A hybrid approach to decision making and information fusion: Combining humans and artificial agents

This paper argues that hybrid humanagent systems can support powerful solutions to relevant problems such as Environmental Crisis management. However, it shows that such solutions require comprehensive approaches covering different aspects of data processing, model construction and the usage. In particular, the solutions (i) must be able to cope with complex correlations (as different data sources are used) and processing of large amounts of data, (ii) must be robust against modeling imperfections and (iii) humanmachine interaction (HMI) approaches must facilitate human use of crisis management tools and reduce the likelihood of miscommunication.In this paper the relevant problem is an environmental protection application involving the detection and tracking of gases in case of chemical spills in an urban area. We show that a combination of Bayesian Networks, agent paradigm and systematic approaches to implementing HMI, support effective and robust solutions. To better integrate human information and demonstrate the usefulness of user generated crisis response information we developed a social media harvesting interface based on data from Twitter tweets and a visual interface to facilitate human smell classification.

[1]  A. Gilbert,et al.  Cross-modal correspondence between vision and olfaction: the color of smells. , 1996, The American journal of psychology.

[2]  Gregor Pavlin,et al.  Efficient Distributed Bayesian Reasoning via Targeted Instantiation of Variables , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[3]  Fue-Sang Lien,et al.  Bayesian inference for source determination with applications to a complex urban environment , 2007 .

[4]  K. S. Rao Source estimation methods for atmospheric dispersion , 2007 .

[5]  Brendan J. Frey,et al.  Factor graphs and the sum-product algorithm , 2001, IEEE Trans. Inf. Theory.

[6]  Joseph Kaye,et al.  Making Scents: aromatic output for HCI , 2004, INTR.

[7]  Vanessa Evers,et al.  Canary in a coal mine: monitoring air quality and detecting environmental incidents by harvesting Twitter , 2011, CHI Extended Abstracts.

[8]  Paulo Cesar G. da Costa,et al.  Evaluating complex fusion systems based on causal probabilistic models , 2013, Proceedings of the 16th International Conference on Information Fusion.

[9]  W. Cain,et al.  Odor quality: Discrimination versus free and cued identification , 1994, Perception & psychophysics.

[10]  N. Sobel,et al.  An odor is not worth a thousand words: from multidimensional odors to unidimensional odor objects. , 2013, Annual review of psychology.

[11]  Vanessa Evers,et al.  DIADEM: a system for collaborative environmental monitoring , 2011, CSCW '11.

[12]  Eelke van Foeken,et al.  An Improved Method for creating Shared Belief in Communication Constrained Sensor Networks , 2009, GI Jahrestagung.

[13]  Carlos Guestrin,et al.  Robust Probabilistic Inference in Distributed Systems , 2004, UAI.

[14]  Gregor Pavlin,et al.  Gas detection and source localization: A Bayesian approach , 2011, 14th International Conference on Information Fusion.

[15]  Marinus Maris,et al.  A multi-agent systems approach to distributed bayesian information fusion , 2010, Inf. Fusion.

[16]  W. Cain,et al.  Sensory and semantic factors in recognition memory for odors and graphic stimuli: elderly versus young persons. , 1991, The American journal of psychology.

[17]  Peter D. Scott,et al.  Source identification of puff-based dispersion models using convex optimization , 2010, 2010 13th International Conference on Information Fusion.

[18]  Nello Cristianini,et al.  Tracking the flu pandemic by monitoring the social web , 2010, 2010 2nd International Workshop on Cognitive Information Processing.

[19]  R. Dolan,et al.  The Nose Smells What the Eye Sees Crossmodal Visual Facilitation of Human Olfactory Perception , 2003, Neuron.

[20]  Jan Nunnink,et al.  Inference Meta Models: Towards Robust Information Fusion with Bayesian Networks , 2006, 2006 9th International Conference on Information Fusion.

[21]  D. Dubourdieu,et al.  The Color of Odors , 2001, Brain and Language.

[22]  Nicholas R. Jennings,et al.  A Roadmap of Agent Research and Development , 2004, Autonomous Agents and Multi-Agent Systems.

[23]  W S Cain,et al.  To know with the nose: keys to odor identification. , 1979, Science.

[24]  Sahar Asadi,et al.  Estimating Predictive Variance for Statistical Gas Distribution Modelling , 2009 .

[25]  R. van Engelen,et al.  Approximating Bayesian belief networks by arc removal , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Charles Spence,et al.  Cross-modal associations between odors and colors. , 2006, Chemical senses.