Evaluasi Performa Oversampling dan Augmentasi pada Klasifikasi Penyakit Kulit Menerapkan Convolutional Neural Network

 (*)Deo Andrianto Iskandar Mail (Universitas Dian Nuswantoro, Semarang, Indonesia)
 Abu Salam (Universitas Dian Nuswantoro, Semarang, Indonesia)

(*) Corresponding Author

Submitted: December 12, 2023; Published: January 10, 2024

Abstract

The skin is the largest outer part of the human body. Maintaining skin is very important. The appearance of unusual things on the skin will raise concerns because it is possible that the skin could be affected by fatal diseases. Limited specialist doctor examinations in Indonesia add to the difficulty in preventing skin diseases. Therefore, this research was conducted to facilitate the classification of skin diseases. Skin disease classification must have good accuracy or precision in classifying each type. This study classifies skin diseases accurately and precisely by evaluating the performance of Oversampling and Augmentation techniques. This research uses the Convolutional Neural Network (CNN) approach. Using the HAM10000 dataset which contains dermoscopic images with a total of 10015 images. This study applies Oversampling to overcome data imbalance and applies image augmentation to improve model training performance. The performance of the model is evaluated using accuracy, recall, precision, f1-score, specificity, sensitivity, gmean. Comparisons are obtained from testing the original dataset, the dataset with oversampling and various augmentation techniques. The evaluation results show that the third test, namely classification using the CNN approach with oversampling and augmentation rotation, zoom, width, height, vertical_flip, gets the best results, namely accuracy 0.98, recall 0.98, precision 0.98, f1-score 0.98, specificity 0.99, sensitivity 0.98, gmean 0.98.

Keywords


Skin Disease; Classification; Augmentation; Oversampling; HAM10000

Full Text:

PDF


Article Metrics

Abstract view : 470 times
PDF - 411 times

References

M. Hidayatullah, Diagnosis Penyakit Kulit pada Manusia dengan Metode Naive Bayes menggunakan Shiny, vol. 3, no. 3, 2023.

I. M. Dijkhoff et al., Impact of airborne particulate matter on skin: A systematic review from epidemiology to in vitro studies, Part. Fibre Toxicol., vol. 17, no. 1, pp. 128, 2020, doi: 10.1186/s12989-020-00366-y.

Scabies - World Health Organization (WHO), Online, 2023. https://www.who.int/news-room/fact-sheets/detail/scabies

Scabies - World Health Organization (WHO), Online, 2023. https://www.who.int/health-topics/scabies

P. Tschandl, C. Rosendahl, and H. Kittler, Data Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions, Nat. Publ. Gr., pp. 19, 2018, doi: 10.1038/sdata.2018.161.

KKI, STR-Konsil Kedokteran Indonesia, 2023. https://kki.go.id/ (accessed Dec. 10, 2023).

Dirjen Pelayanan Kesehatan, PERANAN PATOLOGI ANATOMI, 2022. https://yankes.kemkes.go.id/view_artikel/459/peranan-patologi-anatomi

N. Nurkhasanah and M. Murinto, Klasifikasi Penyakit Kulit Wajah Menggunakan Metode Convolutional Neural Network, Sainteks, vol. 18, no. 2, p. 183, Feb. 2022, doi: 10.30595/sainteks.v18i2.13188.

D. D. Putri, M. T. Furqon, and R. S. Perdana, Klasifikasi Penyakit Kulit Pada Manusia Menggunakan Metode Binary Decision Tree Support Vector Machine ( BDTSVM ), J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 5, pp. 19121920, 2018.

M. F. Naufal, Comparative Analysis of Image Classification Algorithm for, J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 2, pp. 311318, 2021, doi: 10.25126/jtiik.202184553.

N. Nurkhasanah and M. Murinto, Klasifikasi Penyakit Kulit Wajah Menggunakan Metode Convolutional Neural Network, Sainteks, vol. 18, no. 2, p. 183, 2021, doi: 10.30595/sainteks.v18i2.13188.

Z. Huang, X. Yao, Y. Liu, C. O. Dumitru, M. Datcu, and J. Han, Physically explainable CNN for SAR image classification, ISPRS J. Photogramm. Remote Sens., vol. 190, pp. 2537, 2022, doi: 10.1016/j.isprsjprs.2022.05.008.

N. E. Khalifa, M. Loey, and S. Mirjalili, A comprehensive survey of recent trends in deep learning for digital images augmentation, Artif. Intell. Rev., vol. 55, no. 3, pp. 23512377, 2022, doi: 10.1007/s10462-021-10066-4.

T. Kumar, A. Mileo, R. Brennan, and M. Bendechache, Image Data Augmentation Approaches: A Comprehensive Survey and Future directions, vol. 6223, 2023, [Online]. Available: http://arxiv.org/abs/2301.02830

S. Diantika, PENERAPAN TEKNIK RANDOM OVERSAMPLING UNTUK MENGATASI IMBALANCE CLASS DALAM KLASIFIKASI WEBSITE PHISHING MENGGUNAKAN ALGORITMA LIGHTGBM, JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 1, pp. 1925, Jan. 2023, doi: 10.36040/jati.v7i1.6006.

