A Hybrid Deep Learning-Based (HYDRA) Framework for Multifault Diagnosis Using Sparse MDT Reports

A Hybrid Deep Learning-Based (HYDRA) Framework for Multifault Diagnosis Using Sparse MDT Reports

Diminishing viability of manual fault diagnosis in the increasingly complex emerging cellular network has motivated research towards artificial intelligence (AI)-based fault diagnosis using the minimization of drive test (MDT) reports. However, existing AI solutions in the literature remain limited...

Full description

Bibliographic Details
Main Authors: Abu-Dayya, A. (Author), Imran, A. (Author), Masood, U. (Author), Qureshi, H.N (Author), Riaz, M.S (Author), Rizwan, A. (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:
Base stations
cellular data sparsity
Cellular data sparsity
Cellular network
Cellular neural networks
Cellulars
Conformal mapping
Convolution
Convolutional neural network
data enrichment
Data enrichments
Data sparsity
Deep learning
Digital storage
Environment maps
Failure analysis
Fault detection
Faults diagnosis
hybrid deep learning
Hybrid deep learning
image inpainting
Image Inpainting
minimization of drive tests
Minimization of drive tests
multi-fault diagnosis
Multi-fault diagnosis
network automation
Network automations
Radio environment
Radio environment map
radio environment maps
Root cause analysis
self healing
Self organizing maps
Self-healing
Self-organizing feature map
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items