SISTEM TRANSPORTASI PINTAR MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK YANG DIOPTIMASI DENGAN RANDOM SEARCH UNTUK DETEKSI KEPADATAN KENDARAAN

INDRIYANI, SISCA and Oklilas, Ahmad Fali (2024) SISTEM TRANSPORTASI PINTAR MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK YANG DIOPTIMASI DENGAN RANDOM SEARCH UNTUK DETEKSI KEPADATAN KENDARAAN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181924021.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011181924021_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011181924021_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (404kB)
	Text RAMA_56021_09011181924021_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56021_09011181924021_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (454kB) | Request a copy
	Text RAMA_56201_09011181924021_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011181924021_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (144kB) | Request a copy
	Text RAMA_56201_09011181924021_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (118kB) | Request a copy
	Text RAMA_56201_09011181924021_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (173kB) | Request a copy

Abstract

Traffic congestion is always a primary concern in transportation issues, and it continues to pose challenges in daily activities. To address this problem, a system that can detect vehicle density levels is needed. In this research, the latest technology, such as image-based methods using CCTV camera sensors to monitor multiple roadways simultaneously, is employed with the aim of enhancing the vehicle density detection system in a Smart City. This is achieved by implementing an Artificial Neural Network (ANN) method optimized with Random Search. This research also involves a comparison with the use of the YOLOv8 algorithm for detecting, counting, and classifying vehicle types. Using YOLOv8 for image detection with a dataset of 1000 .jpg files and a CSV table consisting of 5 columns and 320 rows from the CCTV recordings of the Palembang City Transportation Agency (Dishub Kota Palembang), an accuracy of 88.4% mAP was achieved at epoch 50, with images of size 640 pixels. When tested with 350 .jpg files, an accuracy of 86.16% was attained, resulting in a 1.74% difference. Artificial Neural Network (ANN) achieved a model accuracy of 91% and a reader accuracy of 98.96%. Subsequently, optimization using Random Search resulted in a model accuracy of 89% and a reader accuracy of 100%. This research demonstrates that the ANN optimized with Random Search experienced a slight decrease in model accuracy of 2% but an increase in reading accuracy of 1.04%, thus improving reading accuracy without affecting vehicle density detection. Keywords: smart transportation, Artificial Neural Network (ANN), Random Search, vehicle density detection.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	smart transportation, Artificial Neural Network (ANN), Random Search, vehicle density detection.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Sisca Indriyani
Date Deposited:	13 May 2024 06:02
Last Modified:	13 May 2024 06:02
URI:	http://repository.unsri.ac.id/id/eprint/143773

Actions (login required)

View Item