optimization algorithm is designed, a high-value sample can be efficiently utilized by a model through a priority experience playback mechanism, and a learning process is optimized through the reward clustering algorithm. By adopting the method, the problem of insufficient available data due to few samples in the fault data set can be effectively solved, and the accuracy and robustness of the model in a few-sample fault diagnosis task are improved.

The present invention is an unsupervised integrated method of instability detection and fault module positioning, including: acquiring a topological structure of a direct current (DC) microgrid and collecting electrical data of each node in the topological structure to construct a corresponding first enhancement dataset and a corresponding second enhancement dataset; constructing a fault type pool based on the topological structure; constructing a corresponding classification network based on a twinborn network framework; training the classification network using the prepared datasets to obtain a detection model; and inputting the electrical data of the DC microgrid to be detected to a detection model, to output whether the DC microgrid to be detected has system stability and a corresponding fault type. Further provided in the present invention is an unsupervised integrated device of instability detection and fault module positioning.

The invention discloses an AI-driven vehicle-mounted sound field real-time modeling and voice separation method, and relates to the technical field of voice signal processing. A main control unit comprising a time sequence synchronizer, a resource scheduler and a health monitor is constructed. 3D sound field modeling is carried out by adopting a lightweight STCN + bidirectional LSTM network, adaptive updating of the model is realized through EWC incremental learning, and a CNN-LSTM noise classification network and targeted suppression algorithms such as ANF / spectral subtraction are developed. The voice separation module adopts an improved Conv-TasNet architecture, 3D spatial constraint and a multi-task loss function are fused, and low delay is realized under INT8 quantization and pipeline processing. The system dynamically optimizes parameters through a real-time regulation and control unit, supports scene self-adaption, finally achieves a separation effect in a mixed noise scene, reduces the delay of the whole system, and effectively improves the definition and stability of vehicle-mounted voice interaction.

The invention relates to the field of microservice system anomaly detection, in particular to a microservice anomaly detection method and device. The method comprises the steps of obtaining historical data of a micro-service system, and obtaining first modal data and a log time sequence matrix based on historical service index data, historical log data and historical call chain data in the historical data; obtaining a first modal feature matrix and a second modal feature matrix according to the first modal data and the log time sequence matrix; obtaining a historical anomaly detection result according to the first modal feature matrix and the second modal feature matrix; obtaining first and second modal reconstruction data according to the first and second modal feature matrixes; optimizing the language model and the classification network to obtain an optimized language model and an optimized classification network; and preprocessing the collected real-time data, and inputting the preprocessed real-time data into the optimized language model and the classification network for anomaly detection to obtain a real-time anomaly detection result. The method is used for realizing accurate positioning and detection of the abnormity of the micro-service system.

The invention relates to the technical field of power information physical system security, and discloses a power transmission system attack scene identification method considering information physical interaction. Constructing a DAD attack and defense model, generating a plurality of typical attack scenes, and collecting historical load data, attack schemes and defense schemes; training is carried out through a classification network, and a mapping relation from a system operation state to a corresponding worst attack response is learned; optimizing network parameters by adopting a gradient descent method, and introducing a Lagrange function and an information physical coupling penalty term; after training is completed, attack scene prediction is carried out; taking the minimum expected loss of the system as an optimization target, and passing through the Camp; and carrying out iterative solution on the CG to obtain an optimized defense resource configuration scheme. According to the method, through a multi-stage collaborative optimization strategy, TCPS toughness improvement under the cyber-physical collaborative attack is realized, it is ensured that the system can quickly respond and recover when facing a dynamic attack environment, and the stability and security of the whole system are enhanced.

The embodiment of the specification provides a multi-party participated model training method, system and device, the method comprises: a first party inputs a plurality of first features into a first feature extraction network, homomorphically encrypts an output result to obtain a plurality of first encrypted vectors and sends the plurality of first encrypted vectors to a second party; the second party inputs a plurality of second features into a second feature extraction network, homomorphically encrypts an output result to obtain a plurality of second encrypted vectors; the second party homomorphically calculates the plurality of first encrypted vectors and the plurality of second encrypted vectors to obtain a plurality of fusion encrypted vectors and sends the plurality of fusion encrypted vectors to the first party after being disordered, and records a first correspondence before and after disordering; the first party decrypts the plurality of fusion encrypted vectors and inputs the plurality of fusion encrypted vectors into a first part of a classification network to obtain a plurality of latent vectors; the first party uses the plurality of latent vectors and a classification label, and the second party uses network parameters of a second part of the classification network and the first correspondence to perform multi-party secure calculation and determine a first loss; the first party and the second party update the classification network according to the first loss.

