Implementation of VGG19 Model for Pest Detection on Mustard Leaves

Raden Ronggo Bintang Pratomo Prawirodirjo; Putri  Sahira; Zahra Windi Aulia; Hirzan Fakhrusy  Syakirin; Febriansyah; Budi  Prayitno; Riki Ruli Affandi  Siregar

doi:10.33365/jatika.v6i1.33

Raden Ronggo Bintang Pratomo Prawirodirjo Institut Teknologi PLN
Putri Sahira Institut Teknologi PLN
Zahra Windi Aulia Institut Teknologi PLN
Hirzan Fakhrusy Syakirin Institut Teknologi PLN
Febriansyah Institut Teknologi PLN
Budi Prayitno Institut Teknologi PLN
Riki Ruli Affandi Siregar Institut Teknologi PLN

DOI: https://doi.org/10.33365/jatika.v6i1.33

Keywords: Green mustard, Spodoptera litura, Convolutional Neural Network (CNN), VGG19, automated pesticide sprayer

Abstract

Green mustard is a leading agricultural commodity in Indonesia but often faces pest attacks such as Spodoptera litura, which can reduce productivity by up to 85%. This study aims to develop an automated pesticide sprayer prototype using Convolutional Neural Network (CNN) technology with the VGG19 architecture. The system utilizes Raspberry Pi, Arduino, ESP8266, and a camera to detect pests in real-time and accurately spray pesticides. The dataset used consists of 1,380 images, divided into 10% for testing, 25% for validation, and 75% for training. The model evaluation values for the ‘mustard with pests’ class achieved precision, recall, and F1-Score of 96% each, while for the ‘mustard without pests’ class they were 95% each. In addition, the MAPE (Mean Absolute Percentage Error) value of 4.61% shows that the percentage error of the model prediction is very small. The developed VGG19 model achieved an accuracy of 95% and high efficiency after conversion to the TFLite format, reducing model size by 75.57%. This tool is highly recommended to enhance farmers' work efficiency, reduce excessive pesticide use, and support sustainable agriculture. Its ability to operate autonomously and precisely makes it an ideal solution to assist farmers regarding pest problems.

Downloads

Download data is not yet available.

References

D. A. Firdaus, F. Damayanti, and R. Pratama, "Potensi biofertilizer berbasis mikroorganisme lokal dari limbah batang pisang kepok untuk pertumbuhan sawi hijau," J. BIOSENSE, vol. 5, no. 1, pp. 54–66, 2022, doi:10.35626/biosense.v5i01.1936.

S. Mulyati, "Efektivitas pestisida alami kulit bawang merah terhadap pengendalian hama ulat tritip (*Plutella xylostella*) pada tanaman sayur sawi hijau," J. Nurs. Public Heal., vol. 8, no. 2, pp. 79–86, 2020, doi:10.37676/jnph.v8i2.1190.

H. Rafu, B. Atini, and M. Santiari, "Populasi dan intensitas serangan larva *Spodoptera litura* F. pada tanaman sawi hijau (*Brassica juncea* L.)," J. Sci. Biodiversity, vol. 4, no. 2, pp. 1–5, 2023, doi:10.32938/jsb/vol4ilpp1-5.

M. Bate, "Pengaruh beberapa jenis pestisida nabati terhadap hama ulat grayak (*Spodoptera litura* F.) pada tanaman sawi (*Brassica juncea* L.) di lapangan," Agrica J. Sustain. Dryl. Agric., vol. 12, no. 1, pp. 70–80, 2019, doi:10.37478/agri.v12i1.13.

R. S. Silaban, Azwana, and A. Indrawati, "Efikasi insektisida nabati terhadap mortalitas ulat grayak (Spodoptera litura) pada tanaman sawi (Brassica juncea L.)," J. Nat. Sci., vol. 3, no. 1, pp. 24–40, 2022, doi:10.34007/jonas.v3i1.230.

Oktaviani and N. D. Lestari, "Sosialisasi keamanan aplikasi dan penggunaan pestisida petani tanaman padi," unpublished.

M. W. R. Syawal, A. A. Muayyadi, and A. Mulyana, "Implementasi pengendalian hama dan monitoring pada tanaman terong berbasis Internet of Things," in eProceedings of Engineering, 2022, pp. 3089–3093.

D. A. Pratama, O. Setiani, and Y. H. Darundiati, "Studi literatur: Pengaruh paparan pestisida terhadap gangguan kesehatan petani," J. Ris. Kesehat. Poltekkes Depkes Bandung, vol. 13, no. 1, pp. 160–171, 2021, doi:10.34011/juriskesbdg.v13i1.1840.

E. Yuliani, A. N. Aini, and C. U. Khasanah, "Perbandingan jumlah epoch dan steps per epoch pada convolutional neural network untuk meningkatkan akurasi dalam klasifikasi gambar," J. Inf. Politek. Indonusa Surakarta, vol. 5, no. 3, pp. 23–27, 2019, doi:10.46808/informa.v5i3.140.

Keras, "Keras Applications," [Online]. Available: https://keras.io/api/applications/. [Accessed: Feb. 12, 2025].

Nurliani, M. Ulfi, Saudah, and T. S. P. A. Adyanatalubis, "Implementasi deep learning dengan convolutional neural network untuk tingkat akurasi citra image hama sawi hijau menggunakan Google Colab," Riau J. Comput. Sci., vol. 10, no. 2, pp. 116–125, 2024.

D. Hindarto, N. Afarini, and E. T. E. H, "Comparison efficacy of VGG16 and VGG19 insect classification models," JIKO (J. Inform. dan Komputer), vol. 6, no. 3, pp. 189–195, 2023, doi:10.33387/jiko.v6i3.7008.

N. C. Patil and N. J. Patil, "Lung cancer detection using CNN VGG19+ model," J. Electr. Syst., vol. 20, no. 3, pp. 541–550, 2024.

A. Akram, K. Fayakun, and H. Ramza, "Klasifikasi hama serangga pada pertanian menggunakan metode convolutional neural network," Build. Informatics, Technol. Sci., vol. 5, no. 2, pp. 397–406, 2023, doi:10.47065/bits.v5i2.4063.

A. M. Lesmana, R. P. Fadhillah, and C. Rozikin, "Identifikasi penyakit pada citra daun kentang menggunakan convolutional neural network (CNN)," J. Sains dan Inform., vol. 8, no. 1, pp. 21–30, 2022, doi:10.34128/jsi.v8i1.377.

F. H. Hawari, F. Fadillah, M. R. Alviandi, and T. Arifin, "Klasifikasi penyakit padi menggunakan algoritma CNN (convolutional neural network)," J. RESPONSIF, vol. 4, no. 2, pp. 184–189, 2022, doi:10.51977/jti.v4i2.856.

C. R. Kotta, D. Paseru, and M. Sumampouw, "Implementasi metode convolutional neural network untuk mendeteksi penyakit pada citra daun tomat," J. Pekommas, vol. 7, no. 2, pp. 123–132, 2022, doi:10.56873/jpkm.v7i2.4961.

A. D. P. Wicaksono and A. Amrulloh, "Klasifikasi tingkat kematangan buah pisang Cavendish menggunakan algoritma convolutional neural network model VGG-19," J. Sist. dan Teknol. Inf., vol. 9, no. 2, pp. 107–114, 2023, doi:10.31961/positif.v9i2.1778.