Intelligent Management of Data Driven Simulations to Support Model Building in the Social Sciences

Abstract

Abstract. Artificial intelligence (AI) can contribute to the management of a data driven simulation system, in particular with regard to adaptive selection of data and refinement of the model on which the simulation is based. We consider two different classes of intelligent agent that can control a data driven simulation: (a) an autonomous agent using internal simulation to test and refine a model of its environment and (b) an assistant agent managing a data-driven simulation to help humans understand a complex system (assisted model-building). In the first case the agent is situated in its environment and can use its own sensors to explore the data sources. In the second case, the agent has much less independent access to data and may have limited capability to refine the model on which the simulation is based. This is particularly true if the data contains subjective statements about the human view of the world, such as in the social sciences.For complex systems involving human actors, we propose an architecture in which assistant agents cooperate with autonomous agents to build a more complete and reliable picture of the observed system.

Symbiotic Simulation Control in Semiconductor Manufacturing

“…Several applications which use symbiotic simulation have been developed since 2002. These include the application of symbiotic simulation for UAV path planning [7], social sciences [8], [9], and business process re-engineering [10]. In the context of semiconductor manufacturing, symbiotic simulation has already been used in [11] to optimise backend operations.…”

Towards an Info-Symbiotic Decision Support System for Disaster Risk Management

“…Considerable effort is required to create ontologies to map out and create relationships between all the datasets. Utilising DDDAS in ABM-based social simulations where multiple ontologies and automated rule adaptation need tobe implemented is a particularly challenging endeavour [32]. From a simulation stand point modeling human factors is still a complex process and seamless integration with scientific code based simulations still need further evaluation.…”

AIMSS: An Architecture for Data Driven Simulations in the Social Sciences

“…The following are some example rules that were mined from the simulation data using the agent rules above and environmental parameters guided by domain specialists S1: if (incomeLevel=1 and moveReason=affordability) 283 then newHomeCost=1 283 conf (1) This specifies that if the income level is in the lowest bracket and the reason for moving was affordability then the rent to be paid for the new home is in the lowest bracket. The following is an example from the CORE data: This has a similar form to S1 above, except that the new home cost is in the second lowest bracket instead of the lowest.…”

“…In earlier work [1] we proposed a conceptual architecture for the intelligent management of a data driven simulation system. In that architecture, a software "assistant" agent should compare simulation predictions with data content and adapt the simulation as necessary.…”