Current Search:   Gonzalez, Avelino J. (x)

View All Items

  • CSV Spreadsheet
(1 - 3 of 3)
Semantic correlation of behavior for the interoperability of heterogeneous simulations
Title
Semantic correlation of behavior for the interoperability of heterogeneous simulations.
Creator
Dean, Christopher James, Gonzalez, Avelino J., Engineering
Abstract / Description
University of Central Florida College of Engineering Thesis; A desirable goal of military simulation training is to provide large scale or joint exercises to train personnel at higher echelons. To help meet this goal, many of the lower echelon combatants must consist of computer generated forces with some of these echelons composed of units from different simulations. The object of the research described is to correlate the behaviors of entities in different simulations so that they can...
Show moreUniversity of Central Florida College of Engineering Thesis; A desirable goal of military simulation training is to provide large scale or joint exercises to train personnel at higher echelons. To help meet this goal, many of the lower echelon combatants must consist of computer generated forces with some of these echelons composed of units from different simulations. The object of the research described is to correlate the behaviors of entities in different simulations so that they can interoperate with one another to support simulation training. Specific source behaviors can be translated to a form in terms of general behaviors which can then be correlated to any desired specific destination simulation behavior without prior knowledge of the pairing. The correlation, however, does not result in 100% effectiveness because most simulations have different semantics and were designed for different training needs. An ontology of general behaviors and behavior parameters, a database of source behaviors written in terms of these general behaviors with a database of destination behaviors. This comparison is based upon the similarity of sub-behaviors and the behavior parameters. Source behaviors/parameters may be deemed similar based upon their sub-behaviors or sub-parameters and their relationship (more specific or more general) to destination behaviors/parameters. As an additional constraint for correlation, a conversion path from all required destination parameters to a souce parameter must be found in order for the behavior to be correlated and thus executed. The length of this conversion path often determines the similarity for behavior parameters, both source and destination. This research has shown, through a set of experiments, that heuristic metrics, in conjunction with a corresponding behavior and parameter ontology, are sufficient for the correlation of heterogeneous simulation behavior. These metrics successfully correlated known pairings provided by experts and provided reasonable correlations for behaviors that have no corresponding destination behavior. For different simulations, these metrics serve as a foundation for more complex methods of behavior correlation.
Show less
Date Issued
1996
Identifier
CFR0008169, ucf:53071
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFR0008169
An efficient method for representing and computing transitive closure over temporal relations
Title
An efficient method for representing and computing transitive closure over temporal relations.
Creator
Kovarik, Vincent J., Gonzalez, Avelino, Engineering
Abstract / Description
University of Central Florida College of Engineering Thesis; The need for temporal reasoning is found throughout the engineering disciplines. James Allen introduced a representation for temporal reasoning based upon the concept of intervals. This approach provides a rich set of temporal relations for reasoning over events and changes in state. The full temporal algebra is NP-complete however. The algorithm developed by Allen executes in 0(n3) time but only ensures consistency between any...
Show moreUniversity of Central Florida College of Engineering Thesis; The need for temporal reasoning is found throughout the engineering disciplines. James Allen introduced a representation for temporal reasoning based upon the concept of intervals. This approach provides a rich set of temporal relations for reasoning over events and changes in state. The full temporal algebra is NP-complete however. The algorithm developed by Allen executes in 0(n3) time but only ensures consistency between any three intervals. This research presents an approach to representing interval relations as a bit-encoded form which captures the relationships between the end-points of the intervals. A bit-algebra is then defined which provides an algorithmic method for computing transitive relations without requiring the table lookup of Allen's algorithm. By reducing the set of ambiguous interval representations to the set of relationships which have unknown temporal extent, a robust subset of the full algebra is defined which maintains the direct computation of transitive relationships.
Show less
Date Issued
1994
Identifier
CFR0001859, ucf:52919
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFR0001859
EVOLVING MODELS FROM OBSERVED HUMAN PERFORMANCE
Title
EVOLVING MODELS FROM OBSERVED HUMAN PERFORMANCE.
Creator
Fernlund, Hans Karl Gustav, Gonzalez, Avelino J., University of Central Florida
Abstract / Description
To create a realistic environment, many simulations require simulated agents with human behavior patterns. Manually creating such agents with realistic behavior is often a tedious and time-consuming task. This dissertation describes a new approach that automatically builds human behavior models for simulated agents by observing human performance. The research described in this dissertation synergistically combines Context-Based Reasoning, a paradigm especially developed to model tactical...
Show moreTo create a realistic environment, many simulations require simulated agents with human behavior patterns. Manually creating such agents with realistic behavior is often a tedious and time-consuming task. This dissertation describes a new approach that automatically builds human behavior models for simulated agents by observing human performance. The research described in this dissertation synergistically combines Context-Based Reasoning, a paradigm especially developed to model tactical human performance within simulated agents, with Genetic Programming, a machine learning algorithm to construct the behavior knowledge in accordance to the paradigm. This synergistic combination of well-documented AI methodologies has resulted in a new algorithm that effectively and automatically builds simulated agents with human behavior. This algorithm was tested extensively with five different simulated agents created by observing the performance of five humans driving an automobile simulator. The agents show not only the ability/capability to automatically learn and generalize the behavior of the human observed, but they also capture some of the personal behavior patterns observed among the five humans. Furthermore, the agents exhibited a performance that was at least as good as agents developed manually by a knowledgeable engineer.
Show less
Date Issued
2004
Identifier
CFE0000013, ucf:46068
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0000013