i
Klasifikasi Citra Kanker Kulit Menggunakan Metode Convolutional Neural Network dengan Arsitektur EfficientNet-B0
Laporan Tugas Akhir
Diajukan Untuk Memenuhi Persyaratan Guna Meraih Gelar Sarjana Informatika Universitas Muhammadiyah Malang
Ela Efriyanti (201810370311066)
Bidang Minat (Data Science)
PROGRAM STUDI INFORMATIKA FAKULTAS TEKNIK
UNIVERSITAS MUHAMMADIYAH MALANG 2022
ii
LEMBAR PERSETUJUAN
Klasifikasi Citra Kanker Kulit Menggunakan Metode Convolutional Neural Network dengan Arsitektur EfficientNet-B0
TUGAS AKHIR
Sebagai Persyaratan Guna Meraih Gelar Sarjana Strata 1 Informatika Universitas Muhammadiyah Malang
Menyetujui, Malang, 4 Juni 2022
Pembimbing I
Agus Eko Minarno, S.Kom., M.Kom.
NIP: 108.1410.0540
Pembimbing II
Yufis Azhar, S.Kom., M.Kom.
NIP: 108.1410.0544
iii
iv
v
KATA PENGANTAR
Dengan memanjatkan puji syukur kehadirat Allah SWT. Atas limpahan rahmat dan hidayah-Nya sehingga peneliti dapat menyelesaikan tugas akhir yang berjudul :
“KLASIFIKASI CITRA KANKER KULIT MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR
EFFICIENTNET-B0”
Didalam tulisan ini disajikan pokok-pokok bahasan yang meliputi Dataset HAM10000, Splitting data train dan data test, Preprocessing menggunakan Image Data Generator, Convolutional Neural Network menggunakan model pretrained EfficientNet-B0, Evaluasi Model, Skenario Pengujian dan Hasil perbandingan skenario model yang diusulkan dengan studi terdahulu.
Peneliti menyadari sepenuhnya bahwa dalam penulisan tugas akhir ini masih banyak kekurangan dan keterbatasan. Oleh karena itu peneliti mengharapkan saran yang membangun agar tulisan ini bermanfaat bagi perkembangan ilmu pengetahuan.
Malang, 4 Juni 2022
Penulis
vi DAFTAR ISI
HALAMAN JUDUL
LEMBAR PERSETUJUAN ...ii
LEMBAR PENGESAHAN ... iii
LEMBAR PERNYATAAN ... iv
KATA PENGANTAR ... v
DAFTAR ISI... vi
DAFTAR GAMBAR ... vii
DAFTAR TABEL ...viii
BAB I PENDAHULUAN ... 1
1.1. Latar Belakang ... 1
1.2. Rumusan Masalah ... 2
1.3. Tujuan Penelitian ... 3
1.4. Batasan Masalah ... 3
BAB II KAJIAN PUSTAKA ... 4
BAB III METODOLOGI PENELITIAN ... 7
3.1. Rancangan Penelitian ... 7
3.2. Dataset ... 7
3.3. Preprocessing ... 8
3.4. Convolutional Neural Network... 9
3.5. Evaluasi Model ... 10
3.6. Skenario Pengujian ... 11
3.7. Lini Masa Penelitian ... 15
BAB IV HASIL DAN PEMBAHASAN ... 16
4.1. Pengumpulan data ... 16
4.2. Pemrosesan Gambar ... 19
4.3. Pemodelan menggunakan Convolutional Neural Network ... 21
4.4. Perbandingan Setiap Skenario Pengujian ... 39
4.5. Perbandingan model arsitektur yang diusulkan dengan studi terdahulu... 44
BAB V KESIMPULAN ... 49
5.1. Kesimpulan ... 49
5.2. Saran ... 49
DAFTAR PUSTAKA ... 50
SCAN SERTIFIKAT PLAGIARISME...54
vii
DAFTAR GAMBAR
Gambar 1. Metodologi Penelitian. ... 6
Gambar 2. HAM10000 Dataset ... 7
Gambar 3. Arsitektur EfficientNet-B0 ... 9
Gambar 4. Visualisasi Data Setiap Kelas ... 16
Gambar 5. Dataset Tabular ... 16
Gambar 6. Ham10000 Images Part 1... 17
Gambar 7. Ham10000 Images Part 2... 17
Gambar 8. Confusion Matrix Skenario 1... 21
