RANCANG BANGUN ALAT DETEKSI KEMATANGAN BUAH TOMAT MENGGUNAKAN ARDUINO UNO, RASPBERRY PI, DAN CNN

Juan Patrick, . (2024) RANCANG BANGUN ALAT DETEKSI KEMATANGAN BUAH TOMAT MENGGUNAKAN ARDUINO UNO, RASPBERRY PI, DAN CNN. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (694kB)
	Text AWAL.pdf Download (2MB)
	Text BAB 1.pdf Restricted to Repository UPNVJ Only Download (1MB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (3MB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (3MB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB)
	Text BAB 5.pdf Download (413kB)
	Text DAFTAR PUSTAKA.pdf Download (1MB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (113kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (6MB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (10MB)
	Text ARTIKEL_KI.pdf Restricted to Repository staff only Download (369kB)

Abstract

Tomatoes are an important commodity in Indonesia, with production reaching 1,143,788 kg in 2023 according to the Central Bureau of Statistics (BPS). Tomatoes have become a staple for the Indonesian population. However, tomato productivity has not kept pace with technological advancements, particularly in the sorting of ripeness, which is still done manually. The process of sorting tomatoes by ripeness considering color, firmness, and weight requires considerable time and cost. This sorting is still performed by market traders who often face difficulties as it demands accuracy and time. To address this issue, the author proposes a solution by designing and building an automatic tomato ripeness sorting device based on machine learning. This design aims to facilitate traders' work by sorting tomatoes based on quality. The tomato ripeness sorter will be designed using Arduino UNO, Raspberry Pi, and a Convolutional Neural Network (CNN) algorithm. This model demonstrates good performance, with precision, accuracy, and F1-score metrics exceeding 90% across four classes: raw, semi-ripe, ripe, and rotten. From the tool's test results, the system has successfully sorted tomatoes 80 times with a success rate of 95%. Out of 80 tomatoes tested, 76 were correctly sorted, while only 4 were incorrectly sorted. This solution is expected to improve the efficiency and accuracy of the tomato sorting process, reduce traders' workload, and enhance the quality of products reaching consumers.

Item Type:	Thesis (Skripsi)
Additional Information:	[No.Panggil: 1910314035] [Pembimbing: Achmad Zuchriadi P.] [Penguji 1: Ferdyanto] [Penguji 2: Yosy Rahmawati Hamid]
Uncontrolled Keywords:	Sorting Machine, Tomato Ripeness, Arduino UNO, Raspberry Pi, Machine Learning, Convolutional Neural Network
Subjects:	T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User:	JUAN PATRICK
Date Deposited:	03 Sep 2024 03:37
Last Modified:	03 Sep 2024 03:37
URI:	http://repository.upnvj.ac.id/id/eprint/32564

Actions (login required)

View Item