The talk will present a solution that T-Systems has created for Deutsche Bahn to improve the passenger information by predicting the arrival of trains in real time based on the trains' current positions.
It will be shown, how classical statistical machine learning approaches can be combined with artificial neural networks to solve the problem. The solution is designed in a way that it can scale horizontally based on an Hadoop based HPC platform.
Fundamental understanding of distributed computing, Fundamantals of statistics
The participant should understand how parallel computing can be applied to real word, real-time problems using scalable approaches.
// Ingo Elsen
is active in the ML and Parallel Computing business for more than 25 years. He learned programming on Transputer based HPC clusters applied in the autonomous vehicles of the PROMETHEUS research programme and later designed an coprocessor card for neural networks during his PhD studies. He is now with T-Systems where he is the Chief Engineer for the Digital Processes branch.