International Journal of Engineering and Manufacturing (IJEM)
IJEM Vol. 16, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 897KB)
A Modified CNN-Based Framework for Real- World Identification of Tephritid Fruit Fly Species
PDF (897KB), PP.300-313
Views: 0 Downloads: 0
Author(s)
Angelina Gill
1
Tarandeep Kaur
1
Yendrembam K. Devi
2
Mukesh Kumar
3,4,*
Index Terms
Agriculture, Machine Learning, Image recognition, Segmentation, Feature extraction, Fruit Fly, Convolutional Neural Network
Abstract
Accurate identification of insect pests is crucial for effective agricultural management and prevention of crop losses. Among these pests, tephritid fruit flies significantly impact fruit and vegetable production, leading to economic losses and reduced market quality. Existing insect identification methods largely rely on manual inspection by taxonomists, which is time-consuming, error-prone, and not feasible for real-time applications in field conditions. Moreover, many existing machine learning-based approaches suffer from limited generalizability and dependence on controlled environments, restricting their practical deployment. To address these challenges, this study proposes a Modified Convolutional Neural Network (MCNN)-based approach for automated identification and classification of tephritid fruit fly species. The proposed method integrates image segmentation, feature extraction, and data augmentation techniques to enhance classification performance under varying conditions. A real-world dataset was collected using pheromone traps from multiple agricultural locations in Punjab, India, comprising four major species: Bactrocera dorsalis, Bactrocera zonata, Zeugodacus cucurbitae, and Zeugodacus tau. The MCNN model is trained using optimized hyperparameters, including learning rate, batch size, and optimizer selection, to improve robustness and accuracy. Experimental results demonstrate that the proposed model achieves an accuracy of 90%, along with improved classification capability compared to traditional approaches. The integration of real-field data and enhanced preprocessing techniques makes the proposed system suitable for practical deployment in precision agriculture. This study contributes to the development of an efficient, scalable, and automated insect identification framework that can assist farmers and agricultural experts in timely pest management.
Cite This Paper
Angelina Gill, Tarandeep Kaur, Yendrembam K. Devi, Mukesh Kumar, "A Modified CNN-Based Framework for Real- World Identification of Tephritid Fruit Fly Species", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.3, pp.300-313, 2026. DOI:10.5815/ijem.2026.03.18
Reference
[1]Gangadevi, E., Soufiane, B. O., Balusamy, B., Khan, F., & Getahun, M. (2025). A novel hybrid fruit fly and simulated annealing optimized faster R-CNN for detection and classification of tomato plant leaf diseases. Scientific Reports, 15(1), 16571.https://doi.org/10.1038/s41598-025-01466-5
[2]Zhang, L., Chen, K., Zheng, L., Liao, X., Lu, F., Li, Y., ... & Yan, S. (2024). Enhancing fruit fly detection in complex backgrounds using transformer architecture with step attention mechanism. Agriculture, 14(3), 490. https://doi.org/10.3390/agriculture14030490
[3]Aladhadh, S., Habib, S., Islam, M., Aloraini, M., Aladhadh, M., & Al-Rawashdeh, H. S. (2022). An efficient pest detection framework with a medium-scale benchmark to increase the agricultural productivity. Sensors, 22(24), 9749.
https://doi.org/10.3390/s22249749
[4]Kumar, N., Kumar L, V., & Flammini, F. (2023). A Comparative Performance Evaluation of Various Classification Models for Detection and Classification of Flying Insects. Interdisciplinary Description of Complex Systems: INDECS, 21(1), 52-68. https://doi.org/10.7906/indecs.21.1.5
[5]Bal, Surajit, Sagata Mondal, and Gautam Kundu. "Biodiversity and population density of fruit flies (Bactrocera sp.) at Kanke, Ranchi (Jharkhand)." Journal of Entomology and Zoology Studies 10.2 (2022): 101-106. DOI: https://doi.org/10.22271/j.ento.2022.v10.i2b.8966
[6]Safari, Y., Nakatumba-Nabende, J., Nakasi, R., & Nakibuule, R. (2024). A review on automated detection and assessment of fruit damage using machine learning. IEEE access, 12, 21358-21381. DOI: 10.1109/ACCESS.2024.3362230
[7]Buschbacher, Keanu, et al. "Image-based species identification of wild bees using convolutional neural networks." Ecological Informatics 55 (2020): 101017.Kaur. T., & Kaur, H. (2018). Machine Learning: An internal review. Journal of Emerging Technilogies and Innovative Research, (Vol.5, pp. 6) IEEE, https://doi.org/10.1016/j.ecoinf.2019.101017
[8]Safari, Y., Nakatumba-Nabende, J., Nakasi, R., & Nakibuule, R. (2024). A review on automated detection and assessment of fruit damage using machine learning. IEEE access, 12, 21358-21381.
[9]Gill, Angelina, Tarandeep Kaur, and Yendrembam K. Devi. "Application of Machine Learning Techniques in Modern Agriculture: A Review." Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing. 2022. https://doi.org/10.1145/3549206.3549255
[10]Xia, Denan, et al. "Insect detection and classification based on an improved convolutional neural network." Sensors 18.12 (2018): 4169. https://doi.org/10.3390/s18124169
[11]Zhong, Yuanhong, et al. "A vision-based counting and recognition system for flying insects in intelligent agriculture." Sensors 18.5 (2018): 1489. https://doi.org/10.3390/s18051489
[12]Leonardo, Matheus Macedo, et al. "Deep feature-based classifiers for fruit fly identification (Diptera: Tephritidae)." 2018 31st SIBGRAPI conference on graphics, patterns, and images (SIBGRAPI). IEEE, 2018. DOI: 10.1109/SIBGRAPI.2018.00012
[13]Peng, Yingqiong, et al. "Fruit fly classification via convolutional neural network." 2018 Chinese Automation Congress (CAC). IEEE, 2018. DOI: 10.1109/CAC.2018.8623178
[14]Martins, Valter AM, et al. "Deep learning applied to the identification of fruit fly in intelligent traps." 2019 IX Brazilian symposium on computing systems engineering (SBESC). IEEE, 2019. DOI: 10.1109/SBESC49506.2019.9046088
[15]Peng, Yingqiong, et al. "FB-CNN: Feature fusion-based bilinear CNN for classification of fruit fly image." IEEE Access 8 (2019): 3987-3995. DOI: 10.1109/ACCESS.2019.2961767
[16]Peng, Yingqiong, et al. "CNN–SVM: a classification method for fruit fly image with the complex background." IET Cyber‐ Physical Systems: Theory & Applications 5.2 (2020): 181-185. https://doi.org/10.1049/iet-cps.2019.0069