KLASIFIKASI JENIS JAMUR MENGGUNAKAN METODE NEURAL NETWORK DENGAN FITUR INCEPTION-V3

Okka Hermawan Yulianto; Setyawan Wibisono

doi:10.51903/elkom.v16i2.1281

Okka Hermawan Yulianto Universitas Stikubank Semarang
Setyawan Wibisono Unisbank Semarang

DOI: https://doi.org/10.51903/elkom.v16i2.1281

Abstract

Mushrooms are very diverse with characteristics of each type, there are 1,433,800 types of mushrooms that have not been recognized. In this study, researchers used the Neural Network and Deep Learning Inception V3 methods as a feature extraction process in images to classify mushroom images based on genus with the Orange Data Mining application. There are 9 genera of mushrooms used in this study, namely Agaricus, Amanita, Boletus, Cortinarius, Entoloma, Hygrocybe, Lactarius, Russula, and Suillus. The total dataset used is 2,700, with 300 images for each genus. The test uses the cross-validation method which is applied to the confusion matrix to get precision, recall, F1-score, and accuracy values. In this study, the final classification results were obtained with an accuracy of 82.5% and the genus Boletus mushroom obtained the best results with an accuracy of 98.9%.

References

[1] Yohannes, Nur Rachmat, and Calvin Oliver Saputra, “Penggunaan Fitur HOG Berbasis Superpixel
Untuk Klasifikasi Jenis Jamur Dengan Metode SVM,” Jusikom :Jurnal Sistem Komputer usirawas,
vol. 6, no. 1, Jun. 2021.
[2] M. G. Wahdini, N. F. A. H, and A. Lawi, “Klasifikasi Jamur dapat Dikonsumsi dan Beracun Menggunakan Model Bayesian Network,” in Prosiding Seminar Nasional Teknik Elektro dan Informatika (SNTEI), S. Said, Ed., Pad: Jurusan Teknik Elektro, Politeknik Negeri Ujung Pandang, 2022.
[3] M. Z. Altim, Faisal, Salmiah, Kasman, A. Yudhistira, And R. A. Syamsu, “Pengklasifikasi Beras Menggunakan Metode CNN (Convolutional Neural Network),” Jurnal INSTEK (Informatika Sains dan Teknologi), vol. 7, no. 1, pp. 151–155, Mar. 2022, doi: 10.24252/instek.v7i1.28922.
[4] A. Hermawan and A. P. Wibowo, “Implementasi Korelasi untuk Seleksi Fitur pada Klasifikasi
Jamur Beracun Menggunakan Jaringan Syaraf Tiruan,” Jurnal INTEK, vol. 5, no. 1, pp. 63–67, May 2022.
[5] J. Kusuma, A. Jinan, M. Z. Lubis, R. Rubianto, and R. Rosnelly, “KomparasiAlgoritma Support Vector Machine Dan Naive Bayes Pada Klasifikasi Ras Kucing,” GENERIC : Jurnal Ilmu Komputer dan Teknologi Informasi, vol. 14, no. 1, pp. 8–12, Jan. 2022.
[6] Yohannes, D. Udjulawa, and T. Ivan Sariyo, “Klasifikasi Jenis Jamur Menggunakan SVM dengan Fitur HSV dan HOG,” PETIR : Jurnal Pengkajian dan Penerapan Teknik Informatika, vol. 15, no. 1, pp. 113–120, Dec. 2022, doi: 10.33322/petir.v15i1.1101.
[7] D. Darmatasia And A. M. Syafar, “Implementasi Convolutional Neural Network Untuk Klasifikasi Tanaman Rimpang Secara Virtual,” Jurnal INSTEK (Informatika Sains dan Teknologi), vol. 8, no. 1, pp. 122–131, Mar. 2023.
[8] K. S. K. H. L. A. R. G. P. R. K. A. S. W. M. P. Fitri Handayani, “Komparasi Support Vector Machine, Logistic Regression Dan Artificial Neural Network Dalam Prediksi Penyakit Jantung,” Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 7, no. 3, p. 329, Dec. 2021, doi: 10.26418/jp.v7i3.48053.