DOI: https://doi.org/10.14710/jtsiskom.2020.13733

Maturity classification of cacao through spectrogram and convolutional neural network

Gilbert E. Bueno  -  Department of Computer and Electronics Engineering, Cavite State University, Philippines
Kristine A. Valenzuela  -  Department of Computer and Electronics Engineering, Cavite State University, Philippines
*Edwin R. Arboleda orcid scopus  -  Department of Computer and Electronics Engineering, Cavite State University, Philippines
Received: 1 May 2020; Revised: 24 May 2020; Accepted: 4 Jun 2020; Published: 31 Jul 2020; Available online: 8 Jun 2020.
Fulltext |
Open Access Copyright (c) 2020 Jurnal Teknologi dan Sistem Komputer under http://creativecommons.org/licenses/by-sa/4.0.

Citation Format:
Abstract
Cacao pod's ideal harvesting time is when it is about to be ripe. Immature harvest would result in hard cacao beans not suitable for fermentation, while overripe cacao pods lead to fungal-infected, defective, and poor-quality yields. The demand for high-quality cacao products is expected to rise due to advancing technology in the present. Pre-harvesting needs to provide optimal identification of which amongst the pods are ripened enough and ready for the next stage of the cacao process. This paper recommends a technique to determine the ripeness of cacao. Nine hundred thirty-three cacao samples were used to collect thumping audio data at five different pod's exocarp locations. Each sound file is 1 second long, creating 4665 cacao sound file datasets at 16kHz sample rate and 16-bit audio bit depth. The process of the Mel-Frequency Cepstral Coefficient Spectogram was then applied to extract recognizable features for the training process. The deep learning method integrated was a convolutional neural network (CNN) to classify the cacao sound successfully. The experimental design model's output exhibits an accuracy of 97.50 % for the training data and 97.13 % for the validation data. While the overall accuracy mean of the classification system is 97.46 %, whether the cacao is unripe or ripe.
Keywords: cacao; CNN; deep learning; feature extraction; maturity level; spectogram
Funding: Cavite State University

Article Metrics:

