Time-space domain model modeling method and system for ecological environment monitoring
A technology for environmental monitoring and model modeling, applied in character and pattern recognition, instrumentation, computing, etc., can solve problems such as inability to become, discrete and sparse ecological environment monitoring data, and achieve good classification results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0033] Example 1
[0034] Such as figure 1 As shown, the present invention provides a spatio-temporal model modeling method for ecological environment monitoring, including the following steps:
[0035] S1. Collect pollutant data regularly to obtain multiple data frames;
[0036] S2. In chronological order, multiple data frames are superimposed using spatial superposition to obtain a data structure in the space-time domain;
[0037] S3. Use the change of the spatio-temporal domain data as the feature quantity to perform feature extraction on the spatiotemporal data structure to obtain a data structure without null values;
[0038] S4. Use the data dimensionality reduction method to reduce the data structure of the data structure without null values to obtain the spatio-temporal domain model;
[0039] S5. Input the sparse monitoring data into the spatio-temporal domain model, and convert the monitoring data into dense data through the spatio-temporal domain model as input for deep learn...
Example Embodiment
[0059] Example 2
[0060] In the data dimensionality reduction processing of the PCA algorithm, the effect of classification is not obvious, which is not particularly ideal for constructing the input of deep learning. Because deep learning data needs to be divided into training set and validation set.
[0061] In order to solve the above technical problems, the Laplacian feature mapping algorithm is used in data dimensionality reduction.
[0062] The working principle is explained below: Laplace algorithm uses the local angle of the data vector to construct the relationship between the data. If the two data frames are very similar, they should be as close as possible in the target subspace after dimensionality reduction. The specific steps of the algorithm when used are: first use the KNN algorithm to construct all the points into a graph, and connect each point with the nearest K points. In this embodiment, the requirement is to reduce the dimensionality of the data from 4 dimensi...
Example Embodiment
[0063] Example 3
[0064] The present invention also provides a spatio-temporal model modeling system for ecological environment monitoring, such as figure 2 As shown, it includes: a data input unit, a data superposition unit, a data feature extraction unit, and a data dimensionality reduction processing unit;
[0065] The data input unit is used to input multiple data frames obtained based on the collected pollutant information;
[0066] The data superimposition unit is used to superimpose multiple data frames in a spatial superposition method to obtain a data structure in the spatio-temporal domain;
[0067] The data feature extraction unit is used to perform feature extraction on the spatiotemporal data structure using the change of the spatiotemporal data as the feature quantity to obtain a data structure without null values;
[0068] The data dimensionality reduction processing unit is used to perform dimensionality reduction processing on data structures that do not contain null...
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