Development of Corn-Care (Corn Observation and Recovery Through Neural Analysis): Integrating Ai-Based Classification and Recommendation for Enhanced Crop Health Monitoring and Management

This study evaluates the usability, performance, and impact of CORN-CARE, an AI-based system designed to assist corn farmers in crop health monitoring through image classification, assessment, and decision support. Usability testing with eight corn farmers was conducted using the System Usability Scale (SUS), assessing functionality, accuracy, acceptability, and overall system usefulness. The system achieved a SUS score of 76.42, indicating good to excellent usability. Performance metrics showed very satisfactory results in efficiency, classification accuracy, reliability, processing speed, and decision support. Comparative analysis demonstrated that CORN-CARE outperforms traditional manual methods in accuracy, speed, consistency, error reduction, and data management, although some input from human expertise remains valuable for rare cases. User feedback highlighted the system’s intuitive interface and reliable recommendations but identified challenges such as connectivity issues, technical language barriers, and occasional processing delays. Limitations include a small sample size and regional concentration, suggesting a need for wider testing and enhanced features like offline capabilities and simplified language. Overall, CORN-CARE proves to be a reliable, efficient, and user-friendly tool that enhances corn crop management through AI technology, with potential for broader agricultural application pending further development and scalability efforts.