Non-linear 3D rendering workload prediction based on a combined fuzzy-neural network architecture for grid computing applications

Doulamis, N; Doulamis, A

dc.contributor.author	Doulamis, N	en
dc.contributor.author	Doulamis, A	en
dc.date.accessioned	2014-03-01T02:42:18Z
dc.date.available	2014-03-01T02:42:18Z
dc.date.issued	2003	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30923
dc.subject	Computational Complexity	en
dc.subject	Computational Grid	en
dc.subject	Fuzzy Classification	en
dc.subject	Fuzzy Neural Network	en
dc.subject	Grid Computing	en
dc.subject	Industrial Application	en
dc.subject	Large Scale	en
dc.subject	Prediction Accuracy	en
dc.subject	Quality of Service	en
dc.subject	Resource Allocation	en
dc.subject	Scientific Research	en
dc.subject	Input Output	en
dc.subject	Neural Network	en
dc.subject	Neural Network Model	en
dc.subject.other	Algorithms	en
dc.subject.other	Bandwidth	en
dc.subject.other	Computational complexity	en
dc.subject.other	Fuzzy control	en
dc.subject.other	Multimedia systems	en
dc.subject.other	Quality of service	en
dc.subject.other	Resource allocation	en
dc.subject.other	Semantics	en
dc.subject.other	Grid computing applications	en
dc.subject.other	Rendering workloads	en
dc.subject.other	Neural networks	en
dc.title	Non-linear 3D rendering workload prediction based on a combined fuzzy-neural network architecture for grid computing applications	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2003.1247433	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2003.1247433	en
heal.publicationDate	2003	en
heal.abstract	Although, computational Grid has been initially developed to solve large-scale scientific research problems, it is extended for commercial and industrial applications. An interesting commercial application with a wide impact on a variety of fields, is 3D rendering, In order to implement, however, 3D rendering to a grid infrastructure, we should develop appropriate scheduling and resource allocation mechanisms so that the negotiated Quality of Service (QoS) requirements are met. Efficient scheduling schemes require modeling and prediction of rendering workload. This is addressed in this paper, based on a combined fuzzy classification and neural network model. Initially, appropriate descriptors are extracted to represent the synthetic world. Fuzzy classification is used for organizing rendering descriptor so that a reliable representation is accomplished which increases the prediction accuracy. Neural network performs workload prediction by modeling the non-linear input-output relationship between rendering descriptors and the respective computational complexity. To increase the prediction accuracy, a constructive algorithm is adopted in this paper to train the neural network so that network weights and size are simultaneously estimated.	en
heal.journalName	IEEE International Conference on Image Processing	en
dc.identifier.doi	10.1109/ICIP.2003.1247433	en
dc.identifier.volume	3	en
dc.identifier.spage	1069	en
dc.identifier.epage	1072	en