Using Deep Learning to Leverage Data Transfer and AI in Smart Vehicles

Smart autonomous vehicles have now become a reality while the efforts are ongoing to improve the safety, security, efficiency, and performance. In the fast paced digital world, all devices including the vehicles generate a huge amount of data every second which has to be analyzed, stored, and communicated with other devices to reach the next technology milestone. Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Device (V2D) communication protocols enable such communications for the smart connected vehicles. Ongoing research is focusing on further optimizing the information processing and data transfer technology to build a scalable and fault tolerant smart vehicle information system that uses a cloud infrastructure and massive parallel stream processing. We will build deep learning models to extract useful knowledge and data patterns from streaming vehicular data with a view to create a minimalistic and standardized dataset that can be efficiently transferred to other vehicles or to the cloud infrastructure for further analysis.

Faculty Supervisor:

Farhana Zulkernine

Student:

Priyanka Trivedi

Partner:

Canadian Urban Transit Research and Innovation Consortium

Discipline:

Computer science

Sector:

Transportation and warehousing

University:

Queen's University