Addressing Class Imbalance in Oil Palm Disease and Micronutrient Deficiency Detection Using Meta-Learned Transfer Metric Learning

Authors

  • Hartono Hartono Universitas Medan Area
  • Erianto Ongko Institut Modern Arsitektur dan Teknologi

DOI:

https://doi.org/10.29207/resti.v9i5.6857

Keywords:

Class Imbalance, Oil Palm, Transfer Metric Learning, MW-FixMatch, MetaTMLDA

Abstract

Class imbalance is a major challenge in oil palm disease and nutrient deficiency detection, where healthy samples dominate while diseased or deficient cases are underrepresented, often leading to biased models with high false-negative rates. To address this issue, this study proposes MetaTMLDA (Meta-Learned Transfer Metric Learning with Distribution Alignment), a hybrid framework that combines Transfer Metric Learning (TML) with MW-FixMatch. TML learns discriminative and domain-invariant features, while MW-FixMatch employs a meta-learned weighting mechanism to adaptively reweight samples, improving sensitivity to minority classes and enhancing robustness against pseudo-label noise. Experiments on four public datasets—Ganoderma Disease Detection, Palm Oil Leaf Disease, and Leaf Nutrient Detection for Boron and Magnesium—demonstrated that the proposed method consistently outperforms TML-DA, MW-FixMatch, SMOTE, Random Undersampling, and Biased SVM. On the smaller datasets (Ganoderma and Palm Oil Leaf Disease), MetaTMLDA achieved accuracy of 0.976, precision 0.951, recall 0.915, Cohen’s Kappa 0.912, and macro F1-score 0.933 for Ganoderma, and accuracy of 0.980, precision 0.972, recall 0.957, Kappa 0.911, and macro F1-score 0.964 for Palm Oil Leaf Disease. On the larger datasets (Boron and Magnesium), the model reached near-perfect accuracy of 0.995, with precision up to 0.967, recall up to 0.973, Kappa above 0.919, and macro F1-scores up to 0.969, highlighting its robustness and balanced predictive performance. These findings confirm that MetaTMLDA effectively addresses both class imbalance and domain shift, providing a scalable solution for precision agriculture through earlier and more reliable detection of oil palm health issues.

Downloads

Download data is not yet available.

References

H. Hartono and E. Ongko, “Hybrid Approach with Distance Feature for Multi-Class Imbalanced Datasets,” JOIV : International Journal on Informatics Visualization, vol. 7, no. 1, pp. 131–138, Feb. 2023, doi: 10.30630/joiv.7.1.1292.

M. Błaszczyk and J. Jȩdrzejowicz, “Framework for imbalanced data classification,” Procedia Computer Science, vol. 192, pp. 3477–3486, Jan. 2021, doi: 10.1016/j.procs.2021.09.121.

K. Dabrock, J. Ulken, N. Pflugradt, J. M. Weinand, and D. Stolten, “Generating a nationwide residential building types dataset using machine learning,” Building and Environment, vol. 274, p. 112782, Apr. 2025, doi: 10.1016/j.buildenv.2025.112782.

Hartono and R. B. Y. Syah, “Hybrid Approach with Membership-Density Based Oversampling for handling multi-class imbalance in Internet Traffic Identification with overlapping and noise,” ICT Express, vol. 10, no. 5, pp. 1094–1102, Oct. 2024, doi: 10.1016/j.icte.2024.04.007.

H. Ghazouani, W. Barhoumi, E. Chakroun, and A. Chehri, “Dealing with Unbalanced Data in Leaf Disease Detection: A Comparative Study of Hierarchical Classification, Clustering-based Undersampling and Reweighting-based Approaches,” Procedia Computer Science, vol. 225, pp. 4891–4900, Jan. 2023, doi: 10.1016/j.procs.2023.10.489.

K. Sai, N. Sood, and I. Saini, “Classification of various nutrient deficiencies in tomato plants through electrophysiological signal decomposition and sample space reduction,” Plant Physiology and Biochemistry, vol. 186, pp. 266–278, Sept. 2022, doi: 10.1016/j.plaphy.2022.07.022.

B. Talukdar, “Handling of Class Imbalance for Plant Disease Classification with Variants of GANs,” in 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), Nov. 2020, pp. 466–471. doi: 10.1109/ICIIS51140.2020.9342728.

A. A. Khan, O. Chaudhari, and R. Chandra, “A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation,” Expert Systems with Applications, vol. 244, p. 122778, June 2024, doi: 10.1016/j.eswa.2023.122778.

M. Vasconcelos and L. Cavique, “Mitigating false negatives in imbalanced datasets: An ensemble approach,” Expert Systems with Applications, vol. 262, p. 125674, Mar. 2025, doi: 10.1016/j.eswa.2024.125674.

Y. W. Khoo and K. P. Chong, “Ganoderma boninense: general characteristics of pathogenicity and methods of control,” Front Plant Sci, vol. 14, p. 1156869, July 2023, doi: 10.3389/fpls.2023.1156869.

X. Song et al., “Effect of boron deficiency on the photosynthetic performance of sugar beet cultivars with contrasting boron efficiencies,” Front. Plant Sci., vol. 13, Jan. 2023, doi: 10.3389/fpls.2022.1101171.

M. Ariza-Sentís, S. Vélez, R. Martínez-Peña, H. Baja, and J. Valente, “Object detection and tracking in Precision Farming: a systematic review,” Computers and Electronics in Agriculture, vol. 219, p. 108757, Apr. 2024, doi: 10.1016/j.compag.2024.108757.

P. Goel and A. Ganatra, “Unsupervised Domain Adaptation for Image Classification and Object Detection Using Guided Transfer Learning Approach and JS Divergence,” Sensors, vol. 23, no. 9, Art. no. 9, Jan. 2023, doi: 10.3390/s23094436.

D. Cacciarelli and M. Kulahci, “Active learning for data streams: a survey,” Mach Learn, vol. 113, no. 1, pp. 185–239, Jan. 2024, doi: 10.1007/s10994-023-06454-2.

X. Wang et al., “Dual adversarial network with meta-learning for domain-generalized few-shot text classification,” Applied Soft Computing, vol. 146, p. 110697, Oct. 2023, doi: 10.1016/j.asoc.2023.110697.

N. Moniz and V. Cerqueira, “Automated imbalanced classification via meta-learning,” Expert Systems with Applications, vol. 178, p. 115011, Sept. 2021, doi: 10.1016/j.eswa.2021.115011.

H. Chamlal, H. Kamel, and T. Ouaderhman, “A hybrid multi-criteria meta-learner based classifier for imbalanced data,” Knowledge-Based Systems, vol. 285, p. 111367, Feb. 2024, doi: 10.1016/j.knosys.2024.111367.

Y. Guo et al., “Meta-ensemble learning with adaptive sampling for imbalanced medical Raman spectroscopy data,” Applied Soft Computing, vol. 176, p. 113142, May 2025, doi: 10.1016/j.asoc.2025.113142.

M. Jindal and B. Singh, “Class imbalance-aware domain specific transfer learning approach for medical image classification: Application on COVID-19 detection,” Engineering Applications of Artificial Intelligence, vol. 150, p. 110583, June 2025, doi: 10.1016/j.engappai.2025.110583.

M. Isnan, A. A. Hidayat, and B. Pardamean, “Indonesian Agricultural-crops Classification Using Transfer Learning Model,” Procedia Computer Science, vol. 227, pp. 128–136, Jan. 2023, doi: 10.1016/j.procs.2023.10.510.

M. Yan, N. Jiang, and N. Li, “TML-DA: Transfer metric learning based distribution alignment framework for domain class imbalanced classification,” Knowledge-Based Systems, vol. 311, p. 113086, Feb. 2025, doi: 10.1016/j.knosys.2025.113086.

J. Wang and X.-L. Zhang, “Improving pseudo labels with intra-class similarity for unsupervised domain adaptation,” Pattern Recognition, vol. 138, p. 109379, June 2023, doi: 10.1016/j.patcog.2023.109379.

Y. Li et al., “Imbalanced complemented subspace representation with adaptive weight learning,” Expert Systems with Applications, vol. 249, p. 123555, Sept. 2024, doi: 10.1016/j.eswa.2024.123555.

X. Zheng, W. Hong, D. Chen, A. Xue, and Y. Kong, “MW-FixMatch: A class imbalance semi-supervised learning algorithm based on re-weighting,” Neurocomputing, vol. 626, p. 129385, Apr. 2025, doi: 10.1016/j.neucom.2025.129385.

R. Roboflow, “Palm Leaves Disease Detection,” Roboflow. Accessed: June 14, 2025. [Online]. Available: https://universe.roboflow.com/firstproject-ofadf/palm-leaves-disease-detection

J. Guo, H. Wu, X. Chen, and W. Lin, “Adaptive SV-Borderline SMOTE-SVM algorithm for imbalanced data classification,” Applied Soft Computing, vol. 150, p. 110986, Jan. 2024, doi: 10.1016/j.asoc.2023.110986.

A. E. Yilmaz and H. Demirhan, “Weighted kappa measures for ordinal multi-class classification performance,” Applied Soft Computing, vol. 134, p. 110020, Feb. 2023, doi: 10.1016/j.asoc.2023.110020.

B. Liu and G. Tsoumakas, “Dealing with class imbalance in classifier chains via random undersampling,” Knowledge-Based Systems, vol. 192, p. 105292, Mar. 2020, doi: 10.1016/j.knosys.2019.105292.

B. S. Raghuwanshi and S. Shukla, “SMOTE based class-specific extreme learning machine for imbalanced learning,” Knowledge-Based Systems, vol. 187, p. 104814, Jan. 2020, doi: 10.1016/j.knosys.2019.06.022.

J.-J. Zhang and P. Zhong, “Learning Biased SVM with Weighted Within-Class Scatter for Imbalanced Classification,” Neural Process Lett, vol. 51, no. 1, pp. 797–817, Feb. 2020, doi: 10.1007/s11063-019-10096-8.

Downloads

Published

2025-10-28

Issue

Section

Artificial Intelligence

How to Cite

Hartono, H., & Ongko, E. (2025). Addressing Class Imbalance in Oil Palm Disease and Micronutrient Deficiency Detection Using Meta-Learned Transfer Metric Learning. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 9(5), 1273-1282. https://doi.org/10.29207/resti.v9i5.6857