96 results about "Residual Blocks" patented technology

The invention relates to an EDSR (Enhanced Depth Super-Resolution) image super-resolution reconstruction method based on particle swarm optimization, and the method comprises the following steps of: (1) carrying out super-resolution reconstruction on an EDSR (Enhanced Depth Super-Resolution) image; the method comprises the following steps: firstly, inputting a low-resolution image data set as a training sample, defining an optimization space containing the number and stage of residual blocks, convolutional layer parameters, an attention module, an up-sampling mode and the like, initializing particle swarm optimization (PSO) parameters, and dynamically constructing a candidate network by particle position coding; a candidate network is dynamically constructed through particle position coding, and a residual block layer, a convolution layer, an attention module and an up-sampling module are sequentially configured. The candidate network is subjected to limited training, and individual and global optimal positions are updated through fitness function evaluation fusing PSNR and model complexity. And finally, a global optimal structure is selected for complete training for low-resolution image reconstruction, the detail reduction capability and the reasoning efficiency are remarkably improved, and a high-quality image is generated.

The invention discloses an Alzheimer disease prediction method and system based on deep learning and electrocardiosignals. Firstly, electrocardiosignals are collected and preprocessed; then, constructing a deep learning prediction model which comprises a feature extraction module and a classification prediction module; the feature extraction module comprises a plurality of residual blocks, and each residual block comprises a convolution layer, a batch normalization layer, a nonlinear activation layer and a jump connection; the classification prediction module realizes a complete mapping process from a feature space to probability prediction through a multi-layer perceptron structure and a softmax function, and obtains a prediction probability of each electrocardiosignal fragment belonging to each category; and fusing the prediction results of the plurality of electrocardiosignal segments of the same sample by adopting a soft voting mechanism to obtain a final prediction result. The system comprises a signal acquisition module, a signal preprocessing module, a deep learning prediction module and a result output module. According to the method, Alzheimer's disease prediction is realized based on the electrocardiosignals, and the method is simple and convenient in acquisition mode, non-invasive, low in cost and suitable for large-scale screening.

The invention provides a flight delay prediction method and system, computer equipment and a storage medium, and belongs to the technical field of traffic delay prediction.The method comprises the steps that firstly, a bacterial foraging algorithm (BFA) is optimized through a genetic algorithm (GA) so as to improve the global search ability and convergence speed of the algorithm; secondly, optimizing the structure and parameters of a deep neural network DNN by using the optimized BFA algorithm, and constructing a deep neural network model based on double hidden layers; according to the model, an attention mechanism and a residual block are introduced, so that the nonlinear mapping capability and the generalization capability are improved, and model overfitting is effectively prevented. In addition, the flight data and the weather condition data are combined, so that the prediction accuracy is further improved. The performance of the model is evaluated through multiple indexes, the result shows that the method can effectively solve the problem of DNN structure and parameter selection, and the training efficiency and generalization ability of the model are remarkably improved.

This invention discloses a deep learning-based Hadamard transform-based anti-screen-capture watermarking method, belonging to the field of watermarking technology. This invention combines a convolutional neural network (CNN) and residual blocks to achieve an end-to-end process of watermark embedding and extraction within the Hadamard domain. By simulating screen-capture attacks and incorporating this method between the embedding and extraction layers, the network ensures robust watermark embedding. This method can efficiently extract watermark information from photos taken by surreptitiously, protecting the copyright of digital media. The use of the transform domain for watermark embedding allows the watermark to spread over a wider area of ​​the image, significantly improving the robustness of the watermarking algorithm. Comparison with related technologies demonstrates the superiority of this invention in terms of imperceptibility and robustness.

This invention discloses an adaptive edge-aware 3D medical image segmentation method, with the following specific steps: S1, constructing an adaptive edge-aware network, which includes an encoder and a decoder, with a skip connection between the encoder and decoder; S2, acquiring and processing a 3D medical image; S3, inputting the preprocessed image from step S2 into the encoder of the adaptive edge-aware network through a patch partitioning layer, then into the decoder through residual blocks and adaptive weight matching blocks. The decoder output and the original input image are skip-connected through adaptive weight matching blocks, and finally, the image segmentation result is output through residual blocks and Fourier convolution. This invention exhibits stronger robustness and boundary accuracy in multi-organ 3D segmentation tasks, providing an efficient and scalable solution for medical image segmentation.

