APPLICATION OF PARTICLE SWARM OPTIMIZATION SUPPORT VECTOR MACHINE FOR ELECTRICAL INSTALLATION CERTIFICATION PREDICTION

Priyono Priyono, Elin Panca Saputra, Suswandi Suswandi, Taufik Rahman

Abstract


Abstract: Feature selection is a crucial process that is very important to improve the performance of machine learning models, in accordance with data preprocessing. The feature selection process can be considered as a global combinatorial optimization problem in machine learning, which reduces the number of features, eliminates irrelevant data, and produces acceptable classification accuracy. The purpose of this study is to predict or determine the results of the electrical installation operation feasibility test based on data and obtain attribute selection features, and obtain accuracy level results. The Particle Swarm Optimization (PSO) approach is used to select the right characteristics to determine the results of the electrical installation operation feasibility test because attribute selection is needed in data analysis, because the PSO method will increase accuracy than just SVM in determining attribute selection. If SVM is used with PSO, the accuracy value is 96% and AUC is 0.994%, while the SVM method produces an accuracy level of 94.89% and AUC of 0.994%. With this finding, the accuracy value increases by 2%, making it a very good categorization category. It has been proven that the use of Particle Swarm Optimization (PSO) based algorithms can improve and improve results.

           
Keywords: PSO; SVM; Certification

 

Abstrak: Pemilihan fitur merupakan proses krusial yang sangat penting untuk meningkatkan kinerja model machine learning, sesuai dengan praproses data. Proses pemilihan fitur dapat dianggap sebagai masalah optimasi kombinatorial global dalam pembelajaran mesin, yang mengurangi jumlah fitur, menghilangkan data yang tidak relevan, dan menghasilkan akurasi klasifikasi yang dapat diterima. Tujuan dari penelitian ini adalah untuk memprediksi atau menentukan hasil uji kelayakan operasi instalasi listrik berdasarkan data dan memperoleh fitur pemilihan atribut, serta memperoleh hasil tingkat akurasi. Pendekatan Particle Swarm Optimization (PSO) digunakan untuk memilih karakteristik yang tepat untuk menentukan hasil uji kelayakan operasi instalasi listrik karena pemilihan atribut diperlukan dalam analisis data, karena metode PSO akan meningkatkan akurasi dari pada hanya SVM dalam menentukan pemilihan atribut. Jika SVM digunakan dengan PSO, nilai akurasinya adalah 96% dan AUC sebesar 0,994%, sedangkan metode SVM menghasilkan tingkat akurasi sebesar 94,89% dan AUC sebesar 0,994%. Dengan temuan ini, nilai akurasi meningkat sebesar 2%, menjadikannya kategori kategorisasi yang sangat baik. Telah terbukti bahwa penggunaan algoritma berbasis Particle Swarm Optimization (PSO) dapat meningkatkan dan memperbaiki hasil.

 

Kata kunci: PSO; SVM; Sertifikasi

 


Full Text:

PDF

References


Y. R. Nugraha, A. P. Wibawa, and I. A. E. Zaeni, “Particle Swarm Optimization-Support Vector Machine (PSO-SVM) Algorithm for Journal Rank Classification,” Proc. - 2019 2nd Int. Conf. Comput. Informatics Eng. Artif. Intell. Roles Ind. Revolut. 4.0, IC2IE 2019, pp. 69–73, 2019.

D. H. Jeong, B. K. Jeong, N. Leslie, C. Kamhoua, and S.-Y. Ji, “Designing a supervised feature selection technique for mixed attribute data analysis,” Mach. Learn. with Appl., vol. 10, no. November, p. 100431, 2022.

E. P. Saputra, Supriatiningsih, Indriyanti, and Sugiono, “Prediction of Evaluation Result of E-learning Success Based on Student Activity Logs with Selection of Neural Network Attributes Base on PSO,” J. Phys. Conf. Ser., vol. 1641, no. 1, 2020.

E. P. Saputra, M. Maulidah, N. Hidayati, and A. Saryoko, “Komparasi Evaluasi Kinerja Siswa Belajar dengan Mengggunakan Algoritma Machine Learning,” J. Media Inform. Budidarma, vol. 6, no. 4, p. 2239, 2022.

L. C. J. Urszula Stańczyk, Feature Selection for Data and Pattern Recognition. Silesian: University of Technology, 2015.

Muhammad Ridha Fauzi, H. Eteruddin, U. Situmeang, S. Suwitno, Y. Yolnasdi, and A. K. Nasution, “Pelatihan Pelatihan dan Pendampingan Sertifikasi Kompetensi untuk Tenaga Kerja Bidang Instalasi Pemanfaatan Tenaga Listrik Tegangan Rendah,” J. Pengabdi. UntukMu NegeRI, vol. 6, no. 1, pp. 187–193, 2022.