Article Info
Section: Original Research Articles
Language : EN
Statistics: 689 249
Share:
Related articles
Visual Place Recognition Method Based-on CNN Features for Indoor Robot Navigation Parallel Spatial Pyramid Convolutional Neural Network for Kinship Verification from Face Images Identification of Bamboo Species Based on Leaf Texture using Gray Level Co-Occurrence Matrix and Gray Level Run Length Matrix Deep learning model for metagenome fragment classification using spaced k-mers feature extraction Carotid Artery Detection in B-Mode Ultrasound Images Based on Convolution Neural Network Single Shot Multibox Detector More related articles
Most cited articles
Pengembangan Teknologi Informasi Mobile Learning Universitas Diponegoro Berbasis Android Android Application of Expert System for Gastroenteritis Detection Aplikasi Pencarian Rute Perguruan Tinggi Berbasis Android Menggunakan Location Based Service (LBS) di Kota Semarang Pengembangan Permainan Edukatif Ragam Budaya Nusantara Berbasis Android PSS Tuning on Power Generator System using Flower Pollination Algorithm More cited articles
  1. C. H. Avendaño-Arrazate, M. Bolaños M, and A. Mendoza-López, "The cocoa (theobroma cacao l) native in Mexico," Biodiversity International Journal, vol. 2, no. 6, pp. 535-536, 2018. doi: 10.15406/bij.2018.02.00109
  2. R. C. Espino and J. V. Ramos, "Cacao production guide," Philippines Department of Agriculture Bureau of Plant Industry, 2008
  3. M. S. Fowler, Cocoa beans: from tree to factory. NJ: Wiley, 2009
  4. M. Apriyanto, "Changes in chemical properties of dried cocoa (theobroma cacao) beans during fermentation," International Journal of Fermented Foods, vol. 5, no. 1, pp. 11-16, 2016. doi: 10.5958/2321-712X.2016.00002.8
  5. E. O. Afoakwa, "Cocoa bean composition and chocolate flavor development," in Chocolate and Science Technology, pp. 80-101, 2016. doi: 10.1002/9781118913758.ch5
  6. M. J. Delwiche, T. McDonald, and S. V. Bowers, "Determination of Peach firmness by analysis of impact forces," Transactions of American Society of Agricultural and Biological Engineering, vol. 30, no. 1, pp. 249-254, 1987. doi: 10.13031/2013.30435
  7. J. R. Cooke and R. H. Rand, "A mathematical study of resonance in intact fruits and vegetables using a 3-media elastic sphere model," Journal of Agricultural Engineering Research, vol. 18, no. 2, pp. 141-157, 1973. doi: 10.1016/0021-8634(73)90023-1
  8. H. Chen and J. De Baerdemaeker, "Effect of apple shape on acoustic measurements of firmness," Journal of Agricultural Engineering Research, vol. 56, no. 3. pp. 253-266, 1993. doi: 10.1006/jaer.1993.1077
  9. N. De Belie, S. Schotte, J. Lammertyn, B. Nicolai, and J. De Baerdemaeker, "Firmness changes of pear fruit before and after harvest with the acoustic impulse response technique," Journal of Agricultural Engineering Research, vol. 77, no. 2, pp. 183-191, 2000. doi: 10.1006/jaer.2000.0592
  10. E. Macrelli, A. Romani, R. P. Paganelli, E. Sangiorgi, and M. Tartagni, "Piezoelectric transducers for real-time evaluation of fruit firmness. Part II: Statistical and sorting analysis," Sensors and Actuators: A Physical, vol. 201, pp. 497-503, 2013. doi: 10.1016/j.sna.2013.07.037
  11. A. H. Gómez, J. Wang, and A. G. Pereira, "Firmness of mandarin at different picking dates," Food Science and Technology International, vol. 12, no. 4, pp. 273-279, 2006. doi: 10.1177/1082013206067870
  12. A. H. Gómez, A. G. Pereira, W. Jun, and H. Yong, "Acoustic testing for peach fruit ripeness evaluation during peach storage stage Evaluación acústica de la madurez del melocotón Durante la fase de almacenamiento," Revista Ciencias Técnicas Agropecuarias, vol. 14, no. 2, pp. 28-34, 2005, pp. 28-34, 2005
  13. F. Khoshnam, M. Namjoo, and H. Golbakhshi, "Acoustic testing for melon fruit ripeness evaluation during different stages of ripening," Agriculturae Conspectus Scientificus, vol. 80, no. 4, pp. 197-204, 2015
  14. T. Tiplica, P. Vandewalle, S. Verron, C. Grémy-Gros, and E. Mehinagic, "Identification of apple varieties using acoustic measurements," in 3rd Conférence Internationale en Métrologie, Le Caire, Egypt, Jun. 2010, pp. 103-110
  15. J. Hongwiangjan, A. Terdwongworakul, and K. Krisanapook, "Evaluation of pomelo maturity based on acoustic response and peel properties," International Journal of Food Science Technology, vol. 50, no. 3, pp. 782-789, 2015. doi: 10.1111/ijfs.12700
  16. M. Lutfi, C. Herlaut, and N. Wahyunanto Agung, "Designing and creating acoustic ripeness tester and experimental testing on Juan Canary melon," Advances in Natural and Applied Sciences, vol. 5, no. 3, pp. 242-246, 2011
  17. A. Zakaria et al., "Improved maturity and ripeness classifications of Magnifera Indica cv. harumanis mangoes through sensor fusion of an electronic nose and acoustic sensor," Sensors, vol. 12, no. 5, pp. 6023-6048, 2012. doi: 10.3390/s120506023
  18. P. B. Bro, C. Rosenberger, H. Laurent, C. Gaete-Eastman, M. Fernández, and M. A. Moya-León, "A support vector machine as an estimator of mountain papaya ripeness using resonant frequency or frequency centroid," in IFIP International Conference on Artificial Intelligence in Theory and Practice, Santiago, Chile, Aug. 2006, pp. 335-344. doi: 10.1007/978-0-387-34747-9_35
  19. C. C. Lien, C. Ay, and C. H. Ting, "Non-destructive impact test for assessment of tomato maturity," Journal of Food Engineering, vol. 91, no. 3, pp. 402-407, 2009. doi: 10.1016/j.jfoodeng.2008.09.036
  20. D. Z. H. Arenga, J. C. Dela Cruz, and D. Z. H. Arenga, "Ripeness classification of cocoa through acoustic sensing and machine learning," in IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management, Manila, Philippines, Dec. 2017, pp. 1-6. doi: 10.1109/HNICEM.2017.8269438
  21. R. Abbaszadeh, A. Moosavian, A. Rajabipour, and G. Najafi, "An intelligent procedure for watermelon ripeness detection based on vibration signals," Journal of Food Science and Technology, vol. 52, no. 2, pp. 1075-1081, 2013. doi: 10.1007/s13197-013-1068-x
  22. K. Kangune, V. Kulkarni, and P. Kosamkar, "Grapes ripeness estimation using convolutional neural network and support vector machine," in Global Conference for Advancement in Technology, Bangaluru, India, Oct. 2019, pp. 1-5. doi: 10.1109/GCAT47503.2019.8978341
  23. Y. Zhang, J. Lian, M. Fan, and Y. Zheng, "Deep indicator for fine-grained classification of banana's ripening stages," EURASIP Journal on Image and Video Processing, vol. 2018, 46, 2018. doi: 10.1186/s13640-018-0284-8
  24. A. Chaikaew, T. Thanavanich, P. Duangtang, K. Sriwanna, and W. Jaikhang, "Convolutional neural network for pineapple ripeness classification machine," in 16th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, Pattaya, Thailand, Jul. 2019, pp. 373-376. doi: 10.1109/ECTI-CON47248.2019.8955408
  25. W. Kharamat, M. Wongsaisuwan, and N. Wattanamongkhol, "Durian ripeness classification from the knocking sound using convolutional neural network," in 8th International Electrical Engineering Congress, Chiang Mai, Thailand, Mar. 2020, pp. 1-4. doi: 10.1109/iEECON48109.2020.229571
  26. Faridah, G. O. F. Parikesit, and Ferdiansjah, "Coffee bean grade determination based on image parameter," Telkomnika, vol. 9, no. 3, pp. 547-554, 2011. doi: 10.12928/telkomnika.v9i3.747
  27. H. Vaviya,1 V. Vishwakarma, A. Yadav, and N. Shah, "Identification of artificially ripened fruits using machine learning," in 2nd International Conference on Advances in Science & Technology, Mumbai, India, Apr. 2019, pp. 1-6. doi: 10.2139/ssrn.3368903
  28. M. A. M. Fuad et al., "Training of convolutional neural network using transfer learning for Aedes Aegypti larvae," Telkomnika, vol. 16, no. 4, pp.White Paper 1894-1900, 2018. doi: 10.12928/telkomnika.v16i4.8744
  29. H. Prasetyo and B. A. Putra Akardihas, "Batik image retrieval using convolutional neural network," Telkomnika, vol. 17, no. 6, pp. 3010-3018, 2019. doi: 10.12928/telkomnika.v17i6.12701
  30. R. F. Rachmadi and I. K. E. Purnama, "Paralel spatial pyramid convolutional neural network untuk verifikasi kekerabatan berbasis citra wajah," Jurnal Teknologi dan Sistem Komputer, vol. 6, no. 4, pp. 152-157, 2018. doi: 10.14710/jtsiskom.6.4.2018.152-157
  31. N. Nurajijah and D. Riana, "Algoritma naïve bayes, decision tree, dan SVM untuk klasifikasi persetujuan pembiayaan nasabah koperasi syariah," Jurnal Teknologi dan Sistem Komputer, vol. 7, no. 2, pp. 77-82, 2019. doi: 10.14710/jtsiskom.7.2.2019.77-82
  32. I. M. G. Sunarya et al., "Deteksi arteri karotis pada citra ultrasound b-mode berbasis convolution neural network single shot multibox detector," Jurnal Teknologi dan Sistem Komputer, vol. 7, no. 2, pp. 56-63, 2019. doi: 10.14710/jtsiskom.7.2.2019.56-63
  33. MathWorks, "Deep learning for signal processing with MATLAB," White Paper, 2019

