Design and Development of a Hybrid Knowledge-Based System for Pest Control Methods and Tomato Disease Diagnosis in Gamo Zone, Ethiopia

Show simple item record

dc.contributor.author Wubet Mada
dc.date.accessioned 2025-10-20T13:33:31Z
dc.date.available 2025-10-20T13:33:31Z
dc.date.issued 2005-05
dc.identifier.uri http://hdl.handle.net/123456789/2496
dc.description.abstract Tomato production is a critical component of Ethiopia's agricultural sector, particularly in the Gamo Zone, where smallholder farmers face significant challenges in managing pests and diseases. Despite the economic importance of tomatoes, farmers often lack access to expert knowledge and reliable information, which hinders effective management strategies. Previous research has highlighted the limitations of traditional pest control methods that rely on manual expertise and insufficient resources, creating a pressing need for innovative solutions. This study addresses the gap in localized knowledge and seeks to provide farmers with timely and accurate pest and disease management strategies. This study aimed to design, develop, and evaluate a Knowledge-Based System (KBS) that facilitates pest control methods and tomato disease diagnosis in the Gamo Zone. The research employed a Design Science Research approach, the study utilized mixed methods (interviews, questionnaires, expert consultations) to acquire knowledge. The developed TPCMDD KBS uniquely integrated explicit rule-based reasoning (SWI-Prolog) with data-driven machine learning (Python Random Forest) for diagnosis. The resulting prototype successfully diagnoses 15 key local tomato diseases and 8 pests, providing tailored control recommendations. User Acceptance Testing (UAT) involving 64 diverse stakeholders demonstrated high system usability (96%), efficiency (94%), and strong perceived accuracy (94% positive rating). The integration of machine learning, achieving high objective accuracy (96% on test data), significantly enhanced the system's diagnostic capabilities. Participants reported that the KBS significantly enhanced their ability to make informed pest and disease management decisions. The findings indicate that the hybrid TPCMDD KBS is a valuable and effective tool for addressing the challenges of pest and disease management in tomato production in the Gamo Zone. By bridging the gap between expert knowledge and practical application through this innovative hybrid approach, the KBS contributes to improved agricultural practices and has the potential to enhance food security in the region en_US
dc.language.iso en en_US
dc.subject Disease diagnosis, Knowledge-Based System, Machine Learning, Pest Control,Rule-Based Reasoning en_US
dc.title Design and Development of a Hybrid Knowledge-Based System for Pest Control Methods and Tomato Disease Diagnosis in Gamo Zone, Ethiopia en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search AMU IR


Advanced Search

Browse

My Account