SISTEM SMART TRANSPORTATION UNTUK PENENTUAN JALUR TERBAIK DENGAN PERBANDINGAN METODE KNN YANG DIOPTIMASI DENGAN GRID SEARCH DAN RANDOM SEARCH

MARIZA, NANDA PUTRI and Sukemi, Sukemi and Oklilas, Ahmad Fali (2023) SISTEM SMART TRANSPORTATION UNTUK PENENTUAN JALUR TERBAIK DENGAN PERBANDINGAN METODE KNN YANG DIOPTIMASI DENGAN GRID SEARCH DAN RANDOM SEARCH. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011381924116.pdf] Text
RAMA_56201_09011381924116.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_TURNITIN.pdf] Text
RAMA_56201_09011381924116_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (9MB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_01_front_ref.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_02.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (474kB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_03.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_04.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_05.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (35kB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_06_ref.pdf] Text
RAMA_56201_09011381924116_0003126604_0015107201_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (193kB) | Request a copy
[thumbnail of RAMA_56201_09011381924116_0003126604_0015107201_07_lamp.pdf] Text
RAMA_56201_09011381924116_0003126604_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

Traffic congestion is currently a major problem in big cities in Indonesia. Therefore, a system for determining the best paths is needed to address traffic congestion issues. This system is part of the concept of smart transportation implemented in smart cities. The use of computer vision techniques has attracted attention for the development of smart transportation in traffic. In this research, the You Only Look Once version 8 (YOLOv8) object detection algorithm is used for vehicle classification and detection to obtain an optimal model. The YOLOv8 Model testing produce a mean Average Precision (mAP) result of 73.2%, with a detection accuracy of 66% for motorcycles and 79% for cars. In addition, the optimized K-Nearest Neighbor (KNN) algorithm with grid search and random search is used to classification road density conditions, while the A-star algorithm is used for determining the best paths. The KNN model achieved an accuracy of 85.9% and a reading accuracy of 84.98%. Optimization with grid search resulted in a model accuracy of 82.81% and a reading accuracy of 91.64%. Meanwhile, optimization with random search resulted in a model accuracy of 87.5% and a reading accuracy of 89.96%. The implementation of the A-star algorithm for determining the best path resulted in the selection of path 2. The chosen path 2 was determined based on road conditions and distance parameters, resulting in the smallest total weight.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Penentuan Jalur Terbaik, Smart Transportation, Smart City, You Only Look Once version 8 (YOLOv8), K-Nearest Neighbor (KNN), Grid Search, Random Search, Algortima A-star
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
T Technology > T Technology (General) > T1-995 Technology (General)
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Nanda Putri Mariza
Date Deposited: 28 Jul 2023 07:15
Last Modified: 28 Jul 2023 07:15
URI: http://repository.unsri.ac.id/id/eprint/123038

Actions (login required)

View Item View Item