Evaluation of the Accuracy and Efficiency of Deep CNN Architecture in Feature Extraction for Guava Disease Classification
DOI:
https://doi.org/10.30871/jaic.v9i6.11655Keywords:
Deep Convolutional Neural Network, Feature Extraction, Guava Disease, ResNet50, Image ClassificationAbstract
This study analyzes and compares several Deep Convolutional Neural Network (DCNN) architectures to evaluate the balance between classification accuracy and computational efficiency in guava fruit disease detection. A hybrid DCNN–Machine Learning (ML) approach was applied to 3,784 images from the Guava Fruit Disease Dataset using a 10-fold cross-validation scheme and undersampling techniques to address data imbalance. Six DCNN architectures were systematically tested, and the combination of ResNet50 with Artificial Neural Network (ANN) showed the best performance with an accuracy of 0.9979 and an F1-score of 0.9975, surpassing the InceptionV3 baseline (0.9974). In addition to being the most accurate, ResNet50 was also 2.5 times faster in feature extraction than DenseNet201, demonstrating an optimal balance between accuracy and time efficiency. These findings emphasize the importance of analyzing the accuracy-efficiency trade-off in selecting a DCNN architecture and open up opportunities for developing more efficient models for future agricultural image classification applications.
Downloads
References
[1] A. Varma, D. Kumar, P. Date, P. Dipke, and S. Wankhade, “Comparative Analysis of Plant Disease Detection System,” International Journal For Multidisciplinary Research, vol. 7, May 2025, doi: g9kvdw.
[2] J. Naranjo-Torres, M. Mora, R. Hernández-García, R. J. Barrientos, C. Fredes, and A. Valenzuela, “A review of convolutional neural network applied to fruit image processing,” Applied Sciences (Switzerland), vol. 10, no. 10, May 2020, doi: 10.3390/app10103443.
[3] D. Anwar, “A Novel CNN Model for Fruit Leaf Disease Detection: A Lightweight Solution for Grapes, Figs, and Oranges,” Fusion: Practice and Applications, vol. 19, no. 2, pp. 278–287, 2025, doi: 10.54216/FPA.190220.
[4] M. T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Comparison of CNN-based deep learning architectures for rice diseases classification,” Artificial Intelligence in Agriculture, vol. 9, pp. 22–35, Sep. 2023, doi: 10.1016/j.aiia.2023.07.001.
[5] O. Kılcı and M. Koklu, “Guava Fruit Disease Classification Using Deep Learning and Machine Learning Models,” Research in Agricultural Sciences, vol. 56, no. 3, pp. 217–226, Sep. 2025, doi: 10.17097/agricultureatauni.1665941.
[6] Md Al Amin, Md Iqbal Mahmud, Asadullah Bin Rahman, Mst Aktarina Parvin, and Md Abdulla Al Mamun, “Guava Fruit Disease Dataset,” Nov. 04, 2024, Mendeley Dataset.
[7] J. Schmidhuber, “Who invented deep residual learning?,” Sep. 2025. [Online]. Available: https://people.idsia.ch/~juergen/who-invented-residual-neural-networks.html
[8] L. Nanni, G. Faldani, S. Brahnam, R. Bravin, and E. Feltrin, “Improving Foraminifera Classification Using Convolutional Neural Networks with Ensemble Learning,” Signals, vol. 4, no. 3, pp. 524–538, Sep. 2023, doi: 10.3390/signals4030028.
[9] W. Li, W. Xie, and Z. Wang, “Complex-Valued Densely Connected Convolutional Networks,” in Communications in Computer and Information Science, Springer, 2020, pp. 299–309. doi: 10.1007/978-981-15-7981-3_21.
[10] F. A. Abdulazeez, I. T. Ahmed, and B. T. Hammad, “Examining the Performance of Various Pretrained Convolutional Neural Network Models in Malware Detection,” Applied Sciences (Switzerland), vol. 14, no. 6, Mar. 2024, doi: 10.3390/app14062614.
[11] S. Hussain Khan and R. Iqbal, “A Comprehensive Survey on Architectural Advances in Deep CNNs: Challenges, Applications, and Emerging Research Directions,” Mar. 2025.
[12] T. Singh and D. K. Vishwakarma, “A deeply coupled ConvNet for human activity recognition using dynamic and RGB images,” Neural Comput Appl, vol. 33, no. 1, pp. 469–485, Jan. 2021, doi: 10.1007/s00521-020-05018-y.
[13] G. X. Shi, Y. N. Wang, Z. F. Yang, Y. Q. Guo, and Z. W. Zhang, “Wildfire Identification Based on an Improved MobileNetV3-Small Model,” Forests, vol. 15, no. 11, Nov. 2024, doi: 10.3390/f15111975.
[14] M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” International Conference on Machine Learning, Sep. 2020, [Online]. Available: http://arxiv.org/abs/1905.11946
[15] C. Su and W. Wang, “Concrete Cracks Detection Using Convolutional NeuralNetwork Based on Transfer Learning,” Math Probl Eng, vol. 2020, 2020, doi: 10.1155/2020/7240129.
[16] Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2201.03545
[17] A. Mustapha, L. Mohamed, H. Hamid, and K. Ali, “Diabetic Retinopathy Classification Using ResNet50 and VGG-16 Pretrained Networks,” International Journal of Computer Engineering and Data Science, vol. 1, pp. 2737–8543, Jul. 2021, [Online]. Available: www.ijceds.com
[18] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Jun. 2018, [Online]. Available: http://arxiv.org/abs/1201.0490
[19] A. Rahmadeyan and M. Mustakim, “Seleksi Fitur pada Supervised Learning: Klasifikasi Prestasi Belajar Mahasiswa Saat dan Pasca Pandemi COVID-19,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 9, no. 1, pp. 21–32, May 2023, doi: 10.25077/teknosi.v9i1.2023.21-32.
[20] P. K. Syriopoulos, N. G. Kalampalikis, S. B. Kotsiantis, and M. N. Vrahatis, “kNN Classification: a review,” Ann Math Artif Intell, vol. 93, no. 1, pp. 43–75, Feb. 2025, doi: 10.1007/s10472-023-09882-x.
[21] L. D. Cahya, A. Luthfiarta, J. I. T. Krisna, S. Winarno, and A. Nugraha, “Improving Multi-label Classification Performance on Imbalanced Datasets Through SMOTE Technique and Data Augmentation Using IndoBERT Model,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 9, no. 3, pp. 290–298, Jan. 2024, doi: 10.25077/teknosi.v9i3.2023.290-298.
[22] A. Miteloudis, “Interpretability in Modern Decision Tree Ensembles: A Meta-Review,” Jul. 2025. doi: 10.5281/zenodo.15853691.
[23] J. Ansel et al., “PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation,” in International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS, Association for Computing Machinery, Apr. 2024, pp. 929–947. doi: 10.1145/3620665.3640366.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Shiva Augusta Wicaqsana, Ardytha Luthfiarta, Amalia Putri Dwi Mareta, Maulatus Shaffira Fitri
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
