Implementation of Artificial Intelligence of Things (AIoT) for Chili Ripeness Classification with YOLO

DOI

10.2991/978-94-6463-926-1_53How to use a DOI?

Keywords

AIoT; Chili; Classification; Ripeness; Yolo

Abstract

Improving the efficiency of chili pepper (Capsicum annuum) post-harvest sorting is a key challenge in advancing precision agriculture. The ripeness of chili peppers affects taste, market value, shelf life, and overall product quality, making sorting a critical step. Conventional sorting methods remain widely used but often lack consistency and are inefficient for large-scale operations. This study aims to design an automatic chili detection and classification system using the YOLOv10 algorithm, integrated within an Artificial Intelligence of Things (AIoT) framework. The system classifies chili peppers into four categories based on size and color: red-large, red-small, green-large, and green-small. Image data were acquired using a Logitech C270HD 720p camera and annotated via Roboflow, then trained over 200 epochs using Google Colaboratory. Classification results are displayed through a graphical interface named Sortasi Cabai and sent automatically via a Telegram Bot as real-time notifications, while also being connected to a conveyor-based physical sorting system. The model demonstrated strong performance, achieving a mAP@0.5 of 89.7%, a Precision of 1.00, a Recall of 95%, an F1-Score of 0.85, and IoU values above 0.5. These results indicate that the system can accurately perform multi-class, real-time classification and is feasible for AIoT-based post-harvest sorting applications in agricultural operations.

Copyright

© 2025 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  - Fenny Aprilliani
AU  - Anri Kurniawan
AU  - Hanis Adila Lestari
AU  - Muhammad Gilang Ramadhan
AU  - Irna Dwi Destiana
AU  - Erin Nurfitriani
PY  - 2025
DA  - 2025/12/31
TI  - Implementation of Artificial Intelligence of Things (AIoT) for Chili Ripeness Classification with YOLO
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2025 (iCAST-ES 2025)
PB  - Atlantis Press
SP  - 468
EP  - 479
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-926-1_53
DO  - 10.2991/978-94-6463-926-1_53
ID  - Aprilliani2025
ER  -