This invention discloses a dynamic obstacle avoidance method for assistive visually impaired scenarios. First, a feature extraction module based on a hierarchical residual structure constructed within residual blocks is built, which expands the receptive field of deep features. Second, a spatial feature recovery module based on bilinear interpolation and transposed convolution upsampling is designed to make segmentation edges more accurate. Third, a discrete sampling strategy is used to extract obstacle category, distance, and contour information, and path planning is performed using a heuristic search algorithm considering safe distance constraints. Finally, priority rules and logical order rules for the obstacle avoidance warning system are assumed, and a decision is generated based on the planned path, effectively guiding blind users to avoid obstacles through auditory and tactile information. This invention solves the problem that single-stage instance segmentation algorithms struggle to simultaneously and accurately segment small target obstacles and background road surfaces, overcoming the difficulty of providing effective information for obstacle avoidance decisions in assistive visually impaired scenarios with instance segmentation results, enabling blind users to avoid obstacles more intelligently and autonomously.

Disclosed are a video signal processing method and device whereby a video signal is encoded or decoded. The video signal processing method may comprise the steps of: determining whether an intra sub-partition (ISP) mode is applicable to a current block; if the ISP mode is applicable to the current block, splitting the current block into a plurality of rectangular transform blocks in the horizontal or vertical direction; generating prediction blocks of the transform blocks by carrying out intra prediction on each of the transform blocks; and reconstructing the current block on the basis of residual blocks of the transform blocks, and the prediction blocks.

This invention provides a weight training method and system for generating geological lithological texture models based on LoCon, belonging to the field of geological lithological texture generation technology. It employs an LDM model as the large model framework for weight training and texture generation. Convolutional layers are integrated into the convolutional weights of the residual blocks in the U-Net model within the LoCon model. The low-rank matrix of the LoCon model is added to the pre-trained weight matrix in the U-Net model to construct the generated geological lithological texture model. The model is trained using a training set. The trained weights are output, loaded into the large model framework for inference, and the training parameters are adjusted based on the inference results. Training is repeated until the preset inference result requirements are met. An API is provided to create an interface between the LDM large model framework and the trained weight matrix. This fills a gap in the geological industry's material library and lowers the technical threshold for geologists to participate in digitization.

This invention discloses a cross-domain fault diagnosis method for bearings, aiming to address the problem of insufficient diagnostic generalization caused by significant differences in the distribution of bearing fault features and the scarcity of target domain labels under varying operating conditions. The method first constructs a multimodal input including a standardized one-dimensional time-series signal, a short-time Fourier transform time-frequency plot, and a phase space reconstruction plot. It then extracts temporal dependencies, time-frequency textures, and phase space topological features in parallel through a three-branch network consisting of a temporal convolutional network, residual blocks, and an inverse residual layer. These features are dynamically fused using a Transformer encoder to generate global features. High-confidence pseudo-labels are generated based on a momentum prototype distance metric, and class-level domain alignment is achieved by combining a homoscedastic uncertainty weighted composite loss function. Finally, iterative training outputs the target domain fault diagnosis results. Experiments show that the method achieves cross-domain diagnosis accuracy of 98.04% and 99.79% on the bearing datasets from the University of Paderborn and Case Western Reserve University, respectively, demonstrating both high accuracy and strong generalization, making it suitable for bearing fault diagnosis in industrial variable operating conditions.

The application discloses an image super-resolution reconstruction method, system, device and medium, relates to the technical field of image super-resolution reconstruction, and comprises the following steps: extracting an image feature map; dividing an input feature map into multiple routing units, introducing a hybrid depth condition calculation in a deep feature extraction network composed of multiple residual blocks; and based on the output of the deep feature extraction network, reconstructing an image with a resolution higher than a threshold value. By introducing a hybrid depth condition calculation mechanism with displacement perception, the application designs a structured routing with displacement perception and a budget tendency for the shift window mechanism, so that the shift window sub-block is protected in terms of computing resources, and the cross-window information interaction link is more complete, so that block-like artifacts and fractures across the window boundary are less likely to occur when recovering long edges, repeated textures and large structures.

