Image of PREDIKSI POLYCYSTIC OVARY SYNDROME (PCOS) PADA CITRA ULTRASONOGRAFI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN)

Skripsi

PREDIKSI POLYCYSTIC OVARY SYNDROME (PCOS) PADA CITRA ULTRASONOGRAFI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Polycystic Ovary Syndrome (PCOS) is a common endocrine system disorder affecting women of reproductive age and a leading cause of infertility. Early detection is crucial to prevent long-term complications, and ovarian ultrasonography images have emerged as an effective non-invasive tool in supporting PCOS diagnosis. This study aims to compare and optimize the performance of Convolutional Neural Network (CNN) models in classifying ovarian ultrasonography images for PCOS prediction. Three CNN architectures (DenseNet201, VGG19, and InceptionV3) were tested with various configurations, involving two types of optimizers (Adam and SGD) and four learning rate values (0.01, 0.001, 0.0001, and 0.00001). The results demonstrate that the optimal configuration is the InceptionV3 architecture with the Adam optimizer and a learning rate of 0.001, achieving the highest accuracy and F1-score of 99.78%. The Adam optimizer proved superior to SGD, and the precise determination of the learning rate was crucial in achieving peak model performance. These findings indicate that the selection of architecture, optimizer, and learning rate are key factors determining the success of PCOS prediction in ultrasonography images.

Availability
Inventory Code Barcode Call Number Location Status
2507004302T179577T1795772025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1795772025
Publisher
Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xvi, 125 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
004.07
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Teknik Informatika
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