Perbandingan SVM dan Perceptron dengan Optimasi Heuristik

Authors

  • Muchamad Kurniawan Program Studi Sistem Komputer, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya
  • Maftahatul Hakimah Program Studi Teknik Informatika, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya
  • Siti Agustini Program Studi Sistem Komputer, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya

DOI:

https://doi.org/10.61769/telematika.v15i2.356

Keywords:

support vector machine, perceptron, gradient descent, genetic algorithm, particle swarm optimization

Abstract

Support Vector Machine (SVM) and Perceptron are methods used in machine learning to determine classification. Both methods have the same motivation, namely to get the dividing line (hyperplane). Hyperplane can be obtained by using the optimization method Gradient Descent (GD), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). This study compares machine learning methods (Support Vector Machine and Perceptron) to optimization methods (Gradient Descent, Genetic Algorithm, and Particle Swarm Optimization) to find hyperplane. The dataset used is Iris Flower obtained from the UCI Machine Learning Repository. The test parameter on the Perceptron is the learning rate, while the optimization algorithm (GA and PSO) is the number of individuals. The results showed that the most suitable optimization method for Perceptron and SVM is PSO, with an accuracy value of 93%.

 

Support Vector Machine (SVM) dan Perceptron merupakan metode yang digunakan dalam machine learning untuk penentuan klasifikasi. Kedua metode tersebut memiliki motivasi yang sama, yaitu untuk mendapatkan garis pemisah (hyperplane). Hyperplane bisa didapatkan dengan metode optimasi Gradient Descent (GD), Genetic Algorithm (GA), dan Particle Swarm Optimization (PSO). Penelitian ini membandingkan metode machine learning (Support Vector Machine dan Perceptron) terhadap metode optimasi (Gradient Descent, Genetic Algorithm, dan Particle Swarm Optimization) untuk menemukan hyperplane. Dataset yang digunakan adalah Iris Flower yang diperoleh dari UCI Machine Learning Repository. Parameter pengujian pada Perceptron adalah learning rate, sedangkan pada algoritme optimasi (GA dan PSO) adalah jumlah individu. Hasil penelitian menunjukkan bahwa metode optimasi yang paling cocok untuk Perceptron dan SVM adalah PSO, dengan nilai akurasi 93%.

Author Biographies

Muchamad Kurniawan, Program Studi Sistem Komputer, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya

Gelar Sarjana Komputer diperoleh di Institut Adhi Tama Surabaya (ITATS) dan gelar Magister Komputer didapatkan di Institut Teknologi Sepuluh November (ITS). Konsentrasi bidang minat yang ditekuni optimization dan mesin pembelajaran.

Maftahatul Hakimah, Program Studi Teknik Informatika, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya

Gelar Sarjana Sains diperoleh di Institut Teknologi Sepuluh Nopember Surabaya (ITS) dan Magister Sains didapatkan di Institut Teknologi Sepuluh November (ITS). Konsentrasi bidang minat yang ditekuni optimization dan prediksi.

Siti Agustini, Program Studi Sistem Komputer, Fakultas Teknik Elektro dan Teknologi Informasi, Institut Teknologi Adhi Tama Surabaya

Gelar Sarjana Sains Terapan diperoleh di Politeknik Elektronika Negeri Surabaya (PENS) dan Magister Teknik didapatkan dari Institut Teknologi Sepuluh Nopember (ITS). Konsentrasi bidang minat yang ditekuni: jaringan komputer, telekomunikasi, dan sekuriti jaringan.

References

C. Cortes dan V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, hlm. 273-297, 1995.

Y. Qiao, J. Peng, L. Ge dan H. Wang, "Application of PSO LS-SVM forecasting model in oil and gas production forecast," 2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing, Oxford, 2017, hlm. 470-474.

S. Wei Fei dan X. Bin Zhang, “Fault diagnosis of power transformer based on support vector machine with genetic algorithm,” Expert Syst. Appl., vol. 36, no. 8, hlm. 11352–11357, 2009.

K. Nguyen, T. Le, V. Lai, dan D. Nguyen, “Least square support vector machine for large-scale dataset,” 2015 International Joint Conference on Neural Networks (IJCNN), 12-17 July 2015.

