Paralleling gauss particle filtering method based on quasi-Monte Carlo sampling
A Gaussian particle filter and quasi-Monte Carlo technology, applied in the field of signal processing, can solve problems such as difficult parallel implementation, degradation of estimation performance, particle degradation, etc., to achieve the effect of ensuring statistical relationship, improving accuracy, and improving stability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0029] The filtering method proposed by the present invention is implemented by establishing a dynamic model of a nonlinear system. The specific model is as follows:
[0030] State equation: X t =f(X t-1 )+w t (1)
[0031] Observation equation: Z t =h(X t )+e t (2)
[0032] Among them, f(·), h(·) are bounded nonlinear functions, X t Is the state of the system at time t, Z t Is the observation value of the system at time t; w t Is process noise, e t To observe the noise.
[0033] The parameters involved in the filtering method of the present invention include:
[0034] N: is the number of samples, P=2 k : Is the number of parallel units, p=1, 2,..., P: is the serial number of the parallel units.
[0035] Reference figure 1 The method of the present invention includes a parallel quasi-Monte Carlo sequence generation step and a parallel Gaussian particle filter step.
[0036] 1. Parallel quasi-Monte Carlo sequence generation steps
[0037] The jump quasi-Monte Carlo sequence g...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap