Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound

Chih Hsiung Chang, Chia Ying Lin, Ru Guan Wang, Chien Cheng Chou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

At present, indoor positioning has great potential for disaster mitigation, such as guiding evacuees to safe places. This research aims at developing such a sound-based method using artificial intelligence (AI) and building information modeling (BIM). Amid a disaster, first responders can quickly set up the proposed system to help indoor positioning, which relies on BIM, virtual reality (VR), and head related transfer functions (HRTF) techniques to simulate virtual sound fields. Then, a deep learning model is trained so as to be able to predict the current zone within a room based on the sound received. Unity, a serious game platform, and Steam Audio, a Unity plugin designed for adding 3D audio to VR experience, are employed to generate input data sets. The overall accuracy of the output results is about 90% though the training time is long, which can be reduced if more powerful computing resources are utilized.

Original languageEnglish
Title of host publicationComputing in Civil Engineering 2019
Subtitle of host publicationVisualization, Information Modeling, and Simulation - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019
EditorsYong K. Cho, Fernanda Leite, Amir Behzadan, Chao Wang
PublisherAmerican Society of Civil Engineers (ASCE)
Pages193-199
Number of pages7
ISBN (Electronic)9780784482421
DOIs
StatePublished - 2019
EventASCE International Conference on Computing in Civil Engineering 2019: Visualization, Information Modeling, and Simulation, i3CE 2019 - Atlanta, United States
Duration: 17 Jun 201919 Jun 2019

Publication series

NameComputing in Civil Engineering 2019: Visualization, Information Modeling, and Simulation - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019

Conference

ConferenceASCE International Conference on Computing in Civil Engineering 2019: Visualization, Information Modeling, and Simulation, i3CE 2019
Country/TerritoryUnited States
CityAtlanta
Period17/06/1919/06/19

Fingerprint

Dive into the research topics of 'Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound'. Together they form a unique fingerprint.

Cite this