PENENTUAN ALGORITMA OPTIMASI 4 PARAMETER ANTENA MIKROSTRIP FRAKTAL SIERPINSKI GASKET BERBASIS MACHINE LEARNING UNTUK WI-FI 7 FREKUENSI 2,4 GHZ

Mayori Permitha, . (2025) PENENTUAN ALGORITMA OPTIMASI 4 PARAMETER ANTENA MIKROSTRIP FRAKTAL SIERPINSKI GASKET BERBASIS MACHINE LEARNING UNTUK WI-FI 7 FREKUENSI 2,4 GHZ. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (206kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (269kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (544kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (497kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (217kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (233kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (143kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (17MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (533kB)

Abstract

This research aims to determine the most suitable machine learning-based optimization algorithms for four parameters of Sierpinski Gasket fractal microstrip antennas at 2.4 GHz for Wi-Fi 7 applications: return loss, gain, VSWR, and bandwidth. The four machine learning algorithms evaluated were K-Nearest Neighbor (KNN), Decision Tree, Random Forest, and Support Vector Regression (SVR). A comprehensive dataset was built from 424 variations of antenna designs simulated using CST Studio Suite software with two types of substrates, FR-4 and RT/duroid 5880. The performance analysis showed that different algorithms excelled for each parameter: KNN for return loss (R2=0.9837), SVR for VSWR (R2=0.9986), and Random Forest for both bandwidth (R2=0.7042) and gain (R2=0.8701). These best-performing algorithms were then integrated with the Random Search method, equipped with a weighted scoring system, to find the optimal antenna design. The optimization recommended the first antenna model design with an RT/duroid 5880 substrate. Verification through simulation confirmed the superior performance of the optimized antenna with a return loss of -41.65 dB, VSWR of 1.01, bandwidth of 166.4 MHz, and gain of 4.56 dBi at a frequency of 2.4086 GHz. This study successfully demonstrated that the integration of machine learning can effectively transform initially non-functional antenna designs into highly efficient ones that fully meet Wi-Fi 7 specifications.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110314060] [Pembimbing 1: Silvia Anggraeni] [Pembimbing 2: Yosy Rahmawati] [Penguji 1: Didit Widiyanto] [Penguji 2: Muhammad Alif Razi]
Uncontrolled Keywords: Microstrip Antenna, Sierpinski Gasket Fractal, Machine Learning, Optimization, Wi-Fi 7
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: MAYORI PERMITHA
Date Deposited: 08 Aug 2025 02:53
Last Modified: 08 Aug 2025 02:53
URI: http://repository.upnvj.ac.id/id/eprint/39471

Actions (login required)

View Item View Item