Driving Behavior Data

Last updated on 
Driving Behavior Data

This post describes how to use Driving Behavior Data to Driving Behavior Classification through AI learning.

Table of Contents

  1. Data Introduction
  2. Data Visualization with Machbase Neo
  3. Table Creation and Data Upload in Machbase Neo
  4. Experimental Methodology
  5. Experiment Code
  6. Experimental Results

1. Data Introduction


  • DataHub Serial Number: 2025-7.
  • Data Name: Driving Behavior Data.
  • Data Collection Methods: The data was collected using a Samsung Galaxy S21 at a sampling rate of 2 samples per second, with gravitational acceleration removed, using accelerometer and gyroscope sensors.
  • Data Source: Link
  • Raw data size and format: 554KB, CSV.
  • Number of tags: 7.
Tag Name Description
AccX Acceleration (X axis in meters per second squared (m/s2))
AccY Acceleration (Y axis in meters per second squared (m/s2))
AccZ Acceleration (Z axis in meters per second squared (m/s2))
GyroX Rotation (X axis in degrees per second (°/s))
GyroY Rotation (Y axis in degrees per second (°/s))
GyroZ Rotation (Z axis in degrees per second (°/s))
Class Slow, Normal, Aggressive

2. Data Visualization with Machbase Neo


  • Data visualization is possible through the Tag Analyzer in Machbase Neo.
  • Select desired tag names and visualize them in various types of graphs.
  • Below, access the 2025-7 DataHub in real-time, select the desired tag names from the data of 7 tags, visualize them, and preview the data patterns.
DataHub Viewer

3. Table Creation and Data Upload in Machbase Neo


  • In the DataHub directory, use setup.wrk located in the Driving Behavior Dataset folder to create tables and load data, as illustrated in the image below.

1) Table Creation

  • The table is created immediately upon pressing the "Run" button in the menu.
  • If the driving_behavior table exists, execute the first line and then the second. If it does not exist, start from the second line.

2) Data Upload


  • Loading tables in two different ways.
Method 1) Table loading method using TQL in Machbase Neo (since machbase-neo v8.0.29-rc1

  • Pros

    • Machbase Neo loads as soon as you hit the launch button.

  • Cons

    • Slower table loading speed compared to other method.
Method 2) Loading tables using commands

  • Pros

    • Fast table loading speed.

  • Cons

    • The table loading process is cumbersome.
    • Run cmd window - Change machbase-neo path - Enter command in cmd window.
  • If run the below script from the command shell, the data will be entered at high speed into the commercial_vehicles table.
curl http://data.yotahub.com/2025-7/datahub-2025-7-Driving-Behavior.csv.gz | machbase-neo shell import --input - --compress gzip --header --method append --timeformat ns driving_behavior
  • If specify a separate username and password, use the --user and --password options (if not sys/manager) and add the options as shown below.
curl http://data.yotahub.com/2025-7/datahub-2025-7-Driving-Behavior.csv.gz | machbase-neo shell import --input - --compress gzip --header --method append --timeformat ns driving_behavior --user USERNAME --password PASSWORD

4. Experimental Methodology


  • Model Objective: Driving Behavior Classification.
  • Tags Used: AccX, AccY, AccZ, GyroX, GyroY, GyroZ, Class.
  • Model Configuration: TCN(Temporal Convolutional Network).
  • Learning Method: supervised Learning.
    • Train: Model Training.
    • Test: Model Performance Evaluation Based on Driving Behavior Classification.
  • Model Optimizer: Adam.
  • Model Loss Function: CrossEntropyLoss.
  • Model Performance Metric: F1 Score.
  • Data Loading Method
    • Loading the Entire Dataset.
    • Loading the Fetch Dataset.
  • Data Preprocessing
    • MinMax Scaling.
    • Time Feature Generating.

5. Experiment Code


  • Composed of three methods.
  • Data Information: Outputs general information about the data.
  • Visual Information: correlation heatmap, plot, Decomposition about the data.
  • Statistical Test: ADF Test, KPSS Test, PP Test, ljung box Test, Arch Test, VIF Test about the data.

Driving Behavior Classification

  • Below is the code for each of the two ways to get data from the database.
  • If all the data can be loaded and trained at once without causing memory errors, then method 1 is the fastest and simplest.
  • If the data is too large, causing memory errors, then the batch loading method proposed in method 2 is the most efficient.

Method 1) Loading the Entire Dataset


  • The code below is implemented in a way that loads all the data needed for training from the database all at once.
  • It is exactly the same as loading all CSV files (The only difference is that the data is loaded from Machbase Neo).
  • Pros
    • Can use the same code that was previously utilizing CSVs (Only the loading process is different).
  • Cons
    • Unable to train if trainable data size exceeds memory size.

Method 2) Loading the Fetch Dataset


  • Method for loading data from the Machbase Neo for a buffer size.
  • Pros
    • It is possible to train the model regardless of the data size, no matter how large it is.
  • Cons
    • It takes longer to train compared to method 1.

6. Experimental Results


Method 1) Loading the Entire Dataset Result


Method 2) Loading the Fetch Dataset Result


  • The F1 scores are 0.38 and 0.39 indicating low performance.
  • The low performance is due to differences in the collection time and the roads on which the train and test data were collected.
  • Try improving the performance by applying various techniques!

※ Various datasets and tutorial codes can be found in the GitHub repository below.

datahub/dataset at main · machbase/datahub
All Industrial IoT DataHub with data visualization and AI source - machbase/datahub
GitHubmachbase

Back to Top