COMPLEX-VALUED NEURAL NETWORK DAN FUZZY INFERENCE SYSTEM PADA DIAGNOSA PENYAKIT DAUN PADI

IRMADHANI, MUTIARA (2025) COMPLEX-VALUED NEURAL NETWORK DAN FUZZY INFERENCE SYSTEM PADA DIAGNOSA PENYAKIT DAUN PADI. Undergraduate thesis, Universitas Pembangunan Nasional “Veteran” Jawa Timur.

	Text (COVER) 21083010079_Cover_Mutiara.pdf Download (1MB)
	Text (BAB I) 21083010079_BAB 1.pdf Download (298kB)
	Text (BAB II) 21083010079_BAB 2.pdf Restricted to Registered users only until 20 June 2028. Download (993kB)
	Text (BAB III) 21083010079_BAB 3.pdf Restricted to Registered users only until 20 June 2028. Download (546kB)
	Text (BAB IV) 21083010079_BAB 4.pdf Restricted to Registered users only until 20 June 2028. Download (5MB)
	Text (BAB V) 21083010079_BAB 5.pdf Download (246kB)
	Text (LAMPIRAN) 21083010079_LAMPIRAN.pdf Restricted to Registered users only until 20 June 2028. Download (128kB)

Abstract

Rice is one of the main food commodities in Indonesia, and the health of rice leaves has a great influence on the level of crop productivity. However, we often face the problem of crop failure caused by disease attacks or outbreaks, either caused by pests or by unfavorable climatic factors. Foliar diseases in rice are a serious challenge in the agricultural sector, affecting crop quality and yield, especially in rice. Control of these diseases requires extensive knowledge so as not to cause adverse impacts on the ecosystem and environment due to errors in diagnosing rice plant diseases. Therefore, identification and classification of rice leaf diseases is a very important step so that farmers can take appropriate preventive measures in maintaining the health of rice plants. This research uses an innovative approach based on Complex-Valued Neural Network and Fuzzy Inference System to diagnose rice leaf diseases. The CVNN model showed superior performance compared to CNN, the CVNN model managed to obtain a very high accuracy of 98% on the test data. Meanwhile, the CNN model recorded an accuracy of 95% on the test data. The FIS model predicted 100% correct accuracy in decision-making, thus strengthening the diagnosis accuracy by including severity values (low, medium, high). This is expected to assist farmers in making more informed decisions regarding rice crop management, as well as reducing the risk of greater damage. Ultimately, this method has the potential to improve successful farm management as well as crop productivity.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Saputra, Wahyu Syaifullah Jauharis	NIDN0725088601	wahyu.s.j.saputra.if@upnjatim.ac.id
Thesis advisor	Idhom, Mohammad	NIDN0010038305	idhom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QA Mathematics > QA76.87 Neural computers

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Mutiara Mutiara Irmadhani

Date Deposited:

20 Jun 2025 08:19

Last Modified:

20 Jun 2025 08:19

URI:

https://repository.upnjatim.ac.id/id/eprint/38830