Klasifikasi Gerakan Cuci Tangan Berbasis Convolutional Neural Network (CNN)

Qalbi, Habibul Rahman (2021) Klasifikasi Gerakan Cuci Tangan Berbasis Convolutional Neural Network (CNN). Undergraduate thesis, Institut Teknologi Sepuluh Nopember Surabaya.

[thumbnail of 07211740000022-Undergraduate_Thesis.pdf] Text
07211740000022-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (3MB) | Request a copy

Abstract

Cuci tangan merupakan langkah awal dalam menjaga kesehatan tubuh. Dengan rajin mencuci tangan kita dapat mencegah penyebaran penyakit. Akan tetapi, masih banyak masyarakat yang tidak sadar akan tata cara cuci tangan yang benar, sehingga tangan tidak bersih sepenuhnya. Pemanfaatan teknologi Deep Learning dapat menjadi solusi untuk mengetahui apakah masyarakat telah mencuci tangan dengan benar. Menggunakan kamera sebagai input yang kemudian di proses menggunakan algoritma Convolutional Neural Network (CNN), kita dapat mengklasifikasikan gerakan - gerakan yang dilakukan pengguna saat mencuci tangan. Metode yang digunakan dalam penelitian ini menghasilkan tingkat akurasi 99% pada fase Training. Pada pengujiannya, sistem ini menghasilkan tingkat akurasi prediksi tertinggi sebesar 12/12 gerakan (100%) dengan tingkat inkonsistensi sebesar 2/12 prediksi (16,67%). Harapannya penelitian ini dapat membantu dalam memantau dan memastikan apakah masyarakat telah mencuci tangan dengan benar, khususnya di tempat umum dimana tingkat penyebaran penyakit cukup tinggi.
=====================================================================================================
Handwashing is the first step when it comes to maintaining health and hygine, by doing so we prevent the spread of diseases. Even though, there is still many people that didn’t wash their hand properly. By using Deep Learning algorithm, we could know if someone had wash their hand properly by capturing their movement with a camera and processing the data through a Convolutional Neural Network (CNN) model. The method used in this study resulted an accuracy level of 99% on the training phase. In testing, the system produce an highest prediction accuracy of 12/12 movement (100%) with inconsistency of 2/12 predicted movement (16.67%). We hope that this technology could help to monitor and ensure that people had wash their hand properly, specially on public places where the potential spread of diseases is quite high.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Classification, CNN, Cuci Tangan, EfficientNet, Handwash, Klasifikasi, Moving Average
Subjects: T Technology > T Technology (General) > T385 Visualization--Technique
T Technology > T Technology (General) > T57.5 Data Processing
T Technology > T Technology (General) > T58.62 Decision support systems
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Habibul Rahman Qalbi
Date Deposited: 01 Sep 2021 05:00
Last Modified: 01 Sep 2021 05:00
URI: http://repository.its.ac.id/id/eprint/91158

Actions (login required)

View Item View Item