In this paper we discuss ongoing efforts at Scientific Systems towards the development of e$ective strategies for traf ic management of ATM networks using SelfLearning Adaptive (SLA) techniques. We extended our previous SLA techniques to bursty trafic patterns and show how an approximation to SLA, called proportional feedback, can be used to manage real-time variable bit rate ATM trafic. Finall...

[n this paper we study an adaptive measurement-based admission control scheme that is suitable for multimedia applications with diversified QoS requirements. The conservativeness of the proposed admission control scheme is selfadjusted based on the measured QoS pe~ormance of the existing multimedia jlows. Extensive simulations performed on actual multimedia trafic with di~erent combinations of ...

Résumé. Nous rendons compte d'une démarche mise en place pour construire une représentation fine des usages d'internet et de leur évolution, en procédant à du traitement secondaire de données de trafic, provenant de panels représentatifs d'internautes. Après avoir présenté les caractéristiques des cohortes étudiées et les différents modes d'enrichissement des données de trafic mis en place, nou...

This diploma thesis investigates integrated tracking and recognition in continuous sign language recogntion as well as efficient approximations to it. Current state-of-the art sign language recognition system use tracking only as a preprocessing step. Hence, tracking errors lead to recognition errors. We propose to integrate scoring functions of a model-free dynamic programming tracking framewo...

The SignSpeak project will be the first step to approach sign language recognition and translation at levels already obtained in similar technologies such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can co...

An automatic road sign recognition system locates road sign of interest within images captured by an imaging sensor on-board of a vehicle, and then identifies road signs assisting the driver of the vehicle to properly operate the vehicle. This paper presents a real-time road sign recognition system that can be used to improve road safety. The developed system is capable of analysing live road s...

The SignSpeak project will be the first step to approach sign language recognition and translation at levels already obtained in similar technologies such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can co...