Hyperparameter Optimization Using Hyperband in Convolutional Neural Network for Image Classification of Indonesian Snacks
Abstract
Abstract. Indonesia is known for its traditional food both domestically and abroad. Several cakes are included in favorite traditional foods. Of the many types of cakes that exist, it is visually easy to recognize by humans, but computer vision requires special techniques in identifying image objects to types of cakes. Therefore, to recognize objects in the form of images of cakes as one of Indonesian specialties, a deep learning algorithm technique, namely the Convolutional Neural Network (CNN) can be used.
Purpose: This study aims to find out how the Convolutional Neural Network (CNN) works by optimizing the hyperband hyperparameter in the classification process and knowing the accuracy value when hyperband is applied to the optimal hyperparameter selection process for classifying Indonesian snack images.
Methods/Study design/approach: This study optimizes the hyperparameter Convolutional Neural Network (CNN) using Hyperband on the Indonesian cake dataset. The dataset is 1845 images of Indonesian snacks which consists of 1523 training data, 162 validation data and 160 testing data with 8 classes. In training data, the dataset is divided by 82% on training data, 9% validation, and 9% testing.
Result/Findings: The best hyperparameter value produced is 480 for the number of dense neurons 2 and 0.0001 for the learning rate. The proposed method succeeded in achieving a training value of 87.53%, for the validation process it was obtained 66.8%, the testing process was obtained 79.37%. Results obtained from model training of 50 epochs.
Novelty/Originality/Value: Previous research focused on the application and development of algorithms for the classification of Indonesian snacks. Therefore, optimizing hyperparameters in a Convolutional Neural Network (CNN) using Hyperband can be an alternative in selecting the optimal architecture and hyperparameters.
References
[2] M. Effendi, Fitriyah, and U. Effendi, “Identifikasi Jenis Dan Mutu Teh Menggunakan Pengolahan Citra Digital Dengan Metode Jaringan Syaraf Tiruan,” J. Teknotan, vol. 11, no. 2, pp. 67–76, 2017, doi: 10.24198/jt.vol11n2.7.
[3] D. Sumarlie et al., “Pengenalan Kue Tradisional Indonesia Menggunakan Algoritma Convolutional Neural Network,” J. Comput. Sci. Inf. Syst., vol. 6, no. 2, pp. 164–171, 2022, [Online]. Available: http://repository.ub.ac.id/185145/.
[4] A. A. Hariman, D. I. Mulyana, and M. B. Yel, “Klasifikasi Jajanan Tradisional Jawa Tengah Dengan Metode Transfer Learning Dan Mobilnetv2 Aloisius,” J. Inf. Interaktif, vol. 8, no. 1, 2023, doi: 10.26594/teknologi.v11i2.2402.
[5] A. S. R. Sinaga, “Implementasi Teknik Threshoding Pada Segmentasi Citra Digital,” J. Mantik Penusa, vol. 1, no. 2, pp. 48–51, 2017.
[6] A. Solikhin, G. Raharjo, and E. Sugiharti, “Alphabet Classification of Sign System Using Convolutional Neural Network with Contrast Limited Adaptive Histogram Equalization and Canny Edge Detection,” vol. 10, no. 3, pp. 239–250, 2023, doi: 10.15294/sji.v10i3.44137.
[7] Y. Lecun, L. Bottou, Y. Bengio, and P. Ha, “Gradient-Based Learning Applied to Document Recognition,” IEEE Access, vol. 86, no. 11, pp. 2278–2323, 1998, doi: 10.1109/5.726791.
[8] C. Rasche, Computer Vision an Overview for Enthusiasts. Bucharest: Bucharest: Polytechnic University of Bucharest, 2019.
[9] A. T. Mauludy, D. C. Khrisne, and K. O. Saputra, “Rancang Bangun Aplikasi Pencarian Slot Parkir
Kosong Untuk Kendaraan Roda Empat dengan Pendekatan Computer Vision,” J. SPEKTRUM, vol. 7, no. 1, pp. 36–40, 2020, doi: 10.24843/SPEKTRUM.2020.v07.i01.p5.
[10] S. Mujilahwati, M. Sholihin, and R. Wardhani, “Optimasi Hyperparameter TensorFlow dengan Menggunakan Optuna di Python : Study Kasus Klasifikasi Dokumen Abstrak Skripsi,” vol. 5, pp. 1084–1089, 2021, doi: 10.30865/mib.v5i3.3090.
[11] N. O. Mahony et al., “Deep Learning vs . Traditional Computer Vision Deep Learning vs . Traditional Computer Vision,” no. April, 2019, doi: 10.1007/978-3-030-17795-9.
[12] E. Sugiharti, R. Arifudin, D. T. Wiyanti, and A. B. Susilo, “Integration of convolutional neural network and extreme gradient boosting for breast cancer detection,” vol. 11, no. 2, pp. 803–813, 2022, doi: 10.11591/eei.v11i2.3562.
[13] D. A. Kurnia, A. Setiawan, D. R. Amalia, R. W. Arifin, and D. Setiyadi, “Image Processing Identifacation for Indonesian Cake Cuisine using CNN Classification Technique Image,” J. Phys. Conf. Ser. Pap., 2021, doi: 10.1088/1742-6596/1783/1/012047.
[14] K. Jamieson and A. Talwalkar, “Non-stochastic Best Arm Identification and Hyperparameter Optimization,” Proc. 19th Int. Conf. Artif. Intell. Stat., vol. 41, pp. 240–248, 2016, [Online]. Available: http://proceedings.mlr.press/v51/jamieson16.html.
[15] J. Wang, J. Xu, and X. Wang, “Combination of Hyperband and Bayesian Optimization for Hyperparameter Optimization in Deep Learning,” 2018, doi: 10.48550/arXiv.1801.01596.
[16] J. Li et al., “Water Quality Soft-sensor Prediction in Anaerobic Process Using Deep Neural Network Optimized by Tree-structured Parzen Estimator,” Front. Environ. Sci. Eng., vol. 17, no. 6, pp. 1–13, 2023, doi: 10.1007/s11783-023-1667-3.
[17] A. I. Khan and S. Al-Habsi, “Machine Learning in Computer Vision,” Procedia Comput. Sci., vol. 167, pp. 1444–1451, 2020, doi: 10.1016/j.procs.2020.03.355.
[18] A. Dhillon and G. K. Verma, “Convolutional neural network : a review of models , methodologies and applications to object detection,” Prog. Artif. Intell., vol. 9, no. 2, pp. 85–112, 2019, doi: 10.1007/s13748-019-00203-0.
