64results about How to "Improve decoding performance" patented technology

The invention provides a decoding and coding method, device and equipment, and the decoding method comprises the steps: decoding a first code stream of a current image block, and obtaining a coefficient hyper-parameter feature of the current image block; for each stage sub-block of the current image block, determining a probability distribution parameter of the stage sub-block based on the coefficient hyper-parameter feature, and decoding a second code stream of the current image block based on the probability distribution parameter to obtain a residual feature of the stage sub-block; based on a mean value prediction network, determining mean value features of the sub-blocks in the stage; determining a reconstruction feature of the stage sub-block based on the mean feature of the stage sub-block and the residual feature of the stage sub-block; performing feature aggregation on the reconstruction features of the sub-blocks in each stage to obtain the reconstruction features of the current image block; a reconstructed image block of the current image block is determined based on the reconstruction feature of the current image block. Through the scheme of the invention, the coding performance and the decoding performance are improved.

The invention discloses a multi-modal feature fusion model construction method and a multi-step wind power prediction method, and belongs to the field of wind power prediction.The multi-modal feature fusion model construction method comprises the steps that firstly, two data conversion channels are added on the basis of a Grubrum angle field to construct a multi-channel Grubrum angle field, and wind power data are converted into RGB color images with color information; secondly, the time text features are embedded into the data features and the image features respectively, and the time sequence expression ability of the data features and the image features is improved; fusing the data features and the image features by using a cross-modal fusion method, and adjusting dynamic weights of the data features and the image features during fusion by using an adaptive decision mode to obtain fusion features containing different modal information; and finally, extracting association information between the fusion features and the wind power by using an encoder of the Transform, and decoding the input data into the wind power to be predicted by a decoder according to the association information and the prior data. A simulation experiment shows that the method effectively improves the prediction precision of the wind power.

The invention discloses a blood vessel segmentation method and device based on large model fine tuning, equipment and a medium, and the method comprises the steps: obtaining a blood vessel image, carrying out the preprocessing of the obtained blood vessel image, and obtaining a training set; performing fine tuning on a pre-trained image segmentation model by adopting the training set, so that the image segmentation model learns related features of blood vessel segmentation; wherein the low-rank adaptive fine tuning technology is adopted to perform fine tuning on the image segmentation model: two parallel low-rank matrixes are inserted into a Transform layer in the image encoder, the input is processed by the two low-rank matrixes in sequence, and the processing result and the original output are added to obtain the final output. According to the method, the defects of a large model in a blood vessel segmentation task are overcome through efficient parameter fine tuning and a multi-scale feature fusion module. Accurate blood vessel segmentation can be realized under limited annotation data, the difficulty and cost of medical image segmentation tasks are greatly reduced, and the method can be widely applied to the technical field of medical image processing.

The invention discloses a high-performance low-complexity LDPC (Low Density Parity Check) decoding method for satellite communication, and belongs to the field of digital signal processing. And performing iterative decoding on the received channel information based on a low density parity check (LDPC) code in the 5G standard. The implementation method comprises the following steps of: dynamically setting an erasing range by utilizing the amplitude of current check node information when a variable node is updated; the amplitude of check node information is gradually increased along with the increase of the number of iterations, the whole iteration process is divided into two parts, and the erasing range is set by adopting different parameters. And outputting the decoding result when the decoding result is correct or reaches the maximum number of iterations. According to the method, the reliability of variable node information is improved through the two points, reliable variable information is prevented from being erased, unreliable variable node information is prevented from being spread, and excellent decoding performance is achieved. Non-linear operation in a log-likelihood ratio belief propagation algorithm LLR-BPA does not exist in the decoding algorithm, and the decoding algorithm has the advantages of being high in decoding performance and low in decoding complexity.

The invention discloses an offset minimum sum LDPC (Low Density Parity Check) code decoding algorithm based on a model-driven neural network, and relates to an offset minimum sum LDPC code decoding algorithm. The invention aims to solve the problem that a traditional LDPC decoding algorithm is insufficient in convergence speed, calculation complexity, flexibility and the like. The method comprises the following steps: step 1, constructing a model-driven offset minimum sum algorithm network model, wherein the network model comprises an input layer, a check node layer, a variable node layer and an output layer; step 2, an input layer calculates a receiving channel LLR by using the receiving signal y to carry out initialization; step 3, the check node layer calculates the LLR value of the CN-to-VN; step 4, the variable node layer calculates the LLR value of the VN-to-CN; and step 5, calculating final decoding output by an output layer. The invention belongs to the technical field of decoding.

The invention discloses a high-resolution remote sensing image compression method and system based on block modulation imaging, a binary mask matrix is generated, an acquisition end configures an optical mask device according to the binary mask matrix, and when a high-resolution remote sensing image is acquired, an optical lens is adopted to acquire an optical signal matrix; after optical mask processing is carried out through the optical mask device, modulation is carried out through the relay lens, then the optical mask device is converted into an electrical signal matrix through the photoelectric sensor, then the electrical signal matrix is partitioned and superposed so as to complete compression, and an obtained measurement value matrix is sent to a receiving end; the receiving end extracts a block mask matrix corresponding to each block from the binary mask matrix according to the block mode of the acquisition end, then extracts each block signal matrix from the measured value matrix to form a three-dimensional signal matrix, and inputs the three-dimensional signal matrix into a pre-constructed and trained decoding network; and decoding to obtain an optical signal matrix of the high-resolution remote sensing image. According to the invention, block modulation imaging is provided, and the decoding restoration quality is improved while the compression speed is improved.

The embodiment of the invention provides an error correction decoding method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring pMLC data; reading target valid bit data from the pMLC data; decoding the target significant bit data based on a preset error correction engine; under the condition of decoding failure, performing combined coding processing on the target significant bit data, the first significant bit data and the second significant bit data to obtain threshold value distribution level information; performing identification processing on a deviation scene of threshold voltage distribution of the pMLC data according to the threshold distribution level information based on an error correction engine; and under the condition that the deviation scene of the threshold voltage distribution of the pMLC data is identified as a right deviation scene, performing bit flipping processing on the data in the target level storage unit corresponding to the target significant bit data. According to the scheme of the embodiment of the invention, the error correction decoding capability can be improved.

The invention discloses a data enhancement-based neuron signal classification method, which comprises the following steps of: (1) collecting neuron reaction signals, calculating the discharge rate of neurons in a specific time box by adopting a sliding window method, and averagely dividing the sequences into a plurality of fragments along the time dimension; (2) constructing a generator based on transformer and SNN, receiving a random vector, and outputting generated data after the random vector passes through an embedded layer, a multi-head self-attention layer and forward transmission; (3) constructing a discriminator, inputting the generated data and the real data into the discriminator, and judging whether the input data is the real data or not; (4) in the training process, using a binary cross entropy error as a loss function to update parameters of a generator and a discriminator; and (5) performing data enhancement by using data generated by the trained generator to improve the classification performance on the SNN classifier. According to the method, the problem of long sparse sequence generation is solved to amplify the neuron reaction signal, so that the classification effect after model training is improved.

The present invention provides a multi-round dialogue generation method, system, storage medium and electronic device with diverse responses based on multi-task learning, and relates to the technical field of multi-round dialogue generation. The present invention first constructs a multi-task learning model, the multi-task learning model includes a pre-trained multi-round dialogue model and a VAE model, the multi-round dialogue model includes a discourse-level encoder, an inter-discourse encoder and a first decoder; each sentence sequence vector in the pre-processed multi-round dialogue history information is sequentially input into the discourse-level encoder and the inter-discourse encoder to obtain a hidden vector containing the entire multi-round dialogue history information; the hidden vector is input into the first decoder, the parameters of the first decoder are loaded from the second decoder parameters in the VAE model, and a response sentence sequence is obtained. The VAE model decoder parameters are shared with the multi-round dialogue generation model, which enhances the decoding ability of the decoder in the multi-round dialogue generation model and improves the text quality of the generated response.

The present invention belongs to the field of mobile communication technology. Aiming at the QC-LDPC code in the 5G data sharing channel, in order to further narrow the gap between the decoding performance of the MS algorithm and the BP algorithm and improve the decoding performance of the NMS algorithm, an LDPC decoding method based on group adaptive normalization factor control is proposed. The present invention is based on the overestimation problem of the MS algorithm, and uses the ratio characteristics of the LLR messages of the check nodes of the BP algorithm and the MS algorithm to calculate the normalization factor. In order to reduce the complexity of decoding, according to the change characteristics of the optimal normalization factor, a weighted average processing is adopted; in order to reduce the average number of iterations and speed up the convergence speed of decoding, the method uses the residual characteristics of the check node information to perform layered processing, prioritizes updating the layer with the largest residual, and dynamically rearranges the layers between different iterations. Simulation results show that the proposed method can achieve better convergence speed and excellent decoding performance.

