Ensemble deep learning approach for apple fruitlet detection from digital images

Agriculture commodities are commodities that have a high economic worth and the potential to be developed further. The green and red apple, in instance, is one type of fruit that has the potential to be cultivated as part of agriculture. The apple economy is reasonably steady, particularly with regard to the supply of production to the market. The purpose of this research is to enhance the performance of the CNN-based model and make it capable of precise detection of the green and red apple fruitlet. To enhance the overall performance of the model, the revised CNN-based YOLOv5 ensemble model was implemented with the SiLU (Sigmoid Linear Units activation function), Batch Normalization, and SGD (Stochastic Gradient Descent) algorithms. The combination of activation function, optimization, batch normalization, and ensemble technique can be later used to enhance the YOLOv5 ensemble model and used to detect the green and red apple fruitlet with the benefits of utilizing limited resources. This is possible thanks to the combination of the activation function, optimization, batch normalization, and ensemble technique. According to the findings of the comprehensive research, the accuracy of the updated yolo ensemble model has climbed into 97.8%, 92.1%, 95% percent of accuracy mAP for green, red and both apples together compared to previous model.

1. Sekharamantry, P.K. (2024). A seamless deep learning approach for apple detection, depth estimation, and tracking using YOLO models enhanced by multi-head attention mechanism. Computers, 13(3), 83. https://doi.ore/10.3390/computers13030083

2. Sekharamantry, P.K. (2023). In this work, we present a deep learning-based scheme to detect apples which uses YOLOv5 architecture in live apple farm images. Journal of Agricultural Robotics, 9(1), 42-53. https://doi.org/10.1016/i.agror.2023.100007

3. Wang, D. (2021). In this study, we developed a channel-pruned YOLO V5s model for the rapid and accurate detection of apple fruitlets before fruit thinning. Agricultural Robotics & Automation, 10(4), 191¬ 202. https://doi.org/10.1109/AGRIROBOT.2021.3078293

4. Tsai, C.F., & Chang, F.Y. (2016). Combining instance selection for better missing value imputation. Journal of Systems and Software, 122, 63-71. https://doi.org/10.1016/i.iss.2016.08.093

5. Janssen, M., van der Voort, H., & Wahyudi, A. (2017). Factors influencing big data decision-making quality. Journal of Business Study, 70, 338-345. https://doi.org/10.1016/i.ibusres.2016.08.007

6. 6 . Batra, S., Khurana, R., Khan, M.Z., Boulila, W., Koubaa, A., & Srivastava, P. (2022). A Pragmatic Ensemble Strategy for Missing Values Imputation in Health Records. Entropy, 24(4), 1 -20. https://doi.org/10.3390/e24040533

7. Chen, Z., Tan, S., Chajewska, U., Rudin, C., & Caruana, R. (2023). Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help? Proceedings of Machine Learning Research, 209, 86-99.

8. Feng, S., Hategeka, C., & Grepin, K.A. (2021). Addressing missing values in routine health information system data: an evaluation of imputation methods using data from the Democratic Republic of the Congo during the COVID-19 pandemic. Population Health Metrics, 19(1), 1-28. https://doi.org/10.1186/s12963-021-00274-z

9. Urda, D., Subirats, J.L., Garda-Laencina, P.J., Franco, L., Sancho-Gomez, J.L., & Jerez, J.M. (2012). WIMP: Web server tool for missing data imputation. Computer Methods and Programs in Biomedicine, 108(3), 1247-1254. https://doi.org/10.1016/i.cmpb.2012.08.006

10. Acampora, G., Vitiello, A., & Siciliano, R. (2020). MIDA: A web tool for missing data imputation based on a boosted and incremental learning algorithm. IEEE International Conference on Fuzzy Systems, 1-6. https://doi.org/10.1109/FUZZ48607.2020.9177644

11. Zhou, Y. H., & Saghapour, E. (2021). ImputEHR: A Visualization Tool of Imputation for the Prediction of Biomedical Data. Frontiers in Genetics, 12(July), 1-9. https://doi.org/10.3389/fgene.2021.691274

12. Gungor Uluta§, Esra & Altin, Cemil. (2023). Kiwi Fruit Detection with Deep Learning Methods. International Journal of Advanced Natural Sciences and Engineering Researches. 7. 39-45. https://doi.org/10.59287/ijanser.1333

13. Alabadla, M., Sidi, F., Ishak, I., Ibrahim, H., & Hamdan, H. (2022). ExtraImpute: A Novel Machine Learning Method for Missing Data Imputation. Journal of Advances in Information Technology, 13(5). https://doi.org/10.12720/iait.13.5.470-476

14. B. Ambrus, G. Teschner, A.J. Kovacs, M. Nemenyi, L. Helyes, Z. Pek, S. Takacs, T. Alahmad, A. Nyeki (2024) Field-grown tomato yield estimation using point cloud segmentation with 3D shaping and RGB pictures from a field robot and digital single lens reflex cameras, Heliyon, Volume 10, Issue 20, 2024, 37997, https://doi.org/10.1016/i.heliyon.2024.e37997

15. Apple collection Dataset (2023). Open-Source Dataset https://universe.roboflow.com/firstieeat/apple-collection. visited on 2024-12-04.