Optimisasi Hyperparameter pada Model Klasifikasi Jenis Bunga dengan arsitektur MobileNetV3-Small
Keywords:
MobileNetV3-Small, Deep Learning, Confusion Matrix, Hyperparamter, Convolutional, Neural Networks,Abstract
This study aims to classify various types of flowers using the deep learning method with the Convolutional Neural Networks MobileNetV3-Small architecture. The research stages include data collection and sharing, model training using the MobileNetV3-Small architecture, and testing with evaluation using the Confusion Matrix. Eight models with hyperparameter variations were tested to find the model with the highest accuracy. Model five achieved the highest validation accuracy of 99.25%. The evaluation showed that model five achieved the highest accuracy of 92%. These results indicate that increasing the amount of data and parameter settings can significantly improve model accuracy, indicating that the model can achieve near-perfect performance with more training data and optimal parameter settings. This study uses open-access data from Kaggle covering five types of flowers: daisy, dandelion, rose, sunflower, and tulip.
References
S. Ratna, “PENGOLAHAN CITRA DIGITAL DAN HISTOGRAM DENGAN PHYTON DAN TEXT EDITOR PHYCHARM,” Technol. J. Ilm., vol. 11, no. 3, p. 181, Jul. 2020, doi: 10.31602/tji.v11i3.3294.
T. A. Bowo, H. Syaputra, and M. Akbar, “Penerapan Algoritma Convolutional Neural Network Untuk Klasifikasi Motif Citra Batik Solo,” J. Softw. Eng. Ampera, vol. 1, no. 2, Art. no. 2, May 2020, doi: 10.51519/journalsea.v1i2.47.
J. P. Hidayatullah, “Klasifikasi Bunga Menggunakan Naïve Bayes Berdasarkan Fitur Warna Dan Texture,” . Volume, vol. 4, 2021.
L. Farokhah, “Implementasi K-Nearest Neighbor untuk Klasifikasi Bunga Dengan Ekstraksi Fitur Warna RGB,” J. Teknol. Inf. Dan Ilmu Komput., vol. 7, no. 6, Art. no. 6, Dec. 2020, doi: 10.25126/jtiik.2020722608.
Y. Pachipala, H. C. Maddipati, P. S. Udimudi, V. Thota, V. N. Sree, and L. R. Burra, “Iris Flower Classification by using Random Forest in AWS,” in 2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS), May 2022, pp. 1772–1777. doi: 10.1109/ICICCS53718.2022.9788415.
I. A. Dly, J. Jasril, S. Sanjaya, L. Handayani, and F. Yanto, “Klasifikasi Citra Daging Sapi dan Babi Menggunakan CNN Alexnet dan Augmentasi Data,” J. Inf. Syst. Res. JOSH, vol. 4, no. 4, pp. 1176–1185, Jul. 2023, doi: 10.47065/josh.v4i4.3702.
L. A. Susanto, A. Nilogiri, and L. Handayani, “Klasifikasi Citra Lesi Kulit Serupa Virus Monkeypox Menggunakan VGG-19 Convolutional Neural Network,” JUSTINDO J. Sist. Dan Teknol. Inf. Indones., vol. 8, no. 1, Art. no. 1, Feb. 2023, doi: 10.32528/justindo.v8i1.168.
F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.” arXiv, Nov. 04, 2016. Accessed: Jul. 14, 2024. [Online]. Available: http://arxiv.org/abs/1602.07360
M. R. W. Budiarto and F. Utaminingrum, “Sistem Klasifikasi Permukaan Jalan dan Penghindaran Jalan Berlubang pada Kursi Roda Pintar dengan Metode MobileNetV3-Small,” J. Pengemb. Teknol. Inf. Dan Ilmu Komput., vol. 7, no. 5, Art. no. 5, Aug. 2023, Accessed: Jul. 14, 2024. [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/12693
A. Akram, K. Fayakun, and H. Ramza, “Klasifikasi Hama Serangga pada Pertanian Menggunakan Metode Convolutional Neural Network,” Build. Inform. Technol. Sci. BITS, vol. 5, no. 2, Art. no. 2, Sep. 2023, doi: 10.47065/bits.v5i2.4063.
T. Susim and C. Darujati, “Pengolahan Citra untuk Pengenalan Wajah (Face Recognition) Menggunakan OpenCV,” J. Syntax Admiration, vol. 2, no. 3, pp. 534–545, Mar. 2021, doi: 10.46799/jsa.v2i3.202.
F. N. Cahya, N. Hardi, D. Riana, and S. Hadiyanti, “Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network (CNN),” SISTEMASI, vol. 10, no. 3, p. 618, Sep. 2021, doi: 10.32520/stmsi.v10i3.1248.
R. Kurniawan, A. T. Martadinata, and S. D. Cahyo, “Klasifikasi Tingkat Kematangan Buah Sawit Berbasis Deep Learning dengan Menggunakan Arsitektur Yolov5,” J. Inf. Syst. Res. JOSH, vol. 5, no. 1, Art. no. 1, Oct. 2023, doi: 10.47065/josh.v5i1.4408.
A. Kholik, “KLASIFIKASI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) PADA TANGKAPAN LAYAR HALAMAN INSTAGRAM,” J. Data Min. Dan Sist. Inf., vol. 2, no. 2, Art. no. 2, Aug. 2021, doi: 10.33365/jdmsi.v2i2.1345.
J. Sumpena, “A Comparative study of Transfer Learning CNN for Flower Type Classification,” J. Appl. Intell. Syst., vol. 8, no. 3, pp. 389–399, Nov. 2023, doi: 10.33633/jais.v8i3.9380.
C. Yu, X. He, H. Ma, X. Qi, J. Lu, and Y. Zhao, “S-DenseNet: A DenseNet Compression Model Based on Convolution Grouping Strategy Using Skyline Method,” IEEE Access, vol. 7, pp. 183604–183613, 2019, doi: 10.1109/ACCESS.2019.2960315.
S. Alfarhood, A. Alrayeh, M. Safran, M. Alfarhood, and D. Che, “Image-Based Arabian Camel Breed Classification Using Transfer Learning on CNNs,” Appl. Sci., vol. 13, no. 14, Art. no. 14, Jan. 2023, doi: 10.3390/app13148192.
N. Kanwal et al., “Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs.” medRxiv, p. 2024.03.11.24304119, Mar. 13, 2024. doi: 10.1101/2024.03.11.24304119.
S. Giraddi, S. Seeri, P. S. Hiremath, and J. G.N, “Flower Classification using Deep Learning models,” 2020 Int. Conf. Smart Technol. Comput. Electr. Electron. ICSTCEE, pp. 130–133, Oct. 2020, doi: 10.1109/ICSTCEE49637.2020.9277041.
K. Han, J. He, Y. Wang, Y. Xiong, and C. Zhang, “An Image Classification Approach based on Deep Learning and Transfer Learning,” IOP Conf. Ser. Mater. Sci. Eng., vol. 768, no. 7, p. 072055, Mar. 2020, doi: 10.1088/1757-899X/768/7/072055.
C.-I. Moon and O. Lee, “Skin Microstructure Segmentation and Aging Classification Using CNN-Based Models,” IEEE Access, vol. 10, pp. 4948–4956, 2022, doi: 10.1109/ACCESS.2021.3140031.
A. Howard et al., “Searching for MobileNetV3.” arXiv, Nov. 20, 2019. Accessed: Jul. 15, 2024. [Online]. Available: http://arxiv.org/abs/1905.02244
“Flowers Recognition.” Accessed: Jul. 14, 2024. [Online]. Available: https://www.kaggle.com/datasets/alxmamaev/flowers-recognition
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Jurnal Nasional Ilmu Komputer
This work is licensed under a Creative Commons Attribution 4.0 International License.
