ISSN: 2226-3624
Open access
This study investigates a hybrid approach for determining optimal date-fruit harvest timing by integrating deep visual features from Convolutional Neural Networks (CNNs) with the Mahalanobis Taguchi System (MTS). High- resolution images of date fruits spanning canonical maturity stages (Kimri, Khalal, Rutab, Tamr) are processed through a pretrained CNN to extract discriminative embeddings emphasizing color, texture, and size cues. Candidate features are organized and screened using MTS orthogonal arrays and signal-to-noise (S/N) analysis to identify a parsimonious subset that maximizes class separability while minimizing redundancy. The Mahalanobis Distance (MD) then calibrated on a “healthy/optimal” reference space to yield decision thresholds for harvest readiness. The pipeline includes stratified cross-validation, ablation of feature groups, and comparisons against conventional machine-learning baselines using the same inputs. Results indicate that MTS-guided feature selection consistently improves generalization and interpretability, producing stable MD thresholds that align with horticultural expectations and reducing computational overhead relative to full-feature CNN embeddings. Beyond classification, the framework yields actionable diagnostic feature contribution ranks and MD control charts, that support field decisions and quality control. The proposed CNN-MTS methodology provides a transparent, statistically grounded route to operationalize computer vision for harvest scheduling and offers a reusable template for similar post-harvest applications where explainability and small-sample robustness are essential.
Akter, T., Kuang, D., Niu, M., Huang, Q., Zhang, K., Wang, L., & Huang, M. (2024). A comprehensive review of external quality measurements for fruit grading: Investigation on evaluation criteria and prospects. Postharvest Biology and Technology, 218, 113021. https://doi.org/10.1016/j.postharvbio.2024.113021
Alqahtani, N. K., Ali, S. A., & Alnemr, T. M. (2025). Quality preservation of date palm (Phoenix dactylifera L.) fruits at the Khalal stage: A review on current challenges, preservation methods, and future trends. Frontiers in Sustainable Food Systems, 9, 1558985. https://doi.org/10.3389/fsufs.2025.1558985
Chang, Z. P., Li, Y. W., & Fatima, N. (2019). A theoretical survey on Mahalanobis-Taguchi system. Measurement, 136, 501–510. https://doi.org/10.1016/j.measurement.2018.12.090
Chen, G., Liu, B., Lei, H., Xiao, J., Yang, H., Chen, J., & Zhang, X. (2024). A lightweight color-changing melon ripeness detection method for non-destructive grading and harvest prediction based on a deep learning framework. Frontiers in Plant Science, 15, 1466171. https://doi.org/10.3389/fpls.2024.1466171
Chuquimarca, L. E., Vintimilla, B. X., & Velastin, S. A. (2024). A review of external quality inspection for fruit grading using CNN models. Artificial Intelligence in Agriculture, 14, 1–20. https://doi.org/10.1016/j.aiia.2024.10.002
Dai, D., Pan, J., & Liang, Y. (2022). Regularized estimation of the Mahalanobis distance based on modified Cholesky decomposition. Communications in Statistics: Case Studies, Data Analysis and Applications, 8(4), 559–573. https://doi.org/10.1080/23737484.2022.2107961
Ghnimi, S., Umer, S., Karim, A., & Kamal-Eldin, A. (2017). Date fruit (Phoenix dactylifera L.): An underutilized food seeking industrial valorization. NFS Journal, 6, 1–10. https://doi.org/10.1016/j.nfs.2016.12.001
Goh, J. Y., Hamid, S. S. A., Tajudin, N., Othman, A. P., Zulkifli, W. M. F. W., Khalid, M. A., & Asri, A. (2025). Fresh fruit bunch ripeness classification methods: A review. Food and Bioprocess Technology, 18, 1626–1662. https://doi.org/10.1007/s11947-025-03334-5
Halim, N. A. M., Abu, M. Y., Razali, N. S., Aris, N. H., Sari, E., Jaafar, N. N., Abdul Ghani, A. S., Ramlie, F., Wan Muhamad, W. Z. A., & Harudin, N. (2025). Impact of Mahalanobis-Taguchi System on health performance among academicians. International Journal of Technology, 16(3), 846–864. https://doi.org/10.14716/ijtech.v16i3.7226
Hassan, E., Abu Ghazalah, S., El-Rashidy, N., Abd El-Hafeez, T., & Shams, M. Y. (2025). Sustainable deep vision systems for date fruit quality assessment using attention-enhanced deep learning models. Frontiers in Plant Science, 16, 1521508. https://doi.org/10.3389/fpls.2025.1521508
Razali, N. S., Abu, M. Y., Zaini, S. N. A. M., Aris, N. H., Halim, N. A. M., & Sari, E. (2024). A review on Mahalanobis-Taguchi system and time-driven activity-based costing for production environment. Journal of Modern Manufacturing Systems and Technology, 8(2), 1–11.
Rybacki, P., Niemann, J., Derouiche, S., Chetehouna, S., Boulaares, I., Seghir, N. M., Diatta, J., & Osuch, A. (2024). Convolutional Neural Network (CNN) model for the classification of varieties of date palm fruits (Phoenix dactylifera L.). Sensors, 24(2), 558. https://doi.org/10.3390/s24020558
Setiawan, D., Utomo, P. E. P., & Alfalah, M. (2025). Detection of oil palm fruit ripeness through image processing using convolutional neural network. Journal of Informatics and Visualization, 8(4), 105–114. https://doi.org/10.30630/joiv.8.4.1447
Tang, C., Liu, Q., Zhang, Z., Jiao, D., Kang, X., Zhang, Y., & Fu, X. (2023). Fine recognition of strawberry ripeness in natural scenes based on light-weight convolutional neural network. Frontiers in Plant Science, 14, 1123562. https://doi.org/10.3389/fpls.2023.1123562
Wang, C., Liu, S., Wang, Y., Xiong, J., Zhang, Z., Zhao, B., Lin, J., Li, Z., & He, P. (2022). Application of convolutional neural network-based detection methods in fresh fruit production: A comprehensive review. Frontiers in Plant Science, 13, 868745. https://doi.org/10.3389/fpls.2022.868745
Mandan, S. A., Jamaludin, K. R. Bin, Mandan, A. A., Mandan, I. A., Sikandar, S., Jatoi, M. A., & Soomro, A. A. (2026). CNN Feature Characterization via the Mahalanobis Taguchi System for Recognizing Optimal Date-Fruit Harvest: A Systematic Literature Review. International Journal of Academic Research in Economics and Management Sciences, 15(1), 85-96.
Copyright: © 2026 The Author(s)
Published by HRMARS (www.hrmars.com)
This article is published under the Creative Commons Attribution (CC BY 4.0) license. Anyone may reproduce, distribute, translate and create derivative works of this article (for both commercial and non-commercial purposes), subject to full attribution to the original publication and authors. The full terms of this license may be seen at: http://creativecommons.org/licences/by/4.0/legalcode