12 results about "Max pooling" patented technology

This invention provides a deep spiking neural network method for ECG classification based on attention and integer training pulse inference, comprising the following steps: acquiring raw ECG signal data and preprocessing the raw ECG signal data; performing three rounds of convolution and corresponding max pooling on the ECG data features; performing block-based local self-attention processing on the ECG data features to obtain feature associations in local regions of the ECG data features; performing global self-attention processing on the ECG data features to obtain feature associations across the entire sequence of the ECG data features; performing two rounds of convolution and corresponding max pooling on the ECG data features; classifying the integrated ECG data features using a classification head, and outputting the ECG data classification result. This invention can effectively mine long-range dependency information of ECG data and retain shallow feature information through residual fusion, avoiding the gradient decay problem in deep networks, thereby enabling deep spiking neural network learning.

This invention discloses a bridge bending detection method based on a lightweight multi-scale sparse gating network, relating to the field of bridge structural health monitoring. The method includes: acquiring multimode fiber speckle images corresponding to different bending states of the bridge and preprocessing them to obtain standardized speckle images; obtaining an initial feature map based on a lightweight multi-scale sparse gating network through initial convolutional layers and max pooling layers; extracting and fusing bending-sensitive features through a multi-level multi-scale feature fusion module to obtain a multi-scale fused feature map; using a learnable sparse gating module for feature selection to obtain a sparse enhanced feature map; modeling global dependencies through a global context enhancement module to obtain a globally enhanced feature map; and inputting the globally enhanced feature map into a dual-task prediction module to output the corresponding result. This method achieves synchronous, lightweight, and high-precision detection of bridge bending degree and location, effectively decoupling the problem of multi-parameter cross-sensitivity.

This application relates to the field of urban pipeline network analysis technology, and particularly to a pipeline network connectivity assessment method, device, and related equipment based on DS-PIGNN. The method includes: acquiring pipeline network data, constructing a macroscopic topology map, and collecting the axial microscopic physical field sequence of each pipeline; extracting the features of the microscopic sequence of each pipeline using a one-dimensional residual convolutional neural network, and obtaining a microscopic health state vector through global max pooling; injecting this vector into the edge features of the macroscopic topology map to drive a graph neural network trained with a physical constraint loss function (including Kirchhoff flow conservation), which dynamically calculates the attention weights between nodes based on the hydraulic features of the nodes and the microscopic health state vector; and performing information aggregation based on this dynamic weight, simultaneously outputting the pipeline failure probability and node connectivity reliability. This application achieves dynamic and coupled analysis of microscopic physical damage details and macroscopic network cascade failures, and ensures the physical reliability of the assessment results while maintaining computational efficiency.

This invention provides a small target detection method based on PBAF-YOLO with progressive boundary awareness and multi-scale fusion. The method involves inputting a feature map, calculating neuron energy values ​​based on the spatial mean and unbiased sample variance of each channel's feature values, generating spatial attention weights based on these neuron energy values, and then weighting and enhancing the input feature map to obtain boundary enhancement features. These boundary enhancement features are grouped along the channel dimension, and average pooling and max pooling are performed on each group in the horizontal and vertical directions respectively. These are then fused to generate direction-sensitive spatial attention weights, resulting in multi-scale enhancement features. Multi-scale feature maps output from different stages of the backbone network are reused, and feature fusion is performed through single downsampling and single upsampling paths with skip connections. The high-resolution features are iteratively optimized to generate a multi-scale detection feature map. This multi-scale detection feature map is then input into a high-resolution prediction head adapted for small targets, outputting the small target detection result.

The application discloses a source code vulnerability detection method based on a graph neural network and multi-level attention fusion, and belongs to the technical field of intelligent software engineering and network space security. First, the source code is preprocessed and parsed to generate a code graph; a pre-trained model is used to extract graph structure features and graph node features; then, a graph neural network model is constructed, the graph node features are input into a multi-layer graph convolution network, and a self-attention mechanism is used to dynamically assign weights to each layer feature, and a global semantic feature matrix is generated through an average pooling layer; then, the original graph node features and the global semantic feature matrix are locally cross-fused, and a soft / hard attention fusion mechanism is used to extract local features; the fused features are input into a max pooling layer to generate local significant features; finally, a classifier is used to output a vulnerability detection result. The application uses global semantics to guide the extraction of local microscopic features, effectively improving the model's ability to capture and detect high-concealment code vulnerabilities.

