Integrasi Model AI pada Platform Web Modular Prediksi Penyakit Tanaman dengan Metode Strategy Pattern

dc.contributor.authorPaulus Aditya Wicaksono
dc.date.accessioned2026-05-12T02:35:51Z
dc.date.issued2025-12-19
dc.descriptionFINALISASI oleh Arif 2026 Mei 12
dc.description.abstractArtificial Intelligence, Strategy Design Pattern, Software Architecture, Modular Web Platform, Plant Disease Prediction, FastAPI, CNN, YOLOv5, Vision Transformer, AI Integration, Modular AI System Abstract This research focuses on the development of a modular web-based platform for plant disease prediction through the integration of multiple Artificial Intelligence (AI) models using the Strategy Design Pattern. The study addresses the architectural challenges commonly found in AI systems, particularly tight coupling, low extensibility, and difficulties in integrating or replacing AI models without modifying the core system structure. The proposed system applies the Strategy Design Pattern to separate AI model implementations from the main application logic, enabling dynamic model selection and flexible integration. The platform was developed using a modular architecture with FastAPI as the backend framework and React-based frontend integration. Several AI models, including Convolutional Neural Network (CNN), YOLOv5, and Vision Transformer (ViT), were integrated as independent strategies for plant disease prediction. System evaluation was conducted using formal design pattern metrics, namely Property Satisfaction Rate (PSR), Critical Property Coverage (CPC), and Pattern Implementation Quality Score (PIQS). Additional evaluation was performed at the code-design level through cohesion, coupling, and extensibility analysis. The results indicate that the implementation successfully satisfies the structural and behavioral characteristics of the Strategy Design Pattern, achieving high modularity, maintainability, and extensibility. Furthermore, the platform supports the addition of new AI models without requiring significant changes to the core architecture. This research demonstrates that the Strategy Design Pattern is an effective architectural approach for developing scalable and maintainable AI-based web platforms, particularly for systems requiring multi-model AI integration in digital agriculture applications.
dc.description.sponsorshipDosen Pembimbing Utama : Nelly Oktavia Adiwijaya, S.Si., M.T.,
dc.identifier.urihttps://repository.unej.ac.id/handle/123456789/7268
dc.language.isoother
dc.publisherFakultas Ilmu Komputer
dc.subjectArtificial Intelligence
dc.subjectStrategy Design Pattern
dc.subjectSoftware Architecture
dc.subjectModular Web Platform
dc.subjectPlant Disease Prediction
dc.subjectFastAPI
dc.subjectCNN
dc.subjectYOLOv5
dc.subjectVision Transformer
dc.subjectAI Integration
dc.subjectModular AI System
dc.titleIntegrasi Model AI pada Platform Web Modular Prediksi Penyakit Tanaman dengan Metode Strategy Pattern
dc.typeOther

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Skripsi_222410103052_Paulus_Aditya.pdf
Size:
2.44 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description: