Hidayatullah, Abdul Rofi (2024) Klasifikasi penyakit pada Daun Tanaman Cabai menggunakan Support Vector Machine dan pemantauan pertumbuhan Tanaman. Sarjana thesis, UIN Sunan Gunung Djati Bandung.
|
Text (COVER)
1_cover.pdf Download (155kB) | Preview |
|
|
Text (ABSTRAK)
2_abstrak.pdf Download (339kB) | Preview |
|
|
Text (DAFTAR ISI)
3_daftarisi.pdf Download (573kB) | Preview |
|
|
Text (BAB I)
4_bab1.pdf Download (560kB) | Preview |
|
Text (BAB II)
5_bab2.pdf Restricted to Registered users only Download (1MB) | Request a copy |
||
Text (BAB III)
6_bab3.pdf Restricted to Registered users only Download (708kB) | Request a copy |
||
Text (BAB IV)
7_bab4.pdf Restricted to Registered users only Download (910kB) | Request a copy |
||
Text (BAB 5)
8_bab5.pdf Restricted to Registered users only Download (1MB) | Request a copy |
||
Text (BAB VI)
9_bab6.pdf Restricted to Registered users only Download (342kB) | Request a copy |
||
Text (DAFTAR PUSTAKA)
10_daftarpustaka.pdf Restricted to Registered users only Download (371kB) | Request a copy |
Abstract
Chili plants are one of the main agricultural commodities that are susceptible to various leaf diseases, which can lead to a decrease in yield. Quick and accurate disease management and identification are crucial for farmers to maintain plant productivity. This research aims to develop a model for classifying leaf diseases in chili plants infected by the Gemini virus and mosaic curl disease using SVM, as well as to measure plant height and leaf area automatically using image processing techniques. The research methodology includes a literature review, needs analysis, system design using the CRISP-DM approach, and model implementation and testing. The research results include a model saved in joblib format. The SVM model developed achieved a classification accuracy of 92.26% after data augmentation, which increased the quantity of data for classifying three leaf conditions: healthy leaves, leaves infected by the Gemini virus, and leaves infected by mosaic curl disease. This model was then implemented using the Flask framework to test whether it could function well in a web application. Meanwhile, the automatic measurement system showed an accuracy of 81.62% for plant height and 81.97% for leaf area, indicating good results but lacking precision, necessitating further development.
Item Type: | Thesis (Sarjana) |
---|---|
Uncontrolled Keywords: | Chili Plants; Classification; Leaf Diseases; CRISP-DM; Augmentation; Image Processing; |
Subjects: | Special Computer Methods > Artificial Intelligence Operations, Archieves, Information Centers > Classification of Specific Subject Natural History of Organism > Classification of Organism Plant Injuries > Viral Diseases |
Divisions: | Fakultas Sains dan Teknologi > Program Studi Teknik Elektro |
Depositing User: | Abdul rofi |
Date Deposited: | 15 Oct 2024 03:54 |
Last Modified: | 15 Oct 2024 07:11 |
URI: | https://digilib.uinsgd.ac.id/id/eprint/100158 |
Actions (login required)
View Item |