Issue |
E3S Web Conf.
Volume 184, 2020
2nd International Conference on Design and Manufacturing Aspects for Sustainable Energy (ICMED 2020)
|
|
---|---|---|
Article Number | 01050 | |
Number of page(s) | 5 | |
DOI | https://doi.org/10.1051/e3sconf/202018401050 | |
Published online | 19 August 2020 |
A Survey on a Nonlinear Regression Application to Machine Learning Techniques for Geomagnetic Data Reconstruction Processing
1 PG Scholar, CSE Dept, GRIET, Hyderabad. Telangana, India
2 Professor, CSE Dept, GRIET, Hyderabad. Telangana, India
The genuineness of geomagnetic written record is a vital issue trig understanding formative methodology of Earth’s appealing field, because it provides necessary data thru move toward surface examination, unexploded insecure weapons area, therefore on. Expected thru recreate under examined geomagnetic dossier, this paper presents a geomagnetic dossier propagation approach considering AI frameworks. Ordinary direct contribution approaches are slanted thru time unskillfulness & high work price, whereas planned approach has an associate huge improvement. Trig this paper, three extraordinary machine learning models, support vector machine, random forests, and gradient boosting were collected. Besides, a significant learning replicas were used thru show an interminable backslide hyperplane commencing an arrangement dossier. Showed backslide hyperplane is a mapping of association between phony up missing dossier & incorporating impeccable dossier. Commencing a certain point, readied replicas, essentially hyperplanes, were used thru imitate missing geomagnetic follows considering endorsement, & they canister endure used considering replicating additionally accumulated new field dossier
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.