7 results about "Random mixing" patented technology

This invention relates to the fields of computer vision and machine learning, specifically to a lightweight classification and segmentation method and system for LiDAR point clouds based on GRSNet. The method includes: acquiring LiDAR point cloud data; generating a representative point set using a sampling method based on the golden ratio to reduce preprocessing complexity; inputting the point set into a GRSNet network for feature extraction, which consists of multiple processing stages. Each stage constructs a local region through a Sample_and_Group module, uses two SA_Ghost Block modules to learn shared weights and extract deep aggregation features, and performs feature aggregation through a Mixed Pooling module with randomly selected pooling methods; finally, classification or segmentation is completed based on the extracted features. This invention, through innovative sampling methods, a lightweight dual-path feature extraction module, and a randomized mixed pooling mechanism, significantly reduces the number of model parameters and computational complexity while maintaining high-precision classification and segmentation performance.

This invention discloses a robust relative navigation method for aircraft based on a hybrid distribution under non-Gaussian noise, belonging to the technical field of computation, estimation, or counting. To address the problem of filter divergence caused by non-stationary heavy-tail noise in time-varying environments during relative navigation, this invention introduces a Dirichlet random mixture vector fusion of Gaussian, Student's t, and multivariate K-distributions, proposing a Gaussian-Student's t-multivariate K-distribution modeling of measurement likelihood. Then, by minimizing the KLD of the true posterior probability density function and the approximate posterior probability density function using variational Bayesian techniques, the approximate posterior estimates of the aircraft's relative motion state and filter parameters are obtained, yielding the target's state information relative to the aircraft and solving for relative position and velocity. Finally, a nonlinear filter based on the Gaussian-Student's t-multivariate K-distribution is derived to improve relative navigation accuracy for angle-only relative navigation of aircraft in time-varying environments.

The application provides a method and system for removing random mixed noise in dynamic electrocardiogram, and relates to the field of digital signal processing of bioelectric signals. A noise signal is used to perform noise adding processing on an original noise-free electrocardiogram signal to obtain a noise-added dynamic electrocardiogram signal, and a training data set is formed. A denoising model is trained until the distortion degree of the noise-free electrocardiogram signal output by the denoising model and the original noise-free electrocardiogram signal is minimum in amplitude and angle. The dynamic electrocardiogram signal to be denoised is input into the trained denoising model to generate and output a noise-free dynamic electrocardiogram signal. The application uses a two-step method of frequency domain filtering and time domain filtering to remove random noise or random mixed noise in the electrocardiogram signal. The frequency domain filtering effectively removes noise outside a specific frequency range, and the effective frequency band range of the dynamic electrocardiogram signal is retained. The time domain filtering uses a deep learning algorithm for denoising, learns the characteristic matrix of the useful signal and the noise, and thus obtains a reconstructed signal with less distortion.

The application discloses a sine sweep plus random mixed signal separation method, and belongs to the field of digital signal processing.The method is as follows: a sine sweep plus random mixed time domain signal is provided, the phase of the sine sweep signal is taken as a reference, the mixed signal is sampled once every interval of the same phase, the obtained sampling signal is subjected to time normalization processing, that is, is reconstructed into a sine fixed frequency plus random mixed signal, then the correlation integral method is used to obtain the instantaneous amplitude and instantaneous phase of the signal, the original sine sweep signal is recovered, the obtained sine sweep signal is subtracted from the original sine sweep plus random mixed signal, and the random signal is obtained, and thus the signal separation is completed.The method can quickly and accurately identify the amplitude and phase of the sine sweep signal in the mixed signal, then subtracts the sine sweep signal from the mixed signal, leaves the random signal, and realizes the separation of the sine sweep signal and the random signal.

The invention belongs to the technical field of multimodal transport logistics service network design, and particularly relates to an optimization method and system for multimodal transport service network design based on uncertain requirements, and the system comprises a two-stage random mixed integer programming model; wherein the first-stage decision variable is a 0-1 discrete variable and is used for representing whether a node is selected as a freight hub position, and the second-stage decision variable comprises a network flow continuous variable of a freight demand, representing the distribution number of goods in a logistics network, and further comprises distribution decision variables of different types of goods vehicles in a freight hub; belongs to discrete integer variables; according to the method, a two-stage random mixed integer programming model is constructed for the problems of random hub site selection and vehicle distribution in multimodal transport service network design under uncertain requirements, and an accelerated Benders decomposition algorithm is adopted to solve the model to obtain an accurate solution.

The invention relates to the technical field of fishing gears, in particular to a fishing device capable of mixing materials freely, which comprises a base, a fishhook, a hook line, a sub line, a space bean, a connector, a counterweight, a beam splitting hook device, a plurality of blades and a water soluble line for binding. According to the automatic mixing and diffusing fishing device, a user puts bait into the cavity, then the bait is wrapped through the blades, the user does not need to specially bond the bait with water or other adhesives in the whole process, and the bait easy to loosen can be used. The bait does not need to be specially kneaded into a ball and is relatively loose, the bait can be always kept upward and the base is kept downward in the water entering process due to the balance weight, the water-soluble line is melted several minutes after the bait enters the water, and the blades are automatically opened under the action of expansion of the bait, so that the atomized bait is formed. And in the process of pulling up the fishhook towards the water surface, the fishline is shrunk through the hook binding device, and meanwhile, the fishhook is wrapped through the blades, so that the phenomenon of bottom hanging can be avoided when the fishhook is pulled up.

The application discloses a kind of generalized theory numerical calculation method of the thermal conductivity of multiphase random mixing porous medium, the method includes the following steps: step 1, obtain the porosity of soil sample;Step 2, obtain the thermal conductivity of soil particles;Step 3, obtain the effective thermal conductivity of soil sample and the full state thermal conductivity surface under the porosity of soil sample;Step 4, obtain the volumetric water content and ice content of soil sample.The application innovatively proposes the strategy of using extreme state to calculate the thermal conductivity of soil particles, realizes the double check of parameters, eliminates the calculation error caused by the difference of soil mineral composition, and can obtain the effective thermal conductivity of soil body by calculation using conventional soil parameters.Using the method of the application, the thermal conductivity of soil body can be predicted with high precision only by using easily obtained physical parameters, and online monitoring and inversion analysis can be carried out.This is especially suitable for large-scale engineering projects and soil thermal response prediction, which greatly saves time and economic cost.