Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Panji Maulana
President University
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Enhancing Plant Recommendation through IoT-integrated LLM Systems Panji Maulana; Cutifa Safitri
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 1, February 2026
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i1.2241

Abstract

Over the past decade, artificial intelligence has experienced phenomenally rapid and extensive expansion across a wide range of industries. Alongside these developments, the agricultural sector stands to benefit significantly from the integration of technology. A significant challenge encountered by farmers is selecting the appropriate crop to plant. The selection of crops is influenced by various factors. Despite advancements in agricultural technology, a considerable gap remains in the integration of IoT with large language models (LLM) for delivering context-specific and data-driven plant recommendation. This study evaluates the reliability of plant recommendations produced by Internet of Things (IoT) devices utilizing the Llama 3.2 model. The model leverages real-time environmental data, including soil pH, altitude, and temperature, to recommend appropriate plant. The recommendations from the base model and a fine-tuned model were compared using precision, recall and F1-score metrics, and were further assessed against established agricultural literature on plant compatibility and growth requirements through human evaluation. The results show substantial performance improvements. The proposed approach achieved an AUC value 59% higher than that of the base model. Precision increased by 40%, recall improved by 105%, and the F1 score rose by 80% compared to the base model.
Co-Authors Cutifa Safitri