Verbal Helper Application for Autism using Natural Language Processing / Nur Farahin Mohd Affendy

Mohd Affendy, Nur Farahin (2020) Verbal Helper Application for Autism using Natural Language Processing / Nur Farahin Mohd Affendy. Degree thesis, Universiti Teknologi MARA, Cawangan Melaka.

Abstract

Autism can make communicating and associating with others difficult for a child. Autistic child tends to live in their own world which they do not socialize with others. Therefore, they are experiencing verbal issues. Autism is a neuro-developmental conditions which makes them behave repetitive tasks. A Recurrent Neural Network (RNN) was used in this project to predict next possible word until it becomes a sentence. Furthermore, N-gram also used for grammar checking for a simple sentence. The prediction words are displayed based on the frequency of the word chosen. This application results a valid sentence generated or chosen by autistic child to ease them communicating with others. Moreover, it helps caretaker or parents to teach them on how to express verbally after this. Thus, this application might be used for autistic children to help them express verbally.

Metadata

Item Type: Thesis (Degree)
Creators:
Creators
Email / ID Num.
Mohd Affendy, Nur Farahin
2017196607
Contributors:
Contribution
Name
Email / ID Num.
Thesis advisor
Shari, Anis Amilah
UNSPECIFIED
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Communication of computer science information
Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Programming. Rule-based programming. Backtrack programming
Divisions: Universiti Teknologi MARA, Melaka > Jasin Campus > Faculty of Computer and Mathematical Sciences
Keywords: Verbal helper application; Autism; Autistic children
Date: 2020
URI: https://ir.uitm.edu.my/id/eprint/31598
Edit Item
Edit Item

Download

[thumbnail of 31598.pdf] Text
31598.pdf

Download (233kB)

Digital Copy

Digital (fulltext) is available at:

Physical Copy

Physical status and holdings:
Item Status:

ID Number

31598

Indexing

Statistic

Statistic details