Sofi, Salsabila Briliana Ananda (2024) Implementasi Sistem Rekomendasi untuk Pengairan dan Pemupukan Otomatis pada Bawang Merah Menggunakan Algoritma LSTM. Other thesis, Institut Teknologi Sepuluh Nopember.
Text
5027201003-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (4MB) | Request a copy |
Abstract
Seiring perkembangan zaman, pertanian bawang merah juga semakin membutuhkan inovasi berbasis teknologi. Tugas akhir ini bertujuan mengembangkan sistem rekomendasi pengairan dan pemupukan bawang merah berbasis Internet of Things (IoT) dan machine learning. Tugas akhir ini melibatkan tantangan petani dalam pengelolaan air, terutama pada musim kemarau dan pemupukan otomatis berdasarkan Standar Operasional Prosedur (SOP), yang dapat diatasi dengan teknologi modern. Terdapat tiga sensor yang digunakan pada alat IoT untuk mengumpulkan data kelembaban tanah, kelembaban udara, dan suhu udara. Hasil evaluasi klasifikasi penyiraman berdasarkan kondisi tiga sensor memiliki akurasi sebesar 83% dibandingkan dengan hanya bedasarkan kelembaban tanah saja. Pemupukan yang dilakukan sesuai dengan jadwal dan Standar Operasional Prosedur (SOP) pemupukan berdasarkan tinggi tanaman juga membantu memudahkan petani. Evaluasi model LSTM menunjukkan kinerja yang baik dengan nilai Mean Squared Error (MSE) dan Root Mean Squared Error (RMSE) yang rendah yaitu 0,7 dan 0,8 untuk suhu, 8 dan 2 untuk kelembaban udara, serta 5 dan 2 untuk kelembaban tanah. Selain itu, nilai MAPE untuk mengukur performa dari model LSTM juga menunjukkan hasil yang baik yaitu 1.13% untuk suhu, 4,6% untuk kelembaban udara dan 3% untuk kelembaban tanah.
================================================================================================================================
In today's technology, growing red onions requires modern solutions. This research focuses on creating a smart system using the Internet of Things (IoT) and machine learning to recommend the best irrigation and fertilization practices for red onion farming. The study addresses challenges faced by farmers, especially in managing water during dry seasons, and suggests an automated fertilization method based on Standard Operating Procedures (SOP), made possible through advanced technology. The IoT device used in this system includes three sensors to collect data on soil moisture, air humidity, and air temperature. The evaluation results for irrigation classification based on the three sensor conditions show an accuracy of 83%, compared to just see the soil moisture. Fertilization conducted according to schedule and SOP based on plant height also helps farmers' tasks. The evaluation of the Long Short-Term Memory (LSTM) model indicates good performance, with low Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) values, 0.7 and 0.8 for temperature, 8 and 2 for humidity, and 5 and 2 for soil moisture. Additionally, the Mean Absolute Percentage Error (MAPE) values to measure LSTM model performance also show promising results, 1.13% for temperature, 4.6% for air humidity, and 3% for soil moisture.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | LSTM, IoT, Smart Farming |
Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T174 Technological forecasting |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis |
Depositing User: | Salsabila Briliana Ananda Sofi |
Date Deposited: | 29 Jan 2024 04:36 |
Last Modified: | 29 Jan 2024 04:36 |
URI: | http://repository.its.ac.id/id/eprint/105700 |
Actions (login required)
View Item |