The application discloses a processor, a chip, a device and a code rate estimation method, and belongs to the chip technical field.The processor comprises a code rate calculation unit and an accumulation unit.The code rate calculation unit is used for calculating a first code rate corresponding to an i-th residual block after the i-th residual block is acquired; and a second code rate is calculated based on N residual blocks.The accumulation unit is used for calculating the sum of the second code rate and the first code rates corresponding to the N residual blocks, so as to obtain a code rate estimation result.The processor does not consider the dependent relationship among the N residual blocks when calculating the first code rate corresponding to each residual block.After the current i-th residual block is acquired, the first code rate corresponding to the i-th residual block is calculated based on the i-th residual block itself.In this way, the problems of calculation delay and low efficiency caused by the fact that the code rate of the current residual block is calculated after all the residual blocks having the dependent relationship are acquired in the related art are avoided, and the calculation efficiency of the code rate estimation result of the encoding unit is improved.

The invention relates to the technical field of 5G communication channel estimation, and discloses a 5GMIMO channel estimation optimization method based on deep learning. According to the method, a deep learning model architecture is constructed, and model parameters are dynamically initialized according to channel coherence time so as to adapt to 5GMIMO channel multipath propagation characteristics. Received signal streams from a plurality of antenna elements containing different orthogonal frequency division multiplexing sub-carrier frequency sequences are processed, channel impulse response estimates are generated based on frequency domain correlation and input into a model for nonlinear transformation. And performing model parameter collaborative optimization, updating the network weight by calculating the gradient variation, constructing a target function according to channel delay extension and model depth association, and adjusting the estimation output towards the direction of minimizing the mean square error. And triggering model structure adaptation based on a norm of gradient variation, acquiring model copy parameters matched with the current channel state from an adjacent cell base station, normalizing the model copy parameters, and adjusting the number of attention heads or the number of residual blocks.

The invention discloses a spherical particle size measurement method and device based on deep learning numerical prediction, and belongs to the field of particle measurement and image processing. The method comprises the following steps: acquiring interference fringe image data of spherical particles with different sizes, marking a corresponding particle size label for each image, and dividing the images into a training set, a verification set and a test set; the training set is used to train a pre-constructed neural network model, the verification set monitors the training process and stores the optimal model weight, and the test set tests the prediction precision of the model; the pre-constructed neural network model is based on an original UNet + + network and comprises a plurality of residual blocks and a space attention module, and a full-connection output head is added to realize end-to-end mapping from an image to a size value; and finally, inputting an interference fringe image of a to-be-measured particle into the trained network, and directly outputting a particle size prediction value. According to the method, high-precision, real-time and end-to-end prediction of the spherical particle size is realized, and the method is suitable for scenes such as cloud particle field on-line monitoring.

This disclosure relates to a bitrate estimation apparatus and method, a video encoder, an electronic device, a storage medium, and a computer program product. The bitrate estimation apparatus includes: a parameter determination module for calculating and storing at least one bitrate estimation reference information corresponding to each residual block in an encoding unit; a bitrate estimation module for determining the input index of the last non-zero residual block in the encoding unit after storing the bitrate estimation reference information of all residual blocks in the encoding unit in the parameter determination module; and a bitrate estimation module for performing bitrate estimation on a target residual block based on at least one bitrate estimation reference information corresponding to the residual block on which bitrate estimation of the target residual block depends, wherein the input index of the target residual block is less than or equal to the input index of the last non-zero residual block. Embodiments of this disclosure can effectively reduce the amount of data that needs to be stored for bitrate estimation and reduce the computational resources required for bitrate estimation.

The application relates to a diversity image style transfer method based on a gating block, a computer device, a readable storage medium and a program product. The diversity image style transfer method is realized by using a diversity image style transfer network. The diversity image style transfer network comprises a style generation network. The style generation network comprises an encoder and a decoder which are connected in sequence. The encoder is used for inputting a content image. The decoder is used for outputting a stylized image. The decoder comprises a decoding gating block and a decoding backbone network which are connected in sequence. The decoding gating block comprises at least a first branch and a second branch which are independent of each other and share an input. The outputs of the first branch and the second branch are transmitted to the decoding backbone network. The sizes of convolution kernels of the first branch and the second branch and / or the number of residual blocks in a bottleneck layer are different. Each branch of the decoding gating block has a gating factor. The gating factor is used for adjusting the usage degree of each branch in the decoding gating block.

This invention provides a pixel-level grasping detection method, apparatus, and storage medium, relating to the field of machine vision technology. The method includes: introducing skip connections: based on a generative residual convolutional neural network (GRN), concatenating the output features of the convolutional layers and the output features of the deconvolutional layers of the GRN; introducing an attention mechanism: introducing an ECA channel attention mechanism into the residual blocks of the GRN, assigning weights to each channel of the feature map through an ECA module; improving the loss function: assigning higher weights to the region where the object is located through a weighted mask to obtain an optimized loss function; and detecting the object to be grasped based on the improved GRN. The pixel-level grasping detection method provided by this invention can more accurately capture the local geometric information and global structural relationships of an object, thereby improving the accuracy and robustness of detection.

This application provides a method, apparatus, computing device, and storage medium for kinship verification, comprising: acquiring at least two images; inputting each image into a feature extraction model to obtain output features of multiple specified residual blocks for each image and global features of individuals for each image; for any image, combining the output features of the multiple specified residual blocks to obtain a first combined feature; inputting the first combined feature into a local attention model to obtain local features of individuals; combining the local features of individuals and the global features of individuals for each image to obtain a second combined feature; inputting the second combined feature into a kinship verification model to obtain kinship verification results between individuals. By extracting significantly different local features of individuals from each image, combining them with the global features of individuals, and then inputting them into the kinship verification model, accurate kinship verification results are obtained.

The invention relates to a code rate estimation device and method, a video encoder, electronic equipment, a storage medium and a computer program product, and the code rate estimation device comprises a parameter determination module which is used for calculating and storing at least one piece of code rate estimation reference information corresponding to each residual block in a coding unit; the code rate estimation module is used for determining an input index of the last non-zero residual block in the coding unit after the code rate estimation reference information of all residual blocks in the coding unit is stored in the parameter determination module; and the code rate estimation module is used for performing code rate estimation on the target residual block according to at least one piece of code rate estimation reference information corresponding to the residual block on which code rate estimation needs to be performed by the target residual block, and the input index of the target residual block is smaller than or equal to the input index of the last non-zero residual block. According to the embodiment of the invention, the data volume required to be stored for code rate estimation can be effectively reduced, and the computing resources required for code rate estimation are reduced.

The present application relates to the technical fields of logistics sorting and deep learning, and particularly discloses a logistics sorting algorithm based on RCNN, the model of which is sequentially stacked by multiple convolution layers, three residual blocks, a pyramid pooling layer and a Softmax layer. The algorithm introduces ResNet to solve the problems of gradient vanishing and gradient explosion in the training process of deep convolutional neural network, so that the network is easier to learn the characteristics of data in the training process, and the performance and stability of the network are improved. The algorithm trains the RCNN model by collecting and integrating large-scale parcel image datasets, systematically adjusts the model parameters in the process, and iteratively optimizes the model to obtain the optimal model parameters. The algorithm can effectively classify the parcels to be sorted according to the parcel size, packaging material and the integrity of the outer package, so as to improve the sorting efficiency and optimize the overall operation effect of logistics.

Methods and apparatus are disclosed for joint optimization of machine learning model architecture and quantization. An example method includes generating a first machine learning model for a resource-constrained device based on quantized outputs from each of a plurality of compute blocks. Each compute block includes a plurality of inverted residual blocks coupled in series. Determining the quantized output of each respective compute block includes performing a first convolution, based at least in part on a first quantization level, on input data to a first inverted residual block, performing a second convolution on an output of the first convolution based at least in part on the first quantization level, adding an output of the second convolution to the input data to generate a first quantized output, and providing the first quantized output to a second inverted residual block, and providing the first machine learning model to the resource-constrained device for execution.

