Optimization Strategy on Deep Learning Model to Improve Fruit Freshness Recognition

I Gusti Agung Indrawan; Putu Andy Novit Pranartha; I Wayan Agus Surya Darma; I Putu Eka Giri Gunawan

doi:10.24843/LKJITI.2023.v14.i01.p01

I Gusti Agung Indrawan Institut Bisnis dan Teknologi Indonesia
Putu Andy Novit Pranartha Institut Bisnis dan Teknologi Indonesia
I Wayan Agus Surya Darma Institut Bisnis dan Teknologi Indonesia
I Putu Eka Giri Gunawan Institut Bisnis dan Teknologi Indonesia

DOI: https://doi.org/10.24843/LKJITI.2023.v14.i01.p01

Abstract

The high fruit production during the harvest season is a challenge in the process of sorting fresh fruit and rotten fruit in plantations. Automatic fruit freshness classification based on deep learning can speed up the sorting process. However, building a model with high accuracy requires the right strategy based on the dataset's characteristics. This research aims to apply optimization strategies to deep learning models to improve model performance. The optimization strategy is implemented by optimizing the model using fine-tuning strategy by selecting the best parameters based on learning rate, optimizers, transfer learning, and data augmentation. The transfer learning process is applied based on the dataset's characteristics by training some parameters with a size of 30% and 60%, which were tested in four scenarios. The fine-tuning strategy is applied to three Deep Learning models, i.e., MobileNetv2, ResNet50, and InceptionResNetV2, which have various parameter sizes. Based on test results, fine-tuning strategy produces the best performance up to 100% with a learning rate of 0.01, the SGD optimizers on the InceptionResNetV2 model are trained on 60% of the parameters.

Downloads

Download data is not yet available.

References

[1] A. Kholik, “Klasifikasi Menggunakan Convolutional Neural Network (Cnn) Pada Tangkapan Layar Halaman Instagram,” Jurnal Data Mining dan Sistem Informasi, vol. 2, no. 2, pp. 10–20, 2021, [Online]. Available: https://ejurnal.teknokrat.ac.id/index.php/JDMSI/article/view/1345/673%0Ahttps://ejurnal.teknokrat.ac.id/index.php/JDMSI/article/view/1345
[2] E. N. Arrofiqoh and H. Harintaka, “Implementasi Metode Convolutional Neural Network Untuk Klasifikasi Tanaman Pada Citra Resolusi Tinggi,” Geomatika, vol. 24, no. 2, p. 61, 2018, doi: 10.24895/jig.2018.24-2.810.
[3] D. Srinivasan and Dr. M. Yousef, “Apple Fruit Detection and Maturity Status Classification,” International Journal of Recent Technology and Engineering (IJRTE), vol. 9, no. 2, pp. 1055–1059, 2020, doi: 10.35940/ijrte.b4063.079220.
[4] S. Chakraborty, F. M. J. M. Shamrat, M. M. Billah, M. al Jubair, M. Alauddin, and R. Ranjan, “Implementation of Deep Learning Methods to Identify Rotten Fruits,” Proceedings of the 5th International Conference on Trends in Electronics and Informatics, ICOEI 2021, pp. 1207–1212, 2021, doi: 10.1109/ICOEI51242.2021.9453004.
[5] Y. Adiwinata, A. Sasaoka, I. P. Agung Bayupati, and O. Sudana, “Fish Species Recognition with Faster R-CNN Inception-v2 using QUT FISH Dataset,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 11, no. 3, p. 144, Dec. 2020, doi: 10.24843/lkjiti.2020.v11.i03.p03.
[6] I. P. B. G. Prasetyo Raharja, I. M. Suwija Putra, and T. Le, “Kekarangan Balinese Carving Classification Using Gabor Convolutional Neural Network,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 13, no. 1, p. 1, Apr. 2022, doi: 10.24843/lkjiti.2022.v13.i01.p01.
[7] A. A. J. V. Priyangka and I. M. S. Kumara, “Classification Of Rice Plant Diseases Using the Convolutional Neural Network Method,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 12, no. 2, p. 123, Aug. 2021, doi: 10.24843/lkjiti.2021.v12.i02.p06.
[8] I. W. A. S. Darma, N. Suciati, and D. Siahaan, “Balinese Carving Recognition using Pre-Trained Convolutional Neural Network,” ICICoS 2020 - Proceeding: 4th International Conference on Informatics and Computational Sciences, 2020, doi: 10.1109/ICICoS51170.2020.9299021.
[9] N. P. Sutramiani, N. Suciati, and D. Siahaan, “Transfer Learning on Balinese Character Recognition of Lontar Manuscript Using MobileNet,” ICICoS 2020 - Proceeding: 4th International Conference on Informatics and Computational Sciences, pp. 0–4, 2020, doi: 10.1109/ICICoS51170.2020.9299030.
[10] I. W. A. S. Darma, N. Suciati, and D. Siahaan, “Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet,” International Journal of Intelligent Engineering and Systems, vol. 13, no. 6, pp. 349–363, 2020, doi: 10.22266/ijies2020.1231.31.
[11] A. J. Ratnerÿ, H. R. Ehrenbergÿ, and J. Dunnmon, “Belajar Menulis Domain-Spesifik Transformasi untuk Augmentasi Data,” no. Nips, 2017.
[12] T. Fatyanosa, “Fine-Tuning Pre-Trained Transformer-based Language Model | by Tirana Fatyanosa | Medium,” www.medium.com, 2020. https://fatyanosa.medium.com/fine-tuning-pre-trained-transformer-based-language-model-c542af0e7fc1 (accessed Mar. 31, 2022).
[13] J. Margeta, A. Criminisi, R. Cabrera Lozoya, D. C. Lee, and N. Ayache, “Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition,” Comput Methods Biomech Biomed Eng Imaging Vis, vol. 5, no. 5, pp. 339–349, 2017, doi: 10.1080/21681163.2015.1061448.
[14] X. Xu, B. Shi, Z. Gu, R. Deng, X. Chen, A.S. Krylov, Y. Ding, “3D No-Reference Image Quality Assessment via Transfer Learning and Saliency-Guided Feature Consolidation,” IEEE Access, vol. 7, pp. 85286–85297, 2019, doi: 10.1109/ACCESS.2019.2925084.
[15] S. Sena, “Pengenalan Deep Learning Part 8 : Gender Classification using Pre-Trained Network (Transfer Learning) | by Samuel Sena | Medium,” www.medium.com, 2018. https://medium.com/@samuelsena/pengenalan-deep-learning-part-8-gender-classification-using-pre-trained-network-transfer-37ac910500d1 (accessed Apr. 06, 2022).
[16] A. Saber, M. Sakr, O. M. Abo-Seida, A. Keshk, and H. Chen, “A Novel Deep-Learning Model for Automatic Detection and Classification of Breast Cancer Using the Transfer-Learning Technique,” IEEE Access, vol. 9, pp. 71194–71209, 2021, doi: 10.1109/ACCESS.2021.3079204.
[17] I. W. A. S. Darma, N. Suciati, and D. Siahaan, “GFF-CARVING: Graph Feature Fusion for the Recognition of Highly Varying and Complex Balinese Carving Motifs,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3228382.