PREDIKSI KEPADATAN KENDARAAN MENGGUNAKAN METODE K-NEAREST NEIGHBORS YANG DIOPTIMASI DENGAN PARTICLE SWARM OPTIMIZATION DI KOTA PINTAR

LESTARI, DIAN YOFITA and Sukemi, Sukemi and Oklilas, Ahmad Fali (2023) PREDIKSI KEPADATAN KENDARAAN MENGGUNAKAN METODE K-NEAREST NEIGHBORS YANG DIOPTIMASI DENGAN PARTICLE SWARM OPTIMIZATION DI KOTA PINTAR. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924084.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011381924084_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381924084_0003126604_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_56201_09011381924084_0003126604_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (536kB) | Request a copy
	Text RAMA_56201_09011381924084_0003126604_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (710kB) | Request a copy
	Text RAMA_56201_09011381924084_0003126604_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_09011381924084_0003126604_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (106kB) | Request a copy
	Text RAMA_56201_09011381924084_0003126604_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (226kB) | Request a copy
	Text RAMA_56201_09011381924084_0003126604_0015107201_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (825kB) | Request a copy

Abstract

Traffic congestion remains a primary concern in the transportation sector and continues to pose challenges for everyday activities. To address this issue, a system capable of detecting vehicle density levels is required. This research leverages cutting-edge technology, such as image-based methods utilizing CCTV camera sensors to monitor multiple roadways simultaneously, with the hope of making surveillance more efficient and effective. The objective of this study is to enhance the vehicle density determination system in the Smart City by implementing the K-Nearest Neighbors (KNN) method optimized with Particle Swarm Optimization (PSO). The study also compares its results with the utilization of the YOLOv8 algorithm for vehicle detection, counting, and classification. YOLOv8 achieved a high level of accuracy, with an F1 Score of 0.94 and a mean Average Precision (mAP@0.50) of 96.6% with an image size of 640. It achieved a 96% accuracy in motorbike classification and 97% in car classification. In contrast, the unoptimized KNN model exhibited an accuracy rate of 85% and a reading accuracy of 76.42% in predicting road conditions based on vehicle count, lane count, and distance traveled. After optimization with PSO, the model's accuracy improved to 91%, with a prediction accuracy rate of 91%, and the reading accuracy increased to 77.83%. The results of this research indicate that the accuracy of PSO-optimized KNN improved, albeit not significantly.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Prediksi Kendaraan, You Only Look Once version 8 (YOLOv8), K-Nearest Neighbor (KNN), Particle Swarm Optimization
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1125-1345 Machine shops and machine shop practice > TJ1180 Machining, Ceramic materials--Machining-Strength of materials-Machine tools-Design and construction > TJ1180.I34 Machining-Machine tools-Numerical control-Computer integrated manufacturing systems-Artificial intelligence
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Dian Yofita Lestari
Date Deposited:	19 Jan 2024 06:47
Last Modified:	19 Jan 2024 06:47
URI:	http://repository.unsri.ac.id/id/eprint/138808

Actions (login required)

View Item