Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 1, 2024

Adaptive region prediction of gravity aided navigation system based on SVM multi-classification and mixed Gaussian clustering model

Download as PDF

DOI: 10.23977/acss.2024.080115 | Downloads: 10 | Views: 116

Author(s)

Yarui Fu 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology, Anshan, Liaoning, 114051, China

Corresponding Author

Yarui Fu

ABSTRACT

This paper aims to solve the problem of determining the adaptive region in gravity aided navigation system. In order to achieve this goal, a SVM-based multi-classification method is proposed to determine the adaptive region. First, the data is divided into three dimensions and the applicability of the regions is determined based on the standard deviation. Secondly, the Kmeans clustering model and Gaussian mixed clustering model are established for comparison and analysis, and the optimal number of regions is 5. By observing and comparing the regions divided by the two methods, it is found that the regions divided by the Kmeans method are not continuous and relatively discrete, while the standard deviation of each region of the Gaussian mixed model is better than that of the Kmeans method. The standard deviations of the five regions divided by the Gaussian method are 17.12, 24.34, 26.28, 13.39, and 21.08, respectively. The corresponding regions are labeled 1-5. Zones 2, 3, and 5 are adaptation zones.

KEYWORDS

Gravity aided navigation; SVM multi-classification; Kmeans clustering; Gaussian mixed clustering; Adaptive region prediction

CITE THIS PAPER

Yarui Fu, Adaptive region prediction of gravity aided navigation system based on SVM multi-classification and mixed Gaussian clustering model. Advances in Computer, Signals and Systems (2024) Vol. 8: 127-135. DOI: http://dx.doi.org/10.23977/acss.2024.080115.

REFERENCES

[1] F. P. Wang, M. H. Yang, D. Q. Xia et al. Research on n/γ screening method of liquid flash detector based on small-batch KMEans++clustering algorithm [J]. Nuclear Electronics and Detection Technology, 2022, 42(06):1073-1081. 
[2] B. S. Li, C. D. Qin. Research on Price prediction of electric vehicle based on SVM multi-classification based on particle swarm optimization [J]. Computer Science, 2019, 47(S2):421-424.
[3] W. H. Cui, S. Zheng, S. Q. Yang et al. Gaussian Mixture model for nuclear power operation condition classification based on density peak clustering [J]. Science Technology and Engineering, 2023, 23(20):8670-8676.
[4] X. Liu, H. W. ZHENG. Construction of Cuiguan Pear size grade evaluation Model based on support vector Machine [J]. Science and Technology Innovation, 2023(24):221-224.
[5] Wang B , Zhu J , Ma Z ,et al.Improved Particle Filter-Based Matching Method With Gravity Sample Vector for Underwater Gravity-Aided Navigation[J].IEEE Transactions on Industrial Electronics, 2020, PP(99):1-1.DOI:10. 1109/TIE.2020.2988227.
[6] Pan Shidong, Zhang Hui. Highway land use prediction based on multiple linear regression model: A case study of Xuancheng City [J]. Green science and technology, 2023, 25 (4): 235-239+271.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 13909
Visits: 262436

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.