Improving the Accuracy of Deep-Learning Models for Coconut Maturity Classification Using Acoustic Signals
Article Sidebar
Read Counter : 159
Download : 147
Main Article Content
Abstract
Nowadays, the development of signal processing technology, advanced intelligent systems and deep learning have become commonplace in agricultural technology. One of the agricultural commodities that are widely available in the world is coconut. Unfortunately, the application of post-harvest agricultural technology is very minimal in coconut farming. So far, farmers have determined the maturity of coconuts by listening to the sound of the coconut being knocked so that it takes a lot of time to check the maturity level. This paper will discuss improving the accuracy of deep learning models in classifying coconuts based on acoustic signals. For the trial of the classification of the maturity level of coconuts, a deep learning method consisting of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) was used. And using an open access dataset consisting of samples used of 129 coconuts with three classification levels - premature, mature and overmature (Caladcad, 2023). In this paper, we propose an improvement in the deep learning model architecture with learning rate parameters of 0.0001, epoch 500, Batch-Normalization and Dropout 0.3 with the results of the coconut acoustic signal classification test having a data testing accuracy of 98.36% and an F1 Score of 99%. The results of this trial are better than the previous trial (Caladcad, 2024) with an accuracy of 97.42% and an F1 Score of 97.20%. and shows that the improvement of the deep learning combination method produces a more reliable coconut ripeness classification system, and is free from class bias
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The proposed policy for journals that offer open access
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- Author grant the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
References
June Anne Caladcad, Shiela Cabahug, Mary Rose Catamco, Paul Elyson Villaceran, Leizel Cosgafa, Karl Norbert Cabizares, Marfe Hermosilla, 2020. Determining philippine coconut maturity level using machine learning algorithms based on acoustic signal. Computers and electronics in agriculture, 172:105327, 2020.
Salsabila, A., Oktavia, A., Dewi, F. M., Purwani, Y., Arsy, F. S., Albar, R., Priyanti, P., Khairiah, A., & Des, M. (2022). Nilai manfaat ekonomi tanaman kelapa (Cocos nucifera L.) di Pasar Tradisional Kemiri Muka di Kota Depok, Jawa Barat. Prosiding SEMNAS BIO 2022, Universitas Islam Negeri (UIN) Syarif Hidayatullah Jakarta, 242–251.
Terdwongworakul, A., Chaiyapong, S., Jarimopas, B., & Meeklangsaen, W. (2009). Physical properties of fresh young Thai coconut for maturity sorting. Biosystems Engineering, 103(2), 208–216.
J. A. Caladcad, E. Piedad, 2024.Deep learning classification system for coconut maturity levels based on acoustic signals, 2024 IEEE 12th Region 10 Humanitarian Technology Conference (R10-HTC), Kuala Lumpur, Malaysia, 2024, doi: 10.1109/R10-HTC59322.2024.10778826.
Jurafsky, D., & Martin, J. H. (2023). Speech and language processing (3rd ed., draft). Retrieved from https://web.stanford.edu/~jurafsky/slp3/
Gatchalian, M.M., De Leon, S.Y., Yano, T., 1994. Measurement of Young Coconut (Cocos nucifera, L.) Maturity by Sound Waves. Journal of Food Eng. 23, 253–276.
June Anne Caladcad., 2023. Acoustic dataset of coconut (cocosnucifera) based on tapping system. Data in Brief, 47:108936, 2023.
Tuan-Tang Le, Chyi-Yeu Lin, 2019. Deep learning for noninvasive classification of clustered horticultural crops–a case for banana fruit tiers. Postharvest Biology and Technology, 156:110922, 2019.
Abdelali Belkhou, Atman Jbari, Othmane El Badlaoui, 2021. A computer-aided-diagnosis system for neuromuscular diseases using mel frequency cepstral coefficients. Scientific African, 13: e00904.
J. Salamon and J. P. Bello,2017. Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification, in IEEE Signal Processing Letters, vol. 24, no. 3, pp. 279-283, March 2017, doi: 10.1109/LSP.2017.2657381.
Jielong Ni, Zao Tang, Jia Liu, Pingliang Zeng, Chimeddorj Baldorj, 2023. A topology identification method based on one-dimensional convolutional neural network for distribution network. Energy Reports, 9:355–362, 2023.
Thomas Fischer, Christopher Krauss, 2018. Deep learning with long short-term memory networks for financial market predictions. European journal of operational research, 270 :654–669, 2018.