A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound
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.
Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound
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.
Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound
Chang, Chih-Hsiung (author) / Lin, Chia-Ying (author) / Wang, Ru-Guan (author) / Chou, Chien-Cheng (author)
ASCE International Conference on Computing in Civil Engineering 2019 ; 2019 ; Atlanta, Georgia
Computing in Civil Engineering 2019 ; 193-199
2019-06-13
Conference paper
Electronic Resource
English
Applying Deep Learning and Building Information Modeling to Indoor Positioning Based on Sound
| British Library Conference Proceedings | 2019
BIM (Building Information Modeling)-based hyperboloid building positioning method and device
| European Patent Office | 2024
Applying Building Information Modeling to Road Pavements Management
| British Library Conference Proceedings | 2021
Smart City Construction Based on Deep Learning and Building Information Modeling
| Springer Verlag | 2024