DETEKSI TUMOR OTAK PADA CITRA DIGITAL MRI MENGGUNAKAN METODE FASTER REGION-BASED CONVOLUTIONAL NEURAL NETWORK

HANIF, AHMAD and Fachrurrozi, M. (2024) DETEKSI TUMOR OTAK PADA CITRA DIGITAL MRI MENGGUNAKAN METODE FASTER REGION-BASED CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Universitas Sriwijaya.

	Text RAMA_55201_09021282025073.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282025073_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282025073_0222058001_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (445kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (380kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (607kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (714kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (186kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (132kB) | Request a copy
	Text RAMA_55201_09021282025073_0222058001_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (176kB) | Request a copy

Abstract

This research evaluates the performance of several Faster R-CNN models with different hyperparameter configurations for brain tumor detection tasks. Evaluation results show that Model with a learning rate of 0.01, batch size of 4, Resnet50 backbone, and a dataset ratio of 80:20, achieved the best results. This model achieved mAP at IoU thresholds of 0.3, 0.4, and 0.5 of 0.9503, 0.9377, and 0.8992, respectively. This configuration proved to provide an optimal balance between learning speed, model stability, and sufficient data for training and evaluation. Recommendations for further research include experimenting with other hyperparameters, using more modern backbones, and deeper validation to enhance model performance.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Faster R-CNN, Deep learning, Hyperparameter, Resnet50, Deteksi tumor otak
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885-7895 Computer engineering. Computer hardware
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Ahmad Hanif
Date Deposited:	05 Aug 2024 06:53
Last Modified:	05 Aug 2024 06:53
URI:	http://repository.unsri.ac.id/id/eprint/154153

Actions (login required)

View Item