IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK MENDETEKSI KEMACETAN LALU LINTAS SERTA MENENTUKAN JALUR TERBAIK MENGGUNAKAN ALGORITMA HEURISTIC SEARCH PADA JALAN RAYA KOTA PALEMBANG

RAMADHAN, HARIS PUTRA and Oklilas, Ahmad Fali (2024) IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK MENDETEKSI KEMACETAN LALU LINTAS SERTA MENENTUKAN JALUR TERBAIK MENGGUNAKAN ALGORITMA HEURISTIC SEARCH PADA JALAN RAYA KOTA PALEMBANG. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281924077.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281924077_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011281924077_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (882kB)
	Text RAMA_56201_09011281924077_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (386kB) | Request a copy
	Text RAMA_56201_09011281924077_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (763kB) | Request a copy
	Text RAMA_56201_09011281924077_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_09011281924077_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (70kB) | Request a copy
	Text RAMA_56201_09011281924077_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (150kB) | Request a copy
	Text RAMA_56201_09011281924077_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (189kB) | Request a copy

Abstract

This study developed the YOLOv8 model to detect five object classes, with training results showing an accuracy of 95%, an f-1 score of 89%, and mAP@0.5 of 93.1%. In the testing phase, the model achieved an accuracy of 93.83%, an f-1 score of 83%, and mAP@0.5 of 86.7%. Vehicle counting using YOLOv8 and DeepSORT on 72 videos showed an average accuracy of 95.51% for motorcycles and 79.02% for cars. Additionally, a CNN model for classifying road conditions using a dataset of 320 data entries achieved an accuracy of 89.06% on testing data. The Heuristic Search (A-Star) algorithm was used to find the best route from Ampera Bridge to Sultan Mahmud Badaruddin II Airport, generating six alternative routes with predictions for 12 different conditions, where the best route varied depending on the conditions.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	YOLOv8, DeepSORT, CNN, algoritma Heustitic Search, Pencarian A-Star
Subjects:	T Technology > TE Highway engineering. Roads and pavements > TE1-450 Highway engineering. Roads and pavements
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Haris Putra Ramadhan
Date Deposited:	06 Aug 2024 05:12
Last Modified:	06 Aug 2024 05:12
URI:	http://repository.unsri.ac.id/id/eprint/154248

Actions (login required)

View Item