Machine Learning Pengenalan Herpetofauna Dilindungi Di Indonesia

Authors

Yasir Hasan Universitas Budi Darma Medan

Keywords:

Machine_learning, Herpetofauna, Classification, YOLO

Abstract

The population of herpetofauna animals in Indonesia is decreasing due to hunting, habitat destruction, and illegal trade. Apart from that, there is very little introduction to Herpetofauna among reptiles and amphibian lovers. There are also many cases of ownership and buying and selling of reptiles and amphibians that end with the forced taking of these Herpetofauna animals and even imprisonment for not having permission from the government. The problem of lack of knowledge about the types of Herpetofauna is one of the causes of the rarity of these animals which will become extinct in the future. Therefore, more effective and efficient conservation support efforts are needed in the form of research based on artificial intelligence to identify protected Herpetofauna animals in Indonesia. This research uses Machine Learning technology and the method used for segmentation is Deep Learning which is included in the YOLO stage and is very supportive in edge detection, color change, and classification. The use of this technology is implemented in a GUI application built in Python which can be used as a detection tool for the types of herpetofauna found in nature, in captivity, or in reptile trading markets. Therefore, Machine Learning Research Herpetofauna is very important to contribute to the government's conservation efforts to protect Herpetofauna and is expected to be sustainable for future generations.

References

A. Korespondensi et al., “Status Konservasi Reptilia Anggota Ordo Squamata yang Diperdagangkan di Surabaya Conservation Status of Reptiles (Order Squamata) Member Traded in Surabaya,” 2016.

D. Sarkar, R. Bali, and T. Sharma, Practical Machine Learning with Rust. 2020. doi: 10.1007/978-1-4842-5121-8.

O. Diaz Annesa, C. Kartiko, and A. Prasetiadi, “Identifikasi Spesies Reptil Menggunakan Convolutional Neural Network (CNN),” masa berlaku mulai, vol. 1, no. 3, pp. 899–906, 2017.

Jan Wira Gotama Putra, “Pengenalan konsep pembelajaran mesin dan deep learning,” Computational Linguistics and Natural Language Processing Laboratory, vol. 4, pp. 1–235, 2019.

A. Singh and S. Anekar, “Text to Image using Deep Learning; Text to Image using Deep Learning,” www.ijert.org, vol. 10, 2021.

K. Yamini, K. Sai Swetha, P. L. Prasanna, M. Rupa, V. Swathi, and V. Rao Maddumala, “IMAGE COLORIZATION WITH DEEP CONVOLUTIONAL OPEN CV,” vol. 11, 2020, [Online]. Available: www.jespublication.com

C. R. Qi, O. Litany, K. He, and L. J. Guibas, “Deep Hough Voting for 3D Object Detection in Point Clouds,” 2019. doi: https://doi.org/10.48550/arXiv.1904.09664.

G. Dai, L. Hu, and J. Fan, “DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification,” Comput Intell Neurosci, vol. 2022, 2022, doi: 10.1155/2022/6114061.

W. Wibowo, B. S. S. Ulama, and H. al Azies., “BELAJAR PEMROGRAMAN BAHASA PYTHON.”

X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios,” Beijing, 2021.

W. H. Nugroho, S. Handoyo, Y. J. Akri, and A. D. Sulistyono, “Building Multiclass Classification Model of Logistic Regression and Decision Tree Using the Chi-Square Test for Variable Selection Method,” Journal of Hunan University Natural Sciences, vol. 49, no. 4, pp. 172–181, Apr. 2022, doi: 10.55463/issn.1674-2974.49.4.17.