The present disclosure relates to a polar code encoding and decoding method and device, an information transmission system, and the field of communication technology. The encoding method includes: dividing m code segments of length n according to a first code symbol sequence to be encoded, where m and n are integer powers of 2; performing a check code generation operation on each information code symbol in each code symbol segment to obtain a check code corresponding to each code symbol segment; encoding each check code using an LDPC algorithm to obtain each coding check code; determining a first coding code symbol sequence according to the polar code encoding result of the first code symbol sequence to be encoded; transmitting the first coding code symbol sequence and each coding check code, so that after the polar code decoding device decodes the first coding code symbol sequence in segments, the information code symbols in the corresponding code symbol segments are checked using each coding check code.

The invention discloses an electroencephalogram signal processing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an electroencephalogram signal collected under intermittent task stimulation, and based on an event mark corresponding to each task stimulation in the electroencephalogram signal, extracting an event related potential corresponding to each event mark; for each event-related potential, performing multi-level feature extraction on the event-related potential in a time dimension to obtain a target time sequence feature; feature extraction is carried out on the target time sequence features based on the channel dimension, and target spatial-temporal features are obtained; and determining a brain activity mode when the target object executes the cognitive task based on the target spatial-temporal characteristics of the multiple event-related potentials. The electroencephalogram signals in the task state enrich the amount of information related to the specific task, multilevel feature extraction is carried out on the event related potential extracted from the electroencephalogram signals in the time dimension, the decoding capacity for the cognitive task is improved, and then the accuracy of electroencephalogram information processing is improved.

An image encoding / decoding method, a bit stream transmission method, and a computer-readable recording medium for storing a bit stream are provided. An image decoding method according to the present disclosure is an image decoding method performed by an image decoding device, and may comprise the steps of: reconstructing a picture from a bitstream; and transforming the reconstructed picture based on one of the at least one candidate transformation, where the at least one candidate transformation corresponds to a rotational transformation or a symmetric transformation for the picture.

The present invention relates to a polarization code transmission method based on transmission channel quantization level optimization, which solves the defect that different antennas will produce different precisions through different ADC links based on mobile communication MIMO system compared with the prior art. The present invention includes the following steps: the transmitting end screens the channel and performs coded transmission of polarization code; the receiving end constructs the transmission channel quantization parameter based on the minimum distortion quantization algorithm; the receiving end quantizes according to the transmission channel quantization level and performs BP decoding. The present invention optimizes quantizers of different precisions under polarization code BP decoding, improves the performance of polarization code decoder in a system with different quantization precisions, and improves the transmission efficiency of polarization code.

A point cloud data transmission method according to an embodiment may comprise the steps of: encoding geometric data of point cloud data; encoding attribute data of the point cloud data based on the geometric data; and transmitting the encoded geometry data, the encoded attribute data, and the signaling information.

The invention provides a decoding and coding method, device and equipment thereof. The decoding and coding method comprises the following steps: decoding a first code stream corresponding to a current image block to obtain a coefficient hyper-parameter feature; determining a probability distribution parameter based on the coefficient hyper-parameter feature, and decoding a second code stream of the current image block based on the probability distribution parameter to obtain a reconstruction feature; inputting the reconstruction features into a synthesis transformation network to obtain a reconstruction image block; the synthesis transformation network comprises an attention module, and the attention module is a cascade mixed attention module or a parallel mixed attention module; the cascaded mixed attention module comprises a first attention sub-module and a second attention sub-module, and the first attention sub-module and the second attention sub-module are serial; the parallel mixed attention module comprises a first attention sub-module and a second attention sub-module, and the first attention sub-module and the second attention sub-module are parallel. Through the scheme of the invention, the decoding performance is improved, and the complexity is reduced.

The invention provides a decoding and coding method, device and equipment thereof. The decoding and coding method comprises the following steps: decoding a first code stream corresponding to a current image block to obtain a coefficient hyper-parameter feature; determining a probability distribution parameter based on the coefficient hyper-parameter feature, and decoding a second code stream of the current image block based on the probability distribution parameter to obtain a reconstruction feature; inputting the reconstruction features into a synthesis transformation network to obtain a reconstruction image block; the synthesis transformation network comprises an attention module, and the attention module is a cascade mixed attention module or a parallel mixed attention module; the cascaded mixed attention module comprises a first attention sub-module and a second attention sub-module, and the first attention sub-module and the second attention sub-module are serial; the parallel mixed attention module comprises a first attention sub-module and a second attention sub-module, and the first attention sub-module and the second attention sub-module are parallel. Through the scheme of the invention, the decoding performance is improved, and the complexity is reduced.