Gambar 9. Plot Categorical Accuracy Skenario 1 ... 22
Gambar 10. Plot Top-2 Accuracy Skenario 1... 23
Gambar 11. Plot Top-3 Accuracy Skenario 1... 23
Gambar 12. Plot Hasil Loss Skenario 1 ... 24
Gambar 13. Confusion Matrix Skenario 2... 25
Gambar 14. Plot Categorical Accuracy Skenario 2 ... 26
Gambar 15. Plot Top-2 Accuracy Skenario 2... 27
Gambar 16. Plot Top-3 Accuracy Skenario 2... 27
Gambar 17. Plot Validation Loss Skenario 2 ... 28
Gambar 18. Confusion Matrix Skenario 3 LR 0,001 ... 29
Gambar 19. Plot Categorical Accuracy Skenario 3 LR 0,001 ... 30
Gambar 20. Plot Top-2 Accuracy Skenario 3 LR 0,001 ... 30
Gambar 21. Plot Top-3 Accuracy Skenario 3 LR 0,001 ... 31
Gambar 22. Plot Hasil Loss Skenario 3 LR 0,001... 31
Gambar 23. Confusion Matrix Skenario 3 LR 0,1 ... 33
Gambar 24. Plot Categorical Accuracy Skenario 3 LR 0,1 ... 34
Gambar 25. Plot Top-2 Accuracy Skenario 3 LR 0,1 ... 35
Gambar 26. Plot Top-3 Accuracy Skenario 3 LR 0,1 ... 35
Gambar 27. Plot Hasil Loss Skenario 3 LR 0,1... 36
Gambar 28. Perbandingan Categorical Accuracy... 39
Gambar 29. Perbandingan Top-2 Accuracy ... 39
Gambar 30. Perbandingan top-3 accuracy ... 40
Gambar 31. Perbandingan Validation Loss ... 40
viii
DAFTAR TABEL
Tabel 1. Studi Terdahulu ... 5
Tabel 2. Parameter Image Data Generator ... 8
Tabel 3. Perbandingan performa setiap kelas dari skenario model yang diusulkan ... 10
Tabel 4. Perbandingan performa keseluruhan skenario model yang diusulkan .... 11
Tabel 5. Perbandingan performa setiap kelas dari studi terdahulu dan skenario yang diusulkan ... 12
Tabel 6. Perbandingan performa keseluruhan studi terdahulu dengan skenario yang diusulkan ... 13
Tabel 7. Lini Masa Penelitian ... 14
Tabel 8. Perbandingan Persentase Jumlah Gambar ... 15
Tabel 9. Splitting Data ... 18
Tabel 10. Augmentasi Data Train ... 19
Tabel 11. Jumlah Data Test Tanpa Augmentasi ... 19
Tabel 12. Parameter Train Flow dan Test Flow ... 19
Tabel 13. Classification Report Skenario 1 ... 22
Tabel 14. Classification Report Skenario 2 ... 26
Tabel 15. Classification Report Skenario 3 LR 0,001 ... 29
Tabel 16. Classification Report Skenario 3 LR 0,1 ... 34
Tabel 17. Hasil Perbandingan Skenario Pengujian ... 36
Tabel 18. Estimasi Waktu Training Skenario Pengujian... 37
Tabel 19. Perbandingan Model Usulan Dengan Model Pada Jurnal Referensi .... 41
Tabel 20. Perbandingan Classification Report Model Arsitektur Usulan dengan Jurnal Referensi ... 41
50
DAFTAR PUSTAKA
[1] P. S. Dampati and E. Veronica, “Potensi Ekstrak Bawang Hitam sebagai Tabir Surya terhadap Paparan Sinar Ultraviolet,” KELUWIH J. Kesehat. dan Kedokt., vol. 2, no. 1, pp. 23–31, 2020, doi: 10.24123/kesdok.v2i1.3020.
[2] S. S. Chaturvedi, K. Gupta, and P. S. Prasad, “Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using mobilenet,”
Adv. Intell. Syst. Comput., vol. 1141, pp. 165–176, 2021, doi: 10.1007/978- 981-15-3383-9_15.
[3] D. J. Restrepo et al., “Biopsy type disparities in patients with melanoma:
Who receives the standard of care?,” Anticancer Res., vol. 39, no. 11, pp.
