Scholarlink

This research focuses on improving edible flower cultivation in smart greenhouses by integrating agricultural knowledge and advanced control technology. Proven agricultural practices related to crop cultivation provide essential data that serve as a foundation for AI-driven environmental decision-making. To enhance greenhouse management, the study introduces a hybrid controller that combines both static and dynamic timer-based mechanisms. The dynamic component uses AI algorithms trained on datasets that reflect environmental conditions and seasonal patterns in Thailand. These AI-driven insights help optimize environmental parameters through a classification process, which generates tailored datasets for more effective plant management. Before training, effective data preprocessing is applied to ensure high-quality data, allowing for rapid and accurate model development. The resulting classification model, used alongside the controller, achieves 100% accuracy in experimental tests, confirming its ability to monitor and display environmental data with precision. Overall, the algorithm shows strong potential for optimizing environmental conditions, improving greenhouse operations, and advancing the future of smart agriculture.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid Controller for Edible Flowers Using Machine Learning-Based Environmental Control

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anamika Pimpa,
  • Narissara Eiamkanitchat

摘要

This research focuses on improving edible flower cultivation in smart greenhouses by integrating agricultural knowledge and advanced control technology. Proven agricultural practices related to crop cultivation provide essential data that serve as a foundation for AI-driven environmental decision-making. To enhance greenhouse management, the study introduces a hybrid controller that combines both static and dynamic timer-based mechanisms. The dynamic component uses AI algorithms trained on datasets that reflect environmental conditions and seasonal patterns in Thailand. These AI-driven insights help optimize environmental parameters through a classification process, which generates tailored datasets for more effective plant management. Before training, effective data preprocessing is applied to ensure high-quality data, allowing for rapid and accurate model development. The resulting classification model, used alongside the controller, achieves 100% accuracy in experimental tests, confirming its ability to monitor and display environmental data with precision. Overall, the algorithm shows strong potential for optimizing environmental conditions, improving greenhouse operations, and advancing the future of smart agriculture.