Results 1 
9 of
9
Evolving Dynamic Bayesian Networks with Multiobjective Genetic Algorithms
, 2005
"... A dynamic Bayesian network (DBN) is a probabilistic network that models interdependent entities that change over time. Given example sequences of multivariate data, we use a genetic algorithm to synthesize a network structure that models the causal relationships that explain the sequence. We use a m ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
A dynamic Bayesian network (DBN) is a probabilistic network that models interdependent entities that change over time. Given example sequences of multivariate data, we use a genetic algorithm to synthesize a network structure that models the causal relationships that explain the sequence. We use a multiobjective evaluation strategy with a genetic algorithm. The multiobjective criteria are a network’s probabilistic score and structural complexity score. Our use of Pareto ranking is ideal for this application, because it naturally balances the effect of the likelihood and structural simplicity terms used in the BIC network evaluation heuristic. We use a simple structural scoring formula, which tries to keep the number of links in the network approximately equivalent to the number of variables. We also use a simple representation that favours sparsely connected networks similar in structure to those modeling biological phenomenon. Our experiments show promising results when evolving networks ranging from 10 to 30 variables, using a maximal connectivity of between 3 and 4 parents per node. The results from the multiobjective GA were superior to those obtained with a single objective GA.
Multimodal face tracking using Bayesian network
 In Proceedings of IEEE International Workshop on Analysis and Modeling of Faces and Gestures
, 2003
"... This paper presents a Bayesian network based multimodal fusion method for robust and realtime face tracking. The Bayesian network integrates a prior of second order system dynamics, and the likelihood cues from color, edge and face appearance. While different modalities have different confidence sc ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
This paper presents a Bayesian network based multimodal fusion method for robust and realtime face tracking. The Bayesian network integrates a prior of second order system dynamics, and the likelihood cues from color, edge and face appearance. While different modalities have different confidence scales, we encode the environmental factors related to the confidences of modalities into the Bayesian network, and develop a Fisher discriminant analysis method for learning optimal fusion. The face tracker may track multiple faces under different poses. It is made up of two stages. First hypotheses are efficiently generated using a coarsetofine strategy; then multiple modalities are integrated in the Bayesian network to evaluate the posterior of each hypothesis. The hypothesis that maximizes a posterior (MAP) is selected as the estimate of the object state. Experimental results demonstrate the robustness and realtime performance of our face tracking approach. 1.
Inference and retrieval of soccer event
"... Abstract: As to the soccer video, the event is defined as the mediumlevel spatiotemporal entity interesting to users, having certain context cues corresponding to the specific domain knowledge model. As a mediumlevel entity, the inference of soccer event is based on the fusion of context cues and ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Abstract: As to the soccer video, the event is defined as the mediumlevel spatiotemporal entity interesting to users, having certain context cues corresponding to the specific domain knowledge model. As a mediumlevel entity, the inference of soccer event is based on the fusion of context cues and domain knowledge model. The shooting event is chosen as research target and the event analysis method is expected to be reusable for other soccer events. According to the analysis of shooting event, the following seven kinds of context cues are extracted, respectively including one kind of caption detection, two kinds of face detection, one kind of audience detection, one kind of goal detection, and two kinds of motion estimation. In the inference of soccer event Bayesian network is used to perform the fusion of context cues. In the experiments the event retrieval is performed based on the video data of World Cup 2002, and the results show that the key to event retrieval is the extraction of context cues related with the userdefined event closely. Key words: soccer video; event retrieval; context cues; Bayesian network 1.
A twostage Bayesian network for effective development of conversational agent
 LNCS
, 2003
"... Abstract. Conversational agent is a system that provides user with proper information and maintains the context of dialogue based on natural language. When experts design the network for conversational agent of a domain, the network is usually very complicated and is hard to be understood. So the si ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
Abstract. Conversational agent is a system that provides user with proper information and maintains the context of dialogue based on natural language. When experts design the network for conversational agent of a domain, the network is usually very complicated and is hard to be understood. So the simplification of network by separating variables in the domain is helpful to design the conversational agent more efficiently. Composing Bayesian network as two stages, we aim to design conversational agent easily and analyze user’s query in detail. Also, by using previous information of dialogue, it is possible to maintain the context of conversation. Actually implementing it for a guide of web pages, we can confirm the usefulness of the proposed architecture for conversational agent. 1
Enhancing user support in open problem solving environments through Bayesian Network inference techniques
"... During the last years, development of open learning environments that support effectively their users has been a challenge for the research community of educational technologies. The open interactive nature of these environments results in users experiencing difficulties in coping with the plethora ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
During the last years, development of open learning environments that support effectively their users has been a challenge for the research community of educational technologies. The open interactive nature of these environments results in users experiencing difficulties in coping with the plethora of available functions, especially during their initial efforts to use the system. In addition,from the tutors ’ perspectivethe problem solving strategies of the students are often particularly difficult to identify. In this paper, we argue that such problems could be tackled using machine learning techniques such as Bayesian Networks. We show how we can take advantage of log files obtained during field studies to build an adaptive help system providing the most useful support to the student, according to the state of interaction. On the other hand, we attempt to support the tutor, by automating the process of diagnosing students ’ problem solving strategies using Bayesian Networks. The presented approaches are discussed through examples of two prototypes that have been developed and corresponding evaluation studies. These studies have shown that the proposed approach can effectively support the tasks of students and tutors in such open learning
Intelligent Computing Method for the Interpretation of Neuropsychiatric Diseases
"... Knowledge based system (KBS) has been widely used in the detection and interpretation of EEG based neuropsychiatric diseases. Heuristicbased detection methods of EEG (Electroencephalography) parameters for a particular disease have been reported in the literature but little effort has been made by ..."
Abstract
 Add to MetaCart
Knowledge based system (KBS) has been widely used in the detection and interpretation of EEG based neuropsychiatric diseases. Heuristicbased detection methods of EEG (Electroencephalography) parameters for a particular disease have been reported in the literature but little effort has been made by researchers to combine rulebased reasoning (RBR) and probabilistic method i.e Bayesian method. A combined method improves the computational and reasoning efficiency of the problem solving strategy. We have hierarchically structured the neuropsychiatric diseases in terms of their physiopyscho (physical, cognitive and psychological) parameters and EEG and FMRI (Functional magnetic resonance imaging) based parameters. RBR model use to create Bayesian network for each disease. The diseases considered are ADHD, Dementia, Mood Disorder, OCD and SI. The basic objective of this work is to develop an intelligent method of RBR and Bayesian model in which RBR is used to hierarchical correlate sign and symptom of the disease and also compute probabilities of diseases. Bayesian method is used for diagnosing the neuropsychiatric diseases and to find the probability of relative importance of sign and symptoms of diseases to other diseases.
Reviewers
, 2008
"... This thesis focuses on the development and improvement of Simultaneous Localization and Mapping algorithms. In particular, we are interested in reliable and effective techniques for unstructured large scale environments. While previous researcher focused on the analysis of class of algorithms or gen ..."
Abstract
 Add to MetaCart
This thesis focuses on the development and improvement of Simultaneous Localization and Mapping algorithms. In particular, we are interested in reliable and effective techniques for unstructured large scale environments. While previous researcher focused on the analysis of class of algorithms or general effects of different algorithms (e.g. complexity, convergence or consistency), in this thesis we focus on analyzing the mapping process itself. At first, we present an introspection analysis that allows efficient optimizations for RaoBlackwellized SLAM on grid maps. The key idea is based on an analysis of the mapping process which allows us to perform filter updates conditioned to the state of the mapping system: localization, mapping or loop closing. We are able to update the complex posterior with substantially less resources by performing the computations only for a set of representatives instead of for all potential hypotheses. Extending this introspective analysis from a filter perspective to a general one, we find out that the SLAM problem can de decomposed in three main subproblems: a) incremental mapping, that is the process of providing local constraints between consecutive poses, in order to maintain the map locally consistent; b) loop closure: that is the process of finding
SPEECH RECOGNITION WITH AUXILIARY INFORMATION
, 2003
"... Automatic speech recognition (ASR) is a very challenging problem due to the wide variety of the data that it must be able to deal with. Being the standard tool for ASR, hidden Markov models (HMMs) have proven to work well for ASR when there are controls over the variety of the data. Being relatively ..."
Abstract
 Add to MetaCart
Automatic speech recognition (ASR) is a very challenging problem due to the wide variety of the data that it must be able to deal with. Being the standard tool for ASR, hidden Markov models (HMMs) have proven to work well for ASR when there are controls over the variety of the data. Being relatively new to ASR, dynamic Bayesian networks (DBNs) are more generic models with algorithms that are more flexible than those of HMMs. Various assumptions can be changed without modifying the underlying algorithm and code, unlike in HMMs; these assumptions relate to the variables to be modeled, the statistical dependencies between these variables, and the observations which are available for certain of the variables. The main objective of this thesis, therefore, is to examine some areas where DBNs can be used to change HMMs ’ assumptions so as to have models that are more robust to the variety of data that ASR must deal with. HMMs model the standard observed features by jointly modeling them with a hidden discrete state variable and by having certain restraints placed upon the states and features. Some of the areas where DBNs can generalize this modeling framework of HMMs involve the incorporation of even more “auxiliary ” variables to help the modeling which HMMs typically can only do with the two variables under certain restraints. The DBN framework is more flexible