This project was funded by the Research Center at Sri Sivasubramaniya Nadar College of Engineering (SSNCE), TN, India and carried out in collaboration with the Computer Science Department at SSNCE.

• Internet of Things (IoT) and Machine Learning (ML) to assuage the uncertainty in city bus schedules.
• Allows commuters to track live running status and avail tentative schedule of buses.
• Live running status for buses in transit; estimated schedule for planned future transits.
• IoT architecture to log and track bus arrivals using RF-based short-range communication beacons.
• Central web-backend to synchronize arrival logs and publish schedule predictions using ML.

• Link to online research article [HTML].
• Published manuscript [PDF].
• Project Completion Report [PDF Slides].
• Research Funding Proposal [PDF Slides].

If you find our work useful in your research, cite us.
Link to the Research Paper.

@article{desingu2023locatemybus,
  author   = {Karthik Desingu and Daniel Mark Isaac and Mirunalini P. and Bharathi B. and Cherry Mathew Philipose},
  title    = {LocateMyBus: IoT-Driven Smart Bus Transit},
  journal  = {Journal of Communications Software and Systems},
  month    = {4},
  year     = {2023},
  volume   = {19},
  number   = {2},
  pages    = {136--146},
  doi      = {10.24138/jcomss-2022-0143},
  url      = {https://doi.org/10.24138/jcomss-2022-0143}
}

Web-based user interface for live-tracking and expected schedule display.

• Track live running status: Viewer interface to access the current running status of in-transit buses, accurate to the granularity of bus stops.

  

• Schedule prediction: Interface to display the estimated schedule of buses on a given future date, predicted by the proposed machine learning algorithm that incorporates dynamic day-specific factors with historical data.

  

• Search for buses between stops: Interface to inquire buses and schedules between two stops.