Prashanth, Sai (2022) Pendeteksi dan pengenalan alfabet isyarat ASL (American Sign Language) menggunakan Convolutional Neural Network. Bachelor thesis, Universitas Pelita Harapan.
Preview
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (41kB) | Preview
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (193kB)
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (480kB)
![Chapter1 [thumbnail of Chapter1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (526kB)
![Chapter2 [thumbnail of Chapter2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter3 [thumbnail of Chapter3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (978kB)
![Chapter4 [thumbnail of Chapter4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (2MB)
![Chapter5 [thumbnail of Chapter5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (191kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (254kB)
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
Abstract
Komunikasi non-verbal merupakan pengiriman informasi melalui bahasa tubuh, ekspresi wajah, dan gerak tubuh. Ketika tersenyum saat bertemu seseorang, bisa didefiniskan sebagai menunjukkan keramahan, penerimaan, dan keterbukaan. Komunikasi non-verbal bergantung pada ekspresi dan gerakan fisik yang bertentangan dengan komunikasi verbal, atau penggunaan bahasa untuk mentransfer informasi melalui teks tertulis, berbicara atau bahasa isyarat, dimana ASL merupakan bahasa isyarat yang paling dikenal di kalangan orang yang menggunakan bahasa isyarat.
ASL adalah bahasa isyarat yang paling banyak digunakan di seluruh dunia, umumnya digunakan di Amerika Serikat, setelah bahasa Inggris dan Spanyol.
Sehubung berkembangnya dunia teknologi ke arah yang lebih canggih, alfabet isyarat dapat dikenal oleh algoritma yang ada pada machine learning. Machine learning merupakan sebuah cara dalam bidang teknik informatika dimana sebuah komputer diberi data untuk mempelajari pola dari data yang diberi untuk menghasilkan sebuah keluaran berupa model yang dapat mengklasifikasi yang memberi kemampuan terhadap sebuah komputer yang sudah mempelajari dataset yang diberi, seperti mengenal teks, suara, dan citra.
Dengan itu, dari hasil penelitian yang dilakukan menggunakan Convolutional Neural Network peneliti mendapatkan nilai keakuratan model yang yang dilatih selama 100 epoch dengan tensorflow mendapatkan keakuratan pelatihan sebesar 93.67% serta keakuratan validasi memiliki tingkat keakuratan sebesar 96.85%. / Non-verbal communication is the transmission of information through body language, facial expressions, and gestures. When smiling during meeting someone, it can be defined as showing friendliness, acceptance, and openness. Nonverbal communication relies on physical expressions and gestures as opposed to verbal communication, or the use of language to transfer information through written text, spoken or sign language, where ASL is the most familiar sign language among people who use sign language.
ASL is the most widely spoken sign language worldwide, generally used in the United States, after English and Spanish.
Due to the development of the technological world in a more sophisticated direction, sign language can be recognized by algorithms in machine learning. Machine learning is a method in information technology where a computer is given a data to study patterns from the data given to produce an output in the form of a model that can be used to classify, which gives the ability to a computer that has studied a given dataset, such as recognizing text, sound, and images.
With that, from the results of research conducted using the Convolutional Neural Network, researchers obtained an accuracy value of the model that was trained for 100 epochs with tensorflow to get a training accuracy of 93.67% and validation accuracy has an accuracy rate of 96.85%.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Prashanth, Sai NIM0382190035 saiprashanth02012001@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Pangaribuan, Jefri Junifer NIDN0130108901 jefri.pangaribuan@uph.edu |
Uncontrolled Keywords: | ASL; machine learning; convolutional neural network |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics |
Depositing User: | Users 23561 not found. |
Date Deposited: | 17 Feb 2023 02:15 |
Last Modified: | 17 Feb 2023 02:15 |
URI: | http://repository.uph.edu/id/eprint/54160 |