6359–6363, 2019, doi: 10.21873/anticanres.13848.
[4] R. Garg, S. Maheshwari, and A. Shukla, “Decision Support System for Detection and Classification of Skin Cancer Using CNN,” Adv. Intell. Syst.
Comput., vol. 1189, pp. 578–586, 2021, doi: 10.1007/978-981-15-6067- 5_65.
[5] Y. N. Fu’adah, N. C. Pratiwi, M. A. Pramudito, and N. Ibrahim,
“Convolutional Neural Network (CNN) for Automatic Skin Cancer Classification System,” IOP Conf. Ser. Mater. Sci. Eng., vol. 982, no. 1, 2020, doi: 10.1088/1757-899X/982/1/012005.
[6] T. R. Savera, W. H. Suryawan, and A. W. Setiawan, “Deteksi Dini Kanker Kulit Menggunakan K-Nn Dan Early Detection of Skin Cancer Using K-Nn and Convolutional,” J. Teknol. Inf. Dan Ilmu Komput., vol. 7, no. 2, pp. 373–
378, 2020, doi: 10.25126/jtiik.202072602.
[7] J. Höhn et al., “Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification,” Eur. J. Cancer, vol.
149, pp. 94–101, 2021, doi: 10.1016/j.ejca.2021.02.032.
[8] S. A. Sanchez, H. J. Romero, and A. D. Morales, “A review: Comparison of performance metrics of pretrained models for object detection using the TensorFlow framework,” IOP Conf. Ser. Mater. Sci. Eng., vol. 844, no. 1, 2020, doi: 10.1088/1757-899X/844/1/012024.
[9] M. V. Valueva, N. N. Nagornov, P. A. Lyakhov, G. V. Valuev, and N. I.
51
Chervyakov, “Application of the residue number system to reduce hardware costs of the convolutional neural network implementation,” Math. Comput.
Simul., vol. 177, pp. 232–243, 2020, doi: 10.1016/j.matcom.2020.04.031.
[10] A. Peryanto, A. Yudhana, and R. Umar, “Klasifikasi Citra Menggunakan Convolutional Neural Network dan K Fold Cross Validation,” J. Appl.
Informatics Comput., vol. 4, no. 1, pp. 45–51, 2020, doi:
10.30871/jaic.v4i1.2017.
[11] S. Mohapatra, N. V. S. Abhishek, D. Bardhan, A. A. Ghosh, and S. Mohanty,
“Comparison of MobileNet and ResNet CNN Architectures in the CNN‐
Based Skin Cancer Classifier Model,” Mach. Learn. Healthc. Appl., pp. 169–
186, 2021, doi: 10.1002/9781119792611.ch11.
[12] R. H. Hridoy, F. Akter, M. Mahfuzullah, and F. Ferdowsy, “A Computer Vision Based Food Recognition Approach for Controlling Inflammation to Enhance Quality of Life of Psoriasis Patients,” 2021 Int. Conf. Inf. Technol.
ICIT 2021 - Proc., no. July, pp. 543–548, 2021, doi:
10.1109/ICIT52682.2021.9491783.
[13] S. R. Karanam, Y. Srinivas, and M. V. Krishna, “Study on image processing using deep learning techniques,” Mater. Today Proc., no. October, 2020, doi:
10.1016/j.matpr.2020.09.536.
[14] J. Carracedo-Cosme, C. Romero-Muñiz, and R. Pérez, “A deep learning approach for molecular classification based on afm images,” Nanomaterials, vol. 11, no. 7, pp. 1–22, 2021, doi: 10.3390/nano11071658.
[15] K. S. Vepuri, “Improving Facial Emotion Recognition with Image processing and Deep Learning,” no. April, 2021, doi:
10.6084/m9.figshare.14411096.
[16] S. RIZAL, N. IBRAHIM, N. K. C. PRATIWI, S. SAIDAH, and R. Y. N.
FU’ADAH, “Deep Learning untuk Klasifikasi Diabetic Retinopathy menggunakan Model EfficientNet,” ELKOMIKA J. Tek. Energi Elektr. Tek.
Telekomun. Tek. Elektron., vol. 8, no. 3, p. 693, 2020, doi:
10.26760/elkomika.v8i3.693.
