Year: 2025
Type: article
Abstract: Tobacco is a plantation commodity that is susceptible to pests and diseases, such as Phytophthora nicotianae (lanas disease), Myzus persicae (aphids), or Cercospora nicotianae (leaf spots). Lack of farmer knowledge in identifying early symptoms often leads to inappropriate handling and economic losses. This study aims to develop an expert system based on the Forward Chaining method to diagnose tobacco plant pests and diseases quickly and accurately. Symptom data are collected through field observations and literature and then represented as rule-based knowledge (for example, "IF leaves with yellow spots AND brown spots in the middle THEN Cercospora nicotianae"). The Forward Chaining method makes inferences by matching user input facts (symptoms) to existing rules to reach conclusions. The system was tested using 50 field cases with an accuracy of 85% compared to manual diagnosis by experts.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: hybrid
OpenAlex ID: W4411217292