Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Astronomical big data optical variable curve abnormity detection method

A light curve and anomaly detection technology, which is applied in the direction of neural learning methods, complex mathematical operations, biological neural network models, etc., can solve the problems of large amount of data and difficult processing, achieve high precision, short learning time, and avoid gradient disappearance Effect

Pending Publication Date: 2020-03-13
BEIJING UNIV OF TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the problem of abnormal light curve prediction is essentially the prediction of time series (sequence of light brightness in the universe changing with time), and there is a problem that it is difficult to deal with due to the huge amount of data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Astronomical big data optical variable curve abnormity detection method
  • Astronomical big data optical variable curve abnormity detection method
  • Astronomical big data optical variable curve abnormity detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0020] Such as figure 1 As shown, the present invention provides a method for abnormal detection of light curve of astronomical big data, including:

[0021] S1. Obtain astronomical light curve data, perform data preprocessing and feature engineering on it, and form a historical time series

[0022] Since the data obtained by astronomical telescopes will have problems such as different dimensions and severe polarization, these problems will cause the learning process to not converge and the desired results cannot be obtained. Therefore, it is necessary to preprocess the astronomical light curve data, which includes: Savitzky-Golay smoothing filtering operation and normalization operation.

[0023] Smoothing filtering is one of the commonly used preprocessing methods in time series analysis. Smoothing filtering with SG method can improve the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an optical variable curve abnormity detection method, and aims to solve the problem that the anomaly phenomenon of an optical variable curve in astronomical data is difficult to detect due to the instantaneity of the anomaly phenomenon and improve the robustness of a model to future observation data. The method comprises the following steps: acquiring time and brightness ofoptical variable curve data to serve as a historical time sequence; carrying out data preprocessing and feature engineering on the obtained data, and respectively constructing a training set and a test set; building a model by using a GRU neural network, respectively adding a Dropout optimization method and a BN optimization method, adjusting network hyper-parameters by using a grid search methodto obtain two sub-models, and performing hybrid optimization according to precision and stability to obtain a final model; and performing prediction by using the trained model, outputting a prediction sequence, and performing optical variable curve abnormity detection by using a Grubbs method.

Description

technical field [0001] The invention belongs to the technical field of astronomical big data, and in particular relates to a method for detecting anomalies in light curves of astronomical big data based on gated cyclic unit model fusion, which is used to predict the abnormalities shown by sudden changes in the value of astronomical light curves that will occur in the future Phenomenon. Background technique [0002] Astronomical research often deals with a large number of large datasets generated and integrated through surveys. For example, the astronomical satellite project (Space Variable Objects Monitor, SVOM) jointly carried out by China and France recently. The main purpose of the project is to detect the phenomenon of gamma-ray bursts in the universe. The Ground Wide Angle Camera Array (GWAC) in the SVOM project is used to measure light data in the universe and generate a dataset of astronomical light curves. This system includes 36 wide-angle cameras, each camera ha...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/18G06N3/04G06N3/08
CPCG06F17/18G06N3/08G06N3/045
Inventor 彭磊毕敬路程
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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