Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal J-Icon : Jurnal Komputer dan Informatika
Zolla Zolla
Universitas Pakuan
Computer Science & IT

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

Found 1 Documents
Search

 1 
IDENTIFIKASI DEFISIENSI UNSUR HARA PADA TANAMAN CABAI MENGGUNAKAN SUPPORT VECTOR MACHINE Arie Qur’ania; Lita Karlitasari; Sufiatul Maryana; Cecep Sudrajat; Zolla Zolla
J-ICON : Jurnal Komputer dan Informatika Vol 11 No 1 (2023): Maret 2023
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v11i1.9803

Abstract

Plants, like other living things, need a combination of nutrients to live, grow and reproduce. Nutrients in plants can also be divided into two, namely mobile nutrients and immobile nutrients (non-moving nutrients). The condition of plants that are deficient or lacking in nutrients will experience growth disturbances and affect the yield of leaves or fruit. Leaf color can be a characteristic of plants under normal conditions or experiencing nutrient deficiencies. Deficiency of nutrients in plants will affect leaf shape, fruit production and plant age which results in stunted growth and rapid death of plants, in fruit production there will be loss of flowers or ovaries so that production will decrease. So far, plant maintenance has been done manually. Each plant is seen for later analysis of the results and it takes time to identify nutrient deficiencies. The aim of the study was to identify nutrient deficiencies in image-based chili plants based on the characteristics of the Red, Green, Blue (RGB) color and texture analysis using the Support Vector Model (SVM). The benefit of the research is to make machine learning-based applications to identify nutrient deficiencies which are divided into four classes, namely nitrogen (N) and phosphorus (P) deficiencies, P and potassium (K) deficiencies, N and K deficiencies, and chili leaves with normal class. .There are 120 plant data with an accuracy of 84.4%.
Co-Authors Arie Qur’ania Cecep Sudrajat Lita Karlitasari Sufiatul Maryana