MONITORING PERAWATAN BIBIT DURIAN DENGAN TENSOR FLOW TERINTEGRASI CONVOLUTIONAL NEURAL NETWORK

Hendra Saputra, Muhammad Taufiq (2024) MONITORING PERAWATAN BIBIT DURIAN DENGAN TENSOR FLOW TERINTEGRASI CONVOLUTIONAL NEURAL NETWORK. Skripsi (S1) thesis, Universitas Muhammadiyah Ponorogo.

	Text (SURAT PERSETUJUAN UNGGAH KARYA ILMIAH) Doc1.pdf Download (168kB)
	Text (HALAMAN DEPAN) HALAMAN DEPAN.pdf Download (1MB)
	Text (BAB I) BAB I.pdf Download (98kB)
	Text (BAB II) BAB II.pdf Restricted to Repository staff only Download (195kB)
	Text (BAB III) BAB III.pdf Restricted to Repository staff only Download (253kB)
	Text (BAB IV) BAB IV.pdf Restricted to Repository staff only Download (830kB)
	Text (BAB V) BAB V.pdf Restricted to Repository staff only Download (104kB)
	Text (DAFTAR PUSTAKA) DAFTAR PUSTAKA.pdf Download (307kB)
	Text (SKRIPSI FULL) SKRIPSI FULL TEXT.pdf Restricted to Repository staff only Download (3MB)

Abstract

Durian has many types with various taste variations and each type has different taste characteristics. In Indonesia, durian is very popular among the people. Pests and diseases are serious obstacles that need to be anticipated because if they are not addressed early they can be detrimental to farmers. Many durian tree cultivators experience a decline in crop productivity due to pest and disease attacks. Based on the experience of cultivators, several problems that often attack durian trees include stem cancer, leaf spots, peel fungus, tip death, and others. Durian cultivators usually immediately observe the symptoms that appear on durian plants to immediately take action. However, the results of observations by eye produce different perceptions among farmers about what type of disease is attacking. A disease detection system is needed in durian plants that can help farmers or agricultural extension workers in diagnosing pests and diseases in durian beetroot plants automatically, accurately and efficiently. The disease detection system for durian seedlings is a system that uses information and communication technology to identify symptoms, causes and solutions for pests and diseases that attack durian seedlings. One method that can be used to develop a disease detection system for durian seedlings is the CNN TensorFlow method. which is a tensor learning method based on Convolutional Neural Network (CNN) that can utilize pre-trained models. Detection using the TensorFlow CNN method, a disease detection system on durian seeds, can receive input in the form of images of durian seed leaves, then adapt the CNN model that has been trained and produce output in the form of a disease diagnosis. The methodological process begins with collecting data to create a dataset. Data preprocessing using the CNN method: The data processing process uses the Convolutional Neural Network (CNN) method to obtain data that is ready to be used. The end point of the model training process, where predictions will be produced. The implemented CNN model succeeded in achieving an accuracy of 92%, showing good ability in recognizing and classifying various types of stem cancer at 97.83%. %. in durian plant nurseries.

Item Type:	Thesis (Skripsi (S1))
Uncontrolled Keywords:	Durian, Disease, CNN, Tensorflow
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering > Department of Informatic Engineering
Depositing User:	ft . userft
Date Deposited:	12 Sep 2024 04:02
Last Modified:	03 Nov 2025 02:27
URI:	https://eprints.umpo.ac.id/id/eprint/15207

Actions (login required)

View Item