RANCANG BANGUN SARUNG TANGAN PENERJEMAH BAHASA ISYARAT INDONESIA (BISINDO) BERBASIS INTERNET OF THINGS DENGAN METODE ARTIFICIAL NEURAL NETWORK

Nasywa Zhafira Putri, . (2026) RANCANG BANGUN SARUNG TANGAN PENERJEMAH BAHASA ISYARAT INDONESIA (BISINDO) BERBASIS INTERNET OF THINGS DENGAN METODE ARTIFICIAL NEURAL NETWORK. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ASBTRAK.pdf
Download (193kB)
[img] Text
AWAL.pdf
Download (855kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (217kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (639kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (605kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (192kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (188kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (276kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (5MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (15MB)
[img] Text
ARTIKEL .pdf
Restricted to Repository staff only
Download (459kB)

Abstract

The limited public understanding of Indonesian Sign Language (Bahasa Isyarat Indonesia/BISINDO) creates communication barriers for individuals with hearing impairments. This study aims to design and analyze an Internet of Things (IoT) based smart glove translation system utilizing the Artificial Neural Network (ANN) method. The system employs an ESP32 microcontroller integrated with 10 flex sensors and two MPU6050 sensors on both hands to wirelessly capture finger curvature and gesture orientation. The sensor data is transmitted in real-time to a cloud platform to be classified into 31 classes, comprising 26 alphabet letters (A Z) and 5 introductory words (Halo, Nama, Saya, Perkenalan Diri, Terima kasih). The translation results are displayed in both text and voice formats via a web based application interface. The performance evaluation of the ANN model achieved a testing accuracy of 96,61% on data simulation. Meanwhile, end-to-end system testing through direct, real-time trials yielded an average success rate of 95% out of a total of 930 experiments. Although highly reliable for static gestures, the system still exhibits limitations in dynamic movements, with failure rates of 20% for the letter "J" and 70% for the phrase "Terima kasih". Overall, this device is viable for deployment as an effective and inclusive communication tool.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil:2210314083] [Pembimbing 1 : Andre Suwardana Adiwidya] [Pembimbing 2 : Muhamad Alif Razi] [Penguji 1 : Subekti Ari Santoso] [Penguji 2 : Fajar Rahayu]
Uncontrolled Keywords: Artificial Neural Network (ANN), BISINDO, ESP32, Internet of Things (IoT), Smart Glove
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: NASYWA ZHAFIRA PUTRI
Date Deposited: 28 Aug 2026 03:12
Last Modified: 28 Aug 2026 03:12
URI: http://repository.upnvj.ac.id/id/eprint/53343

Actions (login required)

View Item View Item