Fadhilnor Abdullah
Thumbnail Image
Preferred name
Fadhilnor Abdullah
Official Name
Fadhilnor, Abdullah
Alternative Name
Abdullah, Fadhilnor
Abdullah, F.
Main Affiliation
Scopus Author ID
57951617900
Researcher ID
GSD-4300-2022

Research Output

Filters

2
2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    AI Assisted and IOT Based Fertilizer Mixing System
    (Universiti Malaysia Perlis, 2024-06-03)
    Wan Mohd Faizal Wan Nik
    ;
    Shahrul Fazly Man@Sulaiman
    ;
    Muhammad Imran Ahmad
    ;
    Shafie Omar
    ;
    Tan Shie Chow
    ;
    Mohd Nazri Abu Bakar
    ;
    Fadhilnor Abdullah
    ;
    Muhammad Khamil Akbar
    Agriculture techniques, particularly fertilizer mixing, have significant impacts on crop productivity. Introducing IoT technology to agriculture can enhance productivity, and machine learning offers a mechanism to gain insights from data, making agricultural practices more efficient. This research aims to design an AI-assisted and IoT-based fertilizer mixing system for greenhouses. This system utilizes sensor data and AI algorithms, specifically the Support Vector Machine (SVM), to optimize fertilizer application. Results from the SVM classifier showed a 100% accuracy rate for temperature and humidity, 65% accuracy for phosphorus, 86% for nitrogen, and 100% for potassium. These findings demonstrate the potential of the proposed system to improve fertilizer efficiency while reducing labor and resource waste.
  • Publication
    Plant Disease Classification Using Image Processing Technique
    (Universiti Malaysia Perlis, 2024-06-03)
    Shahrul Fazly Man@Sulaiman
    ;
    Shafie Omar
    ;
    Muhammad Imran Ahmad
    ;
    Wan Mohd Faizal Wan Nik
    ;
    Tan Shie Chow
    ;
    Mohd Nazri Abu Bakar
    ;
    Fadhilnor Abdullah
    ;
    Asbhir Yuusuf Omar
    Agriculture remains pivotal to our economy, with farming playing a central role in revenue generation. Challenges such as pests, plant diseases, and evolving climate patterns pose threats to crop yield and production. Addressing these challenges, timely and accurate detection of plant diseases emerges as imperative. Manual detection, however, remains resource-intensive and often lags. Addressing this gap, this project proposes an innovative image processing-based system for rapidly detecting plant diseases. The system proficiently identifies specific diseases by analyzing images of plant leaves against a curated dataset. The emphasis of this study was on three major diseases: Bacterial Blight (with an accuracy of 98.6%), Alternaria Alternata (98.5714%), and Cercospora Leaf Spot (97.5%). The compelling results underline the system's capacity to swiftly and effectively categorize diseases, offering monoculture farmers an indispensable tool for obtaining prompt, disease-specific insights.
      5  1