83 results about "Linear network coding" patented technology

The invention relates to the technical field of remote sensing image processing, and discloses a remote sensing image adaptive identification method and system for territorial space planning, and the method comprises the steps: obtaining a multi-source remote sensing image data set of a research region, feature extraction, cloud detection, quality evaluation and adaptive preprocessing are carried out; carrying out prototype network coding, calculating a category prototype and probability, and supporting fine tuning of a set; carrying out multi-scale cavity convolution and category scale attention fusion; evaluating the adaptability score of the comprehensive fusion feature map set, and carrying out weighted fusion, classification and normalization; change detection is carried out, stable and change regions are segmented, and time sequence context features are extracted and constrained optimization is carried out; entropy is fused, a boundary is decided, uncertainty is estimated, and weighted fusion is carried out according to a change area; conditional random field optimization, confidence level grading and connected domain identification are carried out; the automation level, the adaptive capacity and the recognition reliability of remote sensing monitoring of territorial space planning are improved.

The invention relates to the field of network communication, and discloses a multi-source heterogeneous network data cooperative transmission method based on dynamic multi-dimensional evaluation and intelligent disaster recovery, which comprises the following steps: collecting system network parameters of a 5G network and a long-distance wired network in real time through a software definition interface module; performing weighted evaluation on the acquired system network parameters based on a dynamic link selection engine, the evaluation dimensions including real-time bandwidth, transmission delay and current link traffic, and generating an optimal communication link combination scheme; carrying out fragmentation and protocol adaptation on the data by adopting a general packaging framework and an intelligent label technology; distributing multi-path parallel transmission according to a priority strategy; at a receiving end, data recombination and disaster recovery supplementary transmission are realized through network coding and multi-path cooperation; and the evaluation weight is dynamically optimized in combination with reinforcement learning. According to the invention, the problems of rigid link selection, low protocol conversion efficiency and insufficient disaster tolerance in the prior art are solved.

In a blockchain, transacting a record comprises performing linear network coding on the record or on a data file corresponding to the record, to produce a plurality of coded data parts; and storing at least one of the plurality of coded data parts on the blockchain or storing a proof of knowledge on the blockchain, the proof of knowledge derived from the coded data parts. Linear network coding coefficients might be derived from cryptographic hashes of the plurality of coded data parts. An all-or-nothing transform can use the cryptographic hashes to provide the proof of knowledge.

The invention relates to the technical field of computer vision and target detection, and particularly discloses a lightweight real-time two-wheeled vehicle helmet detection method. According to the method, firstly, a video stream is collected and preprocessed through a traffic monitoring camera, then feature extraction and fusion are carried out through a lightweight backbone network, an encoder and a neck network in sequence, finally, a detection result is output through a decoder, a StripCGLU module is introduced to reduce the calculation complexity, a Pola Former module is adopted to enhance the feature interaction capability, and finally, the detection result is output through a decoder. And a GLBiFPN network is designed to optimize multi-scale feature fusion. According to the method, the calculation complexity and parameter quantity of the model are remarkably reduced, the requirement of edge calculation equipment for efficiency is met while high detection precision is guaranteed, and an effective technical means is provided for safety monitoring in an intelligent traffic system.

The invention relates to the technical field of mechanical fault diagnosis, and provides a fault diagnosis and classification method for a bearing of an aluminum alloy impeller die-casting ladling machine, which comprises the following steps: acquiring a vibration signal of the bearing of the ladling machine, carrying out continuous wavelet transform on the vibration signal, generating a time-frequency diagram, and carrying out adaptive grid segmentation on the time-frequency diagram. Grid granularity is adjusted according to the local change rate of the time-frequency graph, multi-scale nodes are generated, edge connection is generated for the multi-scale nodes based on a K-nearest neighbor algorithm, and a multi-scale graph structure is constructed; performing unsupervised feature extraction on the multi-scale image structure, including: performing data enhancement on the multi-scale image structure through edge deletion and feature mask to generate an enhanced view; a graph attention network encoder is used for encoding the enhanced view, graph-level embedding is generated, and graph-level embedding is optimized by comparing a loss function; and based on the optimized graph-level embedding, performing fault classification by using a classifier constructed by a graph attention network and a multi-layer perceptron, and outputting a fault category.

The invention provides a three-dimensional seismic data mixed noise suppression method based on an MSAT-Unet. The method comprises the following specific steps: constructing an MSAT-Unet network comprising a multi-scale expansion convolution residual module, a channel-space attention mechanism and a Transform convolution module; the encoder is improved into multi-scale expansion residual convolution, so that the receptive field is expanded, and the capability of capturing local details and global semantic information is enhanced; a channel-space attention mechanism is integrated behind the decoder, a direction sensitive context is extracted through multi-dimensional adaptive pooling, and details and edge recovery are enhanced; meanwhile, an improved decoder is a Transform convolution module, and the feature reconstruction and complex structure recovery capability is improved; the optimized model carries out training and reasoning on the three-dimensional seismic data, mixed noise can be effectively suppressed, a clear data basis is provided for subsequent interpretation, and the method is high in generalization and robustness and good in performance in the aspect of three-dimensional seismic data denoising.

The invention discloses a reverse knowledge distillation-based cross-stage feature fusion method for industrial anomaly detection and positioning, and relates to the technical field of knowledge distillation and transfer learning. The method comprises the following steps: step 1, constructing a teacher network encoder, a student network encoder and a decoder; 2, extracting input image features through a student network encoder, and reconstructing the features through a student decoder; step 3, student network cross-stage feature fusion design; 4, locally sensing a dynamic attention module LDA, and adding a sliding window and convolution to replace original global pooling; and step 5, a self-adaptive multi-scale feature fusion module CAAMS-FF establishes a dependency relationship of a context so as to realize a fine-grained high-quality feature reconstruction effect. And step 6, inputting an anomaly graph obtained by the teacher-student network into the segmentation sub-network to obtain a final anomaly detection and positioning result. While the calculation efficiency is maintained, the spatial positioning precision and the multi-scale adaptability are significantly improved.

The invention discloses a ship abnormal behavior detection method and device, electronic equipment and a storage medium, and relates to the technical field of intelligent maritime affair monitoring, and the method comprises the steps: obtaining original ship trajectory data, carrying out the augmentation processing and hybrid standardization processing of the original ship trajectory data, and obtaining a standard trajectory sequence; based on the standard trajectory sequence, pseudo labels are generated through unsupervised clustering, and the pseudo labels are used for representing different normal navigation modes; taking the standard trajectory sequence and the pseudo tag as supervision signals, and training a neural network encoder through comparative learning to obtain a target trajectory encoder; based on a target trajectory encoder, constructing a plurality of normal behavior mode reference models according to the trajectory in each cluster corresponding to the pseudo tag; and inputting a to-be-detected new track into the target track encoder to generate a to-be-detected embedded vector, and performing anomaly judgment according to the distance between the to-be-detected embedded vector and each normal behavior mode reference model. According to the invention, the accuracy of ship abnormal behavior detection is improved.

A method is performed by a network node for precoding of downlink communications predicting downlink channel state. The method receives a compressed-dimensional representation of a channel state that is encoded through an encoder neural network of a UE. The method maps the compressed-dimensional representation through a forward-prediction neural network to generate a compressed-dimensional predicted representation of a forward channel state at least one step forward in time k+Δ, wherein Δ is a number of steps forward in time. The method decodes the compressed-dimensional predicted representation of the forward channel state through a decoding neural network to generate an increased-dimensional predicted representation of the forward channel state, where the increased-dimensional predicted representation is a higher dimensional representation than the compressed-dimensional predicted representation. The method precodes signals for transmission through the downlink channel to the UE based on the increased-dimensional predicted representation of the forward channel state.

The invention discloses a knowledge tracking method and system based on group and individual dual-path collaborative evolution, which are used for modeling the knowledge mastering condition of a learner from a problem state, a concept state and an overall knowledge state and comprehensively capturing the dynamic evolution process of the knowledge state. According to the method, the complex interaction relationship among different knowledge dimensions is effectively captured by fusing the LSTM network, the Transform encoder, the multi-head attention mechanism and the MALA linear attention module. Multi-dimensional feature representation is constructed by using question embedding, concept embedding and answer embedding, and fine adjustment of knowledge states is realized through a gating mechanism and a state updating module. The linear attention calculation and rotation position coding technology of amplitude perception is adopted, so that the capturing capability of the model on the long-term dependency relationship is enhanced while the calculation efficiency is ensured. A knowledge forgetting rule is dynamically reflected through a time decay factor and a state updating mechanism, the ability and problem characteristics of a learner are quantified in combination with an IRT model idea, and accurate modeling and performance prediction of the learning process of the student are achieved.

The invention relates to the technical field of artificial intelligence and power systems, and discloses a power system sample generation method, system and device based on a graph attention network, and a medium, and the method comprises the steps: obtaining historical operation data of a power system, and constructing a graph structure; encoding the graph structure by using a graph attention network encoder to obtain a node embedding representation; performing graph-level aggregation on the node embedded representation to obtain a global representation vector, inputting the global representation vector into a variational auto-encoder, and generating a mean vector and a logarithmic variance vector of potential variables; potential variables are obtained through re-parameterization skill sampling, and model parameters are trained; and based on the trained model, generating a potential vector in a potential space through a sphere center sampling mechanism, inputting the potential vector into a decoder, and generating a new power system operation sample. According to the method, a sample generation scheme with high reliability and high robustness is provided for uncertainty modeling and data-driven optimization scheduling of a power system.

This invention discloses an adaptive intrusion detection method based on CDIVAE and a bidirectional temporal model, belonging to the field of network attack detection technology. It uses the GWR algorithm to filter and cluster source domain data, removing a large amount of duplicate data and extracting a clearly distributed and relatively small subset of source domain data. A Gaussian mixture conditional domain-invariant variational autoencoder (GMI) is used to reduce the difference in posterior distribution between the source and target domains. Finally, an intrusion detection is performed using a fusion neural network BRN-BiLSTM, which combines a bidirectional preservative network encoder and a bidirectional long short-term memory network. The BRN first applies bidirectional temporal weighting to the data, and then the BiLSTM identifies and classifies the time-weighted data. The memory unit and gating unit effectively capture data dependencies. This invention achieves better domain-invariant feature extraction and data distribution alignment, and also exhibits better cross-domain intrusion detection performance.

This application discloses a method, apparatus, equipment, and storage medium for locating remaining oil. The method includes: acquiring segmented displacement state data of well groups and boundary transition trajectory data of the development stage; obtaining a continuous potential displacement state sequence by boundary interception, trajectory insertion, and time concatenation; obtaining a continuous displacement state sequence over all time periods by using a three-layer fully connected decoding method mirroring the encoding layer of the preceding depth Koopman autoencoder network; extracting the state at six consecutive sampling times at the boundary to form a local continuous change sequence; obtaining displacement obstruction judgment parameters through two-layer fully connected compression mapping; generating two types of markers through threshold comparison, cross-screening contradictory well groups, associating spatial locations, and merging to obtain the location result. This application can accurately distinguish two types of easily confused areas, and the location result can directly support the selection of sites and potential tapping decisions for later-stage oilfield development measures.

This invention discloses a dual-stream point cloud compression method and system based on semantic scene graphs, relating to the field of point cloud compression. It constructs a point cloud compression network comprising an encoder network and a decoder network: In the encoder network, semantic labels are mapped onto the input point cloud, and scene graphs and octree representations are constructed respectively. Semantic modulation parameters are generated based on the scene graph and encoded to obtain a semantic bitstream. The octree representation, under the influence of semantic modulation parameters, undergoes feature enhancement and attention probability prediction to obtain node occupancy probabilities, and a geometric bitstream is generated through arithmetic encoding. These two bitstreams serve as compressed data. In the decoder network, the bitstreams are decoded, and the octree structure and scene graph information are reconstructed. Node feature representations are recovered by combining the semantic modulation parameters. The reconstructed octree structure is mapped back to the point cloud space through spatial querying and indexing to reconstruct the point cloud. This invention solves the problem of local geometric distortion in low-bitrate octree point cloud compression, ensuring reconstruction quality while reducing the transmission bitrate.

