PERBANDINGAN KEPADATAN KENDARAAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS DAN LONG SHORT-TERM MEMORY PADA JALAN RAYA KOTA PALEMBANG

TARIGAN, FEBIYONA MELISTA BR and Oklilas, Ahmad Fali (2025) PERBANDINGAN KEPADATAN KENDARAAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS DAN LONG SHORT-TERM MEMORY PADA JALAN RAYA KOTA PALEMBANG. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011282126087_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011282126087.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
	Text RAMA_56201_09011282126087_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_56201_09011282126087_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011282126087_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_56201_09011282126087_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011282126087_0015107201_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011282126087_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (260kB) | Request a copy
	Text RAMA_56201_09011282126087_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (285kB) | Request a copy
	Text RAMA_56201_09011282126087_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13MB) | Request a copy

Abstract

This study aims to analyze traffic density in Palembang City by utilizing YOLOv9 for vehicle detection from CCTV recordings and employing K-Nearest Neighbors (KNN) and Long Short-Term Memory (LSTM) to assess density based on the detected vehicle count. The results indicate that YOLOv9 with 100 epochs achieved the best performance, with a mean Average Precision (mAP) of 0.844 for training, 0.843 for validation, and 0.839 for testing. In traffic density analysis, LSTM outperformed KNN, achieving an accuracy of 93.75% compared to KNN's 92.19%. LSTM proved to be more effective in handling sequential data and recognizing dynamic traffic patterns, whereas KNN maintained stability in balancing training and testing data but was less optimal in capturing complex traffic pattern changes.These findings suggest that the combination of YOLOv9 and LSTM offers higher accuracy, making it a strong foundation for developing AI-based systems for urban traffic monitoring and management.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	YOLOv9, K-Nearest Neighbors (KNN), Long Short-Term Memory (LSTM), Kepadatan Lalu Lintas dan Deteksi Kendaraan.
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:	Febiyona Melista Br Tarigan
Date Deposited:	21 May 2025 05:44
Last Modified:	21 May 2025 05:45
URI:	http://repository.unsri.ac.id/id/eprint/173461

Actions (login required)

View Item