Optimization of ShuffleNetV2 Using Self-Knowledge Distillation for Cocoa Fruit Disease Classification

H.R Merdu Wira  Jasa; Anjar  Wanto; Rizky Khairunnisa  Sormin

doi:10.52436/1.jutif.2026.7.3.5649

Authors

H.R Merdu Wira Jasa Information Systems, STIKOM Tunas Bangsa, Indonesia
Anjar Wanto Information Systems, STIKOM Tunas Bangsa, Indonesia
Rizky Khairunnisa Sormin Information Systems, STIKOM Tunas Bangsa, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.3.5649

Keywords:

Cocoa disease classification, Image-based classification, Lightweight CNN, Self-knowledge distillation, ShuffleNetV2

Abstract

Timely cocoa fruit disease diagnosis is critical for field management, yet manual inspection is subjective and inconsistent, while many accurate deep learning models remain too computationally demanding for practical on-device use. This study aims to optimize cocoa fruit disease classification by applying self-knowledge distillation (Self-KD) to a lightweight ShuffleNetV2 architecture without increasing inference complexity. Using a three-class dataset (healthy, pod borer, and black pod rot) with preprocessing and class balancing, ShuffleNetV2 was selected as the baseline and trained with Self-KD, improving accuracy from 96.84% to 98.34% along with consistent gains in precision, recall, and F1-score. These results indicate that Self-KD provides a learning-level optimization that enhances robustness and prediction stability in lightweight CNNs, which is especially relevant for edge AI deployment in agricultural environments. Therefore, the proposed approach supports efficient, scalable, and sustainability-oriented AI (Green/Sustainable AI) for smart farming, with potential transferability to other crops that exhibit similar visual symptom patterns.

Downloads

Download data is not yet available.

References

A. S. Adyanti, J. M. M. Aji, and E. S. Hani, “Mapping and Future Potential of Cocoa Commodity Base Regions in Indonesia,” Agro Ekonomi, vol. 36, no. 2, pp. 136–155, 2025, doi: 10.22146/ae.103907.

S. Dröge et al., “From chocolate to palm oil: The future of Indonesia’s cocoa plantations,” Ambio, vol. 54, no. 1, pp. 151–161, 2025, doi: 10.1007/s13280-024-02061-0.

J. Merga, “Epidemiology and Management Strategies of Cocoa black pod (Phytophthora spp.),” Plant Pathology & Quarantine, vol. 12, no. 1, pp. 34–39, 2022, doi: 10.5943/ppq/12/1/2.

J. B. Rola et al., “Convolutional Neural Network Model for Cacao Phytophthora Palmivora Disease Recognition,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 8, pp. 986–990, 2024, doi: 10.14569/IJACSA.2024.0150897.

J. Liu and X. Wang, “Plant diseases and pests detection based on deep learning: a review,” Plant Methods, vol. 17, no. 1, pp. 1–18, 2021, doi: 10.1186/s13007-021-00722-9.

Y. Gai and H. Wang, “Plant Disease: A Growing Threat to Global Food Security,” Agronomy, vol. 14, no. 8, pp. 1–11, 2024, doi: 10.3390/agronomy14081615.

M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” Front. Plant Sci., vol. 14, pp. 1–22, 2023, doi: 10.3389/fpls.2023.1158933.

M. Shoaib, A. Sadeghi-Niaraki, F. Ali, I. Hussain, and S. Khalid, “Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions,” Front. Plant Sci., vol. 16, pp. 1–19, 2025, doi: 10.3389/fpls.2025.1538163.

S. Wang et al., “Advances in Deep Learning Applications for Plant Disease and Pest Detection: A Review,” Remote Sens. (Basel)., vol. 17, no. 4, pp. 1–30, 2025, doi: 10.3390/rs17040698.

A. Upadhyay et al., “Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture,” Artif. Intell. Rev., vol. 58, no. 3, pp. 1–64, 2025, doi: 10.1007/s10462-024-11100-x.

M. Shafay et al., “Recent advances in plant disease detection: challenges and opportunities,” Plant Methods, vol. 21, no. 1, pp. 1–44, 2025, doi: 10.1186/s13007-025-01450-0.

J. P. Nyakuri, C. Nkundineza, O. Gatera, K. Nkurikiyeyezu, and G. Mwitende, “AI and IoT-powered edge device optimized for crop pest and disease detection,” Sci. Rep., vol. 15, no. 1, pp. 1–14, 2025, doi: 10.1038/s41598-025-06452-5.

