KLASIFIKASI KUALITAS MANGGA HARUM MANIS: PENDEKATAN NEURAL NETWORK
DOI:
https://doi.org/10.58822/tbq.v7i2.161Keywords:
Klasifikasi, multilayer perceptron, ReLU, AdamAbstract
Mangga Harum Manis adalah salah satu komoditas ekspor Indonesia yang dapat dikategorikan menjadi tiga tingkat kualitas: Grade A, B, dan C. Penelitian ini mengimplementasikan algoritma multilayer perceptron (MLP) dengan fungsi aktivasi ReLU dan optimasi Adam, serta variasi jumlah neuron 10, 20, dan 30 pada masing-masing lapisan tersembunyi. Performa dari ketiga model yang dibangun dianalisis menggunakan nilai akurasi, presisi, dan recall yang diperoleh dari evaluasi menggunakan confusion matrix. Model dengan kombinasi 20-30-10 neuron dalam lapisan tersembunyi menunjukkan performa terbaik. Dengan akurasi = 82.5%, presisi = 82.2%, dan recall = 82.4% untuk klasifikasi data latih, dan akurasi = 77.4%, presisi = 78.1%, dan recall = 77.4% untuk klasifikasi data uji, kombinasi ini melampaui performa dua model lainnya. Dengan perbandingan rata-rata antara performa klasifikasi data latih dan data uji di bawah 5%, model yang dihasilkan menunjukkan ketahanan yang sangat baik terhadap perubahan data atau penambahan data selanjutnya.
References
S. Utami, K. Baskoro, L. K. Perwati, and M. Murningsih, “Keragaman Varietas Mangga (Mangifera indica L.) Di Kotamadya Semarang Jawa Tengah,” Bioma Berk. Ilm. Biol., vol. 21, no. 2, pp. 121–125, 2019, doi: 10.14710/bioma.21.2.121-125.
M. B. Sembiring, D. Rahmi, M. Maulina, V. Tari, R. Rahmayanti, and A. B. Suwardi, “Identifikasi Karakter Morfologi dan Sensoris Kultivar Mangga (Mangifera Indica L.) di Kecamatan Langsa Lama, Aceh, Indonesia,” J. Biol. Trop., vol. 20, no. 2, pp. 179–184, 2020, doi: 10.29303/jbt.v20i2.1876.
M. Maryati, A. Primairyani, and S. Irawati, “PENGEMBANGAN LEMBAR KERJA SISWA BERDASARKAN HASIL OBSERVASI KEANEKARAGAMAN MORFOLOGI TANAMAN MANGGA (Mangifera Indica),” Diklabio J. Pendidik. dan Pembelajaran Biol., vol. 2, no. 1, pp. 68–75, 2018, doi: 10.33369/diklabio.2.1.68-75.
S. Hartiningtyas, I. Ruslianto, and R. Hidayati, “Klasifikasi Jenis Mangga Berdasarkan Fitur Bentuk Dan Warna Daun Dengan Menggunakan Metode K-Nearest Neighbor Berbasis Android,” J. Coding, Sist. Komput. Untan, vol. 6, no. 1, pp. 12–23, 2018.
G. Widhiyoga, H. Wijayati, and R. Alma’unah, “Export Performance Of Indonesia’s Leading Tropical Fruit Commodities To Main Destination Countries,” IQTISHADUNA J. Ilm. Ekon. Kita, vol. 12, no. 1, pp. 128–148, 2023, doi: 10.46367/iqtishaduna.v12i1.1126.
V. Bhole and A. Kumar, “Mango Quality Grading using Deep Learning Technique: Perspectives from Agriculture and Food Industry,” SIGITE 2020 - Proc. 21st Annu. Conf. Inf. Technol. Educ., no. October, pp. 180–186, 2020, doi: 10.1145/3368308.3415370.
M. F. Mavi, Z. Husin, R. Badlishah Ahmad, Y. M. Yacob, R. S. M. Farook, and W. K. Tan, “Mango ripeness classification system using hybrid technique,” Indones. J. Electr. Eng. Comput. Sci., vol. 14, no. 2, pp. 859–868, 2019, doi: 10.11591/ijeecs.v14.i2.pp859-868.
L. Agilandeeswari, M. Prabukumar, and G. Shubham, “Automatic Grading System Mangoes Using Multiclass SVM Classifier,” Int. J. Pure Appl. Math., vol. 116, no. 23, pp. 515–523, 2017.
B. Zheng and T. Huang, “Mango Grading System Based on Optimized Convolutional Neural Network,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/2652487.
H. M. Rizwan Iqbal and A. Hakim, “Classification and Grading of Harvested Mangoes Using Convolutional Neural Network,” Int. J. Fruit Sci., vol. 22, no. 1, pp. 95–109, 2022, doi: 10.1080/15538362.2021.2023069.
J. Kusuma, B. H. Hayadi, Wanayumini, and R. Rosnelly, “Comparison of Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM) Methods for Breast Cancer Classification,” MIND (Multimedia Artif. Intell. Netw. Database) J., vol. 7, no. 1, pp. 51–60, 2022, [Online]. Available: https://ejurnal.itenas.ac.id/index.php/mindjournal/article/view/6909
I. Firmansyah and R. Rosnelly, “Inception-V3 Versus VGG-16 : in Rice Classification Using Multilayer Perceptron,” in 2nd International Conference on Information Science and Technology Innovatin (ICoSTEC), 2023, pp. 1–5.
K. F. Margolang, S. Riyadi, R. Rosnelly, and Wanayumini, “Pengenalan Masker Wajah Menggunakan VGG-16 dan Multilayer Perceptron,” J. Telemat., vol. 17, no. 2, pp. 80–87, 2023.