A method for encoding data includes: selecting a sequence of pivot candidate positions from a sequence of g encoded vectors to encode blocks of g data symbols in a round of encoding by the following steps: providing a set of g pivot candidate positions; selecting pivot candidate positions for the sequence from the set of pivot candidate positions; removing the selected pivot candidate positions from the set of pivot candidate positions; and repeating until the set of pivot candidate positions is empty and the sequence of selected pivot candidate positions in the round is non-linear. A set of encoded vectors is generated based on the sequence of selected pivot candidate positions, each encoded vector including zero-valued coefficients at positions within the encoded vector preceding the pivot candidate positions and non-zero-valued coefficients at least at the pivot candidate positions.

The invention relates to the technical field of medical image processing, in particular to a PL medical image segmentation method combining deep supervision and a mixed loss function. The method comprises the following steps: carrying out cutting, registration, normalization, enhancement and dicing preprocessing on an input three-dimensional medical image; inputting the image blocks into an encoder-bottleneck layer-decoder network; an encoder extracts multi-scale features through pooling of a residual VGG block and a dual-channel spatial pyramid; performing depth feature abstraction and context modeling on the bottleneck layer; the decoder performs up-sampling through transposition convolution, fuses encoder features transmitted by jump connection, utilizes space attention to gate and focus a target, and optimizes the features through an ASPP module and a residual block; and setting output in a middle layer and a final layer of the network, and training the network through a mixed loss function combining Dice loss and cross entropy loss and a deep supervision mechanism. The precision and robustness of medical image segmentation can be effectively improved.

A communication device may include: a processor configured to perform a procedure comprising: receiving a first consensus check code from a first communication device; receiving a second consensus check code from a second communication device; generating a combination code by network encoding the first consensus check code and the second consensus check code; and instructing the transmission of the combination code to the first communication device and to the second communication device.

This invention provides a collaborative optimization method for titanium plate annealing process parameters using multi-agent reinforcement learning, belonging to the field of reinforcement learning technology. The method includes collecting and standardizing annealing process data, encoding process parameters through a multi-layer feature extraction network, and constructing a parameter coupling perception matrix to quantify the collaborative strength. A dual-branch encoding structure is used to extract single-parameter features and interaction features, and the fusion weights are dynamically adjusted based on the coupling perception matrix to complete the state collaborative representation. The collaborative representation is input into a constraint-aware policy network to generate adjustment decisions, which are then executed in a real-world scenario and feedback is collected. Based on the feedback, a reward value is calculated, and training samples are sampled with priority to construct a composite loss function. A gradient projection method is used to update the policy network parameters to within the process feasible region, achieving continuous optimization of the policy network.

The application discloses a joint source channel coding channel state information feedback method based on dynamic resource selection. A base station deploys a resource selection network to evaluate each candidate uplink resource by using a history reconstructed downlink channel state information sequence and a history estimated uplink channel state information sequence, and outputs a target uplink resource to a user terminal. The user terminal performs joint source channel coding on the channel state information on the resource, and sends an uplink feedback signal. The base station receives and decodes the downlink channel state information to reconstruct the downlink channel state information, and writes the reconstruction result and the estimated uplink channel state information into a history cache to form an online closed loop deployment. The application jointly trains and optimizes the resource selection network, an encoder and a decoder, jointly optimizes reconstruction, selection and sorting losses, and improves resource selection and channel reconstruction accuracy. Compared with no dynamic resource selection, the application can reduce feedback loss and improve closed loop performance.

