Mobile Device User Simulation with Inertial Data Synthesis

• Grant number: 24/23473-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: April 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Paula Dornhofer Paro Costa
• Grantee: Henrique Parede de Souza
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Studied since the 1950s, cognitive architectures stand out as a promising area in artificial intelligence studies. In particular, the development of cognitive architectures for mobile devices and personal assistants is observed. One of the main challenges within this application lies in the difficulty of evaluating the proposed models due to the scarcity of relevant data for use in research in the area. In this scenario, this project aims to mitigate this problem by proposing a data synthesis model from inertial sensors to be used in simulated intelligent agents subjected to typical behavioral routines of a smartphone user. To materialize this solution, a synthesis model will be proposed initially aimed at the task of generating accelerometer and gyroscope data, in addition to a computational experiment capable of applying this model to the task of generating data from a simulated cognitive agent in a controlled environment.