Fleet managment system

Overview

Fleet Management System is a comprehensive solution tailored for managing bus fleets at schools and universities. This project encompasses various features aimed at streamlining the management of bus routes, drivers, and students while ensuring safety and efficiency through advanced tracking and monitoring technologies.

The Fleet Management System provides a complete suite of tools for efficiently managing school and university bus fleets. It offers functionalities for registering bus routes, assigning drivers and students to these routes, tracking buses in real-time, and monitoring driver behavior to ensure safe driving practices.

Key Features

• Bus Route Management:

  • Register and manage bus routes efficiently.
  • Assign drivers and students to specific routes, ensuring organized transportation.

• Real-Time Route Tracking:

  • Track bus routes on a map in real-time.
  • Use TUIO-based object detection markers to record bus arrival and departual time.

• Driver Behavior Monitoring:

  • Monitor driver behaviors using various car sensors.
  • Differentiate between safe and aggressive driving to ensure student safety.
  • Use data from the Honda Driving Dataset (HDD) to train models for behavior detection.

• Data and Models:

  • Applied machine learning models including CNN, LSTM, Bi-LSTM, and CNN-LSTM for driver behavior detection.
  • Utilized the HDD dataset to train and validate these models.

• Architecture and Database:

  • Built on a microservice architecture using Node.js, ensuring scalability and flexibility.
  • Utilized NoSQL databases like Firebase and MongoDB for real-time data tracking and storage.

Key Contributions

• Comprehensive Fleet Management: Provides a complete solution for managing all aspects of bus fleets, from route registration to real-time tracking and behavior monitoring.

• Advanced Tracking and Monitoring: Uses state-of-the-art technologies for real-time tracking and monitoring, ensuring the safety and efficiency of bus operations.

• Behavior Detection Models: Implements sophisticated machine learning models to monitor and analyze driver behavior, promoting safe driving practices.

• Scalable Architecture: The use of microservice architecture and NoSQL databases ensures the system can scale to meet the demands of large fleets and high data throughput.

• The project resulted into a conference publication.

Publications

• Enhancing Road Safety: Leveraging CNN-LSTM and Bi-LSTM Models for Advanced Driver Behavior Detection. 2024 Intelligent Methods, Systems, and Applications (IMSA) DOI.

The Fleet Management System project represents a significant advancement in the management of school and university bus fleets. By integrating real-time tracking, advanced behavior monitoring, and scalable architecture, this system ensures efficient, safe, and organized transportation for students.

Student List

• Ahmed Diaaeldin LinkedIn

Main Supervisor

• Dr. Islam EL-Shaarawy LinkedIn

Did you find this page helpful? Consider sharing it 🙌