Y. Wu, L. Chen, N. Yang, and Z. Sun, “Research Progress of Deep Learning-Based Artificial Intelligence Technology in Pest and Disease Detection and Control,” Agriculture (Switzerland), vol. 15, no. 19, pp. 1–36, 2025, doi: 10.3390/agriculture15192077.

R. Sun et al., “Survey of Image Edge Detection,” Frontiers in Signal Processing, vol. 2, pp. 1–13, 2022, doi: 10.3389/frsip.2022.826967.

X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, pp. 1–43, 2024, doi: 10.1007/s10462-024-10721-6.

M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 1–41, 2023, doi: 10.3390/computers12080151.

M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, pp. 1–23, 2023, doi: 10.3390/computation11030052.

L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, pp. 1–74, 2021, doi: 10.1186/s40537-021-00444-8.

Q. Lv, S. Zhang, and Y. Wang, “Deep Learning Model of Image Classification Using Machine Learning,” Advances in Multimedia, vol. 2022, 2022, doi: 10.1155/2022/3351256.

J. Alvarado, J. F. Restrepo-Arias, D. Velásquez, and M. Maiza, “Disease Detection on Cocoa Crops Based on Computer-Vision Techniques: A Systematic Literature Review,” Agriculture (Switzerland), vol. 15, no. 10, pp. 1–27, 2025, doi: 10.3390/agriculture15101032.

K. J. Ayikpa, A. B. Ballo, D. Mamadou, and P. Gouton, “A Hybrid Feature Fusion and Machine Learning Approach for Cocoa Pod Disease Detection,” Human-Centric Intelligent Systems, vol. 5, no. 4, pp. 531–544, 2025, doi: 10.1007/s44230-025-00117-2.

N. P. Maylianti, I. G. N. L. Wijayakusuma, and I. P. C. Arta Wiguna, “Comparison of EfficientNet-B0 and ResNet-50 for Detecting Diseases in Cocoa Fruit,” Journal of Applied Informatics and Computing, vol. 9, no. 1, pp. 115–120, 2025, doi: 10.30871/jaic.v9i1.8868.

D. Mamadou, K. J. Ayikpa, A. B. Ballo, and B. M. Kouassi, “Cocoa Pods Diseases Detection by MobileNet Confluence and Classification Algorithms,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 9, pp. 344–352, 2023, doi: 10.14569/IJACSA.2023.0140937.

X. Yue, K. Qi, X. Na, Y. Liu, F. Yang, and W. Wang, “Deep learning for recognition and detection of plant diseases and pests,” Neural Comput. Appl., vol. 37, no. 17, pp. 11265–11310, 2025, doi: 10.1007/s00521-025-11125-5.

S. Zhu and H. Gao, “MC-ShuffleNetV2: A lightweight model for maize disease recognition,” Egyptian Informatics Journal, vol. 27, no. 7, p. 100503, 2024, doi: 10.1016/j.eij.2024.100503.

H. Zhou et al., “Maize Leaf Disease Recognition Based on Improved Convolutional Neural Network ShuffleNetV2,” Plants, vol. 13, no. 12, pp. 1–18, 2024, doi: 10.3390/plants13121621.

J. Su, M. Yang, and X. Tang, “Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators,” Electronics (Switzerland), vol. 13, no. 2, pp. 1–16, 2024, doi: 10.3390/electronics13020394.

M. Xie et al., “MFFSNet: A Lightweight Multi-Scale Shuffle CNN Network for Wheat Disease Identification in Complex Contexts,” Agronomy, vol. 15, no. 4, pp. 1–19, 2025, doi: 10.3390/agronomy15040910.

L. Lu, W. Liu, W. Yang, M. Zhao, and T. Jiang, “Lightweight Corn Seed Disease Identification Method Based on Improved ShuffleNetV2,” Agriculture (Switzerland), vol. 12, no. 11, pp. 1–18, 2022, doi: 10.3390/agriculture12111929.

H. Zhou et al., “Identification of leaf diseases in field crops based on improved ShuffleNetV2,” Front. Plant Sci., vol. 15, pp. 1–17, 2024, doi: 10.3389/fpls.2024.1342123.

H. Zhao et al., “Self-Knowledge Distillation via Progressive Associative Learning,” Electronics (Switzerland), vol. 13, no. 11, pp. 1–15, 2024, doi: 10.3390/electronics13112062.

Z. Qin, S. Ni, M. Zhu, Y. Jia, S. Liu, and Y. Chen, “A Feature Map Fusion Self-Distillation Scheme for Image Classification Networks,” Electronics (Switzerland), vol. 14, no. 1, pp. 1–15, 2025, doi: 10.3390/electronics14010182.

