DESIGN AND DEVELOPMENT OF A DEEP LEARNING APPLICATION FOR CLASSIFICATION OF THE SUITABILITY OF FRUITS AND VEGETABLES FOR CONSUMPTION BASED ON MOBILE APPS AS AN EDUCATIONAL MEDIA FOR THE ACADEMIC CIVITY

Rudiansyah, . (2025) DESIGN AND DEVELOPMENT OF A DEEP LEARNING APPLICATION FOR CLASSIFICATION OF THE SUITABILITY OF FRUITS AND VEGETABLES FOR CONSUMPTION BASED ON MOBILE APPS AS AN EDUCATIONAL MEDIA FOR THE ACADEMIC CIVITY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (407kB)
[img] Text
AWAL.pdf
Download (440kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (409kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (704kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (473kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (399kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (423kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (223kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (587kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (346kB)

Abstract

The use of deep learning technology in digital image processing has experienced significant development and provides efficient solutions to various problems, one of which is the classification of visual objects such as fruits and vegetables. Where in the world of agriculture and education, the need for a system that is able to recognize and classify food products automatically is becoming increasingly important, both for research purposes, nutrition education, and quality control. Based on this, this study aims to design and develop a mobile deep learning-based application using the Convolutional Neural Network (CNN) algorithm to classify types of fruits and vegetables based on the level of suitability for consumption, as well as provide educational information about the nutritional content and benefits of each object. The method applied in this study uses an experimental approach by collecting image data of 1,200 images of fruits and vegetables divided into eight classes, including categories suitable and unsuitable for consumption. The CNN model developed consists of five convolutional layers and two fully connected layers. The model training process produces very optimal performance, marked by an accuracy level of 100% and a loss value of 0.0031. The model that has gone through the training stage is then applied to the Android application by utilizing the Flutter and TensorFlow Lite frameworks. Based on the test results, the application is able to classify accurately and present additional relevant information directly in real-time. This application will not only help users distinguish the condition of fruits and vegetables, but also function as an interactive learning tool about the importance of consuming healthy foods. The conclusion of this study is that the integration of CNN in this educational mobile application is able to be an innovative solution to improve technological literacy and awareness of nutrition, especially for the academic community.

Item Type: Thesis (Skripsi)
Additional Information: [No. Panggil: 2010314062] [Pembimbing: Fajar Rahayu Ikhwanul] [Penguji 1: Muhamad Alif Razi] [Penguji 2: Didit Widiyanto]
Uncontrolled Keywords: Mobile Application, Fruits and Vegetables, CNN, Deep Learning, Education, Image Classification
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: RUDIANSYAH
Date Deposited: 15 Aug 2025 01:40
Last Modified: 15 Aug 2025 01:40
URI: http://repository.upnvj.ac.id/id/eprint/39213

Actions (login required)

View Item View Item