NISSA, CIKAL KHAIRRUN and Oklilas, Ahmad Fali (2024) PENENTUAN JALUR TERBAIK MENGGUNAKAN ALGORITMA PARTICLE SWARM OPTIMIZATION BERDASARKAN DARI HASIL OUTPUT KONDISI KEPADATAN KENDARAAN DENGAN METODE LONG SHORT TERM MEMORY. Undergraduate thesis, Sriwijaya University.
Text
RAMA_56201_09011182025027.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy |
|
Text
RAMA_56201_09011182025027_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy |
|
Text
RAMA_56201_09011182025027_0015107201_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) |
|
Text
RAMA_56201_09011182025027_0015107201_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (275kB) | Request a copy |
|
Text
RAMA_56201_09011182025027_0015107201_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy |
|
Text
RAMA_56201_09011182025027_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_09011182025027_0015107201_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (16kB) | Request a copy |
|
Text
RAMA_56201_09011182025027_0015107201_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (138kB) | Request a copy |
|
Text
RAMA_56201_09011182025027_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
This study aims to determine the best route using Artificial Intelligence (AI) based on the Particle Swarm Optimization algorithm under road conditions in Palembang City. This research employs You Only Look Once version 8 (YOLOv8) to develop a detection system and count the number of vehicles based on CCTV video recordings, achieving a model with mAP accuracy values of 84% for training and 83% for testing. Additionally, the Long Short Term Memory (LSTM) method is used to assess road conditions as clear, moderate, or congested using several parameters, including vehicle count, road width, and travel distance. In predicting road congestion conditions, LSTM achieved a model accuracy of 93%. This is followed by the Particle Swarm Optimization algorithm to determine the best route using travel distance and road conditions as parameters. The research results indicate that route 4 is the best route at different times, namely, in the morning at 8 and 9 AM, in the afternoon at 1 and 2 PM, and in the evening at 4 and 5 PM. Route 4 has a relatively low total route weight of 13.5. It can be concluded that YOLO and Long Short Term Memory are capable of detecting and determining road congestion conditions with accuracy values of 84% for YOLO and 92.18% for LSTM.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Particle Swarm Optimization, Jalur Terbaik, Kondisi Kepadatan Jalan, Yolov8, Long Short Term Memory |
Subjects: | T Technology > T Technology (General) > T1-995 Technology (General) T Technology > T Technology (General) > T1-995 Technology (General) > T15 General works T Technology > T Technology (General) > T1-995 Technology (General) > T205 History and discussions of international agreements ("conventions") resulting from the conferences |
Divisions: | 09-Faculty of Computer Science > 56201-Computer Systems (S1) |
Depositing User: | Cikal Khairrun Nissa |
Date Deposited: | 10 Jun 2024 06:00 |
Last Modified: | 10 Jun 2024 06:00 |
URI: | http://repository.unsri.ac.id/id/eprint/146493 |
Actions (login required)
View Item |