Detection of Durian Seed Borer Moths (Mudaria spp.) Using YOLOv4-Tiny Deep Learning Model for Smart Pest Surveillance System
Main Article Content
Abstract
The durian seed borer moth (Mudaria spp.) is a major insect pest causing significant damage to Thai durian exports. Timely and accurate surveillance is essential for effective integrated pest management. This study developed an image-based detection model using the YOLOv4-tiny deep learning architecture and evaluated its potential for smart surveillance systems across different data sources. The model was trained on 6,437 augmented images and evaluated using a test dataset of 332 images, categorized into three cases: (1) field-collected reference images, (2) images from the iNaturalist database, and (3) a combined dataset. A confidence threshold of over 85% was applied, with performance measured via Accuracy, Precision, Recall, and F1-score. The results demonstrated that YOLOv4-tiny effectively detected adult Mudaria spp. moths. Due to the absence of false detections (False Positive = 0), the model achieved a Precision of 1.000 across all cases. The reference dataset yielded an Accuracy and Recall of 0.920, while the iNaturalist dataset achieved perfect performance (1.000) across all metrics. The combined dataset reached an Accuracy of 0.958 and an F1-score of 0.979. In conclusion, the YOLOv4-tiny model exhibits high potential as a surveillance tool and can be integrated with digital platforms to support early warning systems and proactive pest management in commercial durian orchards.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
King Mongkut's Agricultural Journal
References
Akila, M., Kumar, N. K., & Vishnu, K. (2026). Real-time pest detection and identification system using deep learning. International Journal of Advanced Research in Science, Communication and Technology, 6(5), 8–15. https://doi.org/10.48175/IJARSCT-31902.
Chagkornburee, C., & Chaiklieng, S. (2026). Pesticide poisoning linked to PPE usage among pesticide sprayers in Northeastern Thailand. Journal of Applied Toxicology, 46(7), 2544-2555. https://doi.org/10.1002/jat.70042.
Chamsuk, P., Wannachart, K., Khokyen, W., Pudchimnun, K., Klangpahol, P., Klinpet, A., Sangtongpraow, B., & Poolprasert, P. (2026). Integrative taxonomy, seasonal phenology, and sex pheromone profiling of the durian seed borer (Mudaria stahlgretschae) for enhanced pest monitoring. Diversity, 18(5), 284. https://doi.org/10.3390/d18050284.
Deng, L., Fang, D., Ullah, A., Hou, Q., & Yu, H. (2025). AMS-YOLO: multi-scale feature integration for intelligent plant protection against maize pests. Frontiers in Plant Science, 16(1), 1640405. https://doi.org/10.3389/fpls.2025.1640405.
Ejaz, M. H., Bilal, M., Habib, U., Attique, M., & Chung, T. S. (2025). Crop Pest Classification using Deep Learning Techniques: A Review. Retrieved from: https://doi.org/10.48550/arXiv.2507.01494.
Feng, Z., Shi, R., Jiang, Y., Han, Y., Ma, Z., & Ren, Y. (2025). SPD-YOLO: A Method for Detecting Maize Disease Pests Using Improved YOLOv7. Computers, Materials & Continua, 84(2), 3559-3575. https://doi.org/10.32604/cmc.2025.065152.
Grandini, M., Bagli, E., & Visani, G. (2020). Metrics for Multi-class Classification: An Overview (Version 1). Retrieved from: https://arxiv.org/abs/2008.05756.
Høye, T. T., Ärje, J., Bjerge, K., Hansen, O. L. P., Iosifidis, A., Leese, F., Mann, H. M. R., Meissner, K., Melvad, C., & Raitoharju, J. (2021). Deep learning and computer vision will transform entomology. Proceedings of the National Academy of Sciences of the United States of America, 118(2), e2002545117. https://doi.org/10.1073/pnas.2002545117.
iNaturalist. (2025). Connection with Nature. Retrieved from: https://www.inaturalist.org.
Kongchai, P., & Sombat, W. (2025). Pest classification from photographs using deep learning pre-trained models: A case study in Ubon Ratchathani province. Journal of Science and Science Education (JSSE), 8(1), 168–179. (in Thai).
Lou, L., Liu, J., Yang, Z., Zhou, X., & Yin, Z. (2022). Agricultural pest detection based on improved yolov5. In Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence, pp. 7–12. Association for Computing Machinery. https://doi.org/10.1145/3577530.3577532.
Pang, H., Zhang, Y., Cai, W., Li, B., & Song, R. (2022). A real-time object detection model for orchard pests based on improved YOLOv4 algorithm. Scientific Reports, 12(1), 13783. https://doi.org/10.1038/s41598-022-17826-4.
Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. International Journal of Machine Learning Technology, 2(1), 37-63. https://doi.org/10.48550/arXiv.2010.16061.
Rukkasikorn, A., Chaovalit, S., Dokchan, P., Ratanamahamaneekorn, K., Ruangsuk, K., & Poolprasert, P. (2025). Diversity of moths in the genus Mudaria Moore, 1893 (Lepidoptera: Noctuidae) and their impact on durian production in Thailand. In Proceedings of the 16th National Plant Protection Conference, pp. 49–66. Chiang Mai, Thailand. (in Thai).
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427-437. https://doi.org/10.1016/j.ipm.2009.03.002.
Song, L., Liu, M., Liu, S., Wang, H., & Luo, J. (2023). Pest species identification algorithm based on improved YOLOv4 network. Signal, Image and Video Processing, 17(1), 3127-3134. https://doi.org/10.1007/s11760-023-02534-x.
Supamattra, S., Sayasoonthorn, S., & Chueasamat, A. (2023). Study of impurities detection in frozen spinach with YOLOv4 deep learning model. Thai Interdisciplinary and Sustainability Review, 12(2), 131–144. https://doi.org/10.14456/tisr.2023.12. (in Thai).
Teixeira, A. C., Ribeiro, J., Morais, R., Sousa, J. J., & Cunha, A. (2023). A systematic review on automatic insect detection using deep learning. Agriculture, 13(3), 713. https://doi.org/10.3390/agriculture13030713.
Wan, H., & Wang, S. (2025). Weed detection in cornfields based on improved lightweight neural network model. Alexandria Engineering Journal, 122(1), 334–343. https://doi.org/10.1016/j.aej.2025.03.016.
Wang, Q. J., Zhang, S. Y., Dong, S. F., Zhang, G. C., Yang, J., Li, R., & Wang, H. Q. (2020). Pest24: A large-scale very small object data set of agricultural pests for multi-target detection. Computers and Electronics in Agriculture, 175(1), 105585. https://doi.org/10.1016/j.compag.2020.105585.
Wu, X., Zhan, C., Lai, Y. K., Cheng, M. M., & Yang, J. (2019). IP102: A large-scale benchmark dataset for insect pest recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8779–8788.
Yang, S., Xing, Z., Wang, H., Dong, X., Gao, X., Liu, Z., Zhang, X., Li, S., & Zhao, Y. (2023). Maize-YOLO: A new high-precision and real-time method for maize pest detection. Insects, 14(3), 278. https://doi.org/10.3390/insects14030278.
