Klasifikasi Kanker Payudara Menggunakan Convolutional Neural Networks (CNN)

Rizqy, Aulia Azarine (2021) Klasifikasi Kanker Payudara Menggunakan Convolutional Neural Networks (CNN). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

	Text 01111640000072_ Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text 01111640000072_ Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text 01111640000072_Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text 01111640000072_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy

Abstract

Kanker adalah sekelompok besar penyakit yang dapat dimulai di hampir semua organ atau jaringan tubuh ketika sel abnormal tumbuh tak terkendali. Kasus kanker payudara lebih banyak terjadi di daerah berkembang dibandingkan dengan wilayah yang lebih maju. Tujuan dari penelitian ini adalah menggunakan Convolutional Neural Network (CNN) untuk mengklasifikasi kanker payudara. Data yang diolah sebannyak 198,738 IDC negative dan 78,786 IDC positive dengan ukuran piksel sebesar 5050 yang berasal dari Breast Histopathology Images. Pada tugas akhir ini, digunakan pengomptimal (optimizer) Adam, RMSprop dan SGD dengan learning rate (lr) bervariasi yaitu 0.001 dan 0.0001 serta epoch = 20. Hasil akurasi terbaik dicapai menggunakan optimasi SGD sebesar 76% dengan lr = 0.001. Sementara itu, dengan lr = 0.0001 didapatkan akurasi terbaik menggunakan optimasi RMSProp sebesar 67%.
================================================================================================
Cancer is a large group of diseases that can start in almost any organ or tissue of the body when abnormal cells grow uncontrollably. Breast cancer cases are more common in developing areas than in more developed areas. The purpose of this study was to use the Convolutional Neural Network (CNN) to classify breast cancer. The data processed were 198,738 IDC negative and 78,786 positive IDC with a pixel size of 5050 derived from Breast Histopathology Images. In this final project, Adam, RMSprop and SGD optimizers are used with varying learning rates (lr) of 0.001 and 0.0001 and epoch = 20. The best accuracy results are achieved using SGD optimization of 76% with lr = 0.001. Meanwhile, with lr = 0.0001, the best accuracy was obtained using RMSProp optimization of 67%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Adam, Breast Cancer, Learning Rate, RMSProp and SGD, Kanker Payudara
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QC Physics Q Science > QR Microbiology > QR 201.T84 Tumors. Cancer
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Physics > 45201-(S1) Undergraduate Thesis
Depositing User:	Aulia Azarine Rizqy
Date Deposited:	03 Sep 2021 03:25
Last Modified:	31 Mar 2022 05:42
URI:	http://repository.its.ac.id/id/eprint/87974

Actions (login required)

View Item