Notonegoro, Radityo Hendratmojo Jati
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Identification types of plant using convolutional neural network Notonegoro, Radityo Hendratmojo Jati; Hustinawaty, Hustinawaty
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i6.pp5827-5836

Abstract

Artificial intelligence can be implemented in fields that related to environmental education by providing knowledge for taxonomy which recognize and identify plant species based on its features. The variety of plant species that inhabit in a certain area allows many plant species to be found that look similar so that difficult to distinguish and recognize a particular plant. Convolutional neural network (CNN) often used in object detection, you only look once (YOLO), one of CNN’s object detections, could identify object in real time and obtained good performance and accuracy in several researched. However, no studies have ever identified a plant from its flowers, leaves, and fruits. Therefore, the main object of this paper is identified types of plant with CNN (YOLOv8). The YOLOv8 model with 0.01 learning rate, 32 batch size, stochastic gradient descent (SGD) optimizer obtained highest precision of 69.62% and F1 score of 61.22%, recall of 54.73%, mAP50 and mAP50 – 90 on the training data of 57.61% and 42.49%.
Teknologi AI pada Budidaya Vanili Menuju Pertanian Pintar: Review Notonegoro, Radityo Hendratmojo Jati; Rahayu, Dewi Agushinta; Ikasari, Diana; Kosasih, Rifki
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 2: April 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.132

Abstract

Perkembangan teknologi kecerdasan buatan dan penerapan Deep Learning telah memberikan kemudahan dalam identifikasi objek dengan bantuan mesin. Salah satu pendekatan dalam Deep Learning, yaitu Convolutional Neural Network (CNN), memiliki potensi besar untuk diterapkan di sektor pertanian, khususnya dalam pengelolaan penyakit dan hama pada tanaman. Komoditas vanili pada tahun 2022 mengalami peningkatan permintaan global yang signifikan, namun ekspor vanili Indonesia hanya memenuhi 2,63% dari total ekspor dunia. Salah satu penyebab utama rendahnya ketersediaan vanili adalah serangan penyakit dan hama yang menghambat pertumbuhannya. Penelitian ini bertujuan untuk mengeksplorasi penerapan CNN dalam mengidentifikasi penyakit pada tanaman vanili, yaitu Sclerotium, Fusarium, dan Colletotrichum. Metode yang digunakan adalah pelatihan model CNN untuk mengenali gambar tanaman yang sehat dan yang terinfeksi penyakit. Hasil penelitian menunjukkan bahwa model CNN berhasil mengidentifikasi penyakit dengan akurasi keseluruhan sebesar 71%, mencakup tanaman sehat dan yang terinfeksi penyakit. Temuan ini menunjukkan bahwa teknologi CNN dapat menjadi alat yang efektif dalam mendukung deteksi dini penyakit dan pengelolaan tanaman vanili, serta berpotensi meningkatkan produksi komoditas vanili di Indonesia. Abstract The development of artificial intelligence technology and the application of Deep Learning have made object identification easier with machine assistance. One of the approaches in Deep Learning, namely Convolutional Neural Networks (CNN), holds great potential for application in the agricultural sector, particularly in the management of diseases and pests in plants. In 2022, the global demand for vanilla significantly increased, but Indonesia's vanilla exports only accounted for 2.63% of the world's total vanilla exports. One of the main factors behind the low availability of vanilla is the attack of diseases and pests that hinder its growth. This study aims to explore the application of CNN in identifying diseases in vanilla plants, namely Sclerotium, Fusarium, and Colletotrichum. The method used involves training a CNN model to recognize images of healthy plants and those infected with diseases. The results show that the CNN model successfully identified diseases with an overall accuracy of 71%, including both healthy plants and those affected by disease. These findings suggest that CNN technology can be an effective tool in supporting early disease detection and the management of vanilla plants, with the potential to increase vanilla production in Indonesia.