Skripsi

SISTEM TRANSPORTASI PINTAR MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK YANG DIOPTIMASI DENGAN RANDOM SEARCH UNTUK DETEKSI KEPADATAN KENDARAAN

---

Penilaian

---

Traffic congestion is always a primary concern in transportation issues, and it continues to pose challenges in daily activities. To address this problem, a system that can detect vehicle density levels is needed. In this research, the latest technology, such as image-based methods using CCTV camera sensors to monitor multiple roadways simultaneously, is employed with the aim of enhancing the vehicle density detection system in a Smart City. This is achieved by implementing an Artificial Neural Network (ANN) method optimized with Random Search. This research also involves a comparison with the use of the YOLOv8 algorithm for detecting, counting, and classifying vehicle types. Using YOLOv8 for image detection with a dataset of 1000 .jpg files and a CSV table consisting of 5 columns and 320 rows from the CCTV recordings of the Palembang City Transportation Agency (Dishub Kota Palembang), an accuracy of 88.4% mAP was achieved at epoch 50, with images of size 640 pixels. When tested with 350 .jpg files, an accuracy of 86.16% was attained, resulting in a 1.74% difference. Artificial Neural Network (ANN) achieved a model accuracy of 91% and a reader accuracy of 98.96%. Subsequently, optimization using Random Search resulted in a model accuracy of 89% and a reader accuracy of 100%. This research demonstrates that the ANN optimized with Random Search experienced a slight decrease in model accuracy of 2% but an increase in reading accuracy of 1.04%, thus improving reading accuracy without affecting vehicle density detection. Keywords: smart transportation, Artificial Neural Network (ANN), Random Search, vehicle density detection.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407002692	T143773	T1437732024	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1437732024

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer., 2024

Collation

xii, 113 hlm.; ilus.; tab.; 28 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.707

Content Type

Text

Media Type

unmediated

Carrier Type

unspecified

Edition

-

Subject(s)

Sistem multimedia
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

UIN Farrah

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment