AUB ScholarWorks

Crowd attributes estimation using support vector machine and deep learning with multi-source sensor fusion.

Show simple item record

dc.contributor.author Hassoun, Karim Mohamad Ali,
dc.date.accessioned 2020-03-28T17:18:23Z
dc.date.available 2020-05
dc.date.available 2020-03-28T17:18:23Z
dc.date.issued 2019
dc.date.submitted 2019
dc.identifier.other b23524650
dc.identifier.uri http://hdl.handle.net/10938/21841
dc.description Thesis. M.E. American University of Beirut. Department of Mechanical Engineering, 2019. ET:6983.
dc.description Advisor : Dr. Samir Mustapha, Assistant Professor, Mechanical Engineering ; Members of Committee : Dr. Zaher Dawy, Professor, Electrical and Computer Engineering ; Dr. Mohammad S. Harb, Assistant Professor, Mechanical Engineering.
dc.description Includes bibliographical references (leaves 87-91)
dc.description.abstract Unfortunate tragedies have previously been the result of high-density human crowds or pedestrian flow. In addition to, crowd behavior as a reaction to an incident aggravates the complexity and disruption of human flow, resulting in possible trampling and crushing situations. Therefore, it is important to monitor such crowd motion for danger warning and prevention. In this study, a frame work was established to provide continuous monitoring and estimation of crowd flow and load on pedestrian bridges, with particular focus on high crowd density enhancing operation safety. A main innovation under sensing instrumentation is the employment of structurally mounted Fiber Bragg Gratings (FBG) Fiber Optic Sensors (FOS), in conjunction with individually held wearable sensing devices incorporating Inertial Measurement Unit (IMU). Furthermore, the approach added innovation under machine learning employment, primarily Convolutional Neural Networks (CNN) along with conventional Support Vector Machine (SVM) algorithms thus generating crowd estimation models from gathered sensors’ data. The concept was validated using experimental measurements on two phases based on crowd replication scenarios on a scaled test bridge. Generated machine learning models demonstrated effectiveness in crowd attribute classification for flow activity and load characterization, along with regression model for load estimation. Multi-modal sensor fusion at the input and feature level was further applied on strain and acceleration data collected enriching the machine learning models, thus enhancing system efficiency and robustness against noisy and time shifted input data. The results showed that the monitoring solution to be highly effective with peak testing accuracy for single class flow activity classification at 98percent, multi-class flow and load characterization classification at 91percent, and percentage error for load estimation regression reaching a minimum of 9percent.
dc.format.extent 1 online resource (xii, 91 leaves) : illustrations (some color)
dc.language.iso eng
dc.subject.classification ET:006983
dc.subject.lcsh Machine learning.
dc.subject.lcsh Supervised learning (Machine learning)
dc.subject.lcsh Structural health monitoring.
dc.subject.lcsh Smartphones.
dc.subject.lcsh Multisensor data fusion.
dc.title Crowd attributes estimation using support vector machine and deep learning with multi-source sensor fusion.
dc.type z
dc.contributor.department Maroun Semaan Faculty of Engineering and Architecture.
dc.contributor.department Department of Mechanical Engineering,
dc.subject.classificationsource AUBNO
dc.contributor.institution American University of Beirut.


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search AUB ScholarWorks


Browse

My Account