KURNIAWAN, MUHAMMAD IRFAN (2021) RANCANG BANGUN SISTEM DETEKSI MASKER WAJAH PADA MASA NEW NORMAL MENGGUNAKAN METODE DEEP LEARNING BERBASIS RASPBERRY PI DAN TELEGRAM MESSENGER. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (191kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (93kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (437kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (299kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (963kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (24kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (25kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (105kB) |
Abstract
The corona virus continues to spread in various parts of the world, including in Indonesia. This virus was reported as a pneumonia case for the first time by the Chinese Government in December 2019. Then it entered Indonesia in early March 2020. However, until now in September 2020 cases of the corona virus in this country are still increasing. These mistakes occur due to various factors, one of which is the lack of discipline for people to wear masks. Because of that, it is difficult to reduce the spread of the virus if it is not based on awareness of ourselves. In this final project, a detection system for face mask construction based on the Internet of Things is carried out. With the title "Design of Face Mask Detection System in New Normal Period Using Deep Learning Method Based on Raspberry Pi and Telegram Messenger." The way the detection system works uses a deep learning method that can handle masks on human faces. If this system is active, the camera will take a picture and process the image on the Raspberry Pi. After that, a notification will appear to the telegram messenger. Another feature of this system is the direction of the camera which is arranged horizontally to the right and to the left (panning). From the results of the tests carried out, the average value when the lighting uses bright lights the average lighting system monitors is 85%, when using dim lights the average mask control system is 67.5% and when lighting uses sunlight and is carried out outside the room the average mask-controlled surveillance system was 97.5%. The average face mask detection process is 2.9 seconds and the average time to send notifications to telegram messenger is 1.4 seconds. Keywords : Internet of Things, Deep Learning, Corona virus, Mask, Telegram messenger Virus corona masih terus menyebar di berbagai belahan dunia, tidak terkecuali di Indonesia. Virus ini dilaporkan sebagai kasus pneumonia pertama kali oleh Pemerintah China pada Desember 2019. Kemudian masuk ke Indonesia pada awal Maret 2020. Namun, hingga saat ini pada bulan September 2020 kasus virus corona di negeri ini masih terus bertambah. Permasalahan tersebut terjadi karena berbagai faktor yang salah satunya karena tidak disiplinnya orang-orang untuk memakai masker. Karena hal itu, maka akan sulit menekan angka penyebaran virus tersebut jika tidak didasari oleh kesadaran dari diri kita sendiri. Pada tugas akhir ini dilakukan pembangunan sistem deteksi masker wajah berbasis Internet of Things. Dengan judul “Rancang Bangun Sistem Deteksi Masker Wajah Pada Masa New Normal Menggunakan Metode Deep Learning Berbasis Raspberry Pi dan Telegram Messenger.” Cara kerja sistem deteksi ini menggunakan suatu metode Deep Learning yang dapat mendeteksi masker pada wajah manusia. Jika sistem ini aktif, maka kamera akan mengambil gambar dan memproses gambar tersebut pada raspberry pi. Setelah itu, akan mengirimkan pemberitahuan ke telegram messenger. Fitur lain dari sistem ini adalah arah gerak kamera yang dapat diatur secara horizontal ke kanan dan ke kiri (panning). Dari hasil pengujian yang dilakukan, nilai rata-rata keberhasilan sistem untuk mendeteksi masker adalah bervariasi tergantung dari sumber pencahayaan ketika pengujian dilakukan. Ketika pencahayaan menggunakan lampu yang terang rata-rata keberhasilan sistem mendeteksi masker sebesar 85 %, Ketika pencahayaan menggunakan lampu yang redup rata-rata keberhasilan sistem mendeteksi masker sebesar 67.5 % dan ketika pencahayaan menggunakan cahaya matahari dan dilakukan diluar ruangan rata-rata keberhasilan sistem mendeteksi masker sebesar 97.5 %. Rata-rata proses pendeteksian masker wajah sebesar 2,9 detik dan waktu rata-rata proses pengiriman notifikasi ke telegram messenger sebesar 1,4 detik. Kata kunci : Internet of Things, Deep Learning, Virus Corona, Masker, Telegram Messenger
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41418120144 |
| Uncontrolled Keywords: | Internet of Things, Deep Learning, Virus Corona, Masker, Telegram Messenger |
| Subjects: | 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn |
| Divisions: | Fakultas Teknik > Teknik Elektro |
| Depositing User: | Dede Muksin Lubis |
| Date Deposited: | 27 Jan 2022 03:03 |
| Last Modified: | 27 Jan 2022 03:03 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/54572 |
Actions (login required)
 |
View Item |
