Daulima, Mohamad Rizki (2024) KLASIFIKASI KUALITAS TELUR BERDASARKAN KERABANG MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK. Sarjana thesis, Universitas muhammadiyah gorontalo.
|
Text (Abstrak)
ABSTRAK.pdf Download (165kB) |
|
|
Text (BAB I)
BAB I.pdf Download (116kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFTAR PUSTAKA.pdf Download (90kB) |
|
|
Text (Skripsi Mohamad Rizki Daulima)
Skripsi mohamad rizki daulima.pdf Restricted to Repository staff only Download (4MB) |
Abstract
Chicken egg quality plays an important role in the livestock industry and agribusiness, both for producers and consumers.This study aims to develop a classification model of chicken egg quality based on shells using the Convolutional NeuralNetwork (CNN) method. The research data consists of 1520 egg images categorized into three quality classes: Premium,Good, and Poor. The CNN model was designed to extract important features from egg shell images, such as texture, color,and cleanliness. The dataset was divided into training and test data with varying proportions, while the images were processedthrough augmentation techniques to increase data diversity. Training results showed that the model achieved the highestaccuracy of 99.56% on test data with image size parameters of 224x224 pixels and number of epochs of 50. Performanceevaluation using confusion matrix resulted in consistently high precision, recall, and F1-score values in all classes. Thisresearch proves that the CNN method is able to classify the quality of chicken eggs with high accuracy, so it has the potentialto help the livestock industry in the process of automating egg quality assessment.
| Item Type: | Thesis (Sarjana) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Additional Information: | Kualitas telur ayam memainkan peran penting dalam industri peternakan dan agribisnis, baik untuk produsen maupun konsumen. Penelitian ini bertujuan untuk mengembangkan model klasifikasi kualitas telur ayam berdasarkan kerabang dengan menggunakan metode Convolutional Neural Network (CNN). Data penelitian terdiri dari 1520 citra telur yang dikategorikan menjadi tiga kelas kualitas: Premium, Baik, dan Kurang Baik. Model CNN dirancang untuk mengekstraksi fitur-fitur penting dari gambar kerabang telur, seperti tekstur, warna, dan kebersihan. Dataset dibagi menjadi data latih dan uji dengan proporsi yang bervariasi, sedangkan citra diolah melalui teknik augmentasi untuk meningkatkan keberagaman data. Hasil pelatihan menunjukkan bahwa model mencapai akurasi tertinggi sebesar 99,56% pada data pengujian dengan parameter ukuran citra 224x224 piksel dan jumlah epoch 50. Evaluasi kinerja menggunakan confusion matrix menghasilkan nilai precision, recall, dan F1-score yang konsisten tinggi pada semua kelas. Penelitian ini membuktikan bahwa metode CNN mampu mengklasifikasikan kualitas telur ayam dengan akurasi tinggi, sehingga berpotensi membantu industri peternakan dalam proses otomatisasi penilaian kualitas telur. | ||||||||||||
| Uncontrolled Keywords: | Kata Kunci: Kualitas telur ayam, CNN, pengolahan citra digital, augmentasi data, confusion matrix. | ||||||||||||
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science | ||||||||||||
| Depositing User: | Mohamad Rizki Daulima | ||||||||||||
| Date Deposited: | 19 Mar 2025 02:28 | ||||||||||||
| Last Modified: | 19 Mar 2025 02:28 | ||||||||||||
| URI: | http://repository.umgo.ac.id/id/eprint/2768 |
Actions (login required)
![]() |
View Item |
