Demans EEG Sinyallerinin Görgül Kip Ayrışımı Yöntemi Türleri ile Analizi
Loading...

Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Alzheimer Demansı (AD), insan beynindeki elektriksel aktivite değişikliklerinin neden olduğu son yıllarda en sık görülen nörolojik bozukluktur. Elektroensefalogram (EEG) gibi tıbbi cihazlar kullanılarak demans hastalığının tanısı konulabilir. Bu çalışmada, AD hastalarının ve sağlıklı control bireylerinin EEG sinyalleri analiz edilmiştir. Görgül Kip Ayrışım (GKA) yöntemi ile özgül kip fonksiyonları (ÖKF) elde edilmiştir. Özgül Kip Fonksiyonlarından ve EEG sinyalin kendisinden spectral ve zamansal özellikler çıkartılmıştır. Daha sonra bu özellikler ile topografik ısı haritaları oluşturulmuştur. Topografik ısı haritaları, iki boyutlu Evrişimsel Sinir Ağı (2D-CNN) kullanılarak sınıflandırılmıştır. Farklı CNN mimarileri kullanılmıştır. EfficientNet-b0 mimarisi ile %95.98 sınıflandırma doğruluğuna ulaşılmıştır.
In recent years, Alzheimer dementia (AD) is the most frequent neurological disorder caused by electrical activity changes in the human brain. The diagnosis of AD can be provided by using medical devices such as electroencephalography (EEG). In this study, EEG signals of AD patients and healthy control subjects were analyzed. Intrinsic mode functions (IMFs) were obtained using empirical mode decomposition (EMD) method. Spectral and time-domain features were extracted from IMFs and EEG signal itself. Then topographical heat maps were generated from these features. Topographic heat maps were classified using a two-dimensional convolutional neural network (2D CNN). Different CNN architectures were used. 95.98% classification accuracy was achieved with the EfficienNet-b0 architecture.
In recent years, Alzheimer dementia (AD) is the most frequent neurological disorder caused by electrical activity changes in the human brain. The diagnosis of AD can be provided by using medical devices such as electroencephalography (EEG). In this study, EEG signals of AD patients and healthy control subjects were analyzed. Intrinsic mode functions (IMFs) were obtained using empirical mode decomposition (EMD) method. Spectral and time-domain features were extracted from IMFs and EEG signal itself. Then topographical heat maps were generated from these features. Topographic heat maps were classified using a two-dimensional convolutional neural network (2D CNN). Different CNN architectures were used. 95.98% classification accuracy was achieved with the EfficienNet-b0 architecture.
Description
Keywords
Elektrik Ve Elektronik Mühendisliği, Electrical And Electronics Engineering
Turkish CoHE Thesis Center URL
Fields of Science
Citation
WoS Q
Scopus Q
Source
Volume
Issue
Start Page
End Page
62
