DESAIN SISTEM DETEKSI PENYAKIT AYAM BROILER MENGGUNAKAN ALGORITMA LONG SHORT TERM MEMORY BERBASIS WEBSITE

Maulidia Sita Aswatun Anjani, - and Galura Muhammad Suranegara, - and Ichwan Nul Ichsan, - (2025) DESAIN SISTEM DETEKSI PENYAKIT AYAM BROILER MENGGUNAKAN ALGORITMA LONG SHORT TERM MEMORY BERBASIS WEBSITE. S1 thesis, Universitas Pendidikan Indonesia.

Abstract

Penyakit pada ayam broiler menjadi tantangan serius karena dapat menyebabkan kerugian besar. Deteksi yang masih konvensional rentan terhadap kesalahan manusia dan keterlambatan dalam identifikasi. Penelitian ini bertujuan mengembangkan sistem deteksi penyakit ayam broiler berbasis website menggunakan algoritma Long Short Term Memory (LSTM). Sistem ini dirancang untuk membantu peternak dalam mengidentifikasi penyakit secara lebih cepat dan akurat. Metode pengembangan yang digunakan adalah Agile Software Development Life Cycle (SDLC). Sistem menerima input 36 gejala dalam bentuk biner yang diproses secara berurutan untuk menghasilkan prediksi penyakit. Model dilatih menggunakan PyTorch dengan dataset gejala pada ayam broiler yang telah divalidasi oleh dokter hewan. Hasil prediksi mencakup nama dan deskripsi penyakit. Sistem dibangun dengan Python, HTML, CSS, framework Flask, dan terintegrasi dengan database MYSQL. Pengujian dilakukan menggunakan blackbox testing dan user acceptance test. Model menghasilkan akurasi 99,57%, precision 100%, recall 100%, dan f-1 score 100%. : ----- Broiler chicken diseases pose a serious challenge as they can cause significant losses. Conventional detection methods are prone to human error and delays in identification. This study aims to develop a web-based broiler chicken disease detection system using the Long Short Term Memory (LSTM) algorithm. The system is designed to helm farmers identify diseases more quickly and accurately. The development method used is the Agile Software Development Life Cycle (SDLC). The system receives 36 symptoms as binary inputs, which are processed sequentially to generate disease predictions. The model is trained using PyTorch with a dataset of symptoms to generate disease predictions. The model is trained using PyTorch with a dataset of broiler chicken symptoms validated by a veterinarian. The prediction results include the name and description of the disease. The system was built using Python, HTML,CSS, the Flask Framework, and with a MySQL database. Testing was conducted using blackbox testing and user acceptance testing. The model achieved an accuracy of 99.57%, precision of 100%, recall of 100% and f-1 score of 100%.

	Text S_SISTEL_2101246_Title.pdf Download (1MB)
	Text S_SISTEL_2101246_Chapter1.pdf Download (677kB)
	Text S_SISTEL_2101246_Chapter2.pdf Restricted to Staf Perpustakaan Download (931kB)
	Text S_SISTEL_2101246_Chapter3.pdf Download (1MB)
	Text S_SISTEL_2101246_Chapter4.pdf Restricted to Staf Perpustakaan Download (2MB)
	Text S_SISTEL_2101246_Chapter5.pdf Download (657kB)
	Text S_SISTEL_2101246_Appendix.pdf Restricted to Staf Perpustakaan Download (5MB)

Item Type:	Thesis (S1)
Additional Information:	https://scholar.google.com/citations?view_op=list_works&hl=id&user=CjwNd9AAAAAJ SINTA ID Dosen Pembimbing Galura Muhammad Suranegara: 6703764 Ichwan Nul Ichsan: 6721201
Uncontrolled Keywords:	LSTM, penyakit ayam broiler, website, gejala, Flask broiler chicken diseases, website, symptoms, Flask
Subjects:	T Technology > T Technology (General)
Divisions:	UPI Kampus Purwakarta > S1 Sistem Telekomunikasi
Depositing User:	Maulidia Sita Aswatun Anjani
Date Deposited:	20 Aug 2025 07:29
Last Modified:	20 Aug 2025 07:29
URI:	http://repository.upi.edu/id/eprint/135725

Actions (login required)

View Item