COMPARISON OF MULTILAYER PERCEPTRON’S ACTIVATION AND OP-TIMIZATION FUNCTIONS IN CLASSIFICATION OF COVID-19 PATIENTS

Doughlas Pardede, Ichsan Firmansyah, Meli Handayani, Meisarah Riandini, Rika Rosnelly

Abstract


Abstract: Patient’s symptoms could be used as features in Covid-19 classification. Using multi layer perceptron, the classification uses data set that contains patient’s diagnosis which has Covid-19 symptoms dan processes the data set to see if the patient is Covid-19 positive or not. This paper compare four activation function such as identity, logistic, ReLu and tanh and combined them with optimizer such as L-BFGS-B, SGD and Adam. Using 5-fold and 10-fold cross validation technique to get the accuracy, F1, precision and recall values, the result that we get is that logistic function with L-BFGS-B optimizer and ReLu function with L-BFGS-B optimizer are the best combinations. The logistic function with SGD optimizer, ReLu function with Adam optimizer and tanh function with Adam optimizer are the worst combinations according to their accuration values. The logistic function with SGD optimizer is the worst combination according to its F1 value. The logistic function with SGD optimizer and tanh function with L-BFGS-B optimizer are the worst combinations according to their precision values. The logistic function with SGD optimizer, ReLu function with Adam optimizer and tanh function with Adam optimizer are the worst combinations according to their recall values.

           
Keywords: activation function, covid-19; multi layer perceptron; optimizer algorithm

 

 

Abstrak: Diagnosa gejala yang dialami pasien dapat digunakan sebagai fitur dalam klasifikasi penderita Covid-19. Dengan multi layer perceptron, klasifikasi dilakukan menggunakan data set yang berisi hasil diagnosa pasien yang memiliki gejala Covid-19 dan selanjutnya diolah untuk  melihat apakah memang pasien tersebut menderita Covid-19 atau tidak. Penelitian ini membandingkan fungsi aktivasi identity, logistic, ReLu dan tanh yang dikombinasikan dengan algoritma optimasi L-BFGS-B, SGD dan Adam. Hasil evaluasi cross validation menggunakan 5-fold dan 10-fold digunakan sebagai dasar menentukan kombinasi yang terbaik dan terburuk, dengan hasil yang menunjukkan bahwa kombinasi fungsi logistic dengan optimasi L-BFGS-B dan fungsi ReLu dengan optimasi L-BFGS-B merupakan kombinasi terbaik. Kombinasi fungsi logisctic dengan optimasi SGD, fungsi ReLu dengan optimasi Adam dan fungsi tanh dengan optimasi Adam merupakan yang terburuk dari nilai accuracy. Kombinasi fungsi logistic dan optimasi SGD merupakan kombinasi terburuk dari nilai F1. Kombinasi fungsi logistic dengan optimasi SGD dan fungsi tanh dan optimasi L-BFGS-B merupakan yang terburuk dari nilai precision. Kombinasi fungsi logisctic dengan optimasi SGD, fungsi ReLu dengan optimasi Adam dan fungsi tanh dengan optimasi Adam merupakan kombinasi terburuk dari nilai recall.

 

Kata kunci: algoritma optimasi; covid-19; fungsi optimasi; multi layer perceptron

Full Text:

PDF

References


Z. Car, S. Baressi Šegota, N. Anđelić, I. Lorencin, and V. Mrzljak, “Modeling the Spread of COVID-19 Infection Using a Multilayer Perceptron,” Comput. Math. Methods Med., vol. 2020, 2020, doi: 10.1155/2020/5714714.

D. D. Romani, D. Nasution, A. Syahputra, and ..., “Artificial Neural Network Model In Forecasting Post-Covid-19 Aviation Business Development Using Multi Layer Perceptron (MLP),” Budapest Int. Res. Critics Insitute-Journal, vol. 4, no. 4, pp. 13189–13199, 2021, [Online]. Available: http://bircu-journal.com/index.php/birci/article/view/3384.

M. M. Ahsan, T. E. Alam, T. Trafalis, and P. Huebner, “Deep MLP-CNN model using mixed-data to distinguish between COVID-19 and Non-COVID-19 patients,” Symmetry (Basel)., vol. 12, no. 9, 2020, doi: 10.3390/sym12091526.

F. Mohammadi et al., “Artificial neural network and logistic regression modelling to characterize COVID-19 infected patients in local areas of Iran,” Biomed. J., vol. 44, no. 3, pp. 304–316, 2021, doi: 10.1016/j.bj.2021.02.006.

D. Pardede, B. H. Hayadi, and Iskandar, “Kajian literatur multi layer perceptron: seberapa baik performa algoritma ini,” J. ICT Apl. Syst., vol. 1, no. 1, pp. 23–35, 2022, [Online]. Available: https://e-jurnal.rokania.ac.id/index.php/jictas/article/view/127/84.

S. Ibrahim, S. A. Kamaruddin, N. N. Abu Mangshor, and A. F. Ahmad Fadzil, “A study of Covid-19 spread and death contributing factors in America Using Multi- Layer Perception (MLP) and Radial Basis Function (RBF),” Eur. J. Mol. Clin. Med., vol. 8, no. 2, pp. 144–158, 2021, [Online]. Available: https://www.embase.com/search/results?subaction=viewrecord&id=L2011094292&from=export.

N. N. Samany, A. Toomanian, A. Maher, K. Hanani, and A. R. Zali, “The most places at risk surrounding the COVID-19 treatment hospitals in an urban environment- case study: Tehran city,” Land use policy, vol. 109, no. 1, p. 105725, 2021, doi: 10.1016/j.landusepol.2021.10572.

R. P. Shetty and P. S. Pai, “Forecasting of COVID 19 Cases in Karnataka State using Artificial Neural Network (ANN),” J. Inst. Eng. Ser. B, vol. 102, no. 6, pp. 1201–1211, Dec. 2021, doi: 10.1007/s40031-021-00623-4.

B. Yuen, M. T. Hoang, X. Dong, and T. Lu, “Universal activation function for machine learning,” Sci. Rep., vol. 11, no. 1, pp. 1–12, 2021, doi: 10.1038/s41598-021-96723-8.

M. Handayani, M. Riandini, and Z. Situmorang, “Perbandingan Fungsi Optimasi Neural Network Dalam Klasifikasi Kelayakan Calon Suami,” J. Inform., vol. 9, no. 1, pp. 78–84, 2022, doi: https://doi.org/10.31294/inf.v9i1.12318.

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, 2018, doi: 10.23887/janapati.v7i1.12909.

H. Harikrishnan, “Symptoms and COVID Presence (May 2020 data),” 2020. https://www.kaggle.com/datasets/hemanthhari/symptoms-and-covid-presence.

K. F. Margolang, M. M. Siregar, S. Riyadi, and Z. Situmorang, “Analisa Distance Metric Algoritma K-Nearest Neighbor Pada Klasifikasi Kredit Macet,” J. Inf. Syst. Res., vol. 3, no. 2, pp. 118–124, 2022, doi: 10.47065/josh.v3i2.1262.




DOI: https://doi.org/10.33330/jurteksi.v8i3.1482

Article Metrics

Abstract view : 575 times
PDF - 358 times

Refbacks

  • There are currently no refbacks.


Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK ROYAL 

Copyright © LPPM STMIK ROYAL

 

Lisensi Creative Commons
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.