Source Separation Approach to Video Quality Prediction in Computer Networks

Source Separation Approach to Video Quality Prediction in Computer Networks

Time-varying loads introduce errors in the estimated model parameters of service-level predictors in computer networks. A load-adjusted modification of a traditional unadjusted service-level predictor is contributed, based on source separation. It mitigates these errors and improves the service-qual...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE communications letters 2016-07, Vol.20 (7), p.1333-1336
1. Verfasser: de Frein, Ruairi
Format: Artikel
Sprache:eng
Schlagworte:
Computational modeling
Computer networks
Discrete Fourier transforms
Errors
Kernel
Load modeling
Mathematical models
Measurement
Prediction Methods
Separation
Servers
Source separation
Video on demand
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Time-varying loads introduce errors in the estimated model parameters of service-level predictors in computer networks. A load-adjusted modification of a traditional unadjusted service-level predictor is contributed, based on source separation. It mitigates these errors and improves the service-quality predictions for video-on-demand by ≈ 0.6 -2 dB.
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2016.2563418