Text

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307002955	T123038	T1230382023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1230382023

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xviii, 132 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Jurusan Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment