Influence Diagram for Selection of Pedagogical Strategies in a Multi-Agent System Learning

Bez, Marta Rosecler; Flores, Cecília Dias; Fonseca, João Marcelo; Maroni, Vinícius; Barros, Paulo Ricardo Muniz; Vicari, Rosa María

doi:10.1007/978-3-642-34654-5_63

Cited by 5 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IDs have been used to address problems in supply chain management (Zheng et al , 2017; Xiaofeng et al , 2012); environmental management (Aastrom et al , 2014); healthcare (Fatisson et al , 2016); energy (Zhang et al , 2018); education (Anaya et al , 2013; Bez, et al , 2012); finance (Tseng, 2006); risk assessment and analysis (Zhi and Xue-Jin, 2010; Sedki et al , 2013; Liu et al , 2010); and other industries.…”

Section: Literature Surveymentioning

confidence: 99%

Ishikawa diagrams and Bayesian belief networks for continuous improvement applications

Rodgers

Oppenheim

2019

TQM

View full text Add to dashboard Cite

Purpose In continuous improvement (CI) projects, cause-and-effect diagrams are used to qualitatively express the relationship between a given problem and its root causes. However, when data collection activities are limited, and advanced statistical analyses are not possible, practitioners need to understand causal relationships. The paper aims to discuss these issues. Design/methodology/approach In this research, the authors present a framework that combines cause-and-effect diagrams with Bayesian belief networks (BBNs) to estimate causal relationships in instances where formal data collection/analysis activities are too costly or impractical. Specifically, the authors use cause-and-effect diagrams to create causal networks, and leverage elicitation methods to estimate the likelihood of risk scenarios by means of computer-based simulation. Findings This framework enables CI practitioners to leverage qualitative data and expertise to conduct in-depth statistical analysis in the event that data collection activities cannot be fully executed. Furthermore, this allows CI practitioners to identify critical root causes of a given problem under investigation before generating solutions. Originality/value This is the first framework that translates qualitative insights from a cause-and-effect diagram into a closed-form relationship between inputs and outputs by means of BBN models, simulation and regression.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Ishikawa diagrams and Bayesian belief networks for continuous improvement applications

Rodgers

Oppenheim

2019

TQM

View full text Add to dashboard Cite

show abstract

“…In order to select an ideal message to be emitted to the student, the Mediator agent of the SimDeCS analyzes two important aspects of the student's behavior during simulation: confidence and credibility. The ID represents the credibility of the simulator on the student which is calculated based on collected variables during simulation such as creating a record of the patient, the number of questioned bogus nodes, and the investigation process, which takes into consideration the questions carried out during anamnesis, physical examination and complementary exams [15].…”

Section: Mediator Agentmentioning

confidence: 99%

Leveraging the learning process in health through clinical cases simulator

Flores

Barros

Cazella

et al. 2013

2013 IEEE 2nd International Conference on Serious Games and Applications for Health (SeGAH)

View full text Add to dashboard Cite

This paper presents a multi-agent learning system for health care practitioners named SimDeCS (Simulation for Decision Making in the Health Care Service). The main contribution of this work is the system architecture, model learning environment supported by artificial intelligence techniques, and its evaluation as a educational software. The SimDeCS was designed as a multi-agent system, composed by three intelligent agents: Domain Agent, Learning Agent and Mediator Agent. The Domain Agent implements the knowledge model by probabilistic reasoning (Bayesian networks), with the knowledge encoded by human experts. The pedagogical strategies emerge from an influence diagram, based on the student's conduct during the simulation. Some results related with the SimDeCs evaluation are presented.

show abstract

Development and Evaluation of an Intelligent Pedagogical Agent for the SimDeCS Software

Maroni¹,

Flores²,

Cazella

et al. 2013

Procedia Technology

View full text Add to dashboard Cite

Influence Diagram for Selection of Pedagogical Strategies in a Multi-Agent System Learning

Cited by 5 publications

References 17 publications

Ishikawa diagrams and Bayesian belief networks for continuous improvement applications

Ishikawa diagrams and Bayesian belief networks for continuous improvement applications

Leveraging the learning process in health through clinical cases simulator

Development and Evaluation of an Intelligent Pedagogical Agent for the SimDeCS Software

Contact Info

Product

Resources

About