M. Handayani, M. Riandini, and Z. Zakarias, “Comparison of Neural Network Optimization Functions in Candidate Husband Eligibility Classification,” J. Inform., vol. 9, no. 1, pp. 78–84, Apr. 2022, doi: 10.31294/inf.v9i1.12318.
D. Pardede, I. Firmansyah, M. Handayani, M. Riandini, and R. Rosnelly, “Comparison Of Multilayer Perceptron’s Activation And Optimization Functions In Classification Of Covid-19 Patients,” JURTEKSI (Jurnal Teknol. dan Sist. Informasi), vol. 8, no. 3, pp. 271–278, Aug. 2022, doi: 10.33330/jurteksi.v8i3.1482.
M. S. Wibawa and I. M. D. Maysanjaya, “MULTI LAYER PERCEPTRON DAN PRINCIPAL COMPONENT ANALYSIS UNTUK DIAGNOSA KANKER PAYUDARA,” J. Nas. Pendidik. Tek. Inform., vol. 7, no. 1, p. 90, May 2018, doi: 10.23887/janapati.v7i1.12909.
Y. Franciska, T. S. Gunawan, and B. H. Hayadi, “Combination Of SqueezeNet And Multilayer Backpropagation Algorithm In Hanacaraka Script Recognition,” 2nd Int. Conf. iInformation Sci. Technol. Innov., vol. 2, no. 2(1), pp. 163–170, 2023, [Online]. Available: https://prosiding-icostec.respati.ac.id/index.php/icostec/article/view/51/51
I. Firmansyah and B. H. Hayadi, “Komparasi Fungsi Aktivasi Relu Dan Tanh Pada Multilayer Perceptron,” JIKO (Jurnal Inform. dan Komputer), vol. 6, no. 2, p. 200, 2022, doi: 10.26798/jiko.v6i2.600.
D. Pardede, B. H. Hayadi, and Iskandar, “Multi-Layer Perceptron Literature Review How Well This Algorithm Performs,” J. ICT Apl. Syst., vol. 1, no. 1, pp. 23–35, Jun. 2022, doi: 10.56313/jictas.v1i1.127.
K. L. Kohsasih, M. Dipo, A. Rizky, T. Fahriyani, V. Wijaya, and R. Rosnelly, “Analisis Perbandingan Algoritma Convolutional Neural Network Dan Algoritma Multi-Layer Perceptron Neural Dalam Klasifikasi Citra Sampah,” J. TIMES, vol. 10, no. 2, pp. 22–28, 2022, [Online]. Available: http://ejournal.stmik-time.ac.id
I. G. R. M. Putra, M. W. A. Kesiman, G. A. Pradnyana, and I. M. D. Maysanjaya, “Identifikasi Citra Ukiran Ornamen Tradisional Bali Dengan Metode Multilayer Perceptron,” SINTECH (Science Inf. Technol. J., vol. 4, no. 1, pp. 29–39, 2021, doi: 10.31598/sintechjournal.v4i1.552.
A. N. Handayani, H. W. Herwanto, K. L. Chandrika, and K. Arai, “Recognition of Handwritten Javanese Script using Backpropagation with Zoning Feature Extraction,” Knowl. Eng. Data Sci., vol. 4, no. 2, p. 117, 2021, doi: 10.17977/um018v4i22021p117-127.
I. Gunawan, “Optimasi Model Artificial Neural Network untuk Klasifikasi Paket Jaringan,” Simetris, vol. 14, no. 2, pp. 1–5, 2020, doi: 10.51901/simetris.v14i2.135.
G. R. de Souza, I. P. Bello, F. V. Corrêa, and L. F. C. de Oliveira, “Artificial Neural Networks for Filling Missing Streamflow Data in Rio do Carmo Basin, Minas Gerais, Brazil,” Brazilian Arch. Biol. Technol., vol. 63, pp. 1–8, 2020, doi: 10.1590/1678-4324-2020180522.
J. Mohammadi, M. Ataei, R. Khalo Kakaei, R. Mikaeil, and S. Shaffiee Haghshenas, “Prediction of the Production Rate of Chain Saw Machine using the Multilayer Perceptron (MLP) Neural Network,” Civ. Eng. J., vol. 4, no. 7, p. 1575, 2018, doi: 10.28991/cej-0309196.
D. Pardede and B. H. Hayadi, “Klasifikasi Sentimen Terhadap Gelaran MotoGP Mandalika 2022 Menggunakan Machine Learning,” J. Transform., vol. 20, no. 2, pp. 42–50, 2023.
S. Mandasari, D. Irfan, W. Wanayumini, and R. Rosnelly, “COMPARISON OF SGD, ADADELTA, ADAM OPTIMIZATION IN GENDER CLASSIFICATION USING CNN,” JURTEKSI (Jurnal Teknol. dan Sist. Informasi), vol. 9, no. 3, pp. 345–354, Jun. 2023, doi: 10.33330/jurteksi.v9i3.2067.
D. Pardede, Wanayumini, and R. Rosnelly, “A Combination Of Support Vector Machine And Inception-V3 In Face-Based Gender Classification,” Int. Conf. Inf. Sci. Technol. Innov., vol. 2, no. 1, pp. 34–39, Mar. 2023, doi: 10.35842/icostec.v2i1.30.
S. Riyadi, Hartono, and Wanayumini, “Predicting Children’s Talent Based On Hobby Using C4.5 Algorithm And Random Forest,” in International Conference on Information Science and Technology Innovation (ICoSTEC), Mar. 2023, pp. 182–186. doi: 10.35842/icostec.v2i1.54.
