Multi-class Vehicular Densities in Jeju, South Korea

Citation Author(s):
Asif
Mehmood
Jeju National University, South Korea
Faisal
Mehmood
Gachon University, South Korea
Submitted by:
Asif Mehmood
Last updated:
Fri, 12/09/2022 - 05:24
DOI:
10.21227/k3w6-y146
Data Format:
time, TAC, type, nov
License:
Creative Commons Attribution
189 Views
Categories:
Geo-Sensing
Transportation
Keywords:
vehicle-densities; multi-class-vehicles; vehicle-trajectory; vehicle-type; vehicle-trace; geo-coordinate; jeju; jeju-si; south-korea;
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

This dataset contains the vehicular densities from a location in Jeju-si, South Korea.  The dataset considers the regions to be classified as a tracking area code (TAC) cell, over which the time-series data for multi-class vehicular densities is provided.The dataset contains the major areas/junctions from where the Jeju International Airport and Jeju Seaport traffic passes on daily. Jeju International Airport is one of the busiest airpots in the world. For each timestep, the data comprises up of 22 TAC cells (equally distribute per area) each of which contains four records representing density of four vehicles. Each record contains:

  1. time (timestep in seconds)

  2. TAC (id of a region; the 6 coordinates representing the coverage area polygon area defined in the dataset-file "hsas-map-tx-ps-bs-tr-graph-ieee-dataport.csv".)

  3. type (type of vehicle, bus, truck, passenger-car, taxi)

  4. nov (number of vehicles in a TAC at time t for a specific vehicle-type)

 

Instructions: 

The main dataset file (hsas-map-tx-ps-bs-tr-density-geo-ieee-dataport.csv) contains multi-class vehicular densities over 22 TAC cell regions defined in hsas-map-tx-ps-bs-tr-graph-ieee-dataport.csv file.

To read the main dataset in python language, you can import the dataset by using the following commands, i.e.,

df = pd.read_csv("path_to_csv_file")

df_hierarchical = df.groupby(
    ["time", "TAC", "type"],
    as_index=True
).sum()["nov"]

 

The second command is used to convert the dataframe into a hierarchical dataframe so that it becomes easier to filter the data spanning over regions and time, for example, the following command provides the user to filter data over time [and region]:

df_hierarchical[4999.0] # displays traffic densities of each vehicle-type for 22 graph-nodes/TAC(s)

df_hierarchical[4999.0]["G-6"] # displays traffic densities of each vehicle-type for G-6 (graph-node/TAC) region.

 

Yes! Importing the dataset is that much easy to import and then start using.

Note: If you or any of your friends want to use the dataset, please let them know about this link. It is free to use, and if anyone wants to give a favor, he/she can cite my papers from Google-Scholar (https://scholar.google.com/citations?user=C14nwMMAAAAJ&sortby=pubdate) in their work!

 

Dataset Files

LOGIN TO ACCESS DATASET FILES

QUESTIONS?