A method and system for enhancing the performance of adversarial examples in retrieval question answering based on aggregated representation, the method comprising: S1: preprocessing the text of the question and answer to obtain the corresponding input text sequence X. q and X a S2: X q and X a Input a twin-tower model and obtain X. q and X a High-level representation vector H q and H a And syntactic representation vectors and S3: H q and H a The probability distribution mapped to the vocabulary is used to construct a representation vector v containing local lexical information through max pooling. q and v a S4: For v q and v a Pruning is performed to obtain a low-dimensional lexical representation vector. S5: The reduced-dimensional syntactic representation vector and the low-dimensional lexical representation vector are concatenated and aggregated to obtain the aggregated representation vector e. q and e a S6: According to e q and e a Calculate the matching score between question-answer pairs to obtain the matching loss function L. match S7: Based on L match Calculate the loss function L with added perturbation. adv The method of this invention can obtain more effective adversarial examples under adversarial training, thereby improving retrieval and question-answering performance.

This invention discloses a text classification method and system based on a dynamic graph attention network, belonging to the field of natural language processing technology. The method includes: character-level word segmentation of the text and construction of an encoded vocabulary; construction of a global position graph using the original text structure, establishing three types of edge connections: co-occurrence edges, same-word edges, and self-loop edges; fusing position encoders to all nodes to generate word embedding vectors; constructing a dynamic graph attention mechanism, using multi-head attention computation to learn multi-level semantic associations in parallel, combining a residual module to alleviate the gradient vanishing problem in graph networks, and employing a hybrid strategy of weighted global max pooling and global average pooling to obtain graph-level representations; and outputting the classification results. This invention effectively solves the technical problem of traditional graph construction methods ignoring the semantic differences of the same word in different positions by preserving character position information and word order relationships, thus improving the accuracy and generalization ability of text classification.

An early liver cancer diagnosis model based on CapsNet involves image processing. Features are extracted from the input enhanced liver CT image and processed through a ResNet module using convolution, regularization, activation functions, and max pooling. The output features are captured in the PrimaryCaps layer to obtain primary image features, reducing dimensionality and refining the features. An additional PrimaryCaps layer is added between the PrimaryCaps and DigitCaps layers to identify and integrate local features. After classification by the DigitCaps layer, a digital capsule layer is included for dynamic routing, and a Squash operation is performed to obtain a feature map composed of 8-dimensional vectors. E-CapsNet is designed by fusing the deep residual learning framework of ResNet and the high-level feature representation capabilities of CapsNet to improve the accuracy and efficiency of early liver cancer diagnosis.

This invention discloses a dual-stream feature fusion facial expression recognition method and system based on enhanced ViT, comprising: preprocessing the original image; feeding the original image into a global feature extraction layer to extract global features using a pre-trained IR50 model; feeding the original image into a local feature extraction layer, including convolutional layers, max pooling layers, QuadConv layers, Channel-spatial Modulator layers, and IR Block layers, ultimately obtaining local features; feeding the obtained global and local features into ViT, using an RKD-MSA module to calculate attention weights; introducing a CB module to enhance the connection between non-dropout vectors; and inputting the attention matrix into a fully connected layer network to obtain the facial expression recognition result. This invention improves the accuracy of facial expression recognition under natural conditions.

This invention discloses a gait recognition system and method based on spatiotemporal block convolution and multidimensional feature fusion, belonging to the field of biometric recognition technology. The method includes: acquiring a gait contour sequence and preprocessing it to obtain a three-dimensional feature map; constructing a dual-path parallel branch, where the local branch performs multidimensional physical segmentation of the feature map in terms of time, height, and width, and independently convolves each spatiotemporal sub-block before in-situ splicing to restore it; and the global branch performs overall convolution on the feature map; after fusing the two features, the system is mapped using a spatial horizontal pyramid, dividing the feature map along the height direction into multiple horizontal strips with the same number of height segments as the local branch segmentation, and pooling to obtain part feature vectors; these are then compressed into fixed-length part features using temporal max pooling; multiple independent recognition sub-units are constructed with the same number of strips as the number of strips, each sub-unit receiving only the corresponding strip features for part-level identity discrimination, and the final recognition result is obtained through fusion. This method solves the problems of lost local details, gait phase interference, and weak spatial perception, improving recognition accuracy.

This invention relates to the field of natural language processing technology and discloses a sentiment analysis method for online shopping reviews based on multi-scale feature fusion. The method includes the following steps: inputting a pre-processed text sequence into a pre-trained model ERNIE to generate word vector representations; inputting the word vectors into TextCNN, extracting multi-granularity local features through multi-size convolutional kernels, and concatenating them after max pooling to form sequence features; inputting the sequence features into a BiGRU to capture contextual sequence information; assigning weights to features at each time step through an attention mechanism to focus on key sentiment information; and finally outputting the sentiment classification result through a fully connected layer and a softmax function. This invention provides a sentiment analysis method for online shopping reviews based on multi-scale feature fusion, which can effectively mine multi-level textual features of online shopping review texts.