Klasifikasi Penyakit Padi berdasarkan Citra Daun Menggunakan Model Terlatih Resnet101

Oktaviana, Ulfah Nur; Hendrawan, Ricky; Annas, Alfian Dwi Khoirul; Wicaksono, Galih Wasis

doi:10.29207/resti.v5i6.3607

Cited by 4 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another relevant study proved the excellence of ResNet as in the research [12] on the excellence of ResNet101 in classifying rice diseases according to the images of leaves. The test results show that ResNet101 is capable of giving 100% accuracy according to validation data with the loss value representing 5.61% in 120 datasets.…”

Section: Introductionmentioning

confidence: 95%

“…High accuracy does not guarantee accurate classification in each label as in research [12]. This research carries shortcomings in terms of the classification of each image, which may be due to overfitting.…”

Section: Introductionmentioning

confidence: 98%

“…The study [15] asserts that the more features a model has, the more complex the model will be created, allowing for overfitting because the maximum accuracy is reached during the training data process, but during the testing, the accuracy is relatively lower than the accuracy of the training. This research aims to resolve the existing shortcomings in research [12] by lowering the loss value, reducing overfitting, and performing accurate classification according to limited data as done in research [12]. This can be performed by changing the layer structure in the model and replacing compiling types in the model.…”

Section: Introductionmentioning

confidence: 99%

“…The use of more data was also applied in this research. This application was intended to investigate the worthiness of the model made in research [12] and this research to apply more numbers of data…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ResNet101 Model Performance Enhancement in Classifying Rice Diseases with Leaf Images

Wicaksono

Andreawan

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Indonesia is the fourth biggest rice producer in Asia with its production accounting for 35.4 million metric tons yearly. This figure can increase unless rice crop failure is resolved. Identifying rice diseases, however, may serve as an approach to minimizing the risk of crop failure. The classification to detect rice diseases was previously researched using ResNet101 method with 100% accuracy. Despite this perfect accuracy, this approach does not come without an issue, where the prediction is not yet optimal for each label and loss results which are regarded as too high due to overfitting. Departing from this issue, this research aims to improve the model by reducing the layer complexity of the model and comparing two layers structures of the model, two different data, and the ResNet101 model. The performance resulting from the model could be enhanced with the structuring of simple architectural layers. Despite the small quantity of dataset, the model performance can yield 100% accuracy in the classification of rice diseases with a loss value of 2.91%. The model performance in this research experienced a 2.7% increase at the loss value and it could accurately classify the type of rice diseases according to leaf images on each label. The problem solved by this research is that ResNet101 is able to classify rice disease accurately even with a small amount of data by utilizing the appropriate layer arrangement with data requirements. In addition, the overfitting that occurred in previous research can also be resolved properly. This matter proves that the correlation between the layers of the model with the amount of data is very influential.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ResNet101 Model Performance Enhancement in Classifying Rice Diseases with Leaf Images

Wicaksono

Andreawan

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

show abstract

“…Model jst sangat konsisten menggungguli di peringkat 2 dan algortima KNN juga konsisten kinerja baik pada data latih dan data uji akan tetapi masalah overfitting belum terbukti. Pada penelitian selanjutnya [12], penyakit padi diklasifikasikan menjadi tiga jenis berdasarkan foto penyakit daun padi. Tiga jenis penyakit termasuk: hawar daun, coklat bercak, dan penyakit busuk daun.…”

Section: Tinjauan Pustaka 21 Penelitian Terkaitunclassified

Deep Pre-Trained Model Menggunakan Arsitektur Densenet Untuk Identifikasi Penyakit Daun Padi

Faizin

Arsanto

Lutfi

et al. 2022

jati

View full text Add to dashboard Cite

Salah satu penyebab menurunnya produksi padi ialah serangan hama. hama padi meliputi hama busuk daun, hawar daun, dan hawar batang. Jenis penyakit yang berbeda memerlukan perlakuan yang berbeda, akan tetapi tidak semua petani paham akan sifat hama yang dapat menyebabkan kesalahan penanganan.Untuk mempermudah menyelesaikan masalah yang ada pada identifikasi hama penyakit daun padi perlu adanya inovasi sistem klasifikasi hama daun padi. Sistem ini didasarkan pada metode Convolutional Neural Network (CNN), metode atau model deep learning yang dikembangkan untuk meng-cover kelemahan metode machine learning. Namun, deep learning juga memiliki kelemahan yaitu waktu komputasi pada proses training yang sangat lama dan ukuran data besar. Oleh sebab itu model pra-pelatihan dibutuhkan untuk memperbaiki tingkat akurasi dan performance deep-learning serta mempermudah dalam pengembangan struktur model tanpa membangunnya dari awal. Dan pada ini sudah diimplementasikan model yang digunakan menghasilkan tingkat akurasi terbaik 98% dan validasi 93% serta error yang dihasilkan training dan validasi yaitu 0.07 dan 0.25 sedangkan waktu komputasi yang dibutuhkan untuk training dan validasi adalah 31 detik.

show abstract

Implementation of Pretrained VGG16 Model for Rice Leaf Disease Classification using Image Segmentation

Suseno

Minarno²,

Azhar³

2023

KINETIK

View full text Add to dashboard Cite

Rice is an agricultural sector that produces rice which is one of the staple foods for the majority of the population in Indonesia. In the cultivation of rice plants there are also factors that affect rice production and are not realized by farmers causing that they are late in handling and diagnosing symptoms and making rice production decline. Therefore, it is necessary to have an early diagnosis of rice plants to identify them correctly, quickly and accurately. Machine learning is one of the classification techniques to detect various plant diseases such as rice plants. There are several studies on machine learning using the Convolutional Neural Network with the VGG16 model to classify rice leaf diseases and using Image Segmentation techniques on rice leaf datasets for make the image becomes a form that is not too complicated to analyze. The data used in this research is Rice Leaf Disease which consists of 3 classes including Bacterial leaf blight, Brown spot, and Leaf smut. Then segmentation is carried out using two techniques, namely threshold and k means. Then data augmentation for make dataset used has a large and varied number and training using VGG16 model with hyperparameter tuning and obtained 91.66% accuracy results for scenarios with the k-means dataset.

show abstract

Klasifikasi Penyakit Padi berdasarkan Citra Daun Menggunakan Model Terlatih Resnet101

Cited by 4 publications

References 14 publications

ResNet101 Model Performance Enhancement in Classifying Rice Diseases with Leaf Images

ResNet101 Model Performance Enhancement in Classifying Rice Diseases with Leaf Images

Deep Pre-Trained Model Menggunakan Arsitektur Densenet Untuk Identifikasi Penyakit Daun Padi

Implementation of Pretrained VGG16 Model for Rice Leaf Disease Classification using Image Segmentation

Contact Info

Product

Resources

About