The invention provides a signal decoding method and system, a computer readable storage medium, electronic equipment and a computer program product, and relates to the technical field of communication, and the method comprises the steps: obtaining a received signal, and carrying out the modulation and demodulation of the received signal, and obtaining soft bit information; the received signal is a signal generated through finite field linear block code coding and low-density parity check coding cascade coding; performing belief propagation iterative decoding of new air interface low-density parity check on the soft bit information to obtain a code word corresponding to a low-density parity check mother code; performing bit flipping hard decision decoding on the codeword corresponding to the low-density parity check mother code to obtain a finite field linear block code codeword; and performing finite field linear block code hard decision decoding on the finite field linear block code codeword to obtain information bits after receiving signal decoding. According to the method, the success rate of finite field linear block code hard decision decoding can be increased, an error code platform in a short code scene is remarkably reduced, and decoding time delay is effectively reduced.

The application discloses a model-driven neural network-based offset min-sum LDPC code decoding algorithm and relates to an offset min-sum LDPC code decoding algorithm. The application is designed to solve the problems of the traditional LDPC decoding algorithm in convergence speed, calculation complexity, flexibility and the like. The application comprises the following steps: 1, a model-driven offset min-sum algorithm network model is constructed, wherein the network model comprises an input layer, a check node layer, a variable node layer and an output layer; 2, the input layer is used to calculate the received channel LLR by using a received signal y to perform initialization; 3, the check node layer is used to calculate the CN-to-VN LLR value; 4, the variable node layer is used to calculate the VN-to-CN LLR value; and 5, the output layer is used to calculate a final decoding output. The application belongs to the technical field of decoding.

This application provides a decoding and encoding method, apparatus, and device. The method includes: obtaining a target probability distribution model corresponding to a first scaling factor based on a first bitstream corresponding to a current block; decoding a second bitstream corresponding to the current block based on the target probability distribution model corresponding to the first scaling factor to obtain corrected residual features corresponding to the current block; and determining a reconstructed image block corresponding to the current block based on the corrected residual features. This application improves encoding and decoding performance.

The invention discloses a communication transmission method, device and equipment of a two-dimensional Polar code. On an encoder, inner code Polar coding with the code rate of 1 is adopted to balance the error probability of each outer code, so that the error probability of a total code block is reduced, a Double Gaussian Application (DGA) algorithm is proposed to optimize the Design SNR used when the outer codes are constructed, and the accuracy of reliability estimation of sub-channels of the outer codes is improved. On a decoder, a Selective Successive Cancellation (SSCL) decoder combining inner code SCL decoding and outer code SC selection path re-decoding is adopted, a relatively reliable path obtained by inner code decoding is reserved and is used as a candidate path during re-decoding after decoding failure, and the decoding reliability is improved through re-decoding of multiple re-selection paths. Meanwhile, a plurality of inner code SCL decoders decode at the same time, and additional complexity is almost not introduced under the working signal-to-noise ratio by selecting and re-decoding, so that the overall decoding time delay is reduced.

The application discloses a kind of LDPC multi-bit quantization hardware decoding method suitable for high-speed communication, it is related to the field of communication physical layer digital signal transmission, including the steps 1) reset decoding module, from channel obtains the information sequence to be decoded and carries out suitable bit quantization extension;2) to meet the engineering demand of super high speed, low resource consumption, low latency, the application adopts a kind of full parallel decoding structure, the full parallel decoding structure can realize all check nodes update simultaneously and provide to all variable nodes.3) check node update is carried out by 6 parallel ways, the normalization factor used in the application check node update is obtained by adaptive mode;4) the check node information obtained in step 3 is as the input of variable node update module, variable node update is carried out by 6 parallel ways, the input in the application variable node update module is improved by expanding the number of bit quantization to improve the decoding ability of decoder.

This application provides an encoding / decoding method, apparatus, and device. The method includes: when a reference pixel of the current block is unavailable, removing target prediction modes from an initial prediction mode list corresponding to the current block to obtain a target prediction mode list; and encoding / decoding the current block based on the target prediction mode list. This application can improve encoding and decoding performance.

The invention provides a decoding and coding method, device and equipment, and the decoding method comprises the steps: obtaining a first feature corresponding to a current image block through a first neural network, and obtaining a feature adjustment factor corresponding to the current image block, the first neural network comprising at least one convolution layer; determining a target feature based on the first feature and the feature adjustment factor; and obtaining a reconstructed image block corresponding to the current image block through a second neural network based on the target feature, the second neural network comprising at least one convolutional layer. Through the technical scheme of the invention, the coding performance and the decoding performance can be improved.

