A time series prediction method and device based on indefinite length fuzzy information granules
A technology of fuzzy time series and fuzzy information, applied in the new field of time series prediction, can solve the problems of difficult to achieve dynamic real-time division, indistinguishable fuzzy semantics, and high algorithm complexity, so as to improve interpretability and prediction accuracy, and reduce computational complexity. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] figure 1 It is a flowchart of a new time series prediction method based on fuzzy information particles of indefinite length in this embodiment. Such as figure 1 As shown, the new time series prediction method based on fuzzy information granules of indefinite length in the first embodiment includes the following steps:
[0070] S101: Divide the target time series.
[0071] This embodiment proposes an unequal length division method based on the idea of K-line dividing pens. According to the change trend and distribution of the data, the unequal length interval is determined to construct the fuzzy information granule, so as to improve the interpretability of the fuzzy data. The accuracy of the model and the prediction accuracy of the model give full play to the advantages of fuzzy theory for time series forecasting, make up for the lack of low accuracy and less semantic information due to the uniform division of the universe, and overcome the optimization of particle swarm op...
Embodiment 2
[0265] The purpose of this embodiment is to use the time series prediction method proposed in the above embodiment to predict stock information data.
[0266] As shown in 7, it is the case of 30-minute K-line division in a quarter. It can be seen that the number of structured information particles is small, which is not enough to support the prediction machine to fully carry out the construction of rules. Therefore, this embodiment uses minute-level K-lines as the original data Information; At the same time, stock data fluctuates sharply, which makes the information granularity different.
[0267] In this embodiment, the third quarter of 2016 (July 1st-September 30th) data is selected for experimentation, and the data minute-level K-line graph is used for pen processing, and a total of 1077 pens are obtained, that is, 1077 banded Gaussian blurs are constructed Information particles. This embodiment uses the first 1000 information granules as the training set, and the last 77 infor...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com