Enhanced RegNetY-400MF for Fruit Fly Species Classification: Fine-Tuning Strategies and Data Balancing for Improved Accuracy
DOI:
https://doi.org/10.29207/resti.v9i6.6973Keywords:
balancing, CNN, fruit fly classification, precision agriculture, Regnety-400MFAbstract
Fruit fly infestations pose a significant threat to agricultural productivity, especially in chili plantations, which can cause substantial yield losses. Accurate and rapid species classification is crucial for implementing targeted pest control strategies. This study developed a computationally efficient fruit fly species classification model using a deep learning approach that focused on improving accuracy with fine tuning and class balancing strategies. The dataset consists of 1049 images across 4 fruit fly species, captured in a natural plantation environment and available at www.inaturalist.org. The model evaluated several lightweight Convolutional Neural Network (CNN) architectures, including MobileNetV3-Small, RegNetY-400MF, and SqueezeNet among others, with RegNetY-400MF emerging as the best performing model, achieving a validation accuracy of 96.10% and a macro F1 score of 95.70%. The models tested in this study included several lightweight Convolutional Neural Network (CNN) architectures, including MobileNetV3-Small, RegNetY-400MF, and SqueezeNet, among others. RegNetY-400MF proved to be the best performing model, achieving a validation accuracy of 96.10% and a macro F1 score of 95.70%. Compared to other state-of-the-art models, RegNetY-400MF demonstrated higher accuracy while maintaining a lower number of parameters (8.3 million) and reduced computational complexity (0.41 GFLOPs). This makes the model highly suitable for real-time applications in resource-constrained agricultural environments. The model offers a practical solution for fruit fly species detection, enabling early and accurate identification of pest infestations in chili plantations, thereby reducing the risk of crop failure. By providing an efficient and scalable pest control tool, the model supports precision pest management, improves yield stability, and contributes to sustainable agriculture.
Downloads
References
N. T. Papadopoulos, M. De Meyer, J. S. Terblanche, and D. J. Kriticos, “Fruit flies: challenges and opportunities to stem the tide of global invasions,” Annu Rev Entomol, vol. 69, no. 1, pp. 355–373, 2024, doi: 10.1146/annurev-ento-022723-103200.
A. F. Lubis, S. Sutriono, S. S. Ningsih, D. Hasibuan, F. H. Panggabean, and A. A. Hutapea, “Inventory of fruit flies on red chilies (Capsicum annum L.) in Lubuk Cuik Village,” Contributions of Central Research Institute for Agriculture, vol. 19, no. 2, pp. 61–65, 2025, doi: 10.59651/cceria.v19i2.130.
S. A. Ganie, S. A. Rehman, T. Nisar, M. A. Paray, P. Bano, And R. Khurshid, “Fruit Fly Management And Control Strategies: A Review.,” Biopestic Int, vol. 18, no. 2, 2022, doi: 10.14456/apst.2025.49.
J. L. Hoskins, P. Rempoulakis, M. M. Stevens, and B. C. Dominiak, “Biosecurity and management strategies for economically important exotic tephritid fruit fly species in Australia,” Insects, vol. 14, no. 10, p. 801, 2023, doi: 10.3390/insects14100801.
R. Lasa, J. Rull, L. Suárez, F. R. Mello Garcia, T. Williams, and F. Díaz-Fleischer, “Monitoring and mass trapping of fruit flies (Diptera: Tephritidae) in the Americas,” Management of Fruit Flies in the Americas, pp. 67–126, 2024, doi : 10.1007/978-3-031-48608-1_3
E. D. Bali, V. G. Rodovitis, E. Verykouki, J. S. Terblanche, J. R. Carey, and N. T. Papadopoulos, “Factors affecting detection and trapping efficacy of Mediterranean fruit flies,” Pest Manag Sci, 2025, doi: 10.1002/ps.8723.
P. Gyawali, K. Bohara, S. Rijal, N. Karki, and J. Shahi, “A comprehensive review on integrated pest management of melon fruit fly (Bactrocera cucurbitae),” Int J Pest Manag, pp. 1–9, 2023, doi: 10.1080/09670874.2023.2278052.
U. Methal et al., “The Role of Pesticides in Fruit Fly Management, Balancing Efficacy and Environmental Concerns,” Annual Methodological Archive Research Review, vol. 3, no. 6, pp. 418–428, 2025, doi:10.63075/99m5x871
S. B. Jha and R. F. Babiceanu, “Deep CNN-based visual defect detection: Survey of current literature,” Comput Ind, vol. 148, p. 103911, 2023, doi:10.1016/j.compind.2023.103911.
M. Ramli, S. Rahman, and R. B. Syah, “ConciseCarNet: convolutional neural network for parking space classification,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 4, pp. 4158–4168, 2024, doi: 10.11591/ijai.v13.i4.pp4158-4168.
S. Chen and J. Chen, “Classification for fruit fly images using convolutional neural networks,” Information Technology and Control, vol. 51, no. 2, pp. 376–389, 2022, doi 10.5755/j01.itc.51.2.2974.
M. Li, M. Li, Q. Ren, H. Liu, and C. Liu, “Intelligent identification and classification of sewer pipeline network defects based on improved RegNetY network,” J Civ Struct Health Monit, vol. 13, no. 2, pp. 547–560, 2023, doi : 10.1007/s13349-022-00660-7.
Y. Sun et al., “Real-time recognition and detection of bactrocera minax (diptera: trypetidae) grooming behavior using body region localization and improved c3d network,” Sensors, vol. 23, no. 14, p. 6442, 2023, doi: 10.3390/s23146442.
L. Zhang et al., “Enhancing Fruit Fly Detection in Complex Backgrounds Using Transformer Architecture with Step Attention Mechanism,” Agriculture, vol. 14, no. 3, p. 490, 2024, doi: 10.3390/agriculture14030490
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474.
B. Koonce and B. Koonce, “MobileNetV3,” Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, pp. 125–144, 2021. doi: 10.1007/978-1-4842-6168-2
J. Xu, Y. Pan, X. Pan, S. Hoi, Z. Yi, and Z. Xu, “RegNet: Self-regulated network for image classification,” IEEE Trans Neural Netw Learn Syst, vol. 34, no. 11, pp. 9562–9567, 2022, doi: 10.1109/TNNLS.2022.3158966
J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141, doi: 10.1109/CVPR.2018.00745
X. Zhang, X. Zhou, M. Lin, and J. Sun, “Shufflenet: An extremely efficient convolutional neural network for mobile devices,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 6848–6856, doi: 10.1109/CVPR.2018.00716.
K. Kansal, T. B. Chandra, and A. Singh, “ResNet-50 vs. EfficientNet-B0: multi-centric classification of various lung abnormalities using deep learning,” Procedia Comput Sci, vol. 235, pp. 70–80, 2024, doi: 10.1016/j.procs.2024.04.007.
S. Yang, W. Xiao, M. Zhang, S. Guo, J. Zhao, and F. Shen, “Image data augmentation for deep learning: A survey,” arXiv preprint arXiv:2204.08610, 2022, doi: 10.48550/ arXiv.2204.08610.
Y. Bai et al., “Understanding and improving early stopping for learning with noisy labels,” Adv Neural Inf Process Syst, vol. 34, pp. 24392–24403, 2021. doi:10.48550/arXiv.2106.15853
A. Al-Kababji, F. Bensaali, and S. P. Dakua, “Scheduling techniques for liver segmentation: Reducelronplateau vs onecyclelr,” in International conference on intelligent systems and pattern recognition, Springer, 2022, pp. 204–212, doi: 10.1007/978-3-031-08277-1_17
M. Wojciuk, Z. Swiderska-Chadaj, K. Siwek, and A. Gertych, “Improving classification accuracy of fine-tuned CNN models: Impact of hyperparameter optimization,” Heliyon, vol. 10, no. 5, 2024, doi: 10.1016/j.heliyon.2024.e26586
I. Radosavovic, R. P. Kosaraju, R. Girshick, K. He, and P. Dollár, “Designing network design spaces,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10428–10436, doi: 10.48550/arXiv.2003.13678
T. Chauhan, V. Katkar, and K. Vaghela, “Corn leaf disease detection using RegNet, KernelPCA and XGBoost classifier,” in International Conference on Advancements in Smart Computing and Information Security, Springer, 2022, pp. 346–361, doi: 10.1007/978-3-031-23092-9_28
H. He, J. Wang, S. Huang, and X. Li, “A comparative deep learning algorithms for agricultural insect recognition,” in 2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), IEEE, 2021, pp. 321–325, doi: 10.1109/MLISE54096.2021.00067.
J. Xu, Y. Pan, X. Pan, S. Hoi, Z. Yi, and Z. Xu, “RegNet: Self-regulated network for image classification,” IEEE Trans Neural Netw Learn Syst, vol. 34, no. 11, pp. 9562–9567, 2022, doi: 10.1109/TNNLS.2022.3158966
S. Pranav, S. Ma, and V. Vignesh, “Smart Agriculture: Enhancing Crop and Weed Detection Using MobileNetV2 for Autonomous Farming Systems,” in 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), IEEE, 2025, pp. 1–6. doi: 10.1109/ISACC65211.2025.10969205
J. Chen, D. Zhang, M. Suzauddola, and A. Zeb, “Identifying crop diseases using attention embedded MobileNet-V2 model,” Appl Soft Comput, vol. 113, p. 107901, 2021, doi: 10.1016/j.asoc.2021.107901
C. B. Nwaneto and C. Yinka-Banjo, “Harnessing deep learning algorithms for early plant disease detection: A comparative study and evaluation between SSD (Mobilenet_v2 and Mobilenet_v3) and CNN model,” Ife Journal of Science, vol. 26, no. 3, pp. 555–568, 2024, doi: 10.4314/ijs.v26i3.1.
Y. Zhao, H. Huang, Z. Li, H. Yiwang, and M. Lu, “Intelligent garbage classification system based on improve MobileNetV3-Large,” Conn Sci, vol. 34, no. 1, pp. 1299–1321, 2022, doi: 10.1080/09540091.2022.2067127.
C. Liang, Z. Liu, Y. Li, and H. Yang, “Variety identification of grape based on mobilenetv3-large model.,” 2023, doi: 10.3969/j.issn.1002-2481.2023.07.15
A. Gao, A. Geng, Y. Song, L. Ren, Y. Zhang, and X. Han, “Detection of maize leaf diseases using improved MobileNet V3-small,” International Journal of Agricultural and Biological Engineering, vol. 16, no. 3, pp. 225–232, 2023, doi: 10.25165/j.ijabe.20231603.7799.
H. Zhou et al., “Maize leaf disease recognition based on improved convolutional neural network ShuffleNetV2,” Plants, vol. 13, no. 12, p. 1621, 2024, doi: 10.3390/plants13121621.
J. Han and Y. Yang, “L-Net: lightweight and fast object detector-based ShuffleNetV2,” J Real Time Image Process, vol. 18, no. 6, pp. 2527–2538, 2021, doi: 10.1007/s11554-021-01145-4
I. N. Yulita, A. S. Prabuwono, F. Ardiansyah, J. Rejito, A. Sholahuddin, and R. Rosadi, “Pest Detection in Agricultural Farms using SqueezeNet and Multi-Layer Perceptron Model.,” International Journal of Advanced Computer Science & Applications, vol. 15, no. 6, 2024, doi: 10.14569/IJACSA.2024.0150680
B. Koonce, “SqueezeNet,” in Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization, Springer, 2021, pp. 73–85, doi: 10.1007/978-1-4842-6168-2_7
A. Y. Reddy and T. R. Balaga, “Enhancing Precision Agriculture Based on Explainable AI for Automated Nutrient Deficiency Diagnosis in Rice Using Attention SqueezeNet,” Ingenierie des Systemes d’Information, vol. 30, no. 1, p. 181, 2025, doi:10.18280/isi.300115
S. Rozlan and M. Hanafi, “Efficacy of chili plant diseases classification using deep learning: a preliminary study,” Comput Sci, vol. 25, pp. 1442–1449, 2022, doi: 10.11591/ijeecs.v25.i3.pp1442-1449
Y. Sun et al., “Real-time recognition and detection of bactrocera minax (diptera: trypetidae) grooming behavior using body region localization and improved c3d network,” Sensors, vol. 23, no. 14, p. 6442, 2023, doi: 10.3390/s23146442
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
