October 1, 2021 Thesis Open Access

HABTU REDA

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>HABTU REDA</dc:creator>
  <dc:date>2021-10-01</dc:date>
  <dc:description>Estimating public bus arrival times and delivering accurate arrival time information to
passengers are critical for making public transportation more user-friendly and thereby
increasing its competitiveness among various forms of transportation. However public bus
arrival time prediction remains major bottlenecks With traffic heterogeneity in composition and
diversity of vehicles, as well as a big pedestrian population combined with inadequate lane use,
predicting the arrival time of public buses at stations is a severe concern.. The main objective of
this study is to apply machine learning algorithms to predict bus arrival time. The data was
collected from Addis Ababa Sheger Public Bus Transport. Random Forest, Gradient Boosting,
Artificial Neural Network, K-Nearest Neighbors and Support Vector Machine algorithms are
applied to build the models and to compare and choose the best model to predict the bus arrival
time. After selecting the features and algorithms, different data preprocessing tasks like checking
outliers, missing values and data reduction are done. Finally, 140,000 instances of dataset are
used to train and build the model. The prepared dataset is partitioned into 90% training and 10%
testing set. Beginning Date, Beginning Time, End Date, Time Range, Mileage, Duration, Initial
latitude, Initial longitude, Final latitude, Final longitude, and End Time were used as input
features for developing the model. Based on the experiment result the Random Forest algorithm
achieved a better performance with R-squared score of 0.994, MAE of 0.812, RMSE of 3.780
and MSE of 14.28.</dc:description>
  <dc:identifier>https://zenodo.org/record/4654</dc:identifier>
  <dc:identifier>10.20372/nadre:4654</dc:identifier>
  <dc:identifier>oai:zenodo.org:4654</dc:identifier>
  <dc:relation>doi:10.20372/nadre:4653</dc:relation>
  <dc:relation>url:https://nadre.ethernet.edu.et/communities/aastu</dc:relation>
  <dc:relation>url:https://nadre.ethernet.edu.et/communities/zenodo</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>http://www.opendefinition.org/licenses/cc-by</dc:rights>
  <dc:title>PUBLIC BUS ARRIVAL TIME PREDICTION USING MACHINE LEARNING: IN CASE OF ADDIS ABABA</dc:title>
  <dc:type>info:eu-repo/semantics/doctoralThesis</dc:type>
  <dc:type>publication-thesis</dc:type>
</oai_dc:dc>