Integration of Thermal Images and Agricultural Data for Multi-Class Classification of Palm Seed Origin using MobileNet
DOI:
https://doi.org/10.52436/1.jutif.2026.7.1.4879Keywords:
Hyperparameter tuning, MobileNet, Palm seed classification, Precision agricultureAbstract
This research develops a palm kernel origin classification model by combining thermal images and numerical agricultural data using MobileNet architecture. The quality of palm kernels is highly influenced by origin and environmental conditions, but manual visual identification is difficult. Therefore, a machine learning-based approach is applied to improve classification accuracy. The dataset consists of 7.257 thermal images representing 73 seed origin classes, as well as supporting data in the form of soil, fruit, and socioeconomic information collected from plantations in Aceh, Indonesia. The MobileNet model was tested in two scenarios: using only thermal images, as well as a combination of thermal images with agricultural data. Results show that data integration provides significant performance improvement. The best model was obtained from MobileNet V3-Large with the optimal hyperparameter configuration (batch size 16, learning rate 0.001, and optimizer Adam), resulting in test accuracy of 99.04%, validation 97.25%, and training 98.77%. This finding opens up opportunities for the application of real-time classification technology in the plantation environment, especially to support precision and sustainable agriculture.
Downloads
References
R. Santosa, H. Haryadi, and D. Artis, “Analisis faktor-faktor yang mempengaruhi ekspor minyak kelapa sawit Indonesia ke Uni Eropa,” e-Journal Perdagangan Industri dan Moneter, vol. 10, no. 1, pp. 63–70, Mar. 2022, doi: 10.22437/pim.v10i1.14212.
“BADAN PUSAT STATISTIK BPS-STATISTICS INDONESIA,” 2024.
H. Tandra, A. I. Suroso, Y. Syaukat, and M. Najib, “The Determinants of Competitiveness in Global Palm Oil Trade,” Economies, vol. 10, no. 6, p. 132, Jun. 2022, doi: 10.3390/economies10060132.
D. L. Corwin, “Climate change impacts on soil salinity in agricultural areas,” Eur J Soil Sci, vol. 72, no. 2, pp. 842–862, Mar. 2021, doi: 10.1111/ejss.13010.
H. Singh, B. K. Northup, C. W. Rice, and P. V. V. Prasad, “Biochar applications influence soil physical and chemical properties, microbial diversity, and crop productivity: a meta-analysis,” Biochar, vol. 4, no. 1, p. 8, Dec. 2022, doi: 10.1007/s42773-022-00138-1.
M. A. Farooq, W. Shariff, D. O’callaghan, A. Merla, and P. Corcoran, “On the Role of Thermal Imaging in Automotive Applications: A Critical Review,” IEEE Access, vol. 11, pp. 25152–25173, 2023, doi: 10.1109/ACCESS.2023.3255110.
S. Zolfagharnassab, A. R. B. M. Shariff, R. Ehsani, H. Z. Jaafar, and I. Bin Aris, “Classification of Oil Palm Fresh Fruit Bunches Based on Their Maturity Using Thermal Imaging Technique,” Agriculture, vol. 12, no. 11, p. 1779, Oct. 2022, doi: 10.3390/agriculture12111779.
E. Elfatimi, R. Eryigit, and L. Elfatimi, “Beans Leaf Diseases Classification Using MobileNet Models,” IEEE Access, vol. 10, pp. 9471–9482, 2022, doi: 10.1109/ACCESS.2022.3142817.
R. R. Danda, “Innovations in Agricultural Machinery: Assessing the Impact of Advanced Technologies on Farm Efficiency,” Journal of Artificial Intelligence and Big Data, vol. 2, no. 1, pp. 64–83, May 2022, doi: 10.31586/jaibd.2022.1156.
S. A. Bhat and N.-F. Huang, “Big Data and AI Revolution in Precision Agriculture: Survey and Challenges,” IEEE Access, vol. 9, pp. 110209–110222, 2021, doi: 10.1109/ACCESS.2021.3102227.
M. Francis, K. S. M. Anbananthen, D. Chelliah, S. Kannan, S. Subbiah, and J. Krishnan, “Smart Farm-Care using a Deep Learning Model on Mobile Phones,” Emerging Science Journal, vol. 7, no. 2, pp. 480–497, Feb. 2023, doi: 10.28991/ESJ-2023-07-02-013.
C. Fan, M. Chen, X. Wang, J. Wang, and B. Huang, “A Review on Data Preprocessing Techniques Toward Efficient and Reliable Knowledge Discovery From Building Operational Data,” Front Energy Res, vol. 9, Mar. 2021, doi: 10.3389/fenrg.2021.652801.
J. Li et al., “Comparison of the effects of imputation methods for missing data in predictive modelling of cohort study datasets,” BMC Med Res Methodol, vol. 24, no. 1, p. 41, Feb. 2024, doi: 10.1186/s12874-024-02173-x.
C. Edlund et al., “LIVECell—A large-scale dataset for label-free live cell segmentation,” Nat Methods, vol. 18, no. 9, pp. 1038–1045, Sep. 2021, doi: 10.1038/s41592-021-01249-6.
A. Bommert, T. Welchowski, M. Schmid, and J. Rahnenführer, “Benchmark of filter methods for feature selection in high-dimensional gene expression survival data,” Brief Bioinform, vol. 23, no. 1, Jan. 2022, doi: 10.1093/bib/bbab354.
I. Muraina, “IDEAL DATASET SPLITTING RATIOS IN MACHINE LEARNING ALGORITHMS: GENERAL CONCERNS FOR DATA SCIENTISTS AND DATA ANALYSTS,” Jun. 2022.
Y. Lin, Y. Zhang, and X. Yang, “A Low Memory Requirement MobileNets Accelerator Based on FPGA for Auxiliary Medical Tasks,” Bioengineering, vol. 10, no. 1, p. 28, Dec. 2022, doi: 10.3390/bioengineering10010028.
P. Zhang, E. Lo, and B. Lu, “High Performance Depthwise and Pointwise Convolutions on Mobile Devices,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 6795–6802, Apr. 2020, doi: 10.1609/aaai.v34i04.6159.
W. Wang, Y. Hu, T. Zou, H. Liu, J. Wang, and X. Wang, “A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers,” Comput Intell Neurosci, vol. 2020, pp. 1–10, Aug. 2020, doi: 10.1155/2020/8817849.
J. Liu, M. Li, Y. Luo, S. Yang, W. Li, and Y. Bi, “Alzheimer’s disease detection using depthwise separable convolutional neural networks,” Comput Methods Programs Biomed, vol. 203, p. 106032, May 2021, doi: 10.1016/j.cmpb.2021.106032.
H. Jin, “Hyperparameter Importance for Machine Learning Algorithms,” Jan. 2022.
S. Sathyanarayanan, “Confusion Matrix-Based Performance Evaluation Metrics,” African Journal of Biomedical Research, pp. 4023–4031, Nov. 2024, doi: 10.53555/AJBR.v27i4S.4345.
C. S. Hong and T. G. Oh, “TPR-TNR plot for confusion matrix,” Commun Stat Appl Methods, vol. 28, no. 2, pp. 161–169, Mar. 2021, doi: 10.29220/CSAM.2021.28.2.161.
M. Heydarian, T. E. Doyle, and R. Samavi, “MLCM: Multi-Label Confusion Matrix,” IEEE Access, vol. 10, pp. 19083–19095, 2022, doi: 10.1109/ACCESS.2022.3151048.
S. Puttinaovarat, S. Chai-Arayalert, and W. Saetang, “Oil Palm Bunch Ripeness Classification and Plantation Verification Platform: Leveraging Deep Learning and Geospatial Analysis and Visualization,” ISPRS Int J Geoinf, vol. 13, no. 5, p. 158, May 2024, doi: 10.3390/ijgi13050158.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yusuf Abidin Nurrahman, Rifki Wijaya, Tjokorda Agung Budi Wirayuda
This work is licensed under a Creative Commons Attribution 4.0 International License.
