Skip to content

The project intended to identify trucks based on their model, fuel consumption, driving behaviors and past records of violations/accidents

Notifications You must be signed in to change notification settings

Nagpritam/Identification-of-Trucks-and-potential-risky-driver-using-Databricks-Spark-API-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project Title

ANT SAFE WHEELS

Ensuring Safety and Compliance at ANT

Project Introduction

Accidents caused by large trucks are a significant concern in the United States. Az National Trucking (ANT) aims to mitigate risks associated with trucking operations by identifying drivers exhibiting high-risk behaviors. The organization seeks to ensure compliance with regulations, enhance safety measures, and reduce insurance risks.

Objective

Identify drivers with risk factors of 7.0 or higher to trigger alerts to management and insurance and analyze trucking data to visualize driver risk levels for informed decision-making. Strengthen adherence to FMCSA regulations and internal policies to elevate safety standards across the fleet.

Project Architectural Diagram

Project Architectural Diagram

  • This Project utilises Spark Via Databricks Notebooks, Hadoop file format, Hive Tables and Power BI for Data Visualization

Spark Transformations

Spark Transformations

Analysis

Count of Models

1. Count of Models (Bubble Chart)

  • Displays the number of vehicles for each model.
  • Larger bubbles represent a higher count of vehicles.
  • Ford has the largest bubble, indicating it has the most

MPG by Model

2. MPG by Model (Heat Map)

  • Shows the miles per gallon for each vehicle model.
  • Darker shades represent higher MPG values.
  • Crane appears to have the highest MPG, as indicated by its dark shade.

Risk Factor By Model

3. Risk Factor By Model (Bar Graph):

  • Depicts the risk factor associated with each vehicle model.
  • Oshkosh has the highest risk factor while Navistar has the least
  • The risk factors are relatively similar across models, ranging around 7 to just under 10.

Violation Analysis

4. Violation Analysis (Pie Chart):

  • Lane Departure: The most frequent violation with 152 occurrences, indicating potential issues with driver attention or fatigue.
  • Unsafe Following Distance: Nearly as common, with 150 instances, pointing to risks of rear-end collisions due to inadequate spacing between vehicles.
  • Overspeed and Unsafe Tail Distance: Speeding is noted in 90 instances, a widespread issue, while unsafe tail distance, though less frequent at 65 cases, still poses a significant risk in poor driving conditions.

Risky drivers

5. Top 10 Risky drivers

Namely A97 Driver is the most unsafe driver

Location of Violations

6. Location of Violations

Geographical Spread of Violations: Violations are widespread across California, with concentrations in urban areas like San Francisco and San Diego.

  • Types of Violations: The map indicates two main types of violations: overspeed and unsafe following distance, with unsafe following distance being less common

About

The project intended to identify trucks based on their model, fuel consumption, driving behaviors and past records of violations/accidents

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published