Classification of beetle type using the Convolutional Neural Network algorithm
DOI:
10.33395/sinkron.v7i4.11673Keywords:
Image Classification, Convolutional Neural Network, ResNet50, VGG16, Confusion Matrix, BettleAbstract
Beetles (Order Coleoptera) are the largest order of animals. Beetles are a group of insects that make up the order Coleoptera. Estimates of the total number of living beetle species are millions of beetle species whose features make it difficult to visually identify beetle species. Currently, the beetle classification process is still carried out using direct observation and personal assumptions. CNN model ResNet50 is one of the ResNet variants that has 50 layers and VGG16 is a CNN model that utilizes a convolutional layer with a small convolutional filter specification (3×3) and always uses the same padding and maxpool layers of a 2x2 filter. In this Algorithm (CNN) with the ResNet50 model, it succeeded in exploring beetles with accuracy, precision, recall and F-1 Score with values of 93%, 94.24%, 89.28%, 91.69%, while the VGG16 model succeeded in conducting research on beetle species with accuracy, precision, recall and F-1 Score with values of 86.9%, 87.5%, 87%, 87.2%, so it can be said that the classification of beetle species using the CNN algorithm with the ResNet50 model is better than the VGG16 model.
Downloads
References
Depari E, Dirhamsyah., Darwati H. (2021). Identifikasi Jenis Kumbang (Coleoptera) di Hutan Sekunder Desa Ladangan Kecamatan Menyuke Kabupaten Landak. J Hutan Lestari.,9(3),475–84.
Apriyani S, Wahyuni S, & Azzumar P M. (2021) "KERAGAMAN HAMA PADA PERTANAMAN BAWANG MERAH (Allium ascalonicum L.) DI KABUPATAN PATI". Jurnal Litbang Provinsi Jawa Tengah, 19(1), 13–20.
Ghosh, A., Sufian, A., Sultana, F., Chakrabarti, A., & De, D. (2019). Fundamental concepts of convolutional neural network. Intelligent Systems Reference Library, 172, 519–567.
Arrofiqoh, E. N., & Harintaka, H. (2018). Implementasi Metode Convolutional Neural Network Untuk Klasifikasi Tanaman Pada Citra Resolusi Tinggi. Geomatika, 24(2), 61.
Afif, M., Fawwaz, A., Ramadhani, K. N., & Sthevanie, F. (2020). Klasifikasi Ras pada Kucing menggunakan Algoritma Convolutional Neural Network (CNN). Jurnal Tugas Akhir Fakultas Informatika, 8(1), 715–730.
Pratiwi, N. F. (2020). Klasifikasi Spesies Ikan Air Tawar Menggunakan Convolutional Neural Network. Engineering, Construction and Architectural Management, 25(1), 1–9.
Yunita Y, (2020). Klasifikasi Gambar Menggunakan Metode K-Nearest Neighbor Image Classification Using K-Nearest Neighbor Method. Semin Nas Teknol Inf dan Komun, 451–7.
Borwarnginn P, Thongkanchorn K, Kanchanapreechakorn S, Kusakunniran W. Breakthrough Conventional Based Approach for Dog Breed Classification Using CNN with Transfer Learning. In 2019 11th International Conference on Information Technology and Electrical Engineering.
Wang Z, Zhao D, Hong K. “PROJECT DOG BREED CLASSIFICATION.” Radio Sci. 2017
Ayanzadeh, A., & Vahidnia, S. (2018). Modified Deep Neural Networks for Dog Breeds Identification. Preprints.
Kholik A. (2021). Klasifikasi Menggunakan Convolutional Neural Network (Cnn) Pada Tangkapan Layar Halaman Instagram. JDMSI, 2(2), 10-20, ISSN: 2745-8458.
Kurniawan AA, Mustikasari M. Implementasi Deep Learning Menggunakan Metode CNN dan LSTM untuk Menentukan Berita Palsu dalam Bahasa Indonesia. J Inform Univ Pamulang. 2021;5(4):544.
Maulana FF, Rochmawati N. Klasifikasi Citra Buah Menggunakan Convolutional Neural Network. J Informatics Comput Sci. 2020;1(02):104–8.
Akbar SNAF, Hendra, Supri Bin Hj. Amir. Perbandingan Kinerja Arsitektur Inception-V4 Dan Resnet-50 Dalam Mengklasifikasikan Citra Paru-Paru Terinfeksi Covid-19. 2020;2.
Akbar SNAF, Hendra, Supri Bin Hj. Amir. Perbandingan Kinerja Arsitektur Inception-V4 Dan Resnet-50 Dalam Mengklasifikasikan Citra Paru-Paru Terinfeksi Covid-19. 2020;2
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2022 Insidini Fawwaz, Tomy Candra, Delima Agustina Margareta Marpaung, Arun Dinis, M Reza Fachrozi
![Creative Commons License](http://i.creativecommons.org/l/by-nc/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.