Klasifikasi Ayam Sehat Dan Sakit Snot Serta Kolera Menggunakan Kamera Dengan Metode Convolutional Neural Network Berbasis Internet of Things (IoT)

Fabianus, Nathanael Axlandro Nesta (2025) Klasifikasi Ayam Sehat Dan Sakit Snot Serta Kolera Menggunakan Kamera Dengan Metode Convolutional Neural Network Berbasis Internet of Things (IoT). Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 2042211080-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Penelitian ini mengembangkan sistem berbasis Convolutional Neural Network (CNN) yang terintegrasi dengan teknologi Internet of Things (IoT) untuk mengklasifikasikan kesehatan ayam menjadi kategori sehat, sakit snot, atau sakit kolera. Sistem ini memanfaatkan citra visual yang diambil dengan kamera dan dikirim melalui perangkat Raspberry Pi ke server cloud, di mana data diproses menggunakan teknik preprocessing seperti cropping, grayscaling, dan edge detection. Hasil evaluasi menunjukkan bahwa CNN memiliki akurasi tertinggi sebesar 86,13%, mengungguli Ensemble Model (82,47%) dan Naive Bayes (77,83%). CNN juga mencatat nilai F1-Score dan Recall tertinggi, masing-masing sebesar 0,8507 dan 0,8521. Teknik augmentasi data berhasil meningkatkan kualitas dataset dan mencegah overfitting. Sistem ini memungkinkan pemantauan kesehatan ayam secara real-time melalui aplikasi seluler, memberikan peringatan dini kepada peternak, dan menawarkan solusi inovatif untuk meningkatkan produktivitas serta efisiensi pengelolaan kesehatan unggas.
=========================================================================================================================================
This research develops a Convolutional Neural Network (CNN)-based system integrated with Internet of Things (IoT) technology to classify chicken health into healthy, snot, or cholera categories. The system utilizes visual images taken with a camera and sent through a Raspberry Pi device to a cloud server, where the data is processed using preprocessing techniques such as cropping, grayscaling, and edge detection. The evaluation results show that CNN has the highest accuracy of 86.13%, outperforming Ensemble Model (82.47%) and Naive Bayes (77.83%). CNN also recorded the highest F1-Score and Recall values of 0.8507 and 0.8521, respectively. The data augmentation technique successfully improved the quality of the dataset and prevented overfitting. The system enables real-time monitoring of chicken health through a mobile app, provides early warning to farmers, and offers an innovative solution to improve productivity and efficiency of poultry health management.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Klasifikasi ayam sehat, snot, dan kolera, kamera CNN, IoT, Classification of Healthy, Snot, and Cholera Chickens using CNN, Camera, and IoT.
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) S Agriculture > SF Animal culture T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Vocational > Instrumentation Engineering
Depositing User:	Nathanael Axlandro Nesta Fabianus
Date Deposited:	31 Jul 2025 07:40
Last Modified:	31 Jul 2025 07:40
URI:	http://repository.its.ac.id/id/eprint/124961

Actions (login required)

View Item