The invention relates to the technical field of federated learning algorithms, in particular to a fair federated learning method based on multi-agent reinforcement learning, which comprises the following steps: respectively initializing network parameters of a server and a local client, and calculating an initial state vector of a local environment by the local client according to the initialized network parameters; the server calculates the initial state of the global environment, and a local client selects and executes an action; the server updates the classification network and broadcasts the classification network to all local clients, and the local clients update local states and rewards; the server updates the global environment state and stores the data in an experience batch; and the server updates the value network, and the local client updates the strategy network. The strategy network is trained based on centralized training and distributed execution, and the convergence speed of the strategy network can be greatly improved.

The application discloses an intelligent traffic arrangement method based on a fusion of an expert network and deep reinforcement learning, comprising the following steps: collecting network node and link state data in real time, and constructing a time sequence input vector and a topological graph structure; using a time sequence neural network and a graph neural network to respectively extract traffic space-time features and node topological features, fusing the features, predicting future traffic through a classification network, and completing coarse-grained arrangement to different service level network slices; modeling resource scheduling as a multi-agent Markov decision process, designing a state space, an action space and a reward function; initializing a deep reinforcement learning agent, and training the agent through interactive experience; fusing a pre-trained expert strategy network, constructing a total loss function to optimize network parameters; and finally generating an intelligent strategy capable of dynamically optimizing traffic paths and resource allocation according to real-time states; and the application can realize efficient resource scheduling under differentiated service quality requirements of multiple services.

The application discloses a multi-modal radio frequency authentication method based on a multi-scale signal representation, which comprises the following steps: firstly, pre-processing the original IQ signal of a target device received to obtain an instantaneous envelope signal; carrying out multi-scale decomposition and denoising processing on the instantaneous envelope signal to obtain a denoised envelope signal; constructing a multi-modal data set according to the original IQ signal and the denoised envelope signal; carrying out feature extraction and fusion on the multi-modal data set through a pre-trained target feature extraction network to obtain a fused feature representation; and carrying out classification on the fused feature representation through a pre-trained target classification network to output a classification result corresponding to the target device. The amplitude, frequency and time-frequency energy distribution information can be complementarily fused by constructing the multi-modal data set; the multi-modal features are extracted and fused through the target feature extraction network, so that the information loss is effectively avoided; and the target classification network is used for rapid classification, thereby reducing the calculation cost and ensuring the accuracy of identification.

The application discloses a kind of multi-modal perception data computer system fault diagnosis method and system, the method of the application includes the unified vectorization characterization of the multi-modal perception data of computer system, for the data of each modality in multi-modal perception data, respectively utilize the expert network of multiple channels to generate vectorization feature, according to the data modality of input, share routing network and the modality routing network of corresponding modality are cascaded to calculate the trust degree of the data of one modality to different expert networks, and the feature representation of this data modality is obtained based on trust degree to each expert network feature output weighted summation;The feature representation of each modality is characterized to realize superposition;The feature obtained after feature confusion is sent into classification network to obtain the fault diagnosis result of computer system.The application aims to comprehensively use multi-modal perception data to realize the fault diagnosis of unified computer system, to solve the inconsistency problem when different modal independent fault diagnosis.

The present application belongs to the field of computer vision, and particularly relates to a weakly supervised object localization method based on category correction. In order to solve the problem of inaccurate localization of the CAM technology, the rough-to-fine process is adopted instead of using the category feature map for localization. The model of the present application is composed of a backbone network, a localization network and a classification network. First, the localization network generates a class-independent segmentation map by using unsupervised segmentation technology, so as to determine the rough position of the target object. Then, the classification network is used for fine-grained correction through the category label. The method based on category correction can accurately locate the object and well identify the contour details.

