Res. Agr. Eng., 2024, 70(3):123-133 | DOI: 10.17221/65/2023-RAE

The effect of parameter adjustment in sago palm classification-based convolutional neural network (CNN) modelOriginal Paper

Sri Murniani Angelina Letsoin, David Herák ORCID...
Department of Mechanical Engineering, Faculty of Engineering, Czech University of Life Sciences Prague, Prague, Czech Republic

In our study location, Merauke Regency, the easternmost city in Indonesia, the sago palm is associated with different types of ecosystems and other non-sago vegetation. During the harvesting season, the white flowers blossoming between the leaves on the tops of palm trees may be distinguished manually. Four classes were determined to address the visual inspections involving different parameters that were examined through the metric evaluation and then analysed statistically. The computed Kruskal-Wallis test found that the parameters vary in each network with a P-value of 0.00341, with at least one class being higher than the others, i.e., non-sago with a P-value of 0.044 with respect to precision, recall, and F1-score. Thus, the general linear model (GLM) was tested specifically in trained Network-15 and Network-17, which have similar parameters except for the batch size. It indicated the two networks' differences based on their prediction results, classes, and actual images. Accordingly, a combination of learning rate (Lr) and batch size improved the reliability of the training and classification task.

Keywords: deep learning; detection; model; parameter; transfer learning

Received: June 30, 2023; Revised: March 18, 2024; Accepted: March 22, 2024; Prepublished online: July 16, 2024; Published: September 29, 2024  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Letsoin SMA, Herák D. The effect of parameter adjustment in sago palm classification-based convolutional neural network (CNN) model. Res. Agr. Eng. 2024;70(3):123-133. doi: 10.17221/65/2023-RAE.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Akshit Rajesh Tayade, Safari-Katesari H. (2023): A statistical analysis to develop machine learning models: Prediction of user diet type.
    2. Amin N., Sabli N., Izhar S., Yoshida H. (2019): Sago wastes and its applications. 1841-1862.
    3. da Silva F.G., Ramos L.P., Palm B.G., Machado R. (2022): Assessment of machine learning techniques for oil rig classification in c-band sar images. Remote Sensing, 14: 2966. Go to original source...
    4. Ehara H., Toyoda Y., Johnson D.V. (2018): Sago palm: Multiple contributions to food security and sustainable livelihoods. Springer, Singapore. Go to original source...
    5. Hidayat S., Matsuoka M., Baja S., Rampisela D.A. (2018): Object-based image analysis for sago palm classification: The most important features from high-resolution satellite imagery. Remote Sensing, 10: 1319. Go to original source...
    6. Jonatan N.J., Ekayuliana A., Dhiputra I.M.K., Nugroho Y.S. (2017): The utilization of Metroxylon Sago (Rottb.) dregs for low bioethanol as fuel households needs in Papua province Indonesia. KnE Life Sciences, 3: 150. Go to original source...
    7. Karim A.A., Tie A.P.L., Manan D.M.A., Zaidul I.S.M. (2008): Starch from the Sago (Metroxylon sagu) palm tree properties, prospects, and challenges as a new industrial source for food and other uses. Comprehensive Reviews in Food Science and Food Safety, 7: 215-228. Go to original source...
    8. Kneusel R.T. (2021): Practical Deep Learning: A Python-based Introduction (1st ed.). No Starch Press, Inc., San Francisco.
    9. Kumar S., Janet B. (2022): DTMIC: Deep transfer learning for malware image classification. Journal of Information Security and Applications, 64: 103063. Go to original source...
    10. Lin K., Zhao Y., Wang L., Shi W., Cui F., Zhou T. (2023): MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting. Frontiers of Environmental Science & Engineering, 17: 77. Go to original source...
    11. Li Z., Kristoffersen E., Li J. (2022): Deep transfer learning for failure prediction across failure types. Computers & Industrial Engineering, 172: 108521. Go to original source...
    12. Metaragakusuma A.P., Katsuya O., Bai H. (2016): An overview of the traditional use of sago for sago-based food industry in Indonesia. KnE Life Sciences, 3: 119. Go to original source...
    13. Mofu S.S., Abbas B. (2015): Development of sago palm research and agroindustry in University of Papua. In: Proceeding of the 12th International Sago Symposium in Tokyo, Japan. Sept 15-16, 2015. Japan Society for the Promotion Science.
    14. Mukoya E., Rimiru R., Kimwele M., Gakii C., Mugambi G. (2023): Accelerating deep learning inference via layer truncation and transfer learning for fingerprint classification. Concurrency and Computation: Practice and Experience, 35: e7619. Go to original source...
    15. Santillan J.R., Makinano-Santillan M. (2016): Recent Distribution of Sago Palms in the Philippines. In: M.J.D. Paluga (Ed.): University of the Philippines: Mindanao, Philippines, 186.
    16. Usmani I.A., Qadri M.T., Zia R., Alrayes F.S., Saidani O., Dashtipour K. (2023): Interactive effect of learning rate and batch size to implement transfer learning for brain tumor classification. Electronics, 12: 964. Go to original source...
    17. Wahed Z., Joseph A., Zen H., Kipli K. (2022): Sago palm detection and its maturity identification based on improved convolution neural network. Pertanika Journal of Science and Technology, 30: 1219-1236. Go to original source...
    18. Yasir M., Jianhua W., Shanwei L., Sheng H., Mingming X., Hossain M. (2023): Coupling of deep learning and remote sensing: A comprehensive systematic literature review. International Journal of Remote Sensing, 44: 157-193. Go to original source...
    19. Zheng J., Fu H., Li W., Wu W., Yu L., Yuan S., Tao W.Y.W., Pang T.K., Kanniah K.D. (2021): Growing status observation for oil palm trees using unmanned aerial vehicle (UAV) images. ISPRS Journal of Photogrammetry and Remote Sensing, 173: 95-121. Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content