@proceedings{Asad_S-2020_13498, title = {Travelers-Tracing and Mobility Profiling Using Machine Learning in Railway Systems}, author = {Asad, S. and Dashtipour, K. and Hussain, S. and Abbasi, Q. and Imran, M.}, month = {sep}, year = {2020}, abstract = {With the advent of Coronavirus Disease 2019 (COVID-19) throughout the world, safe transportation becomes critical while maintaining reasonable social distancing that requires a strategy in the mobility of daily travelers. Crowded train carriages, stations, and platforms are highly susceptible to spreading the disease, especially when infected travelers intermix with healthy travelers. Travelers-profiling is one of the essential interventions that railway network professionals rely on managing the disease outbreak while providing safe commute to staff and the public. In this plethora, a Machine Learning (ML) driven intelligent approach is proposed to manage daily train travelers that are in the age-group 16-59 years and over 60 years (vulnerable age-group) with the recommendations of certain times and routes of traveling, designated train carriages, stations, platforms, and special services using the London Underground and Overground (LUO) Network. LUO dataset has been compared with various ML algorithms to classify different agegroup travelers where Support Vector Machine (SVM) mobility prediction classification achieves up to 86.43% and 81.96% in age-group 16-59 years and over 60 years.}, journal = {IEEE Xplore}, publisher = {IEEE}, url = {http://dx.doi.org/10.1109/UCET51115.2020.9205456}, }