5results about How to "Increase computational cost" patented technology

This invention discloses a method and system for binocular image super-resolution reconstruction based on cross-scale disparity prior, comprising: S1: acquiring the original left feature map and the original right feature map corresponding to the low-resolution left and right binocular images; S2: using a binocular attention module to perform cross-view interaction on the original left feature map and the original right feature map respectively, to obtain the interacted left feature map and the interacted right feature map; S3: inputting the interacted left feature map and the interacted right feature map into the cross-scale disparity attention module, and fusing them to obtain an aggregated feature map; S4: inputting the aggregated feature map into a cascaded dynamic upsampling reconstruction network to obtain the reconstructed super-resolution binocular image. This invention can fully utilize disparity information and obtain more realistic and higher-quality super-resolution images in a shorter running time.

The invention discloses a method and a system for accelerating a train-ballast track-roadbed system MBD-DEM-FDM coupling simulation model based on a self-adaptive PID (Proportion Integration Differentiation) algorithm. The method comprises the following steps: firstly, establishing a data interaction interface of MBD and DEM-FDM modules, and calculating and transmitting an acting force and a counter-acting force; a self-adaptive PID control algorithm is introduced, loading force is dynamically corrected according to interface errors, and fast approximation balance in a single time step is achieved; the convergence state of the system is monitored through a sliding window error judgment mechanism, a local fuzzy self-learning or global beetle antenna search optimization algorithm is intelligently triggered according to the convergence state, and PID control parameters are dynamically adjusted in real time and globally optimized. According to the method, a traditional time-consuming space iteration balance process is converted into dynamic feedback adjustment of a time domain, the problems that an existing coupling method is low in calculation efficiency, poor in numerical stability and difficult to apply to a large-scale model are effectively solved, and an efficient and reliable simulation tool is provided for design, operation and maintenance of a railway system.

The application provides a dynamic gesture recognition method based on light-weight multivariate space-time convolution, which comprises the following steps: constructing a space feature extraction module based on a pseudo 3D gated attention fusion network; extracting multi-scale space features by using the space feature extraction module; injecting a guided heat map by using a gated attention fusion module to enhance key region features and suppress background interference, so as to obtain a space refinement feature sequence; decomposing the space refinement feature sequence into multiple sub-variables; capturing long-range and local time dependence in parallel by using a modern convolution module; and modeling the intra-variable and inter-variable relationships respectively by using a decoupling feature interaction network, so as to obtain a dynamic gesture recognition result. By combining the multivariate feature decomposition strategy with the modern convolution, the double-branch design advantage of the modern convolution is to balance long-range dependence and local details, solve the limitations of traditional convolution in capturing long-range time dependence, and model complex dynamics.

The invention provides a multi-scale Patch mixed drug demand prediction system and method, and relates to the technical field of data processing, and the system comprises a data obtaining module which obtains sequence data reflecting drug demands; the data block division module is used for converting the data block into a multi-scale data block matrix; the dimension mapping module is used for dimensionally mapping the data block matrix; the mixing module is used for mixing characteristics among different data blocks in a mapping result and characteristics in refined data blocks; the mixing module is used for mixing and refining the mixed and refined characteristic matrix; the residual error connection module is used for fusing the two characteristic matrixes of the two mixing modules; the channel mixing module is used for carrying out feature weighted recombination on the fusion feature matrix among channels through a mixer; the prediction module is used for predicting a channel mixed feature matrix; and the multi-scale fusion module is used for fusing the multi-scale prediction results to obtain demand prediction results, wherein the demand prediction results comprise prediction results of Xipai gingival fixing liquid, Zukamu particles, cold asthma Zupao particles and the like. The invention aims to improve the drug demand prediction accuracy.

The application relates to a lightweight cell positioning method and system, which comprises the following steps: inputting an image to be processed into a cell positioning model; wherein the cell positioning model is a model obtained after lightweight processing, and a differential convolution and an attention module are introduced into the cell positioning model; in the front end of an initial stage, gradient information of an image is enhanced through differential convolution to obtain a feature map containing the gradient information; in each subsequent stage, multi-channel convolution is performed on the feature map, and the feature map is adaptively optimized through the attention module to obtain an optimized feature map; and cell positioning information is obtained based on the optimized feature map. According to the scheme, the attention module is introduced into the cell positioning model, the cell positioning model can pay attention to dense cell parts in a scene, lightweight processing is performed, the calculation cost of the cell positioning model is reduced, and the cell positioning model can be applied to more low-computing-power scenes.