Privacy-based approach to brain MRI: Federated learning
Abstract
İÇİNDEKİLER BEYAN........................................................................................................................ ii TEŞEKKÜR ................................................................................................................ i İÇİNDEKİLER .......................................................................................................... ii KISALTMALAR ...................................................................................................... iv SİMGELER ............................................................................................................... vi TABLOLAR LİSTESİ............................................................................................viii ŞEKİLLER LİSTESİ................................................................................................ ix ÖZET........................................................................................................................... x ABSTRACT............................................................................................................... xi BÖLÜM 1. GİRİŞ .......................................................................................................................... 1 BÖLÜM 2. DERİN ÖĞRENME................................................................................................... 7 2.1. Derin Öğrenme .................................................................................................. 7 2.1.1. Evrişimli sinir ağları (CNN) .................................................................... 11 BÖLÜM 3. FEDERE ÖĞRENME ............................................................................................. 19 3.1. Şifreleme Yöntemleri ...................................................................................... 21 3.1.1. Homomorfik şifreleme............................................................................. 21 3.1.2. Diferansiyel gizlilik.................................................................................. 23 3.2. Haberleşme Mimarileri.................................................................................... 25 3.2.1. Merkezi haberleşme mimarisi.................................................................. 26 3.2.2. Merkezi olmayan haberleşme mimarisi ................................................... 27 3.2.3. Hibrit haberleşme mimarisi...................................................................... 29 3.3. İletişim Protokolü............................................................................................ 30 3.4. Federe Öğrenme Türleri.................................................................................. 31 iii 3.4.1. Yatay Federe öğrenme ............................................................................. 31 3.4.2. Dikey federe öğrenme.............................................................................. 33 3.4.3. Bölünmüş öğrenme .................................................................................. 35 3.5. Optimizasyon Algoritmaları............................................................................ 36 3.5.1. Federe ortalama alma ............................................................................... 36 3.5.2. QFedAvg.................................................................................................. 38 3.5.3. Hata toleranslı Federe ortalama ............................................................... 40 3.6. Veri Bölümleme .............................................................................................. 42 3.7. Sıkıştırma Metotları......................................................................................... 45 3.8. Federe Öğrenme Avantajları ........................................................................... 46 3.9. Federe Öğrenme Zorlukları............................................................................. 49 3.10. Federe Öğrenme Frameworkleri ................................................................... 53 3.10.1. Flower .................................................................................................... 53 BÖLÜM 4. DENEYSEL ÇALIŞMA .......................................................................................... 55 4.1. Veri Kümesi .................................................................................................... 55 4.2. İstemciler Arası Veri Paylaşımı ...................................................................... 57 4.3. Evrişimli Sinir Ağı’nın Oluşturulması ve Uygulanması ................................. 58 4.4. Eğitim.............................................................................................................. 63 4.5. Deneysel Sonuçlar........................................................................................... 68 4.5.1. FedAvg strajesine göre istemci ve sunucu modelleri gelişimi................. 71 4.5.2.
Keywords
Not available
Specialisations
Similar theses
- Federated Learning-Based Intrusion Detection System for Privacy-Preserving IoT Networks Prasanna Dhanireddy ; Khushboo Kumari · KTH Royal Institute of Technology · 2026
- Evaluating Federated Learning and Multimodal Data for Privacy-Aware Video-Based Fall Detection Dick Kuan ; Martin Dahrén · KTH Royal Institute of Technology · 2026
- Designing for Privacy in Tabular Federated Learning Ivo Osterberg Nilsson ; Maximilian Birr Engvall · Jönköping University · 2026
- Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning Chen, Haokun · Ludwig-Maximilians-Universität München · 2025
- Privacy-preserving federated learning: Strengthening data protection and secure collaboration in healthcare Bjarne Pfitzner · University of Potsdam · 2025
- Secure and Privacy-preserving Federated Learning with Explainable Artificial Intelligence for Smart Healthcare System Ali Raza · 2023
