PENERAPAN SMART TRANSPORTATION PADA SMART CITY UNTUK MENENTUKAN RUTE TERBAIK MENGGUNAKAN METODE RECURRENT NEURAL NETWORK YANG DIOPTIMASI DENGAN GRID SEARCH (RNN-GS)

AZHARI, AHMAD and Oklilas, Ahmad Fali (2023) PENERAPAN SMART TRANSPORTATION PADA SMART CITY UNTUK MENENTUKAN RUTE TERBAIK MENGGUNAKAN METODE RECURRENT NEURAL NETWORK YANG DIOPTIMASI DENGAN GRID SEARCH (RNN-GS). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924083.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011381924083_TURNITIN.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011381924083_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (442kB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (15kB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (88kB) | Request a copy
	Text RAMA_56201_09011381924083_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (882kB) | Request a copy

Abstract

In this study using the You Only Look Once Version 8 (YOLOv8) algorithm to detect and count the number of vehicles based on CCTV recordings, The Recurrent Neural Network (RNN) method optimized with Grid Search (GS) is used to predict road density conditions so as to get smooth, medium, congested output, and to determine the best route using the A-Star algorithm. This study uses a dataset of vehicle images totaling 4224 images and a reference table of 5 columns and 320 rows of road conditions in .csv form. The use of YOLOv8 in this study resulted in an mAP model of 85.4% and an accuracy of 78.61%. Next, the RNN method resulted in model accuracy of 49.84% and prediction accuracy of readings of 95.75%, followed by optimization using Grid Search so as to get model accuracy of 50.48% and reading accuracy of 95.75%, So there was an increase in model accuracy by 0.64% and for reading accuracy remained the same by 95.75%. Finally, the A-Star algorithm determines the best route using the parameters of road conditions and mileage so as to get the best route results on route 4, because route 4 has the smallest weight in all conditions 08.00 am and 09.00 am, 01.00 pm and 02.00 pm, 04.00 PM and 05.00 pm.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	A-Star, Grid Search, Penentuan Rute Terbaik, Recurrent Neural Network, Smart Transportation, Smart City, You Only Look Once Version 8
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Ahmad Azhari
Date Deposited:	26 Jul 2023 02:21
Last Modified:	26 Jul 2023 02:21
URI:	http://repository.unsri.ac.id/id/eprint/121786

Actions (login required)

View Item