Home // SIMUL 2019, The Eleventh International Conference on Advances in System Simulation // View article

Construction Equipment Emission Modeling and Activity Analysis Using Deep Learning

Authors:
Reza Akhavian

Keywords: construction equipment; machine learning; emission; modeling; sensors

Abstract:
Automated activity recognition and modeling of heavy construction equipment can contribute to the correct and accurate measurement of a variety of project performance indicators. Productivity assessment and sustainability measurement through equipment activity cycle monitoring to eliminate ineffective and idle times thus reducing Greenhouse Gas (GHG) Emission, are some potential areas that can benefit from the integration of automated activity recognition and analysis techniques. In light of this, this idea paper describes design and development of a deep-learning framework that uses accelerometer data to detect activities of construction equipment and consequently estimates the emission produced corresponding to various activities.

Pages: 1 to 2

Copyright: Copyright (c) IARIA, 2019

Publication date: November 24, 2019

Published in: conference

ISSN: 2308-4537

ISBN: 978-1-61208-756-6

Location: Valencia, Spain

Dates: from November 24, 2019 to November 28, 2019