G. Cheng, R. Guo, dan W. Wu, “Petroleum lithology discrimination based on PSO-LSSVM classification model,” dalam Proceedings of the 2010 Second International Conference on Computer Modeling and Simulation, vol. 4, January 2010, hlm. 365-368.

P. Samui dan T. Lansivaara, “Least square support vector machine applied to slope reliability analysis,” Geotechnical and Geological Engineering, vol. 31, no. 4, hlm. 1329–1334, 2013.

J. Platt, 1998. Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. [Daring]. Tersedia: <https://www.microsoft.com/en-us/research/publication/sequential-minimal-optimization-a-fast-algorithm-for-training-support-vector-machines/>.

S. S. Shwartz, Y. Singer, N. Srebo, dan A. Cotter. “Pegasos: primal estimated sub-gradient solver for SVM.” Mathematical Programming, vol. 127, hlm. 3-30, 2011.

E. Teran, Z. Wang, dan D. A. Jimenez, “Perceptron learning for reuse prediction,” dalam MICRO-49: The 49th Annual IEEE/ACM International Symposium on Microarchitecture, no. 2, OCt 2016, hlm. 1-12.

M. E. Lasulika, “Komparasi Naïve Bayes, Support Vector Machine, dan K-Nearest Neighbor untuk mengetahui akurasi tertinggi pada prediksi kelancaran pembayaran tv kabel,” Ilkom Jurnal Ilmiah, vol. 11, no. 1, hlm. 11–16, 2019.

Y. Muliono dan F. Tanzil, “A comparison of text classification methods k-NN, Naïve Bayes, and Support Vector Machine for news classification,” Jurnal Informatika: Jurnal Pengembangan IT, vol. 3, no. 2, hlm. 157–160, 2018.

Suyanto, Artificial Intelligence. Bandung: Informatika Bandung, 2007.

Z. Maojin, M. Z. W. Liu, P. Gao, Y. Wang, dan W. Yu, “A unitary weights based one-iteration quantum perceptron algorithm for non-ideal training sets,” IEEE Access, vol. 7, hlm. 36854–36865, 2019.

W. J. Niu, Z. K. Feng, B. F. Feng, Y. W. Min, C. T. Cheng, dan J. Z. Zhou, “Comparison of multiple linear regression, artificial neural network, extreme learning machine, and support vector machine in deriving operation rule of hydropower reservoir,” Water, vol. 11, no. 1, 2019.

L. L. Li, X. Zhao, M. L. Tseng, dan R. R. Tan, “Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm,” Journal of Cleaner Production, vol. 242, hlm. 118447, Jan 2020.

K. Aoyagi, H. Wang, H. Sudo, dan A. Chiba, “Simple method to construct process maps for additive manufacturing using a support vector machine,” Additive Manufacturing, vol. 27, hlm. 353–362, 2019.

S. Abe, Support Vector Machines for Pattern Classification, Second Ed., London: Springer-Verlag London, 2010.

UCI Machine Learning Repository, "Iris Data Set". [Daring]. Tersedia: https://archive.ics.uci.edu/ml/datasets/iris

M. Kurniawan dan N. Suciati, “Premise parameter optimization on adaptive network based fuzzyinference system using modification hybrid particle swarm optimization ad genetic algorithm,” Jurnal Iptek-Media Komunikasi Teknologi, vol. 22, no. 2, hlm. 27–34, 2018.

M. Kurniawan dan N. Suciati, “Modifikasi kombinasi particle swarm optimization dan genetic algorithm untuk permasalahan fungsi non-linier,” Integer: Journal of Information Technology, vol. 2, no. 2, hlm. 31–40, 2017.

Downloads

Published

2021-02-28

Issue

Vol. 15 No. 2 (2020)

Section

Articles

License

 

You are free to:

  1. Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
  2. Adapt — remix, transform, and build upon the material for any purpose, even commercially.
  3. The licensor cannot revoke these freedoms as long as you follow the license terms.

Under the following terms:

  1. Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  2. ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
  3. No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Notices:

You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.

No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.