Image of PENGOLAHAN CITRA TRANSCEREBELLAR PADA KEPALA JANIN DARI CITRA ULTRASONOGRAFI 2 DIMENSI MENGGUNAKAN ARSITEKTUR U-NET DAN YOLO V3

Skripsi

PENGOLAHAN CITRA TRANSCEREBELLAR PADA KEPALA JANIN DARI CITRA ULTRASONOGRAFI 2 DIMENSI MENGGUNAKAN ARSITEKTUR U-NET DAN YOLO V3

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Ultrasonography (USG) is an electronic technology that uses sound waves with high frequencies above 20,000 hertz to produce images of the structure of organs in the body. Ultrasound is usually used by doctors to detect the contents of pregnant women. However, the inspection process takes a long time and requires special expertise. This is a challenge, especially to detect objects that are inside the fetal head. This study uses a Convolutional Neural Network (CNN) based deep learning method to detect fetal head objects in 2D ultrasound images with transcerebellar parameters. The purpose of this study was to compare the sensor accuracy results from a 2D ultrasound image model test of the fetal head using the YOLOv3 architecture with the results from previous studies using the Faster-RCNN architecture. This research will perform segmentation with U-Net and proceed with the object detection process using YOLOv3. Of the 20 models that have been trained and tested using unseen data, the best model is the one that produces the test model with the highest value, namely model 3 which can produce a mAP value of 95.7% and an F1-Score of 95%. Meanwhile, the model evaluation results obtained a mAP value of 86.6% and an F1-Score of 90%. It was concluded that the YOLOv3 architecture has better accuracy results compared to the Faster-RCNN architecture, with a mAP value of 95.7% for YOLOv3 compared to a Faster-RCNN mAP value of 87.3%.

Availability
Inventory Code Barcode Call Number Location Status
2307004848T126269T1262692023Central Library (Referens)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1262692023
Publisher
Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xixx, 140 hlm.; Ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
004.650 7
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Jurusan Sistem Komputer
Jaringan Komunikasi Komputer
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment