Skripsi

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000946	T138808	T1388082024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1388082024

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya., 2024

Collation

xv, 100 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment