DEEP LEARNING FOR ASSESSING HEALTHY LETTUCE HYDROPONIC USING CONVOLUTIONAL NEURAL NETWORK (CNN) BASED ON FASTER R-CNN WITH INCEPTION V2

Pratama, Ichsan Yudha (2020) DEEP LEARNING FOR ASSESSING HEALTHY LETTUCE HYDROPONIC USING CONVOLUTIONAL NEURAL NETWORK (CNN) BASED ON FASTER R-CNN WITH INCEPTION V2. S2 thesis, Universitas Mercu Buana - Menteng.

	Text (COVER) 55416120012-ICHSAN YUDHA PRATAMA-01 COVER - Ichsan Pratama (Ichsan).pdf Download (462kB)
	Text (BAB I) 55416120012-ICHSAN YUDHA PRATAMA-02 BAB 1 - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (437kB)
	Text (BAB II) 55416120012-ICHSAN YUDHA PRATAMA-03 BAB 2 - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (908kB)
	Text (BAB III) 55416120012-ICHSAN YUDHA PRATAMA-04 BAB 3 - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (1MB)
	Text (BAB IV) 55416120012-ICHSAN YUDHA PRATAMA-05 BAB 4 - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (2MB)
	Text (BAB V) 55416120012-ICHSAN YUDHA PRATAMA-06 BAB 5 - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (219kB)
	Text (DAFTAR PUSTAKA) 55416120012-ICHSAN YUDHA PRATAMA-07 DAFTAR PUSTAKA - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (762kB)
	Text (LAMPIRAN) 55416120012-ICHSAN YUDHA PRATAMA-08 LAMPIRAN - Ichsan Pratama (Ichsan).pdf Restricted to Registered users only Download (1MB)

Abstract

Sistem pertanian hidroponik merupakan pengembangan dari sistem pertanian konvensional dimana memanfaatkan media tanam alternatif untuk mengatasi keterbatasan lahan[1]. Sayuran hidroponik jenis Lettuce atau selada, merupakan sayuran yang populer dipasaran. Namun dalam proses panennya, terdapat kendala yang sering dihadapi yaitu terkait dengan kualitas produk yang diakibatkan oleh penyakit. Penelitian ini, berfokus pada fase sortir produk pertanian hidroponik sebelum dipasarkan kepada konsumen dengan memanfaatkan Deep Learning sebagai teknologi deteksi penyakit pada sayuran hidroponik jenis Lettuce dengan memanfaatkan algoritma Faster R-CNN dengan Inception V2, dengan membandingkan rasio training dan validasi dalam 3 kategori yaitu 78/9, 70/17 dan 61/26 dengan rasio testing standar pada semua kriteria adalah 13%. Dimana dari penelitian yang dilakukan, diketahui bahwa rasio testing dan validasi 78/9 memiliki tingkat Accuracy 70%; Precision 97%; Recall 68% dan F1 Score 80% sedangkan rasio 61/26 memiliki performa paling rendah dengan Accuracy 40%; Precision 24%; Recall 100% dan F1 Score 38,5% yang diperoleh dari 412 citra dataset dengan 53 testing citra. Sehingga diketahui bahwa rasio dataset training dan validasi dapat mempengaruhi performa model pada deep learning. The hydroponic system is a development of traditional farming that substitute soil as a medium plant as a modern solution due to land limitation [1]. Lettuce is the most popular hydroponic vegetable product in the market. However, during harvesting, there are huge challenges to ensure product quality especially for mass production has a better quality. In this research, we utilized Deep Learning as detection technology to recognize the disease in Hydroponic vegetables by using Faster R-CNN with Inception V2 algorithm and compare the performance by divided the ratio of training and validation dataset into 3 categories i.e 78/9, 70/17 and 61/26 with the standard testing ratio for all categories is 13%. From this study we obtain a result that ratio 78/9 have a better performance with Accuracy 70%; Precision 97%; Recall 68% and F1 Score 80% however, ratio 61/26 has the lowest performance with Accuracy 40%; Precision 24%; Recall 100% and F1 Score 38,5% from 412 images dataset with 53 testing images. As the result shown that the testing and validation ratio affected the deep learning model performances.

Item Type:	Thesis (S2)
NIM/NIDN Creators:	55416120012
Uncontrolled Keywords:	Deep Learning, Hidroponik Faster R-CNN Inception V2, Kualitas Produk, Pertanian Pintar, Deteksi Objek, Agrikultur Deep Learning, Hydroponic, Faster R-CNN Inception V2, Product Quality, Smart Farming, Object Detection, Agriculture
Subjects:	600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan
Divisions:	Pascasarjana > Magister Teknik Elektro
Depositing User:	SILMI KAFFA MARISKA
Date Deposited:	21 Oct 2024 04:11
Last Modified:	21 Oct 2024 04:11
URI:	http://repository.mercubuana.ac.id/id/eprint/92635

Actions (login required)

View Item