IMPLEMENTASI KLASIFIKASI PRA-KANKER SERVIKS MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS PLATFORM ANDROID

LUBIS, NUR MUHAMMAD ERJI RIDHO and Nurmaini, Siti (2023) IMPLEMENTASI KLASIFIKASI PRA-KANKER SERVIKS MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS PLATFORM ANDROID. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281924072.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281924072_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (998kB)
	Text RAMA_56201_09011281924072_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (148kB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (255kB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (136kB) | Request a copy
	Text RAMA_56201_09011281924072_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (756kB) | Request a copy

Abstract

Cervical cancer is the most common type of cancer in women worldwide. Early classification of pre-cancerous cervical cells is important to prevent the development of more serious cervical cancer. This study proposes the implementation of pre-cancer cervical classification using Convolutional Neural Network (CNN) based on the Android platform. The experimental results show that the CNN model can classify pre-cancerous cervical cells with good accuracy. The best model in the first experiment was obtained using the VGG 19 architecture with an accuracy of 95.50%, while in the second experiment, the best model was obtained using the Xception architecture with an accuracy of 98.98%. Each parameter in the experiment has different accuracy, thus, it is necessary to tune the hyperparameters to obtain maximum accuracy results. The resulting model usually has a large size, thus it needs to be placed inside a server and requires a web service to access the model. In addition, network bandwidth speed also affects the latency testing process. In implementation, the system can run well according to the design that has been made before. In terms of processing time or latency, a private server has better performance than VPS. In the prediction testing, the model built using Torch was faster than using Keras. The implementation of pre-cancer cervical classification using CNN on the Android platform can improve early detection of cervical cancer and speed up access to medical services for the public.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Impelementasi, CNN, Pra-Kanker Serviks, Klasifikasi, Android
Subjects:	Q Science > Q Science (General) > Q1-390 Science (General) > Q223.M517 Science -- Information services. Information storage and retrieval systems --Science. Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Nur Muhammad Erji Ridho Lubis
Date Deposited:	30 Mar 2023 02:26
Last Modified:	30 Mar 2023 02:29
URI:	http://repository.unsri.ac.id/id/eprint/91888

Actions (login required)

View Item