Claim Missing Document
Check
Articles

Found 2 Documents
Search

Real-Time Eggplant Leaf Disease Diagnosis Using Image Classification Abu Tholib; Moh Ainol Yaqin
JOKI: Jurnal Komputasi dan Informatika Vol 3 No 1 (2026): June 2026
Publisher : CV. Laskar Karya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65678/joki.v3i1.378

Abstract

Eggplant is an important horticultural crop whose productivity is often affected by various leaf diseases that reduce crop quality and yield. Manual identification of plant diseases relies heavily on human observation and experience, making it time-consuming and prone to misclassification, especially when symptoms appear visually similar. The system employed a convolutional neural network/transfer learning model to identify eggplant leaf diseases accurately and efficiently. The system utilizes a deep learning model trained on a dataset of 3,551 leaf images categorized into seven disease classes and one healthy class. Image preprocessing and augmentation techniques were applied to improve model performance and generalization. Experimental evaluation showed that the proposed model achieved a testing accuracy of approximately 82% with balanced precision and recall across all categories, indicating stable classification performance. The trained model was integrated into a web-based application that allows users to upload leaf images and obtain real-time diagnostic results along with recommended handling information. The findings demonstrate that the proposed system provides a practical and reliable solution for early disease detection and supports more efficient agricultural management. Future development may include expanding dataset diversity, improving model robustness, and deploying mobile-based applications to enhance accessibility and scalability in precision agriculture.
When the project ends: institutional ownership and the long-term sustainability of university–community partnerships in Indonesia Abu Tholib
Indonesian Journal of Applied Community Research Vol. 1 No. 2 (2026): Co-creation, community resilience, and just transitions in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijac.v1i2.940

Abstract

Background: Post-project sustainability remains a persistent problem in university–community partnerships, especially in post-disaster settings such as Candipuro, Lumajang, where BNPB recorded 10,395 displaced persons across 410 evacuation points after the Semeru eruption. Objective: This community engagement program aimed to strengthen institutional ownership among 40 eligible local actors from village institutions, relocation representatives, volunteers, schools, women’s groups, youth representatives, and livelihood groups in Sumbermujur and Sumberwuluh. Method: The method integrated planning, implementation, and monitoring-evaluation through needs assessment, pre-post questionnaires, observation checklists, product rubrics, FGD guides, attendance records, and partner validation forms. Results: During planning, this program conducted three coordination meetings, recorded 42 needs assessment responses, mapped six stakeholder groups, and prepared five evaluation instruments. During implementation, this program delivered one orientation, three core training sessions, eight weeks of mentoring, two peer discussion forums, and recorded 70% practice-output completion. Implication: During monitoring-evaluation, this program recorded 82% attendance, 70% acceptable outputs, a 20-point pre-post capacity score increase, two validation forums, one institutional follow-up plan, and a 3–6 month monitoring agreement. Novelty: The novelty of this program lies in integrating data-based planning, practice-oriented mentoring, participatory validation, and institutional follow-up as a measurable model for sustaining university–community partnerships after project completion.