Proceedings of the 4th International Seminar on Science and Technology (ISST 2022)

Oil Content and Free Fatty Acid Prediction of Oil Palm Fresh Fruit Bunches Using Multispectral Imaging and Partial Least Square Algorithm

Authors
Minarni Shiddiq1, *, Roni Salambue2, Zulfansyah Zulfansyah3, Jahrizal Jahrizal4, Ikhsan Rahman Husein1, Sinta Afria Ningsih1, Galef Alfahrezi1
1Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Riau, Jl. HR. Soebrantas Km 12.5, Pekanbaru, Riau, 28293, Indonesia
2Department of Computer Science, Faculty of Mathematics and Natural Sciences, Universitas Riau, Jl. HR. Soebrantas Km 12.5, Pekanbaru, Riau, 28293, Indonesia
3Department of Chemical Engineering, Faculty of Engineering, Universitas Riau, Jl. HR. Soebrantas Km 12.5, Pekanbaru, Riau, 28293, Indonesia
4Department of Economy, Faculty of Business and Economics, Universitas Riau, Jl. HR. Soebrantas Km 12.5, Pekanbaru, Riau, 28293, Indonesia
*Corresponding author. Email: minarni.shiddiq@lecturer.unri.ac.id
Corresponding Author
Minarni Shiddiq
Available Online 22 August 2023.
DOI
10.2991/978-94-6463-228-6_17How to use a DOI?
Keywords
Multispectral Imaging; Oil Palm FFB; Oil Content; Free Fatty Acid; PLS algorithms
Abstract

Multispectral imaging has many applications in agriculture, such as the prediction of the internal qualities of fruit and vegetables. Multispectral is preferable to Hyperspectral imaging for fast in-line 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 done manually by experienced 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 a partial least square (PLS) algorithm. The system used three bandpass 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 programming language. Mean Absolute Percentage Error (MAPE) was applied to calculate the accuracy of the prediction results. The MAPE values were 20.94% and 7.5% for the oil content and FFA prediction, respectively. These results show the potential use of multispectral imaging for predicting oil content and FFA of oil palm FFB.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the 4th International Seminar on Science and Technology (ISST 2022)
Series
Advances in Physics Research
Publication Date
22 August 2023
ISBN
978-94-6463-228-6
ISSN
2352-541X
DOI
10.2991/978-94-6463-228-6_17How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Minarni Shiddiq
AU  - Roni Salambue
AU  - Zulfansyah Zulfansyah
AU  - Jahrizal Jahrizal
AU  - Ikhsan Rahman Husein
AU  - Sinta Afria Ningsih
AU  - Galef Alfahrezi
PY  - 2023
DA  - 2023/08/22
TI  - Oil Content and Free Fatty Acid Prediction of Oil Palm Fresh Fruit Bunches Using Multispectral Imaging and Partial Least Square Algorithm
BT  - Proceedings of the 4th International Seminar on Science and Technology (ISST 2022)
PB  - Atlantis Press
SP  - 143
EP  - 154
SN  - 2352-541X
UR  - https://doi.org/10.2991/978-94-6463-228-6_17
DO  - 10.2991/978-94-6463-228-6_17
ID  - Shiddiq2023
ER  -