Category: Civil and Environmental Engineering

Javad Jomehpour: Listen to Scooter Riders

Posted on

https://youtu.be/Fw6sCnEMRPc

In this study, app store reviews from two major micro-mobility companies are investigated using machine learning techniques to identify the factors that influence rider satisfaction. The Latent Dirichlet Allocation model is applied to over 12,000 rider-generated reviews to identify twelve topics discussed within the reviews. These topics cover areas such as pricing, safety, customer service, refund, payment, app interface, and ease of use, to name a few. Using logistic regression, the most significant factors influencing rider satisfaction were identified. Moreover, name-based gender prediction analysis is employed to identify rider gender and then discover differences in review content and factors of satisfaction across gender. Findings contribute to the existing literature by demonstrating the use of app store reviews in a transportation mobility study. The development of a method to assess factors contributing to user or rider satisfaction offers the ability to evaluate e-scooter rider needs and barriers to access and participation.

Javad Jomehpour
Program: PhD in Civil and Environmental Engineering
Faculty mentor: Janille Smith-Colin

Konstantinos Kalfas: The dynamics of utility poles by considering soil-structure interaction (SSI)

Posted on

Winner: Civil and Environmental Engineering (Graduate)

Co-author: Nicos Makris

https://youtu.be/qbSOL76aK-8

Motivated from the large number of transmission and distribution utility poles that experience excessive vibrations during wind storms, this work sheds light to the eigenvalue analysis of a partially embedded flexural, prismatic column with embedded length, L, and exposed length, h, and accounts for the interaction with the soil of its embedded portion. The presentation will show that the dynamics of a partially embedded prismatic column depend solely on the embedment ratio, ε = L/h and a dimensionless stiffness that expresses the relative stiffness between the soil surrounding the embedded length (level of fixity) and the exposed portion of the flexural column. A partially embedded prismatic column exhibits a finite number of eigenmodes that are lower than its rigid-body mode; while, the associated eigenfrequencies are lower than the corresponding eigenfrequencies of the fixed-end cantilever. For a typical value of the embedment ratio ε = L/h = 0.15, the study uncovers that for any eigenmode n > 3, of the fixed-end cantilever, the partially embedded, prismatic column exhibits n + 1 eigenmodes. These rich dynamics result from soil-structure interaction and are associated with the way that the flexural patterns of the partially embedded column emerge from the ground.

Konstantinos Kalfas
Program: PhD in Civil and Environmental Engineering
Faculty mentor: Nicos Makris

Jase Sitton: Indirect Bridge Monitoring Using Crowdsourced Smartphone Data from Passing Vehicles

Posted on

https://youtu.be/mcIlXNE2kl4

United States bridge infrastructure is aging, with more than 231,000 bridges currently in need of repair, rehabilitation, or replacement. In light of the urgent needs surrounding aging bridge infrastructure, and in the absence of sufficient funding to address all required bridge repairs, it is crucial to identify which bridges have the most immediate need for the allocation of available funds for bridge repairs. Typically, structural health monitoring comprises the installation of permanent sensors on a bridge superstructure and the collection of data for analysis to determine bridge condition. These systems, however, are often expensive and logistically difficult to install on a large number of bridges. Smartphones contain a variety of sensors, including accelerometers and gyroscopes, that may be used to record bridge vibration response data from within vehicles as they traverse bridges. This data may then be used isolate the bridge's vibration response and make bridge condition assessments at regular intervals, and bridges requiring immediate attention can be flagged.

Jase Sitton
Program: PhD in Civil and Environmental Engineering
Faculty mentor: Brett Story