Klasifikasi Penyakit Daun Tanaman Tomat Menggunakan EfficientFormer

Wihardi, Yaya
Erlangga, Erlangga
Himmah, Amirah Dzatul
Siregar, Herbert

JATIKOM: Jurnal Aplikasi dan Teori Ilmu Komputer
Vol 7, No 2 (2024): September 2024, Jurnal Aplikasi dan Teori Ilmu Komputer (Jatikom)

Tomatoes are crucial crops for Indonesian farmers, but they often suffer from diseases caused by fungi, bacteria, and viruses, leading to potential 40% yield loss. Current methods of spotting these diseases by eye result in costly and ineffective use of pesticides. This study focuses on a new way to classify tomato plant diseases using EfficientFormer. This method aims for high accuracy and fast inference time. The model reached an impressive 92% accuracy and takes just 0.4 seconds to identify diseases. This new approach could help farmers spot tomato plant diseases more accurately and quickly, potentially reducing economic losses and excessive pesticide use in Indonesia.