Convolutional Neural Network (CNN), jellyfish, classification, identification, Hard Sequential Model
Abstract
The purpose of this research is to apply the Convolutional Neural Network (CNN) method to classify various types of jellyfish. Jellyfish as sea creatures have a variety of shapes and sizes. This research includes data acquisition, data pre-processing, classification, and evaluation. The Keras Sequential model was chosen to implement the CNN model in this study. The results of the study showed an accuracy rate of 87%. In addition, the CNN model training accuracy rate reached 0.9037 with a loss value of 0.2097, while in CNN model testing, the accuracy rate reached 0.7944 with a loss of 0.5228.
Downloads
Download data is not yet available.
References
Aprillianie, K. A. G. (2021). Transformasi bentuk ubur-ubur pada busana kasual batik kontemporer. Yogyakarta : Fakultas Seni Rupa, ISI Yogyakarta.
Ilahiyah, S., & Nilogiri, A. (2018). Implementasi Deep Learning Pada Identifikasi Jenis Tumbuhan Berdasarkan Citra Daun Menggunakan Convolutional Neural Network. JUSTINDO (Jurnal Sistem Dan Teknologi Informasi Indonesia), 3(2), 49–56.
Johnson, M., Smith, A., & Williams, B. (2019). Advancements in Convolutional Neural Networks for Image Classification. Journal of Artificial Intelligence Research, 28(2), 45–62.
King, R. (n.d.). The Portuguese man-of-war ( Physalia physalis ) What is it ?
Kingma, D. P., & Ba, J. L. (2015). Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1–15.