Last update: 2021-03-06 15:58:04

No citation recorded.

Last update: 2021-03-06 15:58:06

No citation recorded.
Copyright (c) 2020 Jurnal Teknologi dan Sistem Komputer
under http://creativecommons.org/licenses/by-sa/4.0.

Starting in 2021, the author(s) whose article is published in the JTSiskom journal attain the copyright for their article. By submitting the manuscript to JTSiskom, the author(s) agree with this policy. No special document approval is required.

The author(s) guarantee that their article is original, written by the mentioned author(s), has never been published before, does not contain statements that violate the law, does not violate the rights of others, is subject to copyright that is held exclusively by the author(s), and is free from the rights of third parties, and that the necessary written permission to quote from other sources has been obtained by the author(s).

The author(s) retain all rights to the published work, such as (but not limited to) the following rights:

  • Copyright and other proprietary rights related to articles, such as patents,
  • The right to use the substance of the article in its own future works, including lectures and books,
  • The right to reproduce articles for its own purposes,
  • The right to archive articles yourself (please read our deposit policy), and
  • The right to enter into separate additional contractual arrangements for the non-exclusive distribution of published versions of articles (for example, posting them to institutional repositories or publishing them in a book), with acknowledgment of its initial publication in this journal (Journal of Technology and Computer Systems).

If the article was prepared jointly by more than one author, each author submitting the manuscript warrants that they have been given permission by all co-authors to agree to copyright and license notices (agreements) on their behalf, and agree to notify the co-authors of the terms of this policy. JTSiskom will not be held responsible for anything that may arise because of the writer's internal dispute. JTSiskom will only communicate with correspondence authors.

Authors should also understand that once published, their articles (and any additional files, including data sets, and analysis/computation data) will become publicly available. The license of published articles (and additional data) will be governed by the Creative Commons Attribution license as currently featured on the Creative Commons Attribution-ShareAlike 4.0 International License. JTSiskom allows users to copy, distribute, display and perform work under license. Users need to attribute the author(s) and JTSiskom to distribute works in journals and other publication media. Unless otherwise stated, the author(s) is a public entity as soon as the article is published.