The application discloses a DAS signal cross-scene multi-category classification method, system, device and medium, belongs to signal recognition classification in the field of optical fiber sensing technology, and aims to solve the technical problems that the DAS signal can only recognize single scene events in the prior art, and the DAS signal cannot be recognized and classified in a complex scene. The application comprises the following steps: acquiring samples and labels; constructing a signal recognition classification model comprising a feature extraction network and an identification classification network; the identification classification network comprises a tree classifier, each non-leaf node of the tree classifier comprises a node classification sub-network and an output layer, the node classification sub-network comprises a one-dimensional convolution layer, a batch normalization layer, a ReLU layer, a one-dimensional maximum pooling layer, a one-dimensional convolution layer, a batch normalization layer, a ReLU layer and a one-dimensional maximum pooling layer, and the output layer comprises a transformation layer, a full connection layer, a ReLU layer, a full connection layer, a ReLU layer and a Softmax layer arranged in sequence; training the signal recognition classification model; and classifying signals in real time.

The present application relates to a kind of based on reinforcement learning's unsupervised mismatch detection method, the present application first inputs the matching point without label to mismatch detection network, training detection network, by multiple iterations to obtain best network parameter, and using the final network model of saving best network parameter to the matching point set to be detected for detection, by generating N extract subset and evaluating its corresponding model, finally the maximum consistent set of model is regarded as correct matching point pair set, to complete mismatch detection and elimination.The present application has higher mismatch detection efficiency, precision and stability, and on the one hand, it overcomes the sample label problem;On the other hand, it is not limited by mismatch rate, and a large number of correct matching points can be obtained with fewer sampling times;And the method is a kind of unsupervised learning framework, which can be compatible with other classification networks, to solve the mismatch detection problem.

The invention discloses a power consumption data anomaly detection method and device based on decoupling anomaly injection driving. The method comprises the following steps: injecting predefined multiple types of pseudo anomalies into a normal data window to generate a pseudo anomaly window; the method comprises the following steps: pre-training a pre-constructed submerged space hybrid anomaly expert network model architecture, and generating a shared encoder, a normal decoder, an anomaly decoder and a plurality of anomaly expert networks of a hybrid anomaly expert network of a submerged space hybrid anomaly expert network model; learning a routing network and a classification head of the hybrid anomaly expert network, and generating a routing network and a classification network of a submerged space hybrid anomaly expert network model; calculating a reconstruction error of to-be-tested data at each time point and an anomaly probability output by the classification network based on a sliding window by adopting a submerged space hybrid anomaly expert network model, and performing linear combination to obtain a point-by-point anomaly score; and judging the point-by-point anomaly score according to a set threshold value to obtain an anomaly detection result.

The invention discloses an SNN learning accelerator for ECG monitoring, which comprises a register configuration module, an asynchronous global control module, an asynchronous neural network control module, an asynchronous binary classification CNN module, an asynchronous quadruple classification SNN module, an asynchronous weight updating module and a memory management module, and is characterized in that firstly, a circuit corresponding to the accelerator constructs a double-layer dynamic network; layered dynamic power consumption management: selectively activating a high-precision secondary anomaly detection four-classification SNN network through a primary anomaly detection two-classification CNN network; secondly, the accelerator supports on-chip reasoning and efficient learning, and effectively eliminates ECG feature differences of different individuals on the premise of ensuring privacy security of user data; and finally, the circuit is controlled by using a pulse neural network and an asynchronous logic circuit, so that compared with a synchronous network, the power consumption is greatly reduced.

The application discloses a high-speed moving target recognition method based on data enhancement and belongs to the field of target recognition. The application introduces a high-speed moving target background data set, the confidence of a pseudo target obtained by a classification network after the pseudo target generated by a differentiable generative adversarial network, and the target instances with a confidence greater than a set threshold and the target instances in the initial data set are segmented objects and are enhanced together in the high-speed moving target background data set, solving the problems of insufficient samples and inconsistency between the high-speed moving target training background and the working environment. When the pseudo target generated by the differentiable generative adversarial network is trained, the confidence of the pseudo target and the CIoU value of the positive sample boundary box and the real box are weighted and summed to form a new confidence loss function in the YOLOv7 target detection algorithm, and the improved loss function can more accurately measure the authenticity of the target. The method can realize accurate recognition of a specific type of high-speed moving target under small samples.

