Browsing by Author "Saydam, Tuncay"

Now showing 1 - 3 of 3

Citation Count: 1
An open software architecture of neural networks: Neurosoft
(2004) Arsan, Taner; Arsan, Taner; Saydam, Tuncay
Software architecture of generic distributed neural networks and its relevant information model have been developed. Principles of on-line architecture building training controlling (managing) and topological optimization guidelines are provided and extensively discussed.
Citation Count: 0
A Software Component Architecture for Adaptive and Predictive Rate Control of Video Streaming
(Springer, 2008) Arsan, Taner; Saydam, Tuncay
Quality of Service and Transmission Rate Optimization in live and on-demand video streaming is a very important issue in lossy IP networks. Infrastructure of the Internet exhibits variable bandwidths delays congestions and time-varying packet losses. Because of such attributes video streaming applications should not only have good end-to-end transport layer performance but also a robust rate control optimization mechanisms. This paper gives an overview of video streaming applications and proposal of a new software architecture that controls transport QoS and path and bandwidth estimation. Predictive Control is one of the best solutions for difficult problems in control engineering applications that can be used in Internet environment. Therefore we provide an end-to-end software architecture between the video requesting clients their destination servers distant streaming servers and video broadcasters. This architecture contains an important Streaming Server Component with Application Layer QoS Manager and Transport Layer Path and Bandwidth Estimator. QoS Manager considers the necessary parameters such as network delay packet loss distortions round trip time channel errors network discontinuity and session dropping probability to make video streaming more efficient and to provide required video quality. Transport Path and Bandwidth Estimator on the other hand provides transmission rates to Destination Servers for optimum video streaming. The paper provides and discusses a software component model of video streaming.
Citation Count: 0
A systems software architecture for training neural fuzzy neural and genetic computational intelligent networks
(IEEE, 2006) Arsan, Taner; Öğrenci, Arif Selçuk; Saydam, Tuncay
A systems software architecture for training distributed neural fuzzy neural and genetic networks and their relevant information models have been developed. Principles of on-line architecture building training managing and optimization guidelines are provided and extensively discussed. Qualitative comparisons of neural training strategies have been provided.