Skripsi

KLASIFIKASI ABNORMALITAS STRUKTUR JANTUNG ANAK DAN VISUALISASI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN GUIDED BACKPROPAGATION

---

Penilaian

---

The application of artificial intelligence in these days is so much, it is beginning to enter a wide range of fields in the world, one of which is in the field of biomedicine. CNN uses several layers to help the classification process, especially the one on this study of the child's heart. The child's heart image will be processed into a previously created model that aims to recognize each class on each image, which will be subsequently grouped into four classes, namely atrial septal defect (ASD), atrioventricular septaldefect (AVSD), ventricultural septal Defect (VSD), and NORMAL. The models used are ResNet50, MobileNetV2, XceptionNet, and DenseNet121, where Xception achieved the best results at the validation and unseen test stages, with accuracy of 99% and 76%. After the classification process is completed, the next stage is the visualization process using Guided Backpropagation (Guided BP). Guided BP aims to clarify the parts on the child's heart image in order to mark any part that has the largest percentage in the process of classification. At this stage of visualization, the DenseNet121 model has a good result when compared to the other three models.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000860	T139284	T1392842024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1392842024

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya., 2024

Collation

xv, 83 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment