Article Per Year (5 Year)
p-Index From 2020 - 2025
1.642
P-Index
This Author published in this journals
All Journal Jurnal Pendidikan dan Pembelajaran Khatulistiwa (JPPK) Jurnal Pengajaran MIPA Lembaran Ilmu Kependidikan Jurnal Pengajaran Matematika dan Ilmu Pengetahuan Alam Jurnal Pendidikan Biologi Indonesia Sriwijaya University Learning and Education International Conference BIOSFER : Jurnal Biologi dan Pendidikan Biologi Didaktik : Jurnal Ilmiah PGSD STKIP Subang Jurnal Indonesia Mengabdi Industrial and Domestic Waste Management Kajian Linguistik dan Sastra Journal of Computing Theories and Applications Journal of Community Service (Abdisci) Jurnal Indonesia Mengabdi
Yusuf Ibrahim
Universitas Pasundan
Agriculture, Biological Sciences & Forestry Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Education Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Social Sciences Other

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Computing Theories and Applications

 1 
EDANet: A Novel Architecture Combining Depthwise Separable Convolutions and Hybrid Attention for Efficient Tomato Disease Recognition Ibrahim, Yusuf; O. Momoh, Muyideen; O. Shobowale, Kafayat; Mukhtar Abubakar, Zainab; Yahaya, Basira
Journal of Computing Theories and Applications Vol. 3 No. 2 (2025): in progress
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.14620

Abstract

Tomato crop yields face significant threats from plant diseases, with existing deep learning solutions often computationally prohibitive for resource-constrained agricultural settings; to address this gap, we propose Efficient Disease Attention Network (EDANet), a novel lightweight architecture combining depthwise separable convolutions with hybrid attention mechanisms for efficient Tomato disease recognition. Our approach integrates channel and spatial attention within hierarchical blocks to prioritize symptomatic regions while utilizing depthwise decomposition to reduce parameters to only 104,043 (multiple times smaller than MobileNet and EfficientNet). Evaluated on ten tomato disease classes from PlantVillage, EDANet achieves 97.32% accuracy and exceptional (~1.00) micro-AUC, with perfect recognition of Mosaic virus (100% F1-score) and robust performance on challenging cases like Early blight (93.2% F1) and Target Spot (93.6% F1). The architecture processes 128×128 RGB images in ~23ms on standard CPUs, enabling real-time field diagnostics without GPU dependencies. This work bridges laboratory AI and practical farm deployment by optimizing the accuracy-efficiency tradeoff, providing farmers with an accessible tool for early disease intervention in resource-limited environments.
Co-Authors Abdulazeez, Abdulmalik Abubakar, Muddassiru Ahmad Mulyadi Anisa Rizki Prasasti Annisa Yuliawati Cartono Cartono Cita Tresnawati, Cita Darta, Darta Darta, Darta Dewi Astuti Dheni Harmaen Dheni Harmaen Ernawati, Reni fata, M. Annisul Gian Fitralisma Gurnita Abi Supandi Gurnita Supandi Ida Yayu Nurul Hizqiyah Ikmanda Nugraha Ilah Nurlaelah Jaja Suteja Junai, . Maryadi, Ega Meily Yanti Mimi Halimah Mr. Cartono, Mr. Mukhtar Abubakar, Zainab Musa, Bilyaminu Nia Nurdiani Nurfitriyana, Yanita O. Momoh, Muyideen O. Shobowale, Kafayat Riani, Dini Salammah, Shelly Ika Nur Siti Nuraeni Sumarlam Sumarlam, Sumarlam Trimayanti, Imas Umar, Abdulrazak Uus Toharudin Wanto Rivaie Yahaya, Basira Yahaya, Tajudeen Yanthi, Winda Dwi Yoseph Thomas