CLASSIFICATION WORTHINESS OF DRINKING WATER FOR THE HUMAN BODY USING SUPPORT VECTOR MACHINE METHOD WITH BACKWARD ELIMINATION
DOI:
https://doi.org/10.33387/jati.v2i1.61Keywords:
Classification, Water Eligibility, support vector machine, backward eliminationAbstract
Water quality can be detected based on the related mineral parameters contained therein, this can be classified using machine learning,, one of the methods used is the Support Vector Machine (SVM) method. The SVM method is not optimal in selecting the feasibility parameters for drinking water so whether using the Backward Elimination method can improve accuracy. This research was conducted with several implementation scenarios of the SVM method and the SVM method with Backward Elimination, in which scaling and without scaling is carried out, the ratio ratio is 80:2, then eliminate each parameter so remaining that the most influential parameters. The highest accuracy value if only using the Support Vector Machine (SVM) method is found in the amount of data 1000 without using scaling, the accuracy is 56%, for the amount of data 2000 without using scaling the accuracy is 47%, and for the amount of data 3276 using scaling data the accuracy is 45%. If Backward Elimination is applied, the accuracy value increases at amount of data 1000 by using scaling, the accuracy is 59%, for amount of data 2000 using scaling the accuracy is 58%, but for amount of data 3276 the accuracy decreases by 1% to 44%. An indicator that affects a suitable water for consumption is the water quality of water with a value of 0 can not be consumed and 1 can be consumed, SVM with Backward Elimination has succeeded in classifying drinking water as suitable and unfit for consumption, if using 1000 data the results of class 0 classification are 136 and class 1 is 64, if using 2000 data class 0 classification results are 269 and class 1 is 131, while using 3276 data class 0 classification results are 399 and class 1 is 257.
References
R. Resmiati, “Klasifikasi Pasien Kanker Payudara Menggunakan Metode Support Vector Machine dengan Backward Elimination,” SISTEMASI, vol. 10, pp. 381–393, 2021, [Online]. Available: http://sistemasi.ftik.unisi.ac.id.
F. Muhamad, “Kualitas Air Pada Sumber Mata Air Di Pura Taman Desa Sanggalangit Sebagai Sumber Air Minum Berbasis Metode Storet,” J. Pendidik. Geogr. Undiksha, vol. 7, no. 2, pp. 74–84, 2019, doi: 10.23887/jjpg.v7i2.20691.
U. Sri, “Ketersediaan Air Bersih Untuk Kesehatan : Kasus Dalam Pencegahan Diare Pada Anak,” Optim. Peran Sains dan Teknol. untuk Mewujudkan Smart City, no. June, pp. 211–236, 2017, [Online]. Available: https://www.researchgate.net/publication/326057942%0AKETERSEDIAAN.
P. A. Riyantoko, “Analisis Sederhana Pada Kualitas Air Minum Berdasarkan Akurasi Model Klasifikasi Dengan Menggunakan Lucifer Machine Learning,” Siminar Nas. Sains Data (SANADA 2021), vol. 2021, no. Senada, pp. 12–18, 2021, [Online]. Available: https://senada.upnjatim.ac.id/index.php/senada/article/view/20.
W. S. Dharmawan, “Komparasi Algoritma Klasifikasi SVM-PSO dan C4.5-PSO Dalam Prediksi Penyakit Jantung,” J. Inform. Manaj. dan Komput., vol. 13, no. 2, pp. 31–41, 2021, doi: http://dx.doi.org/10.36723/juri.v13i2.301.
A. M. Puspitasari, “Klasifikasi Penyakit Gigi Dan Mulut Menggunakan Metode Support Vector Machine,” Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. March, pp. 802–810, 2018, [Online]. Available: http://j-ptiik.ub.ac.id.
F. S. Jumeilah, “Penerapan Support Vector Machine (SVM) untuk Pengkategorian Penelitian,” J. RESTI (Rekayasa Sist. dan
Teknol. Informasi), vol. 1, no. 1, pp. 19–25, 2017, doi: 10.29207/resti.v1i1.11.
D. Kurniawan, “Optimasi Algoritma Support Vector Machine ( Svm ) Menggunakan Adaboost,” Teknol. Inf., vol. 9, p. 13, 2013, [Online]. Available: http://research.pps.dinus.ac.id.
D. Kurniawan, “Optimasi Algoritma Support
Vector Machine (Svm) Menggunakan Adaboost Untuk Penilaian Risiko Kredit,” J. Teknol. Inf., vol. 9, no. 1, pp. 1–13, 2013.
Farizul Ma’arif, “Optimasi Fitur Menggunakan Backward Elimination Dan Algoritma SVM Untuk Klasifikasi Kanker Payudara,” J. Inform., vol. 4, no. 1, pp. 46–53, 2017, doi: https://doi.org/10.31294/ji.v4i1.1548.
S. A. D. Ghani, “Algoritma k-Nearest Neighbor Berbasis Backward Elimination Pada Client Telemarketing,” Pros. Semin. Ilm. Sist. Inf. DAN Teknol. INFORMAS, vol. VIII, no. 2, pp. 141–150, 2019, [Online]. Available: http://ejurnal.dipanegara.ac.id/index.php/sisiti/article/view/610.
V. R. Joseph, “Optimal Ratio for Data Splitting,” pp. 1–16, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Jurnal Jaringan dan Teknologi Informasi

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.