Dynamic neural-based buffer management for queuing systems with self-similar characteristics

H Yousefi'zadeh, EA Jonckheere - IEEE Transactions on …, 2005 - ieeexplore.ieee.org
Buffer management in queuing systems plays an important role in addressing the tradeoff
between efficiency measured in terms of overall packet loss and fairness measured in terms …

Utilizing neural networks to reduce packet loss in self-similar teletraffic patterns

H Yousefi'Zadeh, EA Jonckheere… - … , 2003. ICC'03., 2003 - ieeexplore.ieee.org
Reducing packet loss and increasing overall efficiency in multiple source queuing systems
is one of the most important issues in the design of traffic control algorithms. On the other …

P2P-4-DL: digital library over peer-to-peer

J Walkerdine, P Rayson - … on Peer-to-Peer Computing, 2004 …, 2004 - ieeexplore.ieee.org
The P2P-4-DL project aims to investigate and build a DL system that would operate over a
P2P structure. Rather than storing digital objects centrally they remain the responsibility of …

[PDF][PDF] Neural network modeling of a class of ON-OFF source models with self-similar characteristics

H Yousefi'zadeh - Proc. of the First Workshop on Fractals and Self …, 2002 - academia.edu
The significant characteristic of bursty traf-fic is self-similarity. Self-similarity is the main
reason for observing the burst within burst patterns across a wide range of time scales. This …

Classification of surveillance video objects using chaotic series

H Azhar, A Amer - IET image processing, 2012 - IET
The authors propose a framework for binary classification of challenging objects (eg
incomplete, partial occluded, background over-lapped, scaled, outdoor) in surveillance …

[PDF][PDF] Neural network modeling of self-similar teletraffic patterns

H Yousefi'zadeh - Invited Paper, In Proceedings of the First Workshop on …, 2002 - Citeseer
The significant characteristic of bursty traffic is self-similarity. Self-similarity is the main
reason for observing socalled burst within burst patterns across a wide range of time scales …

MAROQ: a resource allocation model driven through quality of experience

A D'Amato, M Dantas… - International Journal of …, 2017 - inderscienceonline.com
The trend of grid computing available on the internet has generated challenges to the
allocation of resources provided by this type of environment. Many of these challenges can …

[PDF][PDF] Dynamic Neural-Based Buffer Management for Queuing Systems with Self-Similar Characteristics

HYEA Jonckheere - ece.uci.edu
Buffer management in queuing systems plays an im-portant role in addressing the tradeoff
between efficiency measured in terms of overall packet loss and fairness measured in terms …

[PDF][PDF] Neural Network Estimation of Packet Arrival Rate in Self-Similar Queuing Systems

H Yousefi'zadeh - Invited Paper.[in:] Proceedings of the Second …, 2003 - ece.uci.edu
Estimating average latency of queuing systems is one of the most challenging tasks in the
analysis and design of traffic control algorithms. In this paper a new approach for predicting …

Research of chaos theory and local support vector machine in effective prediction of VBR MPEG video traffic

HC Li, W Hong, YR Wu, SJ Xu - … , ICIC 2006, Kunming, China, August 16 …, 2006 - Springer
The highly bursty and time-variant characteristics of VBR MPEG video traffic make it more
difficult to manage network resources, and lead to the significant reduction of network …