University of Illinois Urbana-Champaign

Greenhouse gas emissions prediction of an IoT taxi fleet

Chang, Yu-Ju

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/109142

Description

Title
Greenhouse gas emissions prediction of an IoT taxi fleet
Author(s)
Chang, Yu-Ju
Contributor(s)
Caesar, Matthew
Issue Date
2020-12
Keyword(s)
  • Artificial Neural Network (ANN)
  • Greenhouse Gas (GHG) Emissions
  • Internet of Things (IoT)
  • Vehicles
  • Transportation
  • Education
  • Project-Based Learning
Abstract
With the advancement of technology, more and more things, like vehicles, are connected through the internet. Useful data could be collected from the sensors on the vehicles and transmitted via the internet. The data could then be analyzed. How to make use of the data is an issue. This study focused on developing a greenhouse gas (GHG) emissions prediction model for an autonomous IoT taxi fleet. This study involved extracting data from an autonomous IoT taxi fleet, processing the data, and producing a machine learning model for the data. Traffic simulations were performed to generate data in this study because not many cars on the road today are connected to the internet. The data was processed in Python, and a machine learning model was produced using Tensorflow. The results showed that a vehicle’s sensor data like vehicle position, speed, waiting time, acceleration, fuel and noise could be used to predict a vehicle’s GHG emissions. Another focus of this study was to make the whole procedure an IoT lab that educates future students about IoT and real-world problem solving. Instructive tutorials were developed. The machine learning program was made into a Jupyter Notebook document with educational texts before each code block. Students were recruited to test the educational effectiveness of the lab.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/109142

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research