C. Shi, M. Ding, L. Wang, and H. Pan, “Learn by Yourself: A Feature-Augmented Self-Distillation Convolutional Neural Network for Remote Sensing Scene Image Classification,” Remote Sens. (Basel)., vol. 15, no. 23, 2023, doi: 10.3390/rs15235620.

J. Yan, H. Li, Y. Bai, J. Liu, H. Lv, and Y. Bai, “Timestamp-Guided Knowledge Distillation for Robust Sensor-Based Time-Series Forecasting,” Sensors, vol. 25, no. 15, pp. 1–19, 2025, doi: 10.3390/s25154590.

J. Yu and H. Hu, “A Multi-Scale Convolutional Neural Network with Self-Knowledge Distillation for Bearing Fault Diagnosis,” Machines, vol. 12, no. 11, 2024, doi: 10.3390/machines12110792.

S. Ni et al., “An improved ShuffleNetV2 method based on ensemble self-distillation for tomato leaf diseases recognition,” Front. Plant Sci., vol. 15, no. 1, pp. 1–15, 2024, doi: 10.3389/fpls.2024.1521008.

X. Yang et al., “A Lightweight and Efficient Plant Disease Detection Method Integrating Knowledge Distillation and Dual-Scale Weighted Convolutions,” Algorithms, vol. 18, no. 7, 2025, doi: 10.3390/a18070433.

K. S. Soh, E. G. Moung, J. J. D. Khoo, J. A. Dargham, and A. Farzamnia, “Cocoa Diseases Classification using Deep Learning Algorithm,” in ITM Web of Conferences, Les Ulis, France: EDP Sciences, 2024, p. 1014. doi: 10.1051/itmconf/20246301014.

S. Kumi, D. Kelly, J. Woodstuff, R. K. Lomotey, R. Orji, and R. Deters, “Cocoa Companion: Deep Learning-Based Smartphone Application for Cocoa Disease Detection,” Procedia Comput. Sci., vol. 203, pp. 87–94, 2022, doi: 10.1016/j.procs.2022.07.013.

Q. Huang et al., “Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model,” Plant Phenomics, vol. 5, 2023, doi: 10.34133/plantphenomics.0062.

Y. Li, L. Qing, X. He, H. Chen, and Q. Liu, “Image classification based on self-distillation,” Applied Intelligence, vol. 53, no. 8, pp. 9396–9408, 2022, doi: 10.1007/s10489-022-04008-y.

H. Wang, S. Qiu, H. Ye, and X. Liao, “A Plant Disease Classification Algorithm Based on Attention MobileNet V2,” Algorithms, vol. 16, no. 9, 2023, doi: 10.3390/a16090442.

X. Xu, Y. Zhang, H. Cao, D. Yang, L. Zhou, and H. Yu, “Recognition of Edible Fungi Fruit Body Diseases Based on Improved ShuffleNetV2,” Agronomy, vol. 13, no. 6, 2023, doi: 10.3390/agronomy13061530.

O. G. Ajayi, J. Ashi, and B. Guda, “Performance evaluation of YOLO v5 model for automatic crop and weed classification on UAV images,” Smart Agricultural Technology, vol. 5, p. 100231, 2023, doi: 10.1016/j.atech.2023.100231.

Y. Zhao, Y. Yang, X. Xu, and C. Sun, “Precision detection of crop diseases based on improved YOLOv5 model,” Front. Plant Sci., vol. 13, pp. 1–17, 2023, doi: 10.3389/fpls.2022.1066835.

L. Ma, Y. Hu, Y. Meng, Z. Li, and G. Chen, “Multi-Plant Disease Identification Based on Lightweight ResNet18 Model,” Agronomy, vol. 13, no. 11, 2023, doi: 10.3390/agronomy13112702.

A. M. Mansourian et al., “A Comprehensive Survey on Knowledge Distillation,” Transactions on Machine Learning Research, vol. 2025, no. 9, pp. 1–102, 2025, doi: 10.48550/arXiv.2503.12067.

Z. Hao, J. Guo, K. Han, H. Hu, C. Xu, and Y. Wang, “Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale,” Adv. Neural Inf. Process. Syst., vol. 36, no. NeurIPS, pp. 1–14, 2023.

Robet, J. T. K. Perangin Angin, and T. H. Siregar, “Attention Augmented Deep Learning Model for Enhanced Feature Extraction in Cacao Disease Recognition,” Sinkron : Jurnal dan Penelitian Teknik Informatika, vol. 9, no. 4, pp. 1965–1977, 2025, doi: 10.33395/sinkron.v9i4.15249.