The present invention discloses a machine learning method for segmenting wireless edge node models. The method comprises: constructing a federated learning system, which includes a server and one or more edge devices; segmenting a neural network model into an individual feature extraction network, a classification network, and a general attribute extraction network based on the resource information of each edge device, wherein the individual feature extraction network and the classification network are applied to the edge device, and the general attribute extraction network is applied to the server; under the coordination of the server, iteratively training the neural network model, wherein for each iterative training, each edge device processes data in parallel at the same time, and the server distributes the data uploaded by each edge device to different computing units for processing in a pipeline parallel manner. The present invention satisfies the resource requirements of the edge device and reduces the waiting delay of the edge device by reasonably dividing the tasks.

The application discloses a kind of offshore ship target detection methods based on generation confrontation network anti-shake, comprising the following steps: establishing DeblurGAN-v2 network model and training, using generator and discriminator alternately training method training, finally loss function converges and obtains the deblurred confrontation generation network model;Take out the discriminator network part in the trained network model as binary classification network continues training;Establish based on offshore ship target detection model and training, obtain YOLOv7 detection model;The generator part in the obtained trained network model, binary classification network and YOLOv7 detection model are reformed and fused, new discriminator network is used as front-end module, for fuzzy frame judgment, for selecting whether the picture sample is sent into generator network to deblur, and the target detection network of fusion generation confrontation network DeblurGAN-v2 is constructed.

The embodiments of present disclosure address unresolved problems of label inconsistency, where outputs of different levels create impossible combinations, and error propagation from previous level outputs can significantly impact its performance. Embodiments provide a method and system for a Progressive Multi-level Training framework with a Logit-masking strategy (PMTL) for a retail taxonomy classification. PMTL enables neural network models to be trained separately for each level to reduce error propagation problems. To further enhance the model's performance at each level and get the label-wise constraint from the previous level, the global representation from model of previous level is augmented. Further, a logit masking strategy is used to restrict model(s) to learning only relevant classes through part of final classification layer, thereby addressing label inconsistency issue, and incorporating benefit of parent node-based local classifier. This framework is generalized irrespective of dataset size and is configured for attaching to any hierarchical classification network.

The invention discloses a Spine-Leaf network hidden fault detection method based on deep learning, and the method comprises the steps: collecting the structure information of a Spine-Leaf network and the time sequence state data (TX, RTT and Qlen) of an RDMA network card, analyzing the feature rule of the time sequence state data of the RDMA network card when hidden faults exist, building a feature encoder based on LSTM and CNN dual-branch fusion and a classification network based on a softmax function, and carrying out the detection of the hidden faults of the Spine-Leaf network. And then training model parameters by using a cross entropy loss function in an offline training stage, and finally outputting a probability that a communication path has a hidden fault based on real-time state data of the terminal RDMA network card in an online evaluation stage. The method can effectively solve the problems that Spine-Leaf network hidden fault feature capture is not comprehensive and detection is not sensitive, hidden fault recognition accuracy and real-time performance are improved to the maximum extent, and efficiency loss of a distributed deep learning task caused by network abnormity is reduced.

The invention relates to the technical field, in particular to a DNS (Domain Name Server) tunnel attack real-time detection method based on LSTM-Transform hybrid architecture, which comprises the following steps of: 1, acquiring continuous DNS data streams in a network, and extracting an original DNS query sequence as an input feature; 2, constructing a hybrid neural network architecture composed of a time sequence feature extraction module and a global dependency modeling module; 3, an information fusion module fuses the time sequence feature vector and the long-distance dependency feature vector to generate a joint representation vector; and step 4, the classification network model performs attack behavior classification based on the joint representation vector, and outputs a detection result of DNS tunnel attacks in real time. According to the method, the deep time sequence rule and the global dependency feature of the DNS query sequence are cooperatively extracted through the LSTM-Transform hybrid architecture, and the inherent DNS protocol behavior pattern of the network node can be accurately modeled.