The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional network network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

This invention discloses an interpretable EEG decoding method based on adaptive fuzzy convolution and TSK-guided attention, specifically relating to the field of motor imagery classification technology. The method involves initial processing of the raw input EEG signal through a multi-scale spatiotemporal convolutional front-end; an adaptive fuzzy convolutional network models the highly non-stationary and dynamically changing dependencies in the feature sequences extracted by the multi-scale spatiotemporal convolutional front-end by stacking residual blocks, and expands the receptive field through an exponentially increasing expansion factor; the time-series representation output by the adaptive fuzzy convolutional network is globally averaged to obtain a global and time-independent preliminary feature vector, which is then weighted and averaged to obtain a fuzzy context vector, which is fed back to the attention mechanism, modulating the original query vector with the fuzzy context vector; using guided query, a highly informative final feature vector representing the input trials is obtained and weighted aggregation is performed to achieve high-precision EEG decoding.

The invention provides an intelligent fault diagnosis method and system for a krypton and xenon extraction process and a storage medium, and the method specifically comprises the steps: obtaining multivariable time series data of the krypton and xenon extraction process, and inputting the multivariable time series data into a multi-scale residual dense cavity convolutional network to extract a high-dimensional depth feature sequence; the network uses cavity convolution with different expansion rates in different residual blocks, and fuses multi-scale time sequence features through dense connection; weighting the feature sequence by using a channel attention and time self-attention mechanism to obtain a time weighted feature; meanwhile, on the basis of covariance modeling between feature channels, feature dimension attention scores are calculated, and variable correlation weighted features are obtained; performing first outer product fusion on the time weighted feature and the variable correlation weighted feature, performing second outer product fusion on the original depth feature and the time weighted feature, and splicing the two fusion results to generate a fault representation vector; and inputting the fault representation vector into a classifier, and outputting a fault type diagnosis result.

Methods and apparatus are disclosed for joint optimization of machine learning model architecture and quantization. An example method includes generating a first machine learning model for a resource-constrained device based on quantized outputs from each of a plurality of compute blocks. Each compute block includes a plurality of inverted residual blocks coupled in series. Determining the quantized output of each respective compute block includes performing a first convolution, based at least in part on a first quantization level, on input data to a first inverted residual block, performing a second convolution on an output of the first convolution based at least in part on the first quantization level, adding an output of the second convolution to the input data to generate a first quantized output, and providing the first quantized output to a second inverted residual block, and providing the first machine learning model to the resource-constrained device for execution.

This invention discloses a rock and mineral classification method based on a three-dimensional convolutional residual network, relating to the field of geological exploration technology. The method includes the following steps: Step S1: Acquire hyperspectral image data of the rock and minerals, wherein the hyperspectral image data includes spatial and spectral information; Step S2: Preprocess the hyperspectral image data to obtain a normalized three-dimensional data matrix; Step S3: Construct a three-dimensional convolutional residual network model, wherein the network model includes an input layer, multiple three-dimensional convolutional residual blocks, a feature fusion module, and a classification output layer. This invention achieves end-to-end automated processing, eliminating the need for manual feature engineering design, reducing reliance on experience, adapting to practical engineering applications, and its modular architecture also possesses strong transferability and scalability, adapting to different data and extended scenarios, balancing classification accuracy and practicality.

The invention relates to a server production PXE network card fault pre-identification method based on a deep residual network. The method comprises the following steps: obtaining multi-dimensional operation parameters of a PXE network card of a target server, and preprocessing the multi-dimensional operation parameters to obtain a standardized data set; and constructing a deep residual network model based on the residual block to output the PXE network card fault type probability. A PXE network card fault sample data set is constructed, and the data set comprises normal sample data and five types of fault sample data, namely a PXE boot file loading failure sample, a DHCP address acquisition overtime sample, a TFTP server connection abnormal sample, a network card hardware drive conflict sample and a transmission interruption sample caused by insufficient network bandwidth. Operating data of the PXE network card of the server are collected in real time, preprocessed and input into the trained deep residual network model, and the model outputs the fault type and the fault probability of the current network card. Multi-dimensional data association features are extracted through a deep network, the fault recognition accuracy is high, hardware and protocol layer full-type faults are covered, and the method is adaptive to multiple types of network cards.

