NASA Scientific and Technical Aerospace Reports
NASA Scientific and Technical Aerospace Reports
NASA Scientific and Technical Aerospace Reports
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
near-optimal strategy with DBN serving as a fitness evaluator. The probability of achieving the desired effects (namely, the<br />
probability of success) at a specified terminal time is a r<strong>and</strong>om variable due to uncertainties in the environment. Consequently,<br />
the authors focus on signal-to-noise ratio (SNR), a measure of mean <strong>and</strong> variance of the probability of success, to gauge the<br />
goodness of a strategy. The resulting strategy will not only have a relatively high probability of inducing the desired effects,<br />
but also be robust to environmental uncertainties.<br />
DTIC<br />
Bayes Theorem; Mathematical Models; Optimization; Organizations<br />
20060001859 Connecticut Univ., Storrs, CT USA<br />
Goal Management in Organizations: A Markov Decision Process (MDP) Approach<br />
Meirina, C<strong>and</strong>ra; Levchuk, Yuri N.; Levchuk, Georgiy M.; Pattipati, Krishna R.; Kleinman, David L.; Jan. 1, 2005; 25 pp.;<br />
In English; Original contains color illustrations<br />
Contract(s)/Grant(s): N00014-00-1-0101<br />
Report No.(s): AD-A440393; No Copyright; Avail.: Defense <strong>Technical</strong> Information Center (DTIC)<br />
Goal management is the process of recognizing or inferring goals of individual team members; ab<strong>and</strong>oning goals that are<br />
no longer relevant; identifying <strong>and</strong> resolving conflicts among goals; <strong>and</strong> prioritizing goals consistently for optimal team<br />
collaboration <strong>and</strong> effective operations. A Markov decision process (MDP) approach is employed to maximize the probability<br />
of achieving the primary goals (a subset of all goals). The authors seek to address the computational adequacy of an MDP as<br />
a planning model by introducing novel problem domain-specific heuristic evaluation functions (HEF) to aid the search<br />
process. They employ the optimal AO* search <strong>and</strong> two suboptimal greedy search algorithms to solve the MDP problem. A<br />
comparison of these algorithms to the dynamic programming algorithm shows that computational complexity can be reduced<br />
substantially. In addition, they recognize that embedded in the MDP solution there are a number of different action sequences<br />
by which a team’s goals can be realized. That is, in achieving the aforementioned optimality criterion, they identify alternate<br />
sequences for accomplishing the primary goals.<br />
DTIC<br />
Decision Making; Heuristic Methods; Markov Processes; Military Operations; Optimization; Planning<br />
20060001895 North Dakota Univ., Gr<strong>and</strong> Forks, ND USA<br />
Characteristics, Nonlinearity of Statistical Control <strong>and</strong> Relations with Dynamic Game Theory<br />
Won, Chang-Hee; Nov. 7, 2005; 6 pp.; In English<br />
Contract(s)/Grant(s): W911NF-05-1-0212<br />
Report No.(s): AD-A440472; ARO-47574.3-CI-II; No Copyright; Avail.: CASI: A02, Hardcopy<br />
The PI was awarded a short-term innovative research grant through the University of North Dakota. The grant period was<br />
15 April 2005 to 14 January 2006. However, during the grant period the PI transferred to Temple University in August 2005.<br />
So, the PI is submitting the final progress report with the results that the PI obtained during 15 April 2005 to 31 August 2005.<br />
The main objective of this proposal was to develop statistical control theory. Statistical control is a generalization of Kalman’s<br />
linear-quadratic-Gaussian control, where one optimizes the probability density of the performance index by controlling the<br />
cumulants. A statistical controller will have better performance <strong>and</strong> stability margin than the linear-quadratic-Gaussian<br />
controller. In this project, the authors investigated the characteristics of linear statistical controllers, developed nonlinear<br />
statistical control theory, <strong>and</strong> utilized the statistical control paradigm in dynamic game theory.<br />
DTIC<br />
Dynamic Programming; Game Theory; Nonlinear Systems; Nonlinearity; Optimization<br />
20060001896 North Carolina State Univ., Raleigh, NC USA<br />
Active Contours for Multispectral Images With Non-Homogeneous Sub-Regions<br />
Snyder, Wesley E.; Sep. 16, 2005; 114 pp.; In English<br />
Contract(s)/Grant(s): W911NF-04-1-0432<br />
Report No.(s): AD-A440479; ARO-47072.1-C1; No Copyright; Avail.: Defense <strong>Technical</strong> Information Center (DTIC)<br />
In this work, we develop a framework for image segmentation which partitions an image based on the statistics of image<br />
intensity where the statistical information is represented as a mixture of probability density functions defined in a<br />
multi-dimensional image intensity space. Depending on the method to estimate the mixture density functions, three active<br />
contour models are proposed: unsupervised multi-dimensional histogram method, half-supervised multivariate Gaussian<br />
mixture density method, <strong>and</strong> supervised multivariate Gaussian mixture density method. The implementation of active contours<br />
176