Rancang Bangun Kembali Perangkat Lunak Pendeteksi Angka Sebagai Media Edukasi pada Anak Berbasis Android

Winanto, Rasyid Ridlo (2023) Rancang Bangun Kembali Perangkat Lunak Pendeteksi Angka Sebagai Media Edukasi pada Anak Berbasis Android. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05111840000135-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (5MB) | Request a copy

Abstract

Pemerintah mengembangkan kebijakan untuk membatasi aktivitas di luar rumah dan tetap berada di rumah dikarenakan pandemi Covid-19 yang belum mereda. Hal ini berdampak signifikan pada berbagai sektor termasuk pendidikan. Akibatnya, proses belajar mengajar harus dilakukan secara online dari rumah untuk meminimalisir penyebaran Covid-19. Tugas Akhir ini, dilakukan rancang bangun kembali perangkat lunak pendeteksi angka terhadap aplikasi Welearn dengan melakukan pengubahan model klasifikasi untuk prediksi angka dan penambahan fitur multiplayer. Prediksi angka yang digunakan pada Tugas Akhir ini adalah model klasifikasi Deep Neural Network dan menggunakan Transfer Learning DenseNet169. Pada Tugas Akhir sebelumnya penulis menggunakan metode klasifikasi Convolutional Neural Network(CNN) dengan Transfer Learning MobileNet dan mendapatkan hasil akurasi 98,86%. Pada Tugas Akhir ini metode klasifikasi yang dipakai adalah Deep Neural Network(DNN) dengan Transfer Learning DenseNet169 dan mendapatkan akurasi sebesar 99.62%. Akurasi ini menunjukan metode klasifikasi dan Transfer Learning dapat diterapkan pada aplikasi Android dengan user anak TK. Penerapan teknologi pada aplikasi Android diharapkan dapat membantu proses belajar pada anak terutama pembelajaran angka
=======================================================================================================================================
The government has developed policies to limit activities outside the home and stay at home due to the ongoing Covid-19 pandemic. This has had a significant impact on various sectors including education. As a result, the teaching and learning process must be carried out online from home to minimize the spread of Covid-19. In this final project, a number detection software is redesigned for the Welearn application by changing the classification model for number prediction and adding a multiplayer feature. The number prediction used in this Final Project is a classification model of the Deep Neural Network and uses Transfer Learning DenseNet169. In the previous Final Project the author used the Convolutional Neural Network (CNN) classification method with Transfer Learning MobileNet and obtained an accuracy of 98.86%. In this Final Project the classification method used is Deep Neural Network (DNN) with Transfer Learning DenseNet169 and obtains an accuracy of 99.62%. This accuracy shows that the classification method and Transfer Learning can be applied to Android applications with kindergarten users. The application of technology in Android applications is expected to help the learning process in children, especially learning numbers

Item Type:	Thesis (Other)
Additional Information:	RSIf 005.1 Win r-1 2023
Uncontrolled Keywords:	DenseNet169, DNN, Transfer Learning, Number Recognition, DenseNet169, DNN, Prediksi Angka, Transfer Learning
Subjects:	L Education > L Education (General) T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Rasyid Ridlo Winanto
Date Deposited:	09 Feb 2023 02:07
Last Modified:	28 Aug 2023 02:30
URI:	http://repository.its.ac.id/id/eprint/96487

Actions (login required)

View Item