Network Sensor Error Quantification and Flow Reconstruction Using Deep Learning

Maheshwari, Saurabh

i

Network Sensor Error Quantification and Flow Reconstruction Using Deep Learning

2020-09-01
By Maheshwari, Saurabh

File Language:

English

Details

Creators:

Maheshwari, Saurabh
Corporate Creators:

University of California, Davis. Department of Civil and Environmental Engineering
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
Subject/TRT Terms:

Computer Models Data Fusion Data Processing Operations Infrastructure Machine Learning Neural Networks Simulation
Resource Type:

Thesis
Right Statement:

Public Domain, except where noted in the document.
Geographical Coverage:

United States
Corporate Publisher:

ProQuest LLC
Abstract:

This study approaches the problem of quantifying the network sensor errors as a supervised learning problem and leveraging deep neural networks to map observed traffic flow counts to the systematic errors in the sensors. The author aims at building a model that could reconstruct the erroneous flow irrespective of the level of random noise in the sensors, which is unknown in the real-world. By reconstructing the erroneous flow with high accuracy, the transportation planners could gauge the true traffic flow demand in the network and can make informed infrastructure related decisions.
Content Notes:

This is a thesis manuscript published in the University of California open access publication repository, eScholarship and sponsored by the USDOT UTC program. Please cite this manuscript as Maheshwari, S. (2020). Network Sensor Error Quantification and Flow Reconstruction Using Deep Learning. UC Davis: Institute of Transportation Studies. Retrieved from https://escholarship.org/uc/item/2qk093gx
Format:

PDF
Collection(s):

University Transportation Centers
Main Document Checksum:

urn:sha-512:99c9b60be6d64d867d3b1d7568d6a9d7a04deb083208e1df6dcc60e5fedf0ec708e21bc8b257772533a511b2bccc67fd07aba7e66aa0bcb456bef9c893a40f33
Download URL:

https://rosap.ntl.bts.gov/view/dot/86365/dot_86365_DS1.pdf
File Type:

[PDF - 1.65 MB ]

File Language:

English

ON THIS PAGE

Details

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.