H. Sianturi, LKP Pemeriksaan dan Pengujian Instalasi Pemanfaatan Tenaga Listrik Tegangan Rendah SLO PT. Jasa Kelistrikan Indonesia (JKI) Medan. Medan: Universitas Medan Area, 2020.

Rika Fauziah, Posedur Pembuatan Sertifikat Laik Operasi pada PT. Perintis Perlindungan Instalasi Listrik Nasional (PPILN) Pekanbaru. Riau: Universitas Islam Negeri Sultan Syarif Kasim Riau, 2021.

T. G. Ngo, H. Nguyen-Cong, T. T. T. Nguyen, and T. K. Dao, “Optimal Parameter-Feature Selection Using Binary PSO for Enhanced Classification Performance,” J. Inf. Hiding Multimed. Signal Process., vol. 14, no. 4, pp. 172–183, 2023.

N. Allias, M. N. Megat Mohamed Noor, and M. N. Ismail, “A hybrid gini PSO-SVM feature selection based on Taguchi method: An evaluation on email filtering,” Proc. 8th Int. Conf. Ubiquitous Inf. Manag. Commun. ICUIMC 2014, 2014.

E. P. Saputra, S. Nurajizah, M. Maulidah, N. Hidayati, and T. Rahman, “Komparasi Machine Learning Berbasis Pso Untuk Prediksi Tingkat Keberhasilan Belajar Berbasis E-Learning,” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 2, pp. 321–328, 2023.

O. S. Qasim, “Feature selection using particle swarm optimization-based logistic regression model,” Elsevier, vol. 182, pp. 41–46, 2018.

K. Robindro, S. S. Devi, U. B. Clinton, L. Takhellambam, Y. R. Singh, and N. Hoque, “Hybrid distributed feature selection using particle swarm optimization-mutual information,” Data Sci. Manag., vol. 7, no. 1, pp. 64–73, 2024.

A. S. Dharma, E. R. Silaban, and H. M. Siahaan, “Predictions using Support Vector Machine with Particle Swarm Optimization in Candidates Recipient of Program Keluarga Harapan,” Conf. Ser., vol. 4, no. 1, pp. 115–121, 2023.

M. Mafarja, R. Jarrar, S. Ahmad, and A. A. Abusnaina, “Feature selection using Binary Particle Swarm optimization with time varying inertia weight strategies,” ACM Int. Conf. Proceeding Ser., 2018.

S. Malakar, S. Sen, S. Romanov, D. Kaplun, and R. Sarkar, “Role of transfer functions in PSO to select diagnostic attributes for chronic disease prediction: An experimental study,” J. King Saud Univ. - Comput. Inf. Sci., vol. 35, no. 9, p. 101757, 2023.

A. M. Asri, S. R. Ahmad, and N. M. M. Yusop, “Feature Selection using Particle Swarm Optimization for Sentiment Analysis of Drug Reviews,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 5, pp. 286–295, 2023.

J. Cervantes, F. Garcia-Lamont, L. Rodríguez-Mazahua, and A. Lopez, “A comprehensive survey on support vector machine classification: Applications, challenges and trends,” Neurocomputing, vol. 408, no. xxxx, pp. 189–215, 2020.

M. Alzaqebah et al., “Hybrid feature selection method based on particle swarm optimization and adaptive local search method,” Int. J. Electr. Comput. Eng., vol. 11, no. 3, pp. 2414–2422, 2021.

L. Vanneschi and S. Silva, “Particle Swarm Optimization,” Nat. Comput. Ser., pp. 105–111, 2023.




DOI: https://doi.org/10.33330/jurteksi.v11i2.3418

Article Metrics

Abstract view : 28 times
PDF - 20 times

Refbacks

  • There are currently no refbacks.


Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) Universitas Royal

Copyright © LPPM UNIVERSITAS ROYAL

 

Lisensi Creative Commons
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.
pkv games bandarqq qiu qiu https://kemenagtabalong.id/ https://aoi.ngo/ https://zeronet.id/ https://bilderhoster.org/ https://kemenagbandaaceh.com/ https://perdosrijaya.org/ https://dwr-rental.com/ http://www.anatolekatok.com/ http://www.leonatamusic.com/ http://www.vaudiosoftllc.com/ https://indonesianfeministjournal.org/ https://ugcolleges.com/ https://www.bovendigoelkab.go.id/cak/ http://www.sipp.pn-nunukan.go.id/ https://journal.lemigas.esdm.go.id/public/ https://jurnal.kemendag.go.id/plugins/sob/ https://www.sipp.pn-lamongan.go.id/ https://www.mediaelangnusantara.com/ https://digimarly.com/ slot resmi misterhoki