Nur, Ahmad (2024) PENDETEKSI HELM PADA PENGENDARA SEPEDA MOTOR DENGAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS WEB. S1 thesis, Universitas Malikussaleh.

	Text Cover-1.pdf Download (11kB)
	Text Abstrak.pdf Download (343kB)
	Text BAB 1-1.pdf Download (387kB)
	Text BAB II-1.pdf Restricted to Registered users only Download (801kB)
	Text BAB III-1.pdf Restricted to Registered users only Download (362kB)
	Text IV V Dapus.pdf Restricted to Registered users only Download (2MB)
	Text fuulll.pdf Restricted to Registered users only Download (3MB)

Abstract

This research is motivated by the high number of traffic accidents in Indonesia, especially those involving motorbikes, which are one of the main causes of death on the road. Based on data from the Indonesian National Police in 2020, the number of Road Transport Traffic Accidents (LLAJ) reached 23,529 people, with 73% of them involving motorbikes. This shows the need to develop a system that can monitor motorcyclists' use of helmets to improve road safety. The method used in this research is Convolutional Neural Network (CNN), a type of Deep Learning method that is capable of detecting and recognizing objects in digital images. The data used is a collection of images that have been categorized, including images of people wearing helmets and those without. The process of detecting helmets in images begins with collecting categorized image data, then converting it to grayscale to reduce computational complexity and focus on texture and shape. The research results show that the system successfully detected individuals wearing helmets in 28 images and individuals not wearing helmets in 36 images, with a success rate of 37.33% of the total detection. However, there are still limitations in detection, mainly related to image quality and other factors. The conclusion of this research is that a helmet detection system using web-based CNN can be an important tool in increasing motorcyclist compliance with helmet use. However, optimization and improvement of the detection system is needed to increase accuracy and reliability under various conditions. Thus, this research makes an important contribution to efforts to improve road safety, especially for motorcyclists. Keywords: Helmet, Object Detection, Digital Image, CNN, Dataset, Image Model Training.

Item Type:	Thesis (S1)
Subjects:	Q Science > QA Mathematics Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Divisions:	Fakultas Teknik > 55201 - Jurusan Teknik Informatika
Depositing User:	Ahmad Nur
Date Deposited:	03 Sep 2024 03:26
Last Modified:	03 Sep 2024 03:26
URI:	https://rama.unimal.ac.id/id/eprint/5584

Actions (login required)

View Item