<![CDATA[Background: Indonesia’s aquaculture sector holds vast potential, yet many fish farmers, especially those in remote areas like offshore cages, face limited access to timely fish health services, leading to undetected disease outbreaks, mass fish mortality, and significant economic losses. Contribution: This study introduces Fish Doctor, a scalable platform integrating fish species detection, disease diagnosis, and expert consultation. It bridges the gap between AI-based detection and practical aquaculture needs in developing countries, supporting sustainable practices aligned with SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production). Method: The application was built using Next.js, Express.js, MySQL, and integrates computer vision and expert systems. Its core features include image-based fish species detection using YOLOv11, rule-based disease diagnosis through forward chaining, and an online expert consultation module. Designed as a Progressive Web App (PWA), the system offers offline-first capabilities, enabling its use in low-connectivity environments. Results: The system was evaluated using test datasets of five fish species, achieving an average diagnostic accuracy above 80% and response times of less than 2 seconds per case. Conclusion: The developed platform demonstrates potential for improving early disease detection and reducing reliance on chemical treatments in aquaculture. Future research will involve usability testing with more than 100 fish farmers across multiple provinces to assess scalability and generalizability.]]>
Copyrights © 2025
