Penerapan Algoritma Convolutional Neural Network Dan Arsitektur MobileNet Pada Aplikasi Deteksi Penyakit Daun Padi

Saputra, Rizal Amegia; Wasiyanti, Sri; Supriyatna, Adi; Saefudin, Dede Firmansyah

doi:10.31294/swabumi.v9i2.11678

Cited by 11 publications

(16 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Research conducted by Rizal Amegia Saputra, et al This research is based on the background of several rice leaf diseases that can cause a high risk of crop failure and a decrease in food value, so the authors developed a rice leaf disease detection application by applying the CNN algorithm and MobileNet architecture with feature extraction and feature map. The author's classification results produce very good accuracy with an accuracy value of 92% but with a small amount of data and the use of 100 epochs, which results in a higher validation error value than the error value during training, so the process will experience overfitting (Saputra et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

Faqih,

Irsan,

Fathoni

2024

SinkrOn

View full text Add to dashboard Cite

In this study, we address that foliar diseases of rice (Oryza sativa L.) pose a serious threat to agricultural productivity and propose an effective method for disease detection using Convolutional Neural Network (CNN). We use transfer learning on the MobilenetV3Large model to improve the model's performance. Our study involves a curated dataset containing images of infected rice leaves, followed by a careful preprocessing step. This dataset is then used to train a CNN model. The results show a commendable accuracy rate of over 90% and almost reaching 95% when the model is trained over 200 epochs. The model performance graph shows a consistent upward trend in accuracy coupled with decreasing loss during the training process. Furthermore, the classification results highlight the ability of the model to discriminate between different types of diseases affecting rice leaves. This study demonstrates the effectiveness of our proposed method and positions it as a valuable tool for leaf disease detection in rice. By providing faster and more accurate control measures, our approach has the potential to significantly improve agricultural productivity. The successful application of the CNN model using MobilenetV3Large highlights its adaptability and robust performance in addressing the pressing problem of rice leaf diseases and provides a promising path for future advances in precision agriculture.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

Faqih,

Irsan,

Fathoni

2024

SinkrOn

View full text Add to dashboard Cite

show abstract

“…Upaya proses identifikasi sejak dini gagal panen telah dilakukan melalui pemanfaatan teknologi komputasi. Cuplikan gambar berbagai penyakit daun padi diolah dengan reakyasa komputasi Convolutional Neural Network (CNN) [2] [3], Support Vector Mechine (SVM) [4], dan Gray level co-occurrence matrice (GLCM) [5].…”

Section: Pendahuluanunclassified

“…Algoritma GLCM memiliki kemampuan mengenali ciri sebuah citra dan telah digunakan pada banyak bidang. Ekstraksi ciri menggunakan GLCM dilakukan pada daging [6], bunga, tanaman [7] [8], buah [9] [10] dan padi [2]- [5], [11], [12].…”

Section: Pendahuluanunclassified

Implementasi Gray Level Co-Occurrence Matrix (GLCM) Untuk Klasifikasi Penyakit Daun Padi

Setiaji

Huda²

2022

pseudocode

View full text Add to dashboard Cite

Penyakit pada tanaman padi merupakan salah satu faktor yang menyebabkan turunnya tingkat produksi padi. Penyakit tersebut adalah bacterial leaf blight, leaf smut, brown spot dan sebagainya. Upaya identifikasi sejak dini penyakit tanaman padi dilakukan dengan pemanfaatan algoritma, salah satunya GLCM dan klasifikasi KNN. Identifikasi jenis penyakit menggunakan metode klasifikasi KNN berdasarkan eksktraksi fitur GLCM dengan mengubah citra asli menjadi citra keabuabuan (grayscale). Setelah citra asli tersebut diubah menjadi citra keabu-abuan (grayscale), kemudian diekstraksi menggunakan GLCM untuk mendapatkan ekstraksi nilai ciri. Digunakan metode KNN untuk mengelompokkan jenis kemiripan penyakit. Data yang digunakan sebanyak 240 gambar diperoleh dari UCI Machine Learning Repository yang terdiri atas 3 jenis penyakit padi. Sebanyak 210 gambar sebagai data training dan 30 gambar lainnya untuk data uji. Hasil penenlitian ini setelah dilakukan 2 kali proses uji, tingkat akurasi tertinggi yang didapatkan sebesar 93,3%. Kata Kunci: penyakit daun padi, klasifikasi, GLCM, KNN.

show abstract

“…Penggunaan metode up selling pada aplikasi ecommerce menyediakan fasilistas bagi konsumen untuk dapat memilih barang yang sesuai dengan kebutuhan dan dapat merekomendasikan barang yang serupa dengan barang yang akan dibeli kepada calon pembeli menjadi lebih tepat [5]. Penerapan metode up selling dapat meningkatkan jumlah transaksi penjualan songket serta memperluas segmentasi customer dan area penjualan dan dapat menampilkan informasi produk sesuai dengan kebutuhan customer dan menampilkan strategi penawaran up selling secara otomatis berdasarkan karakteristik produk yang akan dibeli [6].…”

Section: Pendahuluanunclassified

Rekayasa Sistem Informasi Penjualan Suku Cadang Menggunakan Metode Up Selling

Lubis¹,

Aisyah²,

Rismayenti³

et al. 2022

komtekinfo

View full text Add to dashboard Cite

Technological advances are always developing, especially in the field of utilizing computers both in terms of hardware and software. The use of technology in sales activities is expected to increase the number of sales and profits. Fauzan Motor store in its business activities still does not have an integrated system so that in running its business there are still many shortcomings such as the slow delivery of new products to customers, so that customers are only glued to one product. Lack of information obtained by customers causes low sales. Mala conducted this research for the Fauzan Motor store in increasing sales using the up selling method. The system built is a computerized sales system development. The system works by comparing the product that has been selected by the customer with similar products, such as a brand, category with a higher price and quality, one level above the product chosen by the customer. Sales information system development technique using the System Development Life Cycle (SDLC). The programming language used is PHP 7 which is based on Object Oriented Programming (OOP) and JavaScript. Structuring objects using Bootstrap 5 on web pages to make them more informative. This research produces a sales application system that can increase sales turnover. Each customer is given recommendations for several available products so that consumers can choose products according to quality and affordable prices. So this research is very helpful in increasing sales and is more effective in increasing store revenue.

show abstract

Penerapan Algoritma Convolutional Neural Network Dan Arsitektur MobileNet Pada Aplikasi Deteksi Penyakit Daun Padi

Cited by 11 publications

References 4 publications

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

Implementasi Gray Level Co-Occurrence Matrix (GLCM) Untuk Klasifikasi Penyakit Daun Padi

Rekayasa Sistem Informasi Penjualan Suku Cadang Menggunakan Metode Up Selling

Contact Info

Product

Resources

About