You are here:
A Novel Framework for Characterizing Exposure-Related Behaviors Using Agent-Based Models Embedded with Needs-Based Artificial Intelligence (CSSSA2016)
Citation:
Brandon, N., K. Dionisio, K. Isaacs, D. Kapraun, Woodrow Setzer, AND R. Tornero-Velez. A Novel Framework for Characterizing Exposure-Related Behaviors Using Agent-Based Models Embedded with Needs-Based Artificial Intelligence (CSSSA2016). The Computational Social Science Society of the Americas, Santa Fe, NM, November 17 - 20, 2016.
Impact/Purpose:
Preset NERL's research on the use of agent based modeling in exposure assessments. To obtain feed back on the approach from the leading experts in the field.
Description:
Descriptions of where and how individuals spend their time are important for characterizing exposures to chemicals in consumer products and in indoor environments. Herein we create an agent-based model (ABM) that is able to simulate longitudinal patterns in behaviors. By basing our ABM upon a needs-based artificial intelligence (AI) system, we create agents that mimic human decisions on these exposure-relevant behaviors. In a case study of adults, we use the AI to predict the inter-individual variation in the start time and duration of four behaviors: sleeping, eating, commuting, and working. The results demonstrate that the ABM can capture both inter-individual variation and how decisions on one behavior can affect subsequent behaviors.
