muhammad ferdiansyah, 132022027 (2026) PEMODELAN PREDIKSI PATH LOSS MENGGUNAKAN MULTIPLE LINEAR REGRESSION PADA LINGKUNGAN URBAN DAN PERBANDINGANNYA DENGAN MODEL ECC-33 DAN COST231-HATTA. Skripsi thesis, Universitas Muhammadiyah Palembang.

	Text 132022027_BAB I_DAFTAR PUSTAKA.pdf - Published Version Download (1MB)
	Text 132022027_BAB II.pdf - Published Version Restricted to Repository staff only Download (616kB)
	Text 132022027_BAB III.pdf - Published Version Restricted to Repository staff only Download (251kB)
	Text 132022027_BAB IV.pdf - Published Version Restricted to Repository staff only Download (481kB)
	Text 132022027_BAB V.pdf - Published Version Restricted to Repository staff only Download (181kB)
	Text 132022027_DAFTAR PUSTAKA.pdf - Published Version Restricted to Repository staff only Download (179kB)
	Text 132022027_LAMPIRAN.pdf - Published Version Restricted to Repository staff only Download (633kB)
	Text 132022027_Cover_sampai_Lampiran.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

ABSTRAK Penelitianinibertujuanmengembangkan model prediksi path loss pada lingkungan urban menggunakanmetodeMultiple Linear Regression (MLR) sertamembandingkankinerjanyadengan model empiris ECC-33 dan COST231-HATTA. Data penelitiandiperolehmelaluipengukuranlapangan (drive test) pada lingkunganperkotaandenganjumlah data sebanyak 13.054 titikpengukuran. Parameter yang digunakandalampembentukan model MLR meliputijarakantarapemancar dan penerima, frekuensi, tinggiantena base station, dan tinggiantena mobile station, sedangkannilai path loss hasilpengukurandigunakansebagaivariabelrespons. Pembentukan model dilakukanmenggunakanpendekatan Ordinary Least Squares (OLS) melaluiperhitunganmatriksuntukmemperolehnilaikoefisienregresi. Evaluasikinerjamenunjukkanbahwa model MLR menghasilkannilai Mean Squared Error (MSE) sebesar 123,9043 dan Root Mean Square Error (RMSE) sebesar 11,1312 dB.Sementaraitu, model ECC-33 menghasilkan MSE sebesar 2.981,829 dan RMSE sebesar 54,6061 dB dan model COST231-HATTA menghasilkan MSE sebesar 129,2114 dan RMSE 11,36712 Hasil tersebutmenunjukkanbahwa model MLR memilikitingkatkesalahanprediksi yang lebihrendahdibandingkan ECC-33 dan COST231-HATTA. Dengan demikian, model MLR yang dikembangkanmampumerepresentasikankarakteristikpropagasi pada lingkungan urban dengankinerjaprediksi yang lebihbaikdibandingkan model ECC-33. Kata kunci: Path Loss, Multiple Linear Regression, ECC-33, COST231-HATTA ABSTRACT This study aims to develop a path loss prediction model for urban environments using the Multiple Linear Regression (MLR) method and to compare its performance with the empirical ECC-33 and COST231-HATTA models. The research data were obtained through field measurements (drive tests) conducted in an urban environment, comprising a total of 13,054 measurement points. The parameters used to develop the MLR model include the distance between the transmitter and receiver, frequency, base station antenna height, and mobile station antenna height, while the measured path loss values were used as the response variable. The model was developed using the Ordinary Least Squares (OLS) approach through matrix calculations to obtain the regression coefficients. The performance evaluation shows that the MLR model achieved a Mean Squared Error (MSE) of 123.9043 and a Root Mean Square Error (RMSE) of 11.1312 dB. Meanwhile, the ECC-33 model produced an MSE of 2,981.829 and an RMSE of 54.6061 dB, while the COST231-HATTA model resulted in an MSE of 129.2114 and an RMSE of 11.36712 dB. These results indicate that the MLR model has a lower prediction error than the ECC-33 and COST231-HATTA models. Therefore, the developed MLR model is capable of representing propagation characteristics in urban environments and provides better prediction performance than the ECC-33 model. Keywords:Path Loss, Multiple Linear Regression, ECC-33, COST231-HATTA

Item Type:	Thesis (Skripsi)
Additional Information:	1. Dr. Bengawan Alfaresi, S.T., M.T 2. Dr. Wiwin A. Oktaviani, S.T., M.Sc.
Uncontrolled Keywords:	Kata kunci: Path Loss, Multiple Linear Regression, ECC-33, COST231-HATTA Keywords:Path Loss, Multiple Linear Regression, ECC-33, COST231-HATTA
Subjects:	Elektro > Teknik Listrik
Divisions:	Fakultas Teknik > Teknik Elektro (S1)
Depositing User:	Mahasiswa Fakultas Teknik
Date Deposited:	19 Sep 2026 04:10
Last Modified:	19 Sep 2026 04:10
URI:	http://repository.um-palembang.ac.id/id/eprint/37508

Actions (login required)

View Item