Advanced Technology Trends and Computational Tools in Construction: A Case Study of Deep Learning for Activity Recognition
TITLE:
Advanced Technology Trends and Computational Tools in Construction: A Case Study of Deep Learning for Activity Recognition
DATE:
Friday, February 14, 2020
TIME:
3:00 PM
LOCATION:
GMCS-314
SPEAKER:
Dr. Reza Akhavian, Assistant Professor, Department of Civil, Construction, and Environmental Engineering, SDSU
ABSTRACT:
Technological advancements focusing on effective and efficient information modeling, visualization, resource tracking, and collaboration have gained substantial traction in the architectural, engineering, construction, and facility management (AEC/FM) industry in the last 10 years. The use of advanced technologies and computational tools have resulted in safer jobsites that host more productive project teams to build more sustainable and resilient facilities and infrastructure. In this presentation the use of the cutting-edge technology trends and computational methods in today’s construction engineering and management research and practice is discussed. Such technology trends include data analytics, artificial intelligence, machine learning, automation and robotics, Internet-of-Things (IoT), cyber-physical system, augmented- and virtual-reality (AR/VR), and unmanned aerial vehicles (UAVs) in design, construction, and maintenance of buildings and facilities. A recently conducted research project that entails construction equipment activity recognition using inertial sensors and deep neural networks will be presented in more detail. In this project the performance of a simple baseline convolutional neural network (CNN) is compared to a hybrid network that contains both convolutional and recurrent long short-term memory (LSTM) layers to predict the activities of heavy construction equipment monitored via accelerometers.
HOST:
Satchi Venkataraman
DOWNLOAD: