ANALISA PATH LOSS PREDICTION DENGAN MENGGUNAKAN SUPPORT VECTOR REGRESSION

MUHAMMAD RAMADHAN, NIM. 132016071 (2021) ANALISA PATH LOSS PREDICTION DENGAN MENGGUNAKAN SUPPORT VECTOR REGRESSION. Skripsi thesis, Universitas Muhammadiyah Palembang.

[img]
Preview
Text
132016071_BAB I_ DAFTAR PUSTAKA-dikonversi.pdf

Download (504kB) | Preview
[img] Text
132016071_ BAB II_ SAMPAI_ BAB TERAKHIR-dikonversi.pdf
Restricted to Repository staff only

Download (497kB)

Abstract

The world of telecommunication and information technology (ICT) is growing rapidly. One of the main triggers is the development of internet technology which is widely used by the world's population. Propagation is an event of propagation of radio waves from the transmitting antenna to the receiving antenna which passes through the air as a signal distribution medium. In this study, 4G LTE signal measurements were carried out, signal measurements in the Palembang area, the use of SVR using less than 1000 samples of data, all of this research activity used Python software data processing media aimed at obtaining accuracy in accordance with the characteristics of the city of Palembang. Research results From the SVR (Support Vector Regression) modeling with the Polynomial kernel function, Radial Basis Function (RBF) and Sigmoid, the accuracy value obtained shows that the use of the Radial Basis Function (RBF) kernel function has the best level of accuracy with RMSE value 4.618971131830297, MAE 3.784557393393713 , and MSE 21.334894316681655 kernel function Sigmoid has the worst level of accuracy with the value of RMSE 8.053609713151584, MAE 6.36808734815853 and MSE 64.86062941176954 Keywords: propagation, signal, SVR, Polynomial, RBF, Sigmoid MAE, MSE, RSME

Item Type: Thesis (Skripsi)
Additional Information: Pembimbing : 1. Bengawan Alfaresi, S.T., M.T 2. Feby Ardianto, S.T.,M.Cs
Uncontrolled Keywords: Keywords: propagation, signal, SVR, Polynomial, RBF, Sigmoid MAE, MSE, RSME
Subjects: Teknologi informasi > komunikasi
Divisions: Fakultas Teknik > Teknik Elektro (S1)
Depositing User: Fakultas Teknik
Date Deposited: 06 May 2021 03:42
Last Modified: 06 May 2021 03:42
URI: http://repository.um-palembang.ac.id/id/eprint/16327

Actions (login required)

View Item View Item

is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.