Results 1  10
of
10
The graph neural network model
 IEEE Transactions on Neural Networks
, 2009
"... The graph neural network model Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural netw ..."
Abstract

Cited by 12 (4 self)
 Add to MetaCart
(Show Context)
The graph neural network model Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an mdimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.
Semantic Consistency Optimization in Heterogeneous Virtual Environments
, 2002
"... Collaborative virtual environments with heterogeneous computing resources and user preferences often reduce data fidelity to accommodate such heterogeneity. Given the resource limitations and user preferences, the problem is to optimize the fidelity degradation so as to achieve maximum semantic cons ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
Collaborative virtual environments with heterogeneous computing resources and user preferences often reduce data fidelity to accommodate such heterogeneity. Given the resource limitations and user preferences, the problem is to optimize the fidelity degradation so as to achieve maximum semantic consistency across the different data representations. Consistency maximization can be formulated as an integerprogramming problem, wherein constraints are resource limitations and user preferences. We consider several formulations of the problem, some of which do not enforce topological constraints in degraded representation, while others do. The solutions to this problem result in reduced amounts of distributed data which conserve network bandwidth and other system resources. Experimental results and proposed topics for further research are also presented.
Software framework for managing heterogeneity in mobile collaborative systems
 CSCW
, 2004
"... Abstract. Heterogeneity in mobile computing devices and application scenarios complicates the development of collaborative software systems. Heterogeneity includes disparate computing and communication capabilities, differences in users ’ needs and interests, and semantic conflicts across different ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Abstract. Heterogeneity in mobile computing devices and application scenarios complicates the development of collaborative software systems. Heterogeneity includes disparate computing and communication capabilities, differences in users ’ needs and interests, and semantic conflicts across different domains and representations. In this paper, we describe a software framework that supports mobile collaboration by managing several aspects of heterogeneity. Adopting graph as a common data structure for the application state representation enables us to develop a generic solution for handling the heterogeneities. The effect external forces, such as resource constraints and diverging user interests, can be quantified and controlled as relational and attribute heterogeneity of state graphs. When mapping the distributed replicas of the application state, the external forces inflict a loss of graph information, resulting in manytoone correspondences of graph elements. A key requirement for meaningful collaboration is maintaining a consistent shared state across the collaborating sites. Our framework makes the best of maximizing the state consistency, while accommodating the external force constraints, primarily the efficient use of scarce system resources. Furthermore, we describe the mobility aspects of our framework, mainly its extension to peertopeer scenarios and situations of intermittent connectivity. We describe an implementation of our framework applied to the interoperation of shared graphics editors across multiple platforms, where users are able to share 2D and 3D virtual environments represented as XML documents. We also present performance results, namely resource efficiency and latency, which demonstrate its feasibility for mobile scenarios. Key words: collaborative systems, consistency maintenance, content adaptation, mobile computing, scene simplification
LODManager: a framework for rendering multiresolution models in realtime applications
"... Many papers have addressed the problem of achieving real time visualization in interactive applications where millions of polygons are rendered and many objects are visualized. Multiresolution modeling has proven to be a good solution, as it diminishes the quantity of geometry to render. But this so ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Many papers have addressed the problem of achieving real time visualization in interactive applications where millions of polygons are rendered and many objects are visualized. Multiresolution modeling has proven to be a good solution, as it diminishes the quantity of geometry to render. But this solution is not widely used because it presents inefficient level of detail update routines that lower the overall performance. We are introducing a set of techniques to adapt the level of detail while meeting time constraints and maintaining image quality. In order to fulfil the requirements of current game engines, the LODManager considers exploiting graphics hardware and reuses as possible those levels of detail already calculated. Finally, we will show the integration of our LODManager in a game engine and we will prove the validity of our solution in an interactive application.
Software Framework for Managing Heterogeneity in Mobile Collaborative Systems
"... Heterogeneity aspects in mobile collaborative systems, such as differences in user’s interest, semantic conflicts across different domains and representations, and disparate device capabilities, cause difficulties in developing software applications. One of the key problems for collaborative applica ..."
Abstract
 Add to MetaCart
(Show Context)
Heterogeneity aspects in mobile collaborative systems, such as differences in user’s interest, semantic conflicts across different domains and representations, and disparate device capabilities, cause difficulties in developing software applications. One of the key problems for collaborative applications is maintaining a consistent shared state. In this paper, we describe a framework that manages several aspects of heterogeneity to maintain consistency across the collaborating sites. We assume graph data structure for application state representation. Our framework is based on structural and semantic mappings between graph structures. The mapping can be customized to meet different requirements through userdefined policies and rules. An important constraint is efficient use of scarce system resources. We describe several applications built using the framework to collaboratively share XML documents. The XML documents in our case are 2D/3D representations of virtual worlds. We also show the performance results of our framework which demonstrate its feasibility for mobile scenarios.
Exact and Heuristic Algorithms For Dynamic Tree Simplification
, 2004
"... The Tree Knapsack Problem (TKP) is a 01 integer programming problem where hierarchy constraints are enforced. If a node is selected for packing into the knapsack, all the ancestor nodes on the path from the root to the selected node are packed as well. One apparent application of this problem is th ..."
Abstract
 Add to MetaCart
(Show Context)
The Tree Knapsack Problem (TKP) is a 01 integer programming problem where hierarchy constraints are enforced. If a node is selected for packing into the knapsack, all the ancestor nodes on the path from the root to the selected node are packed as well. One apparent application of this problem is the simplification of computer graphics models. Real applications also use alternative representations of the nodes or whole subtrees, called impostors, to provide simplified trees that are visually acceptable. To account for this simplification, we introduce a generalized TKP, called Exclusive Multiple Choice Tree Knapsack Problem (EMCTKP). We present a dynamic programming algorithm to solve EMCTKP and a heuristic, called Lazy Iterative Arrangement, which reuses previous EMCTKP solutions to solve new instances of the problem. We show that this algorithm and heuristic reduce significantly the computation time of EMCTKP problems when changes in their parameters have spatial and temporal coherence. We also compare our algorithm with commercial integer programming solvers, and show that in our case the computation time grows linearly with the size of the problem tree and the available resources, while for generic IP solvers it is unpredictable an varies over a wide range of values.
1 Applying Predictive Level of Detail
"... The predictive hierarchical level of detail optimization algorithm of Mason and Blake is experimentally evaluated in the form of a practical application to hierarchical radiosity. In a novel approach the recursively subdivided patch hierarchy generated by a perceptually refined hierarchical radiosit ..."
Abstract
 Add to MetaCart
(Show Context)
The predictive hierarchical level of detail optimization algorithm of Mason and Blake is experimentally evaluated in the form of a practical application to hierarchical radiosity. In a novel approach the recursively subdivided patch hierarchy generated by a perceptually refined hierarchical radiosity algorithm is treated as a hierarchical level of detail scene description. In this way we use the MasonBlake algorithm to successfully maintain constant frame rates during the interactive rendering of the radiositygenerated scene. We establish that the algorithm is capable of maintaining uniform frame rendering times, but that the execution time of the optimization algorithm itself is significant and is strongly dependent on frametoframe coherence and the granularity of the level of detail description. To compensate we develop techniques which effectively reduce and limit the algorithm execution time: We restrict the execution times of the algorithm to guard against pathological situations and propose simplification transforms that increase the granularity of the scene description, at minimal cost to visual quality. We demonstrate that using these techniques the algorithm is capable of maintaining interactive frame rates for scenes of arbitrary complexity. Furthermore we provide guidelines for the appropriate use of predictive level of detail optimization algorithms derived from our practical experience.
Architecture for Semantic Consistency Optimization in Heterogeneous Virtual Environments
, 2003
"... Collaborative virtual environments with heterogeneous computing resources and user preferences often reduce data fidelity to accommodate such heterogeneity. Given the resource limitations and user preferences, the problem is to optimize the fidelity degradation so as to achieve maximum semantic c ..."
Abstract
 Add to MetaCart
Collaborative virtual environments with heterogeneous computing resources and user preferences often reduce data fidelity to accommodate such heterogeneity. Given the resource limitations and user preferences, the problem is to optimize the fidelity degradation so as to achieve maximum semantic consistency across the different data representations. Consistency maximization can be formulated as an integerprogramming problem, wherein constraints are resource limitations and user preferences. In this thesis, a mathematical model for semantic interoperation and semantic consistency optimization is presented. Several formulations of the optimization problem are considered, some of which do not enforce topological constraints in degraded representation, while others do. The solutions to this problem result in reduced amounts of distributed data which conserve network bandwidth and other system resources.
A Simplification Architecture for Exploring Navigation Tradeoffs in Mobile VR
, 2004
"... Interactive applications on mobile devices often reduce data fidelity to adapt to resource constraints and variable user preferences. In virtual reality applications, the problem of reducing scene graph fidelity can be stated as a combinatorial optimization problem, where a part of the scene graph w ..."
Abstract
 Add to MetaCart
Interactive applications on mobile devices often reduce data fidelity to adapt to resource constraints and variable user preferences. In virtual reality applications, the problem of reducing scene graph fidelity can be stated as a combinatorial optimization problem, where a part of the scene graph with maximum fidelity is chosen such that the resources it requires are below a given threshold and the hierarchical relationships are maintained. The problem can be formulated as a variation of the Tree Knapsack Problem, which is known to be NPhard. For this reason, solutions to this problem result in a tradeoff that affects user navigation. On one hand, exact solutions provide the highest fidelity but may take long time to compute. On the other hand, greedy solutions are fast but lack high fidelity. We present a simplification architecture that allows the exploration of such navigation tradeoffs. This is achieved by a formulating the problem in a generic way and developing software components that allow the dynamic selection of algorithms and constraints. The experimental results show that the architecture is flexible and supports dynamic reconfiguration.
Research Article Hierarchical Level of Detail Optimization for Constant Frame Rate Rendering of Radiosity Scenes
"... The predictive hierarchical level of detail optimization algorithm of Mason and Blake is experimentally evaluated in the form of a practical application to hierarchical radiosity. In a novel approach the recursively subdivided patch hierarchy generated by a perceptually refined hierarchical radiosit ..."
Abstract
 Add to MetaCart
(Show Context)
The predictive hierarchical level of detail optimization algorithm of Mason and Blake is experimentally evaluated in the form of a practical application to hierarchical radiosity. In a novel approach the recursively subdivided patch hierarchy generated by a perceptually refined hierarchical radiosity algorithm is treated as a hierarchical level of detail scene description. In this way we use the MasonBlake algorithm to successfully maintain constant frame rates during the interactive rendering of the radiositygenerated scene. We establish that the algorithm is capable of maintaining uniform frame rendering times, but that the execution time of the optimization algorithm itself is significant and is strongly dependent on frametoframe coherence and the granularity of the level of detail description. To compensate we develop techniques which effectively reduce and limit the algorithm execution time: We restrict the execution times of the algorithm to guard against pathological situations and propose simplification transforms that increase the granularity of the scene description, at minimal cost to visual quality. We demonstrate that using these techniques the algorithm is capable of maintaining interactive frame rates for scenes of arbitrary complexity. Furthermore we provide guidelines for the appropriate use of predictive level of detail optimization algorithms derived from our practical experience.