ZULFAH, ZULFAH (2024) PERBANDINGAN ALGORITMA DECISION TREE DAN RANDOM MULTIMODEL ENSEMBLE UNTUK DETEKSI TINGKAT KELEMBABAN TANAH PADA TANAMAN KOPI BERDASARKAN EKSTRAKSI FITUR NORMALIZED DIFFERENCE MOISTURE INDEX. S1 thesis, Universitas Mercu Buana Jakarta.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (HAL COVER)
01 COVER.pdf Download (619kB) |
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (210kB) |
|
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (238kB) |
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (404kB) |
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (422kB) |
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (653kB) |
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (155kB) |
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (200kB) |
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (599kB) |
Abstract
This research evaluates and compares the performance of two algorithms, Deci-sion Tree and Random Multimodel Ensemble, for detecting soil moisture levels in coffee plants using Normalized Difference Moisture Index (NDMI) feature extrac-tion. The problem faced is the importance of managing soil moisture in coffee farm-ing to increase yields and production quality. The aim of this research is to assess the effectiveness of Decision Tree and Random Multimodel Ensemble in detecting soil moisture and compare the performance of both. The experimental method was carried out using a dataset that included variations in soil conditions on coffee plants. Random Multimodel Ensemble involves a number of random models to in-crease precision and accuracy. The research results show that Random Multimodel Ensemble significantly outperforms Decision Tree in terms of precision (0.97), re-call (0.97), accuracy (0.97), as well as MAE (0.02), MSE (0.02), RMSE (0.14), MAPE (1.47) values. , and R2 (0.94). The position of Random Multimodel Ensem-ble as a superior method for detecting soil moisture in coffee plants is supported by experimental results which show consistently higher performance compared to De-cision Tree. This research provides an in-depth look at the potential of implement-ing the Random Multimodel Ensemble as a more reliable solution for soil moisture management in the context of coffee farming. Keywords: Decision Tree, Soil Moisture, NDMI, Random Multimodel Ensemble, Coffee Plants Penelitian ini mengevaluasi dan membandingkan kinerja dua algoritma, Deci-sion Tree dan Random Multimodel Ensemble, untuk deteksi tingkat kelembaban tanah pada tanaman kopi dengan menggunakan ekstraksi fitur Normalized Differ-ence Moisture Index (NDMI). Masalah yang dihadapi adalah pentingnya pengel-olaan kelembaban tanah dalam pertanian kopi untuk meningkatkan hasil dan kuali-tas produksi. Tujuan penelitian ini adalah untuk menilai keefektifan Decision Tree dan Random Multimodel Ensemble dalam mendeteksi kelembaban tanah dan mem-bandingkan performa keduanya. Metode eksperimen dilakukan dengan menggunakan dataset yang mencakup variasi kondisi tanah pada tanaman kopi. Random Multimodel Ensemble melibatkan sejumlah model acak untuk meningkat-kan presisi dan akurasi. Hasil penelitian menunjukkan bahwa Random Multimodel Ensemble secara signifikan melampaui Decision Tree dalam hal presisi (0.97), re-call (0.97), akurasi (0.97), serta nilai MAE (0.02), MSE (0.02), RMSE (0.14), MAPE (1.47), dan R2 (0.94). Posisi Random Multimodel Ensemble sebagai metode superior dalam deteksi kelembaban tanah pada tanaman kopi didukung oleh hasil eksperimen yang menunjukkan performa yang lebih tinggi secara konsisten dibandingkan dengan Decision Tree. Penelitian ini memberikan pandangan men-dalam tentang potensi implementasi Random Multimodel Ensemble sebagai solusi yang lebih handal untuk pengelolaan kelembaban tanah dalam konteks pertanian kopi. Kata Kunci: Decision Tree, Soil Moisture, NDMI, Random Multimodel Ensemble, Coffee Plants.
Actions (login required)
 |
View Item |
