Improved Elman neural network prediction method based on noise reduction algorithm
A technology of neural network and prediction method, which is applied in the field of computer neural network application, can solve the problems of high resource consumption and single-dimensional time series data prediction, and achieve the effects of low time and resources, strong long-term dependence on time, and excellent memory ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0061] Embodiment:
[0062] This embodiment provides a prediction method of improving ELMAN neural network based on noise reduction algorithm, as shown, including the following steps:
[0063] S1, obtain the physical machine resource usage time series as the original data, divide the original data into the training set, test set, and verification set, and focused on the training set, test set and verification of the training set, test set and verification in accordance with a given time window and predicted steps The data is sampled.
[0064] Such as figure 2 As shown, the training data is organized according to the form of training, and the original time series data is divided into training sets, verification sets and test sets. When dividing, the proportion of 8: 1: 1 is generally divided into training set, verification set and test set. At the time of segmentation training set, 80% of the data from the starting point of the original data, 10% of the remaining data is the data o...
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