RAMADHAN, RIZKI (2025) SISTEM DIAGNOSA PENENTUAN MASA PANEN TEBU BERDASARKAN DAUNNYA MENGGUNAKAN K-NEAREST NEIGHBOR PADA METODE PENGOLAHAN CITRA. S1 thesis, Universitas PGRI Madiun.
![[img]](https://eprint.unipma.ac.id/style/images/fileicons/text.png) |
Text
Halaman Depan.pdf Download (1MB) |
|
Text
Abstrak.pdf Download (178kB) |
|
Text
BAB I.pdf Download (193kB) |
|
Text
BAB II.pdf Download (414kB) |
|
Text
BAB III.pdf Restricted to Repository staff only Download (347kB) | Request a copy |
|
Text
BAB IV.pdf Restricted to Repository staff only Download (1MB) | Request a copy |
|
Text
BAB V.pdf Download (189kB) |
|
Text
Daftar Pustaka.pdf Download (191kB) |
|
Text
Lampiran.pdf Restricted to Repository staff only Download (648kB) | Request a copy |
Abstract
Ramadhan R, 2025. Sugarcane Harvest Time Diagnosis System Based on Leaf Characteristics Using K-Nearest Neighbor in Image Processing Method. Informatics Engineering Study Program, Faculty of Engineering, Universitas PGRI Madiun. Supervisors: Saifulloh, S.Kom., M.Kom. and Pratiwi Susanti, S.Kom., M.MT. Accurate determination of sugarcane harvest time significantly affects the increase in sugar yield (rendemen). However, the manual methods commonly used by farmers are still subjective and inconsistent. This study aims to develop an automatic diagnosis system based on digital image processing using the K-Nearest Neighbor (KNN) algorithm to assist in classifying the maturity level of sugarcane leaves. The system was designed as an interactive website using Python and Streamlit, utilizing 1,462 leaf images processed into 34 numerical features, then classified into three categories: unripe, harvest-ready, and overripe. The test results showed an accuracy of 95.22%, RMSE of 0.9353, MSE of 0.0547, and the highest F1-score of 0.99 in the “Overripe” class. The System Usability Scale (SUS) test obtained a score of 80, which is categorized as “Good.” This system is expected to be a solution for farmers in making more accurate, objective, and technology-based harvest decisions. Keywords: Leaf Diagnosis, Sugarcane, KNN, Digital Image, Streamlit, Harvest.
| Item Type: | Thesis/Skripsi/Tugas Akhir (S1) |
|---|---|
| Kata Kunci: | Leaf Diagnosis, Sugarcane, KNN, Digital Image, Streamlit, Harverst. |
| Subjects: | S Agriculture > S Agriculture (General) T Technology > T Technology (General) |
| Divisions: | Fakultas Teknik > Teknik Informatika |
| Depositing User: | RIZKI RAMADHAN RIZKI |
| Date Deposited: | 12 Aug 2025 04:31 |
| Last Modified: | 12 Aug 2025 04:31 |
| URI: | http://eprint.unipma.ac.id/id/eprint/3948 |
Actions (login required)
 |
View Item |