S. Choirunnisa, Metode Hibrida Oversampling dan Undersampling Untuk Menangani Ketidakseimbangan Data Kegagalan Aakademik Universitas XYZ, 2019.

L. Qadrini, H. Hikmah, and M. Megasari, Oversampling, Undersampling, Smote SVM dan Random Forest pada Klasifikasi Penerima Bidikmisi Sejawa Timur Tahun 2017, J. Comput. Syst. Informatics, vol. 3, no. 4, pp. 386391, 2022, doi: 10.47065/josyc.v3i4.2154.

T. B. Sasongko, H. Haryoko, and A. Amrullah, Analisis Efek Augmentasi Dataset dan Fine Tune pada Algoritma Pre-Trained Convolutional Neural Network (CNN), J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 4, pp. 763768, 2023, doi: 10.25126/jtiik.20241046583.

L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, J. Big Data, vol. 8, no. 1, p. 53, Mar. 2021, doi: 10.1186/s40537-021-00444-8.

G. Lukas Hansel and H. Bunyamin, Penggunaan Augmentasi Data pada Klasifikasi Jenis Kanker Payudara dengan Model Resnet-34, J. Strateg., vol. 3, no. 1, pp. 187193, 2021.

G. Aresta et al., BACH: Grand challenge on breast cancer histology images, Med. Image Anal., vol. 56, pp. 122139, 2019, doi: 10.1016/j.media.2019.05.010.

A. Jordan et al., Improving Batik Pattern Classification using CNN with Advanced Augmentation and Oversampling on Imbalanced Dataset, Procedia Comput. Sci., vol. 227, pp. 508517, 2023, doi: 10.1016/j.procs.2023.10.552.

M. Hayaty, S. Muthmainah, and S. M. Ghufran, Random and Synthetic Over-Sampling Approach to Resolve Data Imbalance in Classification, Int. J. Artif. Intell. Res., vol. 4, no. 2, p. 86, 2021, doi: 10.29099/ijair.v4i2.152.

J. M. Johnson and T. M. Khoshgoftaar, Deep learning and data sampling with imbalanced big data, Proc. - 2019 IEEE 20th Int. Conf. Inf. Reuse Integr. Data Sci. IRI 2019, no. October, pp. 175183, 2019, doi: 10.1109/IRI.2019.00038.

K. Thaiyalnayaki, S. Raghul, U. K. Kumar, and S. Ramachandran, Automatic classification of cassava using data augmentation and CNN, AIP Conf. Proc., vol. 2405, no. August, 2022, doi: 10.1063/5.0072729.

A. Maistry, A. Pillay, and E. Jembere, Improving the accuracy of diabetes retinopathy image classification using augmentation, ACM Int. Conf. Proceeding Ser., pp. 134140, 2020, doi: 10.1145/3410886.3410914.

K. Mallikharjuna Rao, G. Saikrishna, and K. Supriya, Data preprocessing techniques: emergence and selection towards machine learning models - a practical review using HPA dataset, Multimed. Tools Appl., vol. 82, no. 24, pp. 3717737196, Oct. 2023, doi: 10.1007/s11042-023-15087-5.

F. Last, G. Douzas, and F. Bacao, Oversampling for Imbalanced Learning Based on K-Means and SMOTE, pp. 119, 2017, doi: 10.1016/j.ins.2018.06.056.

G. Alwakid, W. Gouda, M. Humayun, and N. Z. Jhanjhi, Diagnosing Melanomas in Dermoscopy Images Using Deep Learning, Diagnostics, vol. 13, no. 10, pp. 115, 2023, doi: 10.3390/diagnostics13101815.

B. Kalpana, A. K. Reshmy, S. Senthil Pandi, and S. Dhanasekaran, OESV-KRF: Optimal ensemble support vector kernel random forest based early detection and classification of skin diseases, Biomed. Signal Process. Control, vol. 85, p. 104779, Aug. 2023, doi: 10.1016/j.bspc.2023.104779.

P. Shan, C. Fu, L. Dai, T. Jia, M. Tie, and J. Liu, Automatic skin lesion classification using a new densely connected convolutional network with an SF module, Med. Biol. Eng. Comput., vol. 60, no. 8, pp. 21732188, Aug. 2022, doi: 10.1007/s11517-022-02583-3.

X. Ma, J. Shan, F. Ning, W. Li, and H. Li, EFFNet: A skin cancer classification model based on feature fusion and random forests, PLoS One, vol. 18, no. 10 October, pp. 117, 2023, doi: 10.1371/journal.pone.0293266.

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 JURNAL MEDIA INFORMATIKA BUDIDARMA

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.



JURNAL MEDIA INFORMATIKA BUDIDARMA
STMIK Budi Darma
Secretariat: Sisingamangaraja No. 338 Telp 061-7875998
Email: mib.stmikbd@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.