[17] M. Umer, I. Ashraf, S. Ullah, A. Mehmood, and G. S. Choi, “COVINet: a convolutional neural network approach for predicting COVID-19 from chest
52
X-ray images,” J. Ambient Intell. Humaniz. Comput., no. 2020, 2021, doi:
10.1007/s12652-021-02917-3.
[18] A. S. Shete, A. Sanjay Rane, P. S. Gaikwad, and M. H. Patil, “Detection of Skin Cancer Using Cnn Algorithm,” vol. 6, no. 5, pp. 215–218, 2021.
[19] N. Makanapura, C. Sujatha, P. R. Patil, and P. Desai, “Classification of plant seedlings using deep convolutional neural network architectures,” J. Phys.
Conf. Ser., vol. 2161, no. 1, p. 012006, 2022, doi: 10.1088/1742- 6596/2161/1/012006.
[20] M. Yaqub et al., “State-of-the-art CNN optimizer for brain tumor segmentation in magnetic resonance images,” Brain Sci., vol. 10, no. 7, pp.
1–19, 2020, doi: 10.3390/brainsci10070427.
[21] I. Kandel and M. Castelli, “The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset,” ICT Express, vol. 6, no. 4, pp. 312–315, 2020, doi: 10.1016/j.icte.2020.04.010.
[22] M. Li, M. Soltanolkotabi, and S. Oymak, “Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks,” vol. 108, 2019, [Online]. Available:
http://arxiv.org/abs/1903.11680.
[23] T. H. Rafi and R. M. Shubair, “A scaled-2D CNN for skin cancer diagnosis,”
2021 IEEE Conf. Comput. Intell. Bioinforma. Comput. Biol. CIBCB 2021, 2021, doi: 10.1109/CIBCB49929.2021.9562888.
[24] W. R. Perdani, R. Magdalena, and N. O. R. K. Caecar, “dengan menggunakan Arsitektur EfficientNet Deep Learning untuk Klasifikasi Glaukoma,” vol. 10, no. 2, pp. 322–333, 2022.
[25] K. Ali, Z. A. Shaikh, A. A. Khan, and A. A. Laghari, “Multiclass skin cancer classification using EfficientNets – a first step towards preventing skin cancer,” Neurosci. Informatics, vol. 2, no. 4, p. 100034, 2022, doi:
10.1016/j.neuri.2021.100034.
[26] Suharjito, G. N. Elwirehardja, and J. S. Prayoga, “Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches,”
Comput. Electron. Agric., vol. 188, no. March, p. 106359, 2021, doi:
10.1016/j.compag.2021.106359.
53
[27] M. Louis, “20:21,” Can. J. Emerg. Med., vol. 15, no. 3, p. 190, 2013, doi:
10.2310/8000.2013.131108.
[28] J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-Excitation Networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 8, pp. 2011–
2023, 2020, doi: 10.1109/TPAMI.2019.2913372.
[29] D. Vijendra Babu, C. Karthikeyan, Shreya, and A. Kumar, “Performance analysis of cost and accuracy for whale swarm and RMSprop optimizer,”
IOP Conf. Ser. Mater. Sci. Eng., vol. 993, no. 1, 2020, doi: 10.1088/1757- 899X/993/1/012080.
[30] J. Yang and G. Yang, “Modified convolutional neural network based on dropout and the stochastic gradient descent optimizer,” Algorithms, vol. 11, no. 3, pp. 1–15, 2018, doi: 10.3390/a11030028.
[31] E. Yuliani, A. N. Aini, and C. U. Khasanah, “Perbandingan Jumlah Epoch Dan Steps Per Epoch Pada Convolutional Neural Network Untuk Meningkatkan Akurasi Dalam Klasifikasi Gambar,” J. Inf. J. Penelit. dan Pengabdi. Masy., vol. 5, no. 3, pp. 23–27, 2020, doi:
10.46808/informa.v5i3.140.
[32] J. Sanjaya and M. Ayub, “Augmentasi Data Pengenalan Citra Mobil Menggunakan Pendekatan Random Crop, Rotate, dan Mixup,” J. Tek.
Inform. dan Sist. Inf., vol. 6, no. 2, pp. 311–323, 2020, doi:
10.28932/jutisi.v6i2.2688.
54
SCAN SERTIFIKAT PLAGIARISME
