Image of Prediksi Kadar Minyak Dan Asam Lemak Bebas Tandan Buah Segar Kelapa Sawit Menggunakan Pencitraan Multispektral Dan Machine Learning
Penanda Bagikan

CD Skripsi

Prediksi Kadar Minyak Dan Asam Lemak Bebas Tandan Buah Segar Kelapa Sawit Menggunakan Pencitraan Multispektral Dan Machine Learning

ABSTRACT
Multispectral imaging has many applications in agriculture, such as prediction of the internal qualities of fruit and vegetables. Multispectral is preferable than Hyperspectral imaging for fast inline sorting and grading machine vision due to fewer wavelength bands applied. Oil palm fresh fruit bunches (FFBs) are the source of crude palm oil (CPO) in Indonesia and Malaysia. However, the sorting and grading of FFBs are still operated manually by graders. Oil content and free fatty acid (FFA) are the main qualities of FFBs. Predicting the oil and FFA contents as part of the grading process is crucial. This study aimed to predict the oil content and FFA using a multispectral imaging system with artificial neural network (ANN) and partial least square (PLS) algorithm. The system used three band pass filters with wavelengths of 710 nm, 800 nm and 830 nm, attached to a filter wheel in front of a monochrome camera. The acquisition and image processing used Python code. Mean Absolute Percentage Error (MAPE) was applied to calculate the accuracy of prediction results. The MAPE values were 21.62% and 25.48% for the oil content and FFA prediction using ANN algorithm and values were 20.94% and 7.5% for the oil content and FFA prediction using PLS algorithm, respectively. These results show the potential use of multispectral imaging for predicting oil content and FFA of oil palm FFB.
Keywords: Multispectral Imaging, Oil Palm FFB, Oil Content, Free Fatty Acid, ANN algorithms, PLS algorithms

Ketersediaan
#
Perpustakaan Universitas Riau 1703110184
1703110184
Tersedia
Informasi Detail
Judul Seri
-
No. Panggil
1703110184
Penerbit
Pekanbaru : Universitas Riau - FISIP -FISIKA.,
Deskripsi Fisik
-
Bahasa
Indonesia
ISBN/ISSN
-
Klasifikasi
1703110184
Tipe Isi
-
Tipe Media
-
Tipe Pembawa
-
Edisi
-
Subjek
FISIKA
Info Detail Spesifik
-
Pernyataan Tanggungjawab
Versi lain/terkait

Tidak tersedia versi lain

Lampiran Berkas
Komentar
Anda harus masuk sebelum memberikan komentar