TY - JOUR
T1 - SISG4HEI_Alpha
T2 - Alpha version of simulated indoor scenario generator for houses with elderly individuals
AU - Jiang, Can
AU - Mita, Akira
N1 - Funding Information:
This research was partially supported by a grant from the Japan Society for the Promotion of Science ( JSPS KAKENHI 18H00968 ) and a scholarship from the Mizuho International Foundation .
Publisher Copyright:
© 2020 Elsevier Ltd
PY - 2021/3
Y1 - 2021/3
N2 - Developers improve and test the sensor networks and robots of smart houses by conducting simulations. However, they need to build scenarios in the simulators manually, which takes a lot of time. Manually built scenarios are also few in number. Moreover, developers have to repeat this procedure whenever they conduct a simulation with the same scenario on another simulator. To address these issues, we have developed a simulation tool (alpha version), called SISG4HEI_Alpha, which produces diverse simulated indoor scenarios of houses with elderly individuals for multiple simulators. It consists of a GUI, database, three generators, and interfaces. The spatial attribute generator produces virtual spatial data necessary for building the models of the house and furniture. The activity schedule and travel pattern generator generate resident's information to control the virtual agent within a simulator. One interface converts the generated data into simulated PIR sensor records, which are simulation results of the OPENSHS simulator. The two other interfaces convert data into scenarios of the Stage and Gazebo simulators. SISG4HEI_Alpha is modular and extensible; it is easy to improve the generators and/or add new interfaces.
AB - Developers improve and test the sensor networks and robots of smart houses by conducting simulations. However, they need to build scenarios in the simulators manually, which takes a lot of time. Manually built scenarios are also few in number. Moreover, developers have to repeat this procedure whenever they conduct a simulation with the same scenario on another simulator. To address these issues, we have developed a simulation tool (alpha version), called SISG4HEI_Alpha, which produces diverse simulated indoor scenarios of houses with elderly individuals for multiple simulators. It consists of a GUI, database, three generators, and interfaces. The spatial attribute generator produces virtual spatial data necessary for building the models of the house and furniture. The activity schedule and travel pattern generator generate resident's information to control the virtual agent within a simulator. One interface converts the generated data into simulated PIR sensor records, which are simulation results of the OPENSHS simulator. The two other interfaces convert data into scenarios of the Stage and Gazebo simulators. SISG4HEI_Alpha is modular and extensible; it is easy to improve the generators and/or add new interfaces.
KW - Automatic simulation
KW - Elderly people living alone
KW - Machine learning datasets
KW - Simulation scenario generation
KW - Smart house simulator
UR - http://www.scopus.com/inward/record.url?scp=85096828111&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096828111&partnerID=8YFLogxK
U2 - 10.1016/j.jobe.2020.101963
DO - 10.1016/j.jobe.2020.101963
M3 - Article
AN - SCOPUS:85096828111
SN - 2352-7102
VL - 35
JO - Journal of Building Engineering
JF - Journal of Building Engineering
M1 - 101963
ER -