The application relates to the technical field of energetic material design and performance prediction, and relates to an energetic material multitask property prediction method. Standardized data sets are constructed by collecting energetic material sample data and performing molecular graph data enhancement processing on a training subset; molecular SMILES strings are respectively parsed into molecular topological graphs and word sequences, three-dimensional graph neural network is used to encode atomic space position information to extract molecular local topological features, a Transformer encoder is used to extract molecular global long-range correlation features, and a dynamic weighting mechanism is used to realize adaptive fusion of the two types of features, so that the depth and comprehensiveness of feature mining are improved; a multitask prediction model with a shared encoding layer, multiple independent decoding layers and a task decoupling constraint mechanism is built, an end-to-end training is completed by using a multitask loss function, the problems that existing multitask methods are difficult to balance the internal conflicts between energy performance and safety performance and are difficult to simultaneously predict multiple key indicators are solved, and the simultaneous prediction of multiple performance indicators is realized.

The invention discloses a time-varying working condition fault diagnosis method capable of explaining deep learning driving, equipment and a medium. According to the method, a convolutional sparse intrinsic mode expansion network is provided, a convolutional sparse intrinsic mode dictionary is constructed based on an impact failure mechanism, a fast coding solution algorithm is designed and expanded, a network encoder is constructed, and intrinsic mode sparse coding is realized through multiple channels; and the decoder performs weighted stacking on the intrinsic mode impact response of each channel, and outputs time-varying fault impact characteristics with clear physical significance. According to the method, a fault mechanism is embedded in feature extraction, interpretable generalization of an unknown time-varying working condition can be realized without multi-source domain data, and the diagnosis accuracy and credibility of the mechanical fault under the time-varying working condition are remarkably enhanced.

The invention relates to the technical field of wireless communication, and discloses a wireless communication transmission service demand generation method and system, a terminal and a storage medium, and the method comprises the steps: obtaining an external scene factor of a user terminal, carrying out the modeling of an environment according to the external scene factor, and obtaining an environment embedded code after full-connection network coding; acquiring a user position of a user terminal, and modeling a target layer behavior state of a user according to the user position to obtain behavior layer behavior probability distribution; and acquiring a historical traffic feature, integrating the environment embedded code, the historical traffic feature, the target layer behavior state and the behavior layer behavior probability distribution into a network input feature, inputting the network input feature and the UE type code into a time sequence generation model, outputting a UE traffic feature, and predicting the UE behavior state. According to the method, continuous UE flow characteristics are dynamically output, user behavior prediction can be updated in real time, and the requirements of a digital twin communication simulation system for reality and dynamics are met.

The invention discloses a double-flow point cloud compression method and system based on a semantic scene graph, and relates to the field of point cloud compression, and the method comprises the steps: constructing a point cloud compression network comprising an encoder network and a decoder network: in a coding end network, carrying out the semantic label mapping of an input point cloud, and respectively constructing a scene graph and octree representation; semantic modulation parameters are generated based on the scene graph and coded to obtain semantic bit streams, octree representation obtains node occupancy probability through feature enhancement and attention probability prediction under the action of the semantic modulation parameters, geometric bit streams are generated through arithmetic coding, and the two bit streams serve as compressed data; in the decoder network, bit streams are decoded, an octree structure and scene graph information are reconstructed, node feature representation is recovered in combination with semantic modulation parameters, and the reconstructed octree structure is mapped back to a point cloud space through spatial query and indexing to reconstruct a point cloud. According to the method, the local geometric distortion problem of low-bit-rate octree point cloud compression is solved, the reconstruction quality is ensured, and the transmission bit rate is reduced.

