Image of KLASIFIKASI PENYAKIT STROKE DENGAN CONVOLUTIONAL NEURAL NETWORK (CNN) DAN METODE EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI)
Bookmark Share

Skripsi

KLASIFIKASI PENYAKIT STROKE DENGAN CONVOLUTIONAL NEURAL NETWORK (CNN) DAN METODE EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI)

Stroke is a disease in which the sufferer experiences bleeding or blockage of the brain arteries. The focus of this research is the use of Convolutional Neural Network (CNN) method in stroke disease classification and Explainable Artificial Intelligence (XAI) method as an approach to understand more deeply the decision-making process used by the CNN model. There are 3 models used by OzNet, ResNet50V2 and EfficientNetV2, This classification uses the dataset "Brain Stroke CT Image Dataset" obtained from Kaggle. This dataset contains 2501 images of brain CT scans categorized as "Normal" and "Stroke". The classifier obtained a testing accuracy of 97% for the OzNet model, 98% for the ResNet50V2 model and 97% for the EfficientNetV2 model. For the XAI approach, the heatmap showed more specific results for the ResNet50V2 model.

Availability
#
Central Library (REFERENCES) T1445062024
T144506
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1445062024
Publisher
Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer.,
Collation
xv, VI-1 hlm.; ilus.; tab.; 28 cm
Language
Indonesia
ISBN/ISSN
-
Classification
618.810 7
Content Type
Text
Media Type
unmediated
Carrier Type
unspecified
Edition
-
Subject(s)
Prodi Teknik Informatika
Convolutional Neural Network (CNN)
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment