UnBBayes Around the World
Have you ever heard about UnBBayes? Is this the first time you see it around? Would you like to know what the community think about it?
If not, have you ever used UnBBayes? Have you ever written an article and referenced it? Did you like it?
Well, here we will show some references and comments about UnBBayes. We would love to list all projects and articles that ever used or mentioned UnBBayes, but unfortunately we do not know them all.
If you know any other project, article, link, whatever that used or talked about UnBBayes, please let us know! We, and the community, would appreciate it a lot! Please send us an e-mail (email@example.com) talking about it. We also encourage the curious user to send his/her comment to us. We will try our best to make this open source project better and better.
Now, the awaited list:
- Although the above approaches are promising where applicable, a workable solution for the Semantic Web requires a general-purpose formalism that gives ontology designers a range of options to balance tractability against expressiveness. Current research on SW formalisms using first-order probabilistic logics is still in its infancy, and generally lack a complete set of publicly available tools. Examples include PR-OWL (Costa, 2005), which is an upper ontology for building probabilistic ontologies based on MEBN logic, and KEEPER (Pool and Aiken, 2004), an OWL-based interface for the relational probabilistic toolset Quiddity*Suite, developed by IET, Inc. Their constructs are similar in spirit and provide an expressive method for representing uncertainty in OWL ontologies. Costa (2005) gives a definition for Probabilistic Ontologies, develops rules for constructing PR-OWL ontologies in a manner that can be translated into Quiddity*Suite, and describes how to perform the translation. Carvalho et al. (2007) and Costa et. al. (2008) present an open source, Java-based, PR-OWL/MEBN GUI and reasoner package, UnBBayes-MEBN, that greatly facilitates the process of building probabilistic ontologies and reasoning with them.
Uncertainty Reasoning for the World Wide Web - W3C Incubator Group Report
- UnBBayes allows a more adequate and better visualization of the MTheory and MFrags being created, as well as their nodes. In short, it is not difficult to perceive the advantages of building POs with the GUI implemented in UnBBayes.
Uncertainty Reasoning for the Semantic Web I
- However, building MFrags in a probabilistic ontology is a manual, error prone, and tedious process. Avoiding errors or inconsistencies requires deep knowledge of the logic and of the data structures of PR-OWL, since the user would have to know all technical terms such as hasPossibleValues, is-NodeFrom, isResidentNodeIn, etc. In an ideal scenario, many of these terms could be omitted and filled automatic by a software application projected to enforce the consistency of a MEBN model.
The development of UnBBayes-MEBN [12, 13], an open source, Java-based application that is currently in alpha phase (public release March 08), is an important step towards this objective, as it provides both a GUI for building probabilistic ontologies and a reasoner based on the PR-OWL/MEBN framework.
Probabilistic Ontologies for Knowledge Fusion
- The probabilistic network for the speed decision is generated from the existing data. So instead of building up the network and defining the probability function later on, the data is given and the UnBBayes learning tool  generates the nodes and afterward gives the definition of the relations between the nodes, thus the probability functions are calculated.
A Self-Learning Driving Behavior Model for Microscopic Online Simulation based on Remote Sensing and Equipped Vehicle Data
- Calibrating Driving Behavior with Microscopic Measurement Data
- This article describes cooperation with the Brazilian Federal Police (DPF/INI) and the academia to use data mining techniques to make faster the criminal identification based on the matching of deca-dactylograms. The DPF/INI fingerprint files use the Vucetichs system that codes all the ten fingers of a person with a unique dactyloscopic formula. Many times, only fragments of fingerprints are found in the scene of the crime. Our goal is to study how to deal with this missing of information to reduce the search space into the fingerprints identification processes. To infer missing codes, we had tested classifier based on naïve Bayes, Bayesian network, decision tree, neural network, and CNM. As a result, Lupa Digital was developed in Java (<<using UnBBayes>).>
(Lupa Digital: Agilizacao da Busca Decadactilar na Identificacao Criminal Atraves de Mineracao de Dados)
- Environment for Supervised Learning for Data Mining in Bayesian Networks in Endocrinology Field (Ambiente de Aprendizagem Supervisionada para Mineracao de Dados em Redes Bayesianas na Area de Endocrinologia)
- To update the probability vector software named UnBBayes developed by Fernandes (2004) was used. UnBBayes uses K2 Algorithm which heuristically searches for the most probable belief network structure given a database of cases to estimate conditional probabilities.
Self Learning Tool for Travel Time Estimation in Signalized Urban Networks Based on Probe Data
- Advanced AI Techniques
- The probabilistic classifiers Naive Bayes, TAN, and BAN were generated by UnBBayes, while the classifiers Neural Network and Decision Tree were generated by UnBMiner. (Free translation)
(Aplicabilidade de Memoria Logica como Ferramenta Coadjuvante no Diagnostico das Doencas Geneticas)
- UnBBayes: BN, ID, Multiply Sectioned Bayesian Network (MSBN) and Multi-Entity Bayesian Networks (MEBN). It also includes various algorithms for Bayesian Learning. From the Group of Artificial Intelligence at University of Brasília (UnB), Brazil.
- According to Marcelo Ladeira, UnBBayes works as the problem solver from Microsoft Windows. There, the user answers a series of objective questions to find out the possible causes to the problem. The same thing happens in UnBBayes: the physician enters the symptoms and the computer answers with a diagnostic. The program also allows the physician to ask why and why not the computer got a certain conclusion. (Free translation)
Article in a Brazilian Newspaper (E grave, computador?)
- It was really worth using the UnBBayes framework. Its interface allowed the visualization of the internal structures that were created by the learning algorithm. (Free translation)
EM Algorithms for BN Learning with Incomplete Data (Algoritmos EM para Aprendizagem de Redes Bayesianas a partir de Dados Incompletos)
To the UnB group: to Prof. Marcelo Ladeira, that allowed me several and endless conversations, tips, and references about Bayesian networks, and in the end, gently allowed me to use UnBBayes in this project. Special thanks to Michael Onishi and Rommel Carvalho, students advised by Dr. Marcelo Ladeira, that were always ready and available to answer questions about UnBBayes implementation and use. (Free translation)
Complex System Simulation for Entertainment Use. Using Bayesian Networks: The FutSim Case (Simulacao de Sistemas Complexos para Fins de Entretenimento. Usando Redes Bayesianas: O Caso do FutSim)