Open Access Open Access  Restricted Access Subscription or Fee Access

Evidence-Based Argumentation versus Complete Sharing in Multi-Agent Sensor Webs

Chris Redford, Arvin Agah

Abstract


Abstract Argument Systems continue to be an important branch in computational argumentation research. However, for the implementation of concrete systems applied to real world problem domains, computational argumentation research can benefit from specific argument structure conventions. We have developed such a convention as an extension of the Argument Interchange Format along with other evidence-based argument structure conventions, providing a general convention for specifying evidence-based arguments. We have applied this evidence-based argumentation convention to the multi-agent Sensor Web problem domain, generating a specific set of evidence-based argument types and meta-argumentation data structures for use in that domain. We compare the performance of an agent system using evidence-based argumentation to an agent system using the approach of complete data sharing. This performance comparison is executed against real world geophysical data with blizzard properties. The metrics of message cost, message amount, total accuracy, super region accuracy, and super strength accuracy performance of each system are used. Our hypotheses are that the evidence-based argumentation system will perform better on message costs (with a high effect size according to ANOVA) and that the complete data sharing system will perform better on the other metrics (with a low effect size according to ANOVA). The results of our experiments confirm these hypotheses, demonstrating the relevance and importance of computational argumentation in general, and evidence-based argumentation in particular, to solving real world problems.

Keywords


Metrics, Multiagent Systems, Sensor Fusion, Experimentation, Performance, Theory, Computational Argumentation, Knowledge Representation, Sensor Webs

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.