Classification of Planktonic Foraminifera Fossil Types with Feature Optimization of Support Vector Machine (SVM) Algorithm Using Particle Swarm Optimization (PSO)

DOI

10.2991/978-94-6463-366-5_4How to use a DOI?

Keywords

SVM; GLCM; Classification; Fossils

Abstract

Objective: To build a Support Vector Machine model with a good Particle Swarm Optimization parameter selection algorithm for object classification in images. Can determine the best features used for classification in the Support Vector Machine algorithm using Particle Swarm Optimization feature optimization. Design/method/approach: Image data will be extracted GLCM features namely homogeneity, contrast, correlation, and energy as well as shape feature extraction namely area, perimeter, and metric eccentricity. The results of feature extraction are then used for training SVM models and PSO-SVM models. This research uses multiclass SVM, namely One Versus Rest (OVR) with C of 10 and RBF kernel. For feature selection using PSO, the parameters used are C1 by 2.0, C2 by 2.0, W by 1.0, the number of particles by 50 and the maximum iteration is 50. Results: In the PSO-SVM model, after feature selection, the number of features used is 9 features from the total feature extraction of 19 features. After testing with confusion matrix, the SVM model gets an accuracy of 92% while the accuracy of the PSO-SVM model is 97%. The test results show that feature selection using PSO can overcome the problems in the SVM algorithm and can improve the performance of the model for the classification of plankton foraminifera fossils. Originality / state of the art: the use of the PSO method for the selection of relevant features in the results of GLCM feature extraction and shape feature extraction with SVM classification algorithm.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Herlina Jayadianti
AU  - Dhimas Wahyu Asshidiq
AU  - Budi Santosa
AU  - Siti Umiyatun Choiriah
AU  - Frans Richard Kodong
AU  - Bambang Yuwono
PY  - 2024
DA  - 2024/02/02
TI  - Classification of Planktonic Foraminifera Fossil Types with Feature Optimization of Support Vector Machine (SVM) Algorithm Using Particle Swarm Optimization (PSO)
BT  - Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023)
PB  - Atlantis Press
SP  - 23
EP  - 36
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-366-5_4
DO  - 10.2991/978-94-6463-366-5_4
ID  - Jayadianti2024
ER  -