Klasifikasi Akses Internet Oleh Anak-Anak dan Remaja Dewasa di Jawa Timur Menggunakan Support Vector Machine

Article Sidebar

PDF
Published: Apr 30, 2020
DOI: https://doi.org/10.26740/jram.v4n1.p17-27

Main Article Content

Mukti Ratna Dewi
Insitut Teknologi Sepuluh Nopember
http://orcid.org/0000-0002-5145-9749

Abstract

Pada tahun 2018 penetrasi pengguna internet di Indonesia naik sebesar 10,12% dibanding tahun sebelumnyan dengan pengguna terbanyak berada di Pulau Jawa yang mencapai 55%. Kelompok usia pengguna internet terbanyak berturut-turut berada pada usia 15 hingga 19 tahun, umur 20 hingga 24 tahun, dan anak-anak yang berumur 5 hingga 9 tahun. Berdasarkan penelitian yang dilakukan oleh Nurrahman (2017), faktor- faktor yang secara signifikan mempengaruhi penggunaan internet di Jawa Timur antara lain adalah umur, jenjang pendidikan, perbedaan tempat tinggal antara perkotaan dan pedesaan, status pekerjaan, perangkat yang digunakan dalam mengakses internet dalam tiga bulan terakhir serta kepemilikan bangunan. Untuk mengetahui besar tingkat pengguna internet maka perlu dilakukan pengelompokkan berdasarkan faktor-faktor yang mempengaruhinya. Oleh karena itu, penelitian ini melakukan klasifikasi akses internet oleh anak-anak dan remaja usia 6 hingga 21 tahun di Jawa Timur berdasarkan faktor-faktor yang signifikan menggunakan Support Vector Machine (SVM) dengan fungsi kernel Radial Basis Fuction (RBF). Berdasarkan nilai AUC sebesar 0,92, kinerja model SVM yang terbentuk tergolong sangat bagus (excellent) dengan nilai akurasi, sensitivitas, dan spesifisitas berturut-turut sebesar 86,45%; 84,64% dan 88,63%.

Article Details

Issue
Vol. 4 No. 1 (2020): April, JRAM
Section
Combinatorics and Computational Mathematics
The copyright of the received article once accepted for publication shall be assigned to the journal as the publisher of the journal. The intended copyright includes the right to publish the article in various forms (including reprints). The journal maintains the publishing rights to the published articles.
 
 
Author Biography

Mukti Ratna Dewi, Insitut Teknologi Sepuluh Nopember

Department of Business Statistics

References

[1]

Asosiasi Penyelenggara Jasa Internet Indonesia (APJII), "Survei APJII yang Ditunggu-tunggu, Penetrasi Internet Indonesia 2018," Buletin APJII, p. 1, Mei 2019.

[2]

Asosiasi Penyelenggara Jasa Internet Indonesia, "Penetrasi dan Profil Perilaku Pengguna Internet di Indonesia," Asosiasi Penyelenggara Jasa Internet Indonesia, Jakarta, Infografis 2019.

[3]

Ryan R. Nurrahman, "Analisis Faktor-Faktor yang Mempenharuhi Kepala Rumah Tangga Jawa Timur dalam Mengakses Internet Tahun 2017," Institut Teknologi Sepuluh Nopember, Surabaya, Tugas Akhir 2017.

[4]

T Verplancke et al., "Support Vector Machine Versus Logistic Regression Modeling for Prediction of Hospital Mortality in Critically Ill Patients with Haematological Malignancies," BMC Medical Informatics and Decision Making, vol. 8, p. 56, Desember 2008. [Online]. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2612652/

[5]

Corinna Cortes and Vladimir Vapnik, "Support-Vector Networks," Machine Learning, vol. 20, no. 3, pp. 273-297, September 1995. [Online]. http://link.springer.com/article/10.1007%2FBF00994018?LI=true

[6]

Chih W. Hsu, Chih C. Chang, and Chih J. Lin, "A practical guide to Support Vector Classification," Information Engineering, Naional Taiwan University, Taipe, 2008.

[7]

Budi Santosa, Data Mining : Teknik Pemanfaatan Data untuk Keperluan Bisnis/Studi, 1st ed. Yogyakarta: Graha Ilmu, 2007.

[8]

S. Sathiya Keerthi and Chih-Jen Lin, "Asymptotic behaviors of support vector machines with Gaussian kernel," Neural Computation, vol. 15, no. 7, pp. 16671689, July 2003.

[9]

Hsuan-Tien Lin and Chih-Jen Lin, "A Study on Sigmoid Kernels for SVM and the Training of non-PSD Kernels by SMO-type Methods," Department of Computer Science, National Taiwan University, Technical report 2003. [Online]. http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf

[10]

Chenghai Yang et al., "Evaluating unsupervised and supervised image classification methods for mapping cotton root rot.," Precision Agriculture, vol. 16, pp. 201-215, April 2015.

[11]

Wen Zhu, Nancy Zeng, and Ning Wang, "Sensitivity, Specificity, Accuracy, Associated Confidence Interval and ROC Analysis with Practical SAS Implementations," Health Care and Life Sciences, 2010.

[12]

Arian R. V. Erke and Peter M. Th. Pattynama, "Receiver operating characteristic (ROC) analysis: Basic principles and applications in radiology," European Journal of Radiology, pp. 88-94, 1998.

[13]

S.M. Chou, J.W. Shan, Y. Guo, and L. Zhang, "Automated Breast Cancer Detection and Classification Using Ultrasound Image : A Survey, Pattern Recognition," vol. 43, pp. 299-317, 2010.

[14]

Mark H. Zweig and Gregory Campbell, "Receiver Operating Characteristic (ROC) Plots : A Fundamental Evaluation Clinical Medicine," Clinical Chemistry, pp. 561-577, 1993.

[15]

Ertugrul Colak et al., "Comparison of Semiparametric, Parametric, and Nonparametric ROC Analysis for Continuous Diagnostic Tests Using a Simulation Study and Acute Coronary Syndrome Data," Computational and Mathematical Methods in Medicine, vol. 2012, p. 7, 2012. [Online]. http://downloads.hindawi.com/journals/cmmm/2012/698320.pdf