Simulating exposure-related behaviors using agent-based models embedded with needs-based artificial intelligence

Abstract

Exposure to a chemical is a critical consideration in the assessment of risk, as it adds real-world context to toxicological information. 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 simulates longitudinal patterns in human behavior. By basing the ABM upon an artificial intelligence (AI) system, we create agents that mimic human decisions on performing behaviors relevant for determining exposures to chemicals and other stressors. We implement the ABM in a computer program called the Agent-Based Model of Human Activity Patterns (ABMHAP) that predicts the longitudinal patterns for sleeping, eating, commuting, and working. We then show that ABMHAP is capable of simulating behavior over extended periods of time. We propose that this framework, and models based on it, can generate longitudinal human behavior data for use in exposure assessments.

Keywords: Agent-based model; Artificial-intelligence; Exposure-related behavior; Simulation.

Fig. 1

Decay behavior of needs. (Left) The behavior of a need modeled by a linear function. (Right) The behavior of a need modeled by a step function

Fig. 2

AI for action decision-making

Fig. 3

Visualization of ABMHAP simulation output

Fig. 4

Visualization of activity durations of an ABMHAP simulation. The durations are expressed in a log₁₀ scale

Fig. 5

The mathematical components involved for decision-making from the ABMHAP simulation on Day 1, Monday. (Top) The satiation values n(t) for each need (recall the value of the threshold λ = 0.2). (Bottom) The non-zero values of the weight function W(n). The values are expressed in a log₁₀ scale