Manifold-Based Machine Learning for Activity Detection in Grant-Free Massive MIMO Systems

Manifold-Based Machine Learning for Activity Detection in Grant-Free Massive MIMO Systems

A Master of Science thesis in Electrical Engineering by Omar ElSakka entitled, “Manifold-Based Machine Learning for Activity Detection in Grant-Free Massive MIMO Systems”, submitted in April 2026. Thesis advisor is Dr. Mahmoud H. Ismail. Soft copy is available (Thesis, Completion Certificate, Approv...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: ElSakka, Omar (author)
التنسيق: doctoralThesis
منشور في: 2026
الموضوعات:
Cell-free architecture
Grant-Free Random Access (GFRA)
Massive MIMO (mMIMO)
User Activity Detection (UAD)
Covariance-Based Detection
Sparse Bayesian Learning (SBL)
Riemannian Distances
Fisher Information Matrix (FIM)
K-Means
CatBoost
XGBoost
Akaike Information Criterion (AIC)
Minimum Description Length (MDL)
Machine Learning
5G Networks
الوصول للمادة أونلاين:https://hdl.handle.net/11073/33525
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

مواد مشابهة

مواد مشابهة