Results 1 
9 of
9
Mendelian error detection in complex pedigree using weighted constraint satisfaction techniques
 In ICLP05 workshop on Constraint Based Methods for Bioinformatics
, 2005
"... satisfaction techniques ..."
(Show Context)
Evaluation, Selection, and Application of ModelBased Diagnosis Tools and Approaches
"... Modelbased approaches have proven fruitful in the design and implementation of intelligent systems that provide automated diagnostic functions. A wide variety of models are used in these approaches to represent the particular domain knowledge, including analytic statebased models, inputoutput tra ..."
Abstract

Cited by 9 (6 self)
 Add to MetaCart
Modelbased approaches have proven fruitful in the design and implementation of intelligent systems that provide automated diagnostic functions. A wide variety of models are used in these approaches to represent the particular domain knowledge, including analytic statebased models, inputoutput transfer function models, fault propagation models, and qualitative and quantitative physicsbased models. Diagnostic applications are built around three main steps: observation, comparison, and diagnosis. If the modeling begins in the early stages of system development, engineering models such as fault propagation models can be used for testability analysis to aid definition and evaluation of instrumentation suites for observation of system behavior. Analytical models can be used in the design of monitoring algorithms that process observations to provide information for the second step in the process, comparison of expected behavior of the system to actual measured behavior. In the final diagnostic step, reasoning about the results of the comparison can be performed in a variety of ways, such as dependency matrices, graph propagation, constraint propagation, and state estimation. Realistic empirical evaluation and comparison of these approaches is often hampered by a lack of standard data sets and suitable testbeds. In this paper we
Diagnosing Faults in Electrical Power Systems of Spacecraft and Aircraft
"... Electrical power systems play a critical role in spacecraft and aircraft. This paper discusses our development of a diagnostic capability for an electrical power system testbed, ADAPT, using probabilistic techniques. In the context of ADAPT, we present two challenges, regarding modelling and realti ..."
Abstract

Cited by 8 (6 self)
 Add to MetaCart
Electrical power systems play a critical role in spacecraft and aircraft. This paper discusses our development of a diagnostic capability for an electrical power system testbed, ADAPT, using probabilistic techniques. In the context of ADAPT, we present two challenges, regarding modelling and realtime performance, often encountered in realworld diagnostic applications. To meet the modelling challenge, we discuss our novel highlevel speci cation language which supports autogeneration of Bayesian networks. To meet the realtime challenge, we compile Bayesian networks into arithmetic circuits. Arithmetic circuits typically have small footprints and are optimized for the realtime avionics systems found in spacecraft and aircraft. Using our approach, we present how Bayesian networks with over 400 nodes are autogenerated and then compiled into arithmetic circuits. Using realworld data from ADAPT as well as simulated data, we obtain average inference times smaller than one millisecond when computing diagnostic queries using arithmetic circuits that model our realworld electrical power system.
Understanding the role of noise in stochastic local search: Analysis and experiments
 Artificial Intelligence
, 2008
"... Stochastic local search (SLS) algorithms have recently been proven to be among the best approaches to solving computationally hard problems. SLS algorithms typically have a number of parameters, optimized empirically, that characterize and determine their performance. In this article, we focus on th ..."
Abstract

Cited by 8 (4 self)
 Add to MetaCart
(Show Context)
Stochastic local search (SLS) algorithms have recently been proven to be among the best approaches to solving computationally hard problems. SLS algorithms typically have a number of parameters, optimized empirically, that characterize and determine their performance. In this article, we focus on the noise parameter. The theoretical foundation of SLS, including an understanding of how to the optimal noise varies with problem di ¢ culty, is lagging compared to the strong empirical results obtained using these algorithms. A purely empirical approach to understanding and optimizing SLS noise, as problem instances vary, can be very computationally intensive. To complement existing experimental results, we formulate and analyze several Markov chain models of SLS. In particular, we compute expected hitting times and show that they are rational functions for individual problem instances as well as their mixtures. Expected hitting time curves are analytical counterparts to noise response curves reported in the experimental literature. Hitting time analysis using polynomials and convex functions is also discussed. In addition, we present examples and experimental results illustrating the impact of varying noise probability on SLS run time. In experiments, where most probable explanations in Bayesian networks are computed, we use synthetic problem instances as well as problem instances from applications. We believe that our results provide an improved theoretical understanding of the role of noise in stochastic local search, thereby providing a foundation for further progress in this area. 1
Designing resourcebounded reasoners using Bayesian networks: System health monitoring and diagnosis
 in Proceedings of the 18th International Workshop on Principles of Diagnosis (DX07
, 2007
"... In this work we are concerned with the conceptual design of largescale diagnostic and health management systems that use Bayesian networks. While they are potentially powerful, improperly designed Bayesian networks can result in too high memory requirements or too long inference times, to they poin ..."
Abstract

Cited by 7 (6 self)
 Add to MetaCart
In this work we are concerned with the conceptual design of largescale diagnostic and health management systems that use Bayesian networks. While they are potentially powerful, improperly designed Bayesian networks can result in too high memory requirements or too long inference times, to they point where they may not be acceptable for realtime diagnosis and health management in resourcebounded systems such as NASA's aerospace vehicles. We investigate the clique tree clustering approach to Bayesian network inference, where increasing the size and connectivity of a Bayesian network typically also increases clique tree size. This paper combines techniques for analytically characterizing clique tree growth with bounds on clique tree size imposed by resource constraints, thereby aiding the design and optimization of largescale Bayesian networks in resourcebounded systems. We provide both theoretical and experimental results, and illustrate our approach using a NASA case study.
Advanced diagnostics and prognostics testbed
 in Proceedings of the 18th International Workshop on Principles of Diagnosis
, 2007
"... Researchers in the diagnosis community have developed a number of promising techniques for system health management. However, realistic empirical evaluation and comparison of these approaches is often hampered by a lack of standard data sets and suitable testbeds. In this paper we describe the Advan ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
Researchers in the diagnosis community have developed a number of promising techniques for system health management. However, realistic empirical evaluation and comparison of these approaches is often hampered by a lack of standard data sets and suitable testbeds. In this paper we describe the Advanced Diagnostics and Prognostics Testbed (ADAPT) at NASA Ames Research Center. The purpose of the testbed is to measure, evaluate, and mature diagnostic and prognostic health management technologies. This paper describes the testbed’s hardware, software architecture, and concept of operations. A simulation testbed that accompanies ADAPT, and some of the diagnostic and decision support approaches being investigated are also discussed.
Understanding the Scalability of Bayesian Network Inference using Clique Tree Growth Curves
"... Bayesian networks (BNs) are used to represent and ef ciently compute with multivariate probability distributions in a wide range of disciplines. One of the main approaches to perform computation in BNs is clique tree clustering and propagation. In this approach, BN computation consists of propagati ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
(Show Context)
Bayesian networks (BNs) are used to represent and ef ciently compute with multivariate probability distributions in a wide range of disciplines. One of the main approaches to perform computation in BNs is clique tree clustering and propagation. In this approach, BN computation consists of propagation in a clique tree compiled from a Bayesian network. There is a lack of understanding of how clique tree computation time, and BN computation time in more general, depends on variations in BN size and structure. On the one hand, complexity results tell us that many interesting BN queries are NPhard or worse to answer, and it is not hard to nd application BNs where the clique tree approach in practice cannot be used. On the other hand, it is wellknown that treestructured BNs can be used to answer probabilistic queries in polynomial time. In this article, we develop an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, speci cally: (i) the ratio of the number of a BN's nonroot nodes to the number of root nodes, or (ii) the expected number of moral edges in their moral graphs. Our approach is based on combining analytical and experimental results. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for each set. For the special case of bipartite BNs, we consequently have two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, we systematically increase the degree of the root nodes in bipartite Bayesian networks, and nd that root clique growth is wellapproximated by Gompertz growth curves. It is believed that this research improves the understanding of the scaling behavior of clique tree clustering, provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms, and presents an aid for analytical tradeoff studies of clique tree clustering using growth curves.
Constraint handling using tournament selection: Abductive inference in partly deterministic Bayesian networks. Accepted for publication, Evolutionary Computation
, 2008
"... Constraints occur in many application areas of interest to evolutionary computation. The area considered here is Bayesian networks (BNs), which is a probabilitybased method for representing and reasoning with uncertain knowledge. This work deals with constraints in BNs and investigates how tourname ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Constraints occur in many application areas of interest to evolutionary computation. The area considered here is Bayesian networks (BNs), which is a probabilitybased method for representing and reasoning with uncertain knowledge. This work deals with constraints in BNs and investigates how tournament selection can be adapted to better process such constraints in the context of abductive inference. Abductive inference in BNs consists of finding the most probable explanation given some evidence. Since exact abductive inference is N Phard, several approximate approaches to this inference task have been developed. One of them applies evolutionary techniques in order to find optimal or closetooptimal explanations. A problem with the traditional evolutionary approach is this: As the number of constraints determined by the zeros in the conditional probability tables grows, performance deteriorates because the number of explanations whose probability is greater than zero decreases. To minimize this problem, this paper presents and analyzes a new evolutionary approach to abductive inference in BNs. By considering abductive inference as a constraint optimization problem, the novel approach improves performance dramatically when a BN’s conditional probability tables contain a significant number of zeros. Experimental results are presented comparing the performances of the traditional evolutionary approach and the approach introduced in this work. The results show that the new approach significantly outperforms the traditional one.
Portfolios in Stochastic Local Search: Efficiently Computing Most Probable Explanations in Bayesian Networks
"... In this article we investigate the use of portfolios (or collections) of heuristics when solving computationally hard problems using stochastic local search. We consider uncertainty reasoning, specifically the computation of most probable explanations in Bayesian networks (BNs). Our contribution is ..."
Abstract
 Add to MetaCart
(Show Context)
In this article we investigate the use of portfolios (or collections) of heuristics when solving computationally hard problems using stochastic local search. We consider uncertainty reasoning, specifically the computation of most probable explanations in Bayesian networks (BNs). Our contribution is twofold. First, we introduce a portfoliobased stochastic local search approach that utilizes an initialization portfolio and a search portfolio. Second, and leveraging our portfolio approach, we investigate determinism in BNs. We introduce a novel additive measure of gain (or gradient), which is tailored to partly deterministic Bayesian networks, and show how it generalizes the MAXSAT measure of gain from stochastic local search for the satisfiability (SAT) problem. This measure of gain provides, along with an explanation’s gain in probability and their respective noisy variants, different heuristics that locally improve an explanation. Our approach is implemented in a stochastic local search system, Stochastic Greedy Search. Stochastic Greedy Search is here compared to the stateoftheart inference system H����, which performs BN inference by compilation to and propagation in clique trees. We report on experiments using partly deterministic Bayesian networks from applications as well as synthetically generated networks. On synthetic