The application discloses a decoding method of a check code, an electronic device, a storage medium and a program product, and relates to the technical field of data storage. The method comprises the following steps: performing check on an initial check code according to a check matrix, determining a first error weight value according to a first check result if the check fails, and determining a target decoding mode according to the first error weight value and a switch switching threshold value; determining a to-be-decoded area and a flip threshold value according to the target decoding mode and column weights of the initial check code; determining a second error weight value of information bits in the to-be-decoded area according to the check matrix, determining a target bit according to the second error weight value and the flip threshold value, flipping the target bit, and obtaining an intermediate check code; and if the intermediate check code passes the check, taking the intermediate check code as a target check code and outputting the target check code. The method solves the problem that the column weights of different check codes are not considered when the check code is decoded, a fixed threshold value is used to determine whether a bit flipping operation is performed, and the decoding performance is affected.

The application provides a decoding and encoding method, device and equipment, including: decoding a first code stream corresponding to a current image block to obtain a coefficient hyperparameter feature; determining a probability distribution parameter based on the coefficient hyperparameter feature, and decoding a second code stream of the current image block based on the probability distribution parameter to obtain a reconstructed feature; inputting the reconstructed feature into a synthesis transformation network to obtain a reconstructed image block; the synthesis transformation network includes an attention module, and the attention module is a cascaded hybrid attention module or a parallel hybrid attention module; the cascaded hybrid attention module includes a first attention submodule and a second attention submodule, and the first attention submodule and the second attention submodule are in series; the parallel hybrid attention module includes a first attention submodule and a second attention submodule, and the first attention submodule and the second attention submodule are in parallel. The application improves the decoding performance and reduces the complexity.

The application provides an LDPC code decoding method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining an input code word, a grouped check matrix and an initial confidence of an LDPC code, wherein the grouped check matrix is obtained by grouping an original check matrix according to a preset condition; presetting two initial quantization values with a given magnitude bit width, calculating an initial companion based on the input code word and the grouped check matrix; starting from the initial companion and the two initial quantization values, performing decoding iteration column by column, updating a current column variable node in the iteration, obtaining a soft decision message and transmitting the soft decision message to a next column, updating an associated grouped check node, and performing post-processing compensation on an oscillation correctable code word; updating the companion after each column is updated and judging a decoding success condition; and outputting a result when the condition is met or a maximum iteration number is reached. The scheme can realize the collaborative optimization of decoding performance and hardware implementation efficiency.

This invention provides a public-key encryption and decryption method based on rank distance, relating to the field of information security technology. The invention utilizes hybrid block noise with partially intersecting support sets to generate the public key. During encryption, the ciphertext is calculated by combining the block noise vector, the public key, and the generator matrix of the Augmented Gabidulin auxiliary code. Decryption is performed using the decoding algorithm of the Augmented Gabidulin auxiliary code. The hybrid block noise mechanism allows partial intersection of the support sets of the respective block noises, effectively reducing the total rank weight generated during decryption, making error correction easier, and greatly expanding the range of system parameters. Due to its ability to tolerate greater parameter flexibility and the efficient decoding capability of the Augmented Gabidulin auxiliary code, the size of the public key and ciphertext can be significantly reduced while maintaining similar security strength, ultimately improving the storage and transmission efficiency of the rank-distance-based cryptosystem.

This invention belongs to the field of computer vision technology, specifically relating to a skin lesion image segmentation method based on a Transformer dual-branch model. The method constructs and trains a Transformer dual-branch model, inputting the image to be processed into the trained Transformer dual-branch model to obtain the segmentation result. The Transformer dual-branch model includes a main branch network, an auxiliary branch network, and an information aggregation module. This invention proposes a novel skin lesion image segmentation method that addresses the shortcomings of traditional deep learning methods in extracting global contextual information. It utilizes an efficient multi-scale visual Transformer as an encoder to extract more powerful and robust features. Simultaneously, it introduces low-level feature modules and high-level feature fusion modules to effectively improve the network's feature learning ability and segmentation performance.

The invention provides a decoding and coding method, device and equipment, and the decoding method comprises the steps: obtaining a first feature corresponding to a current image block through a first neural network, and obtaining a feature adjustment factor corresponding to the current image block, the first neural network comprising at least one convolution layer; determining a target feature based on the first feature and the feature adjustment factor; and obtaining a reconstructed image block corresponding to the current image block through a second neural network based on the target feature, the second neural network comprising at least one convolutional layer. Through the technical scheme of the invention, the coding performance and the decoding performance can be improved.