The invention discloses an attention interpretable electroencephalogram decoding method based on adaptive fuzzy convolution and TSK guidance, and particularly relates to the technical field of motor imagery classification, and the method comprises the steps: carrying out the preliminary processing of an input original EEG signal through a multi-scale space-time convolution front end; the adaptive fuzzy convolutional network performs modeling on a highly non-stable and dynamically changing dependency relationship in a feature sequence extracted by the multi-scale space-time convolution front end through a stacked residual block, and expands a receptive field through an exponentially increased expansion factor; performing global average pooling on a time sequence representation output by the adaptive fuzzy convolutional network to obtain a global and time-independent initial feature vector, then performing weighted average to obtain a fuzzy context vector, feeding back the fuzzy context vector to an attention mechanism, and modulating an original query vector by the fuzzy context vector; and obtaining a final feature vector represented by a highly informationized input test number by utilizing guide type query, and carrying out weighted aggregation to realize EEG decoding high-precision processing.

The invention discloses a processor, a chip, equipment and a code rate estimation method, and belongs to the technical field of chips. The processor comprises a code rate calculation unit and an accumulation unit. The code rate calculation unit is used for calculating a first code rate corresponding to the ith residual block after the ith residual block is obtained; and calculating a second code rate based on the N residual blocks. And the accumulation unit is used for calculating the sum of the second code rate and the first code rates corresponding to the N residual blocks respectively to obtain a code rate estimation result. When the processor calculates the first code rate corresponding to each residual block, the dependency relationship among the N residual blocks is not considered. After a current ith residual block is obtained, a corresponding first code rate is calculated only based on the ith residual block. In this way, the problems of calculation delay and low efficiency caused by the fact that code rate calculation of the current residual block needs to be carried out after all residual blocks with the dependency relationship are obtained in the prior art are solved, and the calculation efficiency of the code rate estimation result of the coding unit is improved.

The invention relates to an insulator crack detection method based on generative adversarial network image super-resolution reconstruction. The method comprises the following steps: S1, acquiring an image data set with insulator defects; s2, building a generator; s3, constructing a discriminator; s4, constructing an overall convolutional neural network suitable for image super-resolution reconstruction; s5, in the deep learning environment built in the steps S1 to S4, for the generator built in the step S2, using a plurality of dense residual blocks to realize maximum extraction of features; and S6, training a generator by using the randomly cut image in the step S1, and using the finally generated super-resolution image for insulator crack detection, thereby improving the judgment accuracy. According to the method, the problem of low identification precision of a traditional method caused by the lack of crack details of the low-resolution insulator inspection image can be solved.

The invention relates to an EDSR (Enhanced Depth Super-Resolution) image super-resolution reconstruction method based on particle swarm optimization, and the method comprises the following steps of: (1) carrying out super-resolution reconstruction on an EDSR (Enhanced Depth Super-Resolution) image; the method comprises the following steps: firstly, inputting a low-resolution image data set as a training sample, defining an optimization space containing the number and stage of residual blocks, convolutional layer parameters, an attention module, an up-sampling mode and the like, initializing particle swarm optimization (PSO) parameters, and dynamically constructing a candidate network by particle position coding; a candidate network is dynamically constructed through particle position coding, and a residual block layer, a convolution layer, an attention module and an up-sampling module are sequentially configured. The candidate network is subjected to limited training, and individual and global optimal positions are updated through fitness function evaluation fusing PSNR and model complexity. And finally, a global optimal structure is selected for complete training for low-resolution image reconstruction, the detail reduction capability and the reasoning efficiency are remarkably improved, and a high-quality image is generated.