This invention discloses a method and system for optimizing data interaction between intelligent terminals based on link state awareness, relating to the field of wireless communication data transmission technology. The method includes: constructing a directed acyclic graph topology; performing cooperative topology state discovery to generate a real-time link state communication topology; performing hierarchical packetization for transmission quality constraints; performing random linear network coding to obtain multiple linearly independent coded packets; performing distributed congestion-aware scheduling decisions to obtain multiple primary transmission links; performing differential coding and obfuscation transformation to obtain multiple obfuscated coded packets; and concurrently transmitting multiple obfuscated coded packets to a second terminal for Gaussian elimination decoding and reception. This invention solves the technical problems of weak topology adaptability, unreasonable congestion scheduling, and insufficient security protection in existing technologies, achieving efficient and secure data interaction between terminals and improving the real-time performance and transmission security of local area network data transmission.

The invention provides a battery state-of-charge prediction method based on a Hemma optimization algorithm, and relates to the technical field of battery management, and the method comprises the steps: obtaining a historical time sequence data set; dividing the historical time sequence data set to obtain a plurality of sample sets; constructing a charge state prediction model; the charge state prediction model comprises a time domain convolutional network, an encoder network and a full connection network; the time domain convolutional network, the encoder network and the full connection network are connected in sequence; based on each sample set, carrying out optimization training on parameters of the charge state prediction model by adopting a He-horse optimization algorithm to obtain a trained charge state prediction model; and acquiring real-time time sequence data of the battery, and combining with the trained state-of-charge prediction model to obtain a state-of-charge prediction value. The method can effectively capture the local and global features of the battery time sequence data, optimizes the hyper-parameters of the model based on the Hemma optimization algorithm, improves the estimation precision, and can adapt to complex dynamic working conditions.

This invention provides a method, system, and device for deblurring dynamic scene images. The specific steps are as follows: Constructing a dynamic scene image deblurring network, including a multi-scale dense feature extraction module connected between convolutional layers of a U-Net network, a ConvLSTM bidirectional connected structure inserted between adjacent skip connections in the U-Net network, and a U-Net network structure optimization strategy inserted into the U-Net network encoder and decoder; constructing a total loss function and training the dynamic scene image deblurring network to obtain a dynamic scene image deblurring network model; inputting the image to be processed into the dynamic scene image deblurring network model to obtain a deblurred image. This invention effectively reduces the loss of texture details during image restoration, suppresses noise to a certain extent, and prevents ringing artifacts, facilitating subsequent tasks and work.

The invention discloses a terahertz reflection type linear array imaging quality optimization system and method, and the method comprises the steps: S1, taking a degraded terahertz reflection image as an optimization target, initializing a symmetric coding and decoding convolutional neural network, and generating an input tensor input network with disturbance; s2, the encoder extracts and outputs bottleneck features through wavelet downsampling; s3, performing dual-branch processing on the bottleneck features, and fusing residual connection to obtain enhanced features; s4, the decoder performs bilinear up-sampling reconstruction and outputs a restored image; s5, calculating loss update parameters, and stopping iteration when the loss of the verification set is optimal; and S6, outputting the restored image as a final enhanced image. By adopting the system and the method, external training data is not needed, the quality of the terahertz reflection type linear array image is adaptively improved, the inherent defects of a traditional method and a conventional deep learning model are overcome, the image features are optimized by relying on image prior information, and the practicability of the terahertz imaging technology in the fields of nondestructive testing and the like is assisted.

The invention discloses a wireless communication method and a wireless communication system. In the wireless communication method, each of N slave unmanned aerial vehicles passing an authentication program confirms that the slave unmanned aerial vehicles have the same time scale area as ground processing equipment according to a synchronization timestamp received from the ground processing equipment, selecting a corresponding key in a random key group permutation sequence as a current key according to a time point of receiving the random key group permutation sequence from the ground processing equipment, and encrypting k public advancing tracks received from the ground processing equipment by using the current key based on a random perturbation algorithm to obtain perturbation encryption data, transmitting the disturbance encrypted data to the main unmanned aerial vehicle according to the received serial number and coordinate of the main unmanned aerial vehicle from the ground processing equipment; and the master unmanned aerial vehicle executes random linear network coding on the received N disturbance encrypted data transmitted by the N slave unmanned aerial vehicles to generate a coding code block, and transmits the coding code block to ground processing equipment.