Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of watermelon sweetness using a reflected sound

반향 소리를 이용한 기계 학습 기반 수박의 당도 예측

  • Kim, Ki-Hoon (Department of Biomedical Engineering, School of Electrical Engineering, University of Ulsan) ;
  • Woo, Ji-Hwan (Department of Biomedical Engineering, School of Electrical Engineering, University of Ulsan)
  • 김기훈 (울산대학교 의용생체공학전공) ;
  • 우지환 (울산대학교 전기공학부 의공학전공)
  • Received : 2020.05.26
  • Accepted : 2020.08.20
  • Published : 2020.08.28
Download PDF
⟨ Previous Next ⟩

Abstract

There are various approaches to evaluate a watermelon sweetness. However, there are some limitations to evaluating cost, watermelon damage, and subjective issue. In this study, we developed a novel approach to predict a watermelon sweetness using reflected sound and the machine learning algorithm. It was observed that higher brix watermelon produced higher spectral power is reflected sound. Based on the spectral-temporal features of reflected sound, the machine learning algorithms could accurately predict the sweetness group at a rate of 83.2 and 59.6 % in 2-groups and 3-groups classification, respectively.

수박의 맛을 평가하는 다양한 방식이 있으나, 기존의 방법들은 주관적 방식, 평가 비용, 대상의 손상 등과 같은 평가 방식의 한계점이 있다. 최근에는 이러한 단점들을 해소하기 위해 소리를 이용하여 수박을 평가하는 연구들이 진행되고 있다. 본 연구에서는 수박을 두드렸을 때 나는 반향 소리를 AI기반의 기계 학습을 이용하여 수박의 당도를 예측하는 모델을 개발 하였다. 수박의 당도가 높을수록 높은 주파수 성분이 특이점으로 나타나며, 따라서 반향소리 시간-주파수 특이점에 기반 하여 기계 학습 방법을 개발하였다. 2개의 수박 당도별 그룹을 구분 시에 83.2%, 3개의 그룹을 구분시에 59.6%의 정확도로 당도를 예측 할 수 있었다.

Keywords

References

  1. Jie, D. F., Xie, L. J., Fu, X. P., Rao, X. Q. & Ying, Y. B. (2013). Variable selection for partial least squares analysis of soluble solids content in watermelon using near-infrared diffuse transmission technique. Journal of Food Engineering, 118(4), 387-392. DOI:10.1016/j.jfoodeng.2013.04.027
  2. Jie, D. F., Zhou, W. H. & Wei, X. (2019). Nondestructive detection of maturity of watermelon by spectral characteristic using NIR diffuse transmittance technique. Scientia Horticulturae, 257. DOI:108718, 10.1016/j.scienta.2019.108718
  3. Fuzeng Yang, L. Y., Qing Yang & Likui Kang. (2009). Nondestructive detection of the internal quality of apple using X-ray and machine vision. LWT-Food Science and Technology, 41(9), 1720-1725. DOI:10.1007/978-1-4419-0213-9_20
  4. Milczarek, R. R., Saltveit, M. E., Garvey, T. C. & McCarthy, M. J. (2009). Assessment of tomato pericarp mechanical damage using multivariate analysis of magnetic resonance images. Postharvest Biology and Technology, 52(2), 189-195. DOI:10.1016/j.postharvbio.2009.01.002
  5. Sun, T. et al. (2010). Research advances in nondestructive determination of internal quality in watermelon/melon: A review. Journal of Food Engineering, 100(4), 569-577. DOI:10.1016/j.jfoodeng.2010.05.019
  6. Diezma-Iglesias, B., Ruiz-Altisent, M. & Barreiro, P. (2004). Detection of internal quality in seedless watermelon by acoustic impulse response. Biosystems Engineering, 88(2), 221-230. DOI:10.1016/j.biosystemseng.2004.03.007
  7. Kyriacou, M. C., Leskovar, D. I., Colla, G. & Rouphael, Y. (2018). Watermelon and melon fruit quality: The genotypic and agro-environmental factors implicated. Scientia Horticulturae, 234, 393-408. DOI:10.1016/j.scienta.2018.01.032
  8. Shah Rizam M. Shah Baki, M. Z. M. a., Ihsan M. Yassin, Hasliza A. Hassan & Azlee Zabidi. (2010). Non-Destructive Classification of Watermelon Ripeness using MelFrequency Cepstrum Coefficients and Multilayer Perceptrons. The 2010 International Joint Conference on Neural Networks (IJCNN), 1-6. DOI:10.1109/ijcnn.2010.5596573
  9. Chen, X., Yuan, P. P. & Deng, X. Y. (2018). Watermelon ripeness detection by wavelet multiresolution decomposition of acoustic impulse response signals. Postharvest Biology and Technology, 142, 135-141. DOI:10.1016/j.postharvbio.2017.08.018
  10. Zeng, W., Huang, X. F., Arisona, S. M. & McLoughlin, I. V. (2014). Classifying watermelon ripeness by analysing acoustic signals using mobile devices. Personal and Ubiquitous Computing, 18(7), 1753-1762. DOI:10.1007/s00779-013-0706-7
  11. Ikeda, T., Choi, P. K., Ishii, T., Arai, I. & Osawa, M. (2015). Firmness evaluation of watermelon flesh by using surface elastic waves. Journal of Food Engineering, 160, 28-33. DOI:10.1016/j.jfoodeng.2015.03.020
  12. Leskovar, D., Othman, Y. & Dong, X. J. (2016). Strip tillage improves soil biological activity, fruit yield and sugar content of triploid watermelon. Soil & Tillage Research, 163, 266-273. DOI:10.1016/j.still.2016.06.007
  13. Qian, M., Huang, W. Q., Wang, Q. Y., Fan, S. X., Zhang, B. H. & Chen, L. P. (2016). Assessment of Influence Detective Position Variability on Precision of Near Infrared Models for Soluble Solid Content of Watermelon. Spectroscopy and Spectral Analysis, 36(6), 1700-1705. DOI:10.3964/j.issn.1000-0593(2016)06-1700-06
  14. Muller, M., Ellis, D. P. W., Klapuri, A. & Richard, G. (2011). Signal Processing for Music Analysis. IEEE Journal of Selected Topics in Signal Processing, 5(6), 1088-1110. DOI:10.1109/Jstsp.2011.2112333
  15. Peng, H. (2005). Feature Selection Based Mutual Information: Criteria of Max-Dependency, Max-Relevance and Min-Redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1226-1238. DOI:10.1109/tpami.2005.159