Deteksi Jenis Penyakit Dan Hama Pada Tanaman Jagung Menggunakan Arsitektur Spatial Pyramid Pooling Pada YOLOv5s

M Mira(1*), Listra Firgia(2), Shanti Thomas(3),

(1) Institut Shanti Bhuana, Indonesia
(2) Institut Shanti Bhuana, Indonesia
(3) Institut Shanti Bhuana, Indonesia
(*) Corresponding Author


Corn is one of the important crops in the agricultural sector in the global and national economy because it is a food resource as food, animal feed and other raw materials for the community. Based on, the projected corn production in 2020-2024 will still increase between 0.94% and 0.97% per year. In this study, detection of diseases and pests in maize was carried out using YOLO technology with spatial pyramid pooling (SPP) architecture as a form of intelligent innovation in maize farming. The research data consisted of 309 image data with class values as labels representing types of disease and types of pests in corn plants consisting of Locusta (Locust), Sitophilus (Powder Flower), Spodoptera (Arrayworm), Mysus Persicase (Aphids), and Bulai . The indicators for testing and evaluating the model use precision, recall, f1 score, mAP0.5 and Map0.5:0.95 as evaluation metrics. Based on the results of training and evaluation of the model, it is known that the precision value with batch size 32 epoch 64 produces a precision value of 0.65, recall, 0.76, f1 score 0.65 Map0.5 0.704 and Map-.5:0.95 0.298. Whereas with a batch size of 64 epoch 100 the precision value is 0.73, the recall is 0.77 f1 score is 0.73 Map0.5 0.795 and Map0.5:0.95 0.346. Model predictions using YOLO technology with spatial pyramid pooling architecture in detecting types of diseases and pests in corn plants contribute to smart agriculture. With accurate information about the types of diseases and pests that attack corn plants, farmers can respond quickly and take appropriate actions, such as using specific pesticides or suitable organic control methods.

Full Text:



Nurhidayati and I. Marzuki, “Deteksi Otomatis Penyakit Daun Jagung Menggunakan Teknik Klasterisasi Data dan Operasi Morfologi,” Energy-Jurnal Ilm. Ilmu-Ilmu Tek., vol. 10, no. 1, pp. 1–6, 2020, [Online]. Available:

I. Syahriani, C. Evelyn, D. Istiqomah, E. Noviyanti, H. Adila, and R. Putri, “Identifikasi Penyakit pada Batang Tanaman Jagung ( Zea Mays ) di Kecamatan Panyabungan Kabupaten Mandailing Natal, Sumatera Utara,” J. Biodjati, vol. 2, no. 2, pp. 325–332, 2021.

Y. Kang, N. Cho, J. Yoon, S. Park, and J. Kim, “Transfer learning of a deep learning model for exploring tourists’ urban image using geotagged photos,” ISPRS Int. J. Geo-Information, vol. 10, no. 3, 2021, doi: 10.3390/ijgi10030137.

K. Kristiawan, D. D. Somali, T. A. Linggan jaya, and A. Widjaja, “Deteksi Buah Menggunakan Supervised Learning dan Ekstraksi Fitur untuk Pemeriksa Harga,” J. Tek. Inform. dan Sist. Inf., vol. 6, no. 3, pp. 541–548, 2020, doi: 10.28932/jutisi.v6i3.3029.

K. A. Baihaqi and Y. Cahyana, “Application of Convolution Neural Network Algorithm for Rice Type Detection Using Yolo v3,” Systematics, vol. 3, no. 2, pp. 272–280, 2021.

S. S. Bhoomika and K. M. Poornima, “Plant Leaf Disease Detection and Classification Using Deep Learning Technique BT - Intelligent System Design,” 2023, pp. 73–83.

A. Etienne, A. Ahmad, V. Aggarwal, and D. Saraswat, “Deep learning-based object detection system for identifying weeds using uas imagery,” Remote Sens., vol. 13, no. 24, pp. 1–22, 2021, doi: 10.3390/rs13245182.

Z. Zhou, “Detection and Counting Method of Pigs Based on YOLOV5_Plus: A Combination of YOLOV5 and Attention Mechanism,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/7078670.

M. Mira, I. Sembiring, and H. D. Purnomo, “Implementasi Transfer Learning Pada Algoritma Convolutional Neural Network untuk Mengklasifikasikan Image Objek Wisata,” Build. Informatics, Technol. Sci., vol. 4, no. 1, pp. 209–216, 2022, doi: 10.47065/bits.v4i1.1764.

M. Dio, R. Pratama, B. Priyatna, S. Shofiah, and A. Lia, “Deteksi Objek Kecelakaan Pada Kendaraan Roda Empat Menggunakan Algoritma YOLOv5 Car Vehicle Accident Object Detection Using YOLOv5 Algorithm,” vol. 12, no. 2, pp. 15–24, 2022.

X. Zhang, W. Wang, Y. Zhao, and H. Xie, “An improved YOLOv3 model based on skipping connections and spatial pyramid pooling,” Syst. Sci. Control Eng., vol. 9, no. S1, pp. 142–149, 2021, doi: 10.1080/21642583.2020.1824132.

C. Dewi, R. C. Chen, and S. K. Tai, “Evaluation of robust spatial pyramid pooling based on convolutional neural network for traffic sign recognition system,” Electron., vol. 9, no. 6, 2020, doi: 10.3390/electronics9060889.




  • There are currently no refbacks.

JURASIK (Jurnal Riset Sistem Informasi dan Teknik Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan : View My Stats