Detection of Sugar Apple (Annona squamosa L.) Ripeness Based on Physical and Chemical Properties Using the K-Nearest Neighbor (k-NN) and Random Forest Algorithm

DOI

10.2991/978-94-6463-274-3_2How to use a DOI?

Keywords

detection; physical and chemical properties; ripeness based; sugar apple

Abstract

West Nusa Tenggara is one of the very high sugar apples producing regions every year. Post-harvest handling of sugar apples or srikaya fruits presents several challenges, one of which is judging the quality of the fruit by its ripeness. A lot of research has been done on fruit classification using one or two parameters using machine learning. Physical and chemical properties such as aroma, moisture content, total dissolved solids, texture, and weight loss are typically indicators for judging fruit ripeness. The purpose of this study is to use the k-Nearest Neighbor (k-NN) and random forest algorithms to determine the ripeness of sugar apples based on their physical and chemical properties and to measure the accuracy of the algorithms. The methods used in this study are k-NN classification methods and random forests, and their performance is measured using a confusion matrix. The parameters observed were physical properties (weight loss and texture) and chemical properties (moisture content, total dissolved solids, and gas content) and the number of test samples varied from 20%, 30% and 40%. Results were achieved to determine the ripeness of sugar apples, and the random forest method achieved 100% of accuracy for various number of test samples. On the other hand, the accuracy of the k-NN method decreases as the number of test samples increases i.e. 100%, 100%, 50% for each variant of the test sample, respectively. Therefore, it can be concluded that determining the ripeness of sugar apples by random forest method is better.

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)

TY  - CONF
AU  - Murad
AU  - Joko Sumarsono
AU  - Sukmawaty
AU  - Amni Aulia
AU  - Syahroni Hidayat
PY  - 2023
DA  - 2023/10/27
TI  - Detection of Sugar Apple (Annona squamosa L.) Ripeness Based on Physical and Chemical Properties Using the K-Nearest Neighbor (k-NN) and Random Forest Algorithm
BT  - Proceedings of the 7th International Conference on Food, Agriculture, and Natural Resources (IC-FANRES 2022)
PB  - Atlantis Press
SP  - 4
EP  - 19
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-274-3_2
DO  - 10.2991/978-94-6463-274-3_2
ID  - 2023
ER  -