SmartSPEC: Customizable Smart Space Datasets via Event-driven Simulations
Loading...
Author/Creator ORCID
Date
2022-03-19
Department
Program
Citation of Original Publication
A. Chio et al., "SmartSPEC: Customizable Smart Space Datasets via Event-driven Simulations," 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom), 2022, pp. 152-162, doi: 10.1109/PerCom53586.2022.9762405.
Rights
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects
Abstract
This paper presents SmartSPEC, an approach to
generate customizable smart space datasets using sensorized
spaces in which people and events are embedded. Smart space
datasets are critical to design, deploy and evaluate robust systems
and applications to ensure cost-effective operation and safety/-
comfort/convenience of the space occupants. Often, real-world
data is difficult to obtain due to the lack of fine-grained sensing;
privacy/security concerns prevent the release and sharing of
individual and spatial data. SmartSPEC is a smart space simu lator and data generator that can create a digital representation
(twin) of a smart space and its activities. SmartSPEC uses a
semantic model and ML-based approaches to characterize and
learn attributes in a sensorized space, and applies an event driven simulation strategy to generate realistic simulated data
about the space (events, trajectories, sensor datasets, etc). To
evaluate the realism of the data generated by SmartSPEC, we
develop a structured methodology and metrics to assess various
aspects of smart space datasets, including trajectories of people
and occupancy of spaces. Our experimental study looks at
two real-world settings/datasets: an instrumented smart campus
building and a city-wide GPS dataset. Our results show that
the trajectories produced by SmartSPEC are 1.4x to 4.4x more
realistic than the best synthetic data baseline when compared to
real-world data, depending on the scenario and configuration.