SB21: Portable Watermelon Ripeness Detector Through Acoustics Analysis and Spectral Identification

Watermelon is one of the most challenging fruits to determine if it is ripe, unripe, or overripe. Monitoring its quality is essential for boosting its marketability and productivity. Manual methods used in identifying its maturity level depend on tapping, color inspection, and the number of days. Wh...

Full description

Saved in:

Bibliographic Details
Published in:	2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) pp. 1 - 6
Main Authors:	Balakit, Raymart B., Dela Cruz, Jennifer C., Reano, Rose Anne L., Castillo, Acer Jay G., Garcia, Christian Julius R., Libang, Ma. Caira Gail M., Mallapre, Joshua S., Navarro, Anthony D., Pangyarihan, Rosemarie L., Parino, Krisha Mae N., Wenceslao, Erecha B.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-12-2022
Subjects:	Acoustics Acoustics Analysis Detectors Fast Fourier transforms K-Nearest Neighbor Manuals Pediatrics Productivity Spectral Identification Sugar Sugar Baby watermelon
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Watermelon is one of the most challenging fruits to determine if it is ripe, unripe, or overripe. Monitoring its quality is essential for boosting its marketability and productivity. Manual methods used in identifying its maturity level depend on tapping, color inspection, and the number of days. While they are useful, their accuracy and precision are limited due to reliance on guesswork. This study aims to provide a non-destructive method for watermelon ripeness detection of Sugar Baby variety through Acoustics Analysis and Spectral Identification using Fast Fourier Transform and Near-Infrared Spectroscopy (NIRS). A portable and automated device is designed, consisting of processes including the detection of sound and internal content qualities using NIRS sensor and microphone, assessing the wavelength and frequencies acquired, and interpreting the findings in line with the standard values set. K-Nearest Neighbor technique is employed, where transformed signals are passed through computation, comparing, and voting. A total of 300 watermelon samples were evaluated and 30 respondents were also surveyed to assess the effectiveness of the device. Results revealed that utilizing both NIRS and Fast Fourier Transform can effectively detect watermelon ripeness with high accuracy of 90.7%. The automated watermelon ripeness detector is strongly preferred over manual detection.
ISSN:	2770-0682
DOI:	10.1109/HNICEM57413.2022.10109373