MODEL KEPUTUSAN CERDAS DALAM MENENTUKAN JALUR TERBAIK TRANSPORTASI PADA SMART CITY MENGGUNAKAN ALGORITMA RANDOM FOREST DAN BAYESIAN OPTIMIZATION (RF-BO)

KAMILIA, MILDA and Oklilas, Ahmad Fali (2023) MODEL KEPUTUSAN CERDAS DALAM MENENTUKAN JALUR TERBAIK TRANSPORTASI PADA SMART CITY MENGGUNAKAN ALGORITMA RANDOM FOREST DAN BAYESIAN OPTIMIZATION (RF-BO). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181924011.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011181924011_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (635kB)
	Text RAMA_56201_09011181924011_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (385kB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (816kB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (111kB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (109kB) | Request a copy
	Text RAMA_56201_09011181924011_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

This research analyzes various methods and algorithms in the context of object detection and optimal route determination in vehicle traffic in the city of Palembang, as a step towards developing the concept of a smart city. The YOLOv3 method is employed to detect vehicles in video recordings, yielding an accuracy ranging from 72.72% to 79.35% for the categories of motorcycles and cars. The overall detection accuracy of the model reaches 76.03%. Furthermore, the Random Forest algorithm is implemented to classify road conditions into three categories: smooth-flowing, moderate, and congested. After optimization using Bayesian Optimization, the model's accuracy improves from 89% to 92%, and reading accuracy increases from 91.66% to 92.36%. The results of the A* Heuristic Search algorithm demonstrate that Route 5 (from SMK PGRI 1 Palembang to Bom Baru Jl Perintis Kemerdekaan Arah Charitas (STMIK MBC)) is the most frequently chosen optimal route in 9 out of 12 tested instances. This route selection is based on the tendency of lighter traffic congestion and the shortest travel distance compared to other routes. The width of the road also influences the optimal route selection, where wider roads can reduce traffic density and the risk of congestion.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Smart City, YOLOv3, Object Detection, Random Forest Algorithm, Bayesian Optimization, A* Heuristic Search, Traffic Conditions, Route Determination
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76 Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Milda Kamilia
Date Deposited:	20 Sep 2023 06:32
Last Modified:	20 Sep 2023 06:32
URI:	http://repository.unsri.ac.id/id/eprint/128774

Actions (login required)

View Item