Adams, AAbu-Mahfouz, Adnan MIHancke, GP2024-03-152024-03-152023-11Adams, A., Abu-Mahfouz, A.M. & Hancke, G. 2023. Machine learning – Imaging applications in transport systems: A review. http://hdl.handle.net/10204/13631 .979-8-3503-2781-6DOI: 10.1109/ICECET58911.2023.10389341http://hdl.handle.net/10204/13631Transport systems are fundamental to supporting economic growth, and the need for smarter, safer, more efficient and climate neutral transport systems continues to grow. Maintenance and operation of transport infrastructure is expensive and has many difficulties. In recent years, the application of machine learning to solve problems has been pursued with varying success rates. Many open problems still remain at this stage. This paper provides a review of deep learning applications in transport systems. Multiple deep learning applications are discussed e.g. railway safety, self-driving cars, pedestrian crossing and traffic light detection. Reviewed papers are evaluated in terms of challenges, contribution, weakness, research gaps. Key research questions for future study are proposed: performance optimization, data set improvement and the need for research on real-time performance on edge devices.AbstractenDeep learningEdge-deviceTransport systemsNeural networkRailway safetyObject detectionSelf-drivingConference PresentationAdams, A., Abu-Mahfouz, A. M., & Hancke, G. (2023). Machine learning – Imaging applications in transport systems: A review. http://hdl.handle.net/10204/13631Adams, A, Adnan MI Abu-Mahfouz, and GP Hancke. "Machine learning – Imaging applications in transport systems: A review." <i>International Conference on Electrical, Computer and Energy Technologies (ICECET 2023), Cape Town, South Africa, 16-17 November 2023</i> (2023): http://hdl.handle.net/10204/13631Adams A, Abu-Mahfouz AM, Hancke G, Machine learning – Imaging applications in transport systems: A review; 2023. http://hdl.handle.net/10204/13631 .TY - Conference Presentation AU - Adams, A AU - Abu-Mahfouz, Adnan MI AU - Hancke, GP AB - Transport systems are fundamental to supporting economic growth, and the need for smarter, safer, more efficient and climate neutral transport systems continues to grow. Maintenance and operation of transport infrastructure is expensive and has many difficulties. In recent years, the application of machine learning to solve problems has been pursued with varying success rates. Many open problems still remain at this stage. This paper provides a review of deep learning applications in transport systems. Multiple deep learning applications are discussed e.g. railway safety, self-driving cars, pedestrian crossing and traffic light detection. Reviewed papers are evaluated in terms of challenges, contribution, weakness, research gaps. Key research questions for future study are proposed: performance optimization, data set improvement and the need for research on real-time performance on edge devices. DA - 2023-11 DB - ResearchSpace DP - CSIR J1 - International Conference on Electrical, Computer and Energy Technologies (ICECET 2023), Cape Town, South Africa, 16-17 November 2023 KW - Deep learning KW - Edge-device KW - Transport systems KW - Neural network KW - Railway safety KW - Object detection KW - Self-driving LK - https://researchspace.csir.co.za PY - 2023 SM - 979-8-3503-2781-6 T1 - Machine learning – Imaging applications in transport systems: A review TI - Machine learning – Imaging applications in transport systems: A review UR - http://